1. A method (300) for automatically generating Design for Excellence (DFX) checklists for Computer-Aided Design (CAD) models, the method (300) comprising: receiving (302), by a computing device (102), feedback data (224) for a physical product corresponding to a CAD model from one or more data sources; analyzing (304), by the computing device (102) via a Generative Artificial Intelligence (GenAI) model (220), the feedback data (224) to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model; automatically generating (306), by the computing device (102) via a Machine Learning (ML) model (222), a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values; for each DFX rule of the set of DFX rules, validating (308), by the computing device (102), the DFX rule based on at least one of the confidence score or a user validation; and generating (312), by the computing device (102), a DFX checklist (226) for the CAD model corresponding to the physical product based on the comparing, wherein the DFX checklist (226) comprises one or more validated DFX rules from the set of DFX rules.

2. The method (300) as claimed in claim 1, wherein the feedback data (224) comprise at least one of quality check (QC) logs, user feedback data, image-based feedback data, or material-based feedback data.

3. The method (300) as claimed in claim 1, wherein validating the DFX rule comprises: for each DFX rule of the set of DFX rules, comparing (310) the confidence score with a predefined threshold score.

4. The method (300) as claimed in claim 3, comprising: when the confidence score is greater than the predefined threshold, adding (314) the DFX rule to the DFX checklist (226).

5. The method (300) as claimed in claim 3, comprising: when the confidence score is less than the predefined threshold, receiving (316) a user feedback corresponding to the DFX rule, wherein the user feedback comprises a modification to the DFX rule, a data label corresponding to the modification, and context corresponding to the modification; modifying (318) the DFX rule based on the user feedback; and adding (320) the modified DFX rule to the DFX checklist (226).

6. The method (300) as claimed in claim 5, comprising performing (322) reinforcement learning (RL) on the ML model (222) using the user feedback.

7. A system (100) for automatically generating DFX checklists for CAD models, the system (100) comprising: a processor (104); and a memory (106) communicatively coupled to the processor (104), wherein the memory (106) stores processor executable instructions, which, on execution, causes the processor (104) to: receive (302) feedback data (224) for a physical product corresponding to a CAD model from one or more data sources; analyze (304), via a GenAI model (220), the feedback data (224) to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model; automatically generate (306), via a ML model (222), a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values; for each DFX rule of the set of DFX rules, validate (308) the DFX rule based on at least one of the confidence score or a user validation; and generate (312) a DFX checklist (226) for the CAD model corresponding to the physical product based on the comparing, wherein the DFX checklist (226) comprises one or more validated DFX rules from the set of DFX rules.

8. The system (100) as claimed in claim 7, wherein the feedback data (224) comprise at least one of quality check (QC) logs, user feedback data, image-based feedback data, or material-based feedback data.

9. The system (100) as claimed in claim 7, wherein to validate the DFX rule, the processor executable instructions cause the processor (104) to: for each DFX rule of the set of DFX rules, compare (310) the confidence score with a predefined threshold score.

10. The system (100) as claimed in claim 9, wherein the processor executable instructions cause the processor (104) to: when the confidence score is greater than the predefined threshold, add (314) the DFX rule to the DFX checklist (226).

11. The system (100) as claimed in claim 9, wherein the processor executable instructions cause the processor (104) to: when the confidence score is less than the predefined threshold, receive (316) a user feedback corresponding to the DFX rule, wherein the user feedback comprises a modification to the DFX rule, a data label corresponding to the modification, and context corresponding to the modification; modify (318) the DFX rule based on the user feedback; and add (320) the modified DFX rule to the DFX checklist (226).

12. The system (100) as claimed in claim 11, wherein the processor executable instructions cause the processor (104) to perform RL on the ML model (222) using the user feedback.

Description:DESCRIPTION
Technical Field
[001] This disclosure relates generally to Computer-Aided Design (CAD) models and more particularly to a method and system for automatically generating Design for Excellence (DFX) checklists for CAD models.
Background
[002] Design for Excellence (DFX) encompasses various design methodologies, which help in analysing and optimizing product designs throughout a lifecycle of a product. In modern product development, once the product is deployed, direct feedbacks received from shop floor relating to various issues (such as production component failure, assembly failures, rework, scrap, etc.) in the product are raw and unstructured. Typically, the feedback from the shop floor needs to be manually consolidated to obtain a DFX checklist. The DFX checklist is then shared with a product designer to be incorporated in future product designs. The product designer uses DFX checklists to define various rules and constraints to evaluate and identify potential manufacturing issues, assembly challenges, and cost inefficiencies in a product Computer-Aided Design (CAD) model.
[003] Conventionally, the product designers manually create the DFX checklists in form of a spreadsheet. The product designers then manually validate the product design with respect to the DFX checklists prior to releasing the product design for manufacturing. However, existing DFX tools may lack the capability to automatically adapt and refine rules of the DFX checklists based on ongoing and evolving shop floor feedback. Without a mechanism for continuous learning and rule refinement, the DFX checklists may become outdated as manufacturing processes evolve, new materials are introduced, or production equipment changes. This static nature of conventional DFX systems may result in repeated manufacturing errors, increased rework rates, higher scrap costs, and longer product development cycles.
[004] Furthermore, traditional DFX validation methods may fail to effectively capture real-time feedback from shop-floor operations, quality control logs, or operator experiences. This disconnect between design and manufacturing may lead to designs that appear compliant with generic DFX rules but still encounter issues during actual production.
[005] Therefore, there exists a need in the present state of art for an automated system that can dynamically generate DFX checklists based on real manufacturing feedback data, continuously adapt rules to reflect actual production conditions, and provide designers with actionable insights that are tailored to specific manufacturing environments and material characteristics.
SUMMARY
[006] In one embodiment, a method for automatically generating Design for Excellence (DFX) checklists for Computer-Aided Design (CAD) models is disclosed. In one example, the method may include receiving feedback data for a physical product corresponding to a CAD model from one or more data sources. The method may further include analyzing, via a Generative Artificial Intelligence (GenAI) model, the feedback data to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model. The method may further include automatically generating, via a Machine Learning (ML) model, a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values. For each DFX rule of the set of DFX rules, the method may further include validating the DFX rule based on at least one of the confidence score or a user validation. The method may further include generating a DFX checklist for the CAD model corresponding to the physical product based on the comparing. It should be noted that the DFX checklist may include one or more validated DFX rules from the set of DFX rules.
[007] In another embodiment, a system for automatically generating DFX checklists for CAD models is disclosed. In one example, the system may include a processor and a computer-readable medium communicatively coupled to the processor. The computer-readable medium may store processor-executable instructions, which, on execution, may cause the processor to receive feedback data for a physical product corresponding to a CAD model from one or more data sources. The processor-executable instructions, on execution, may further cause the processor to analyze, via a GenAI model, the feedback data to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model. The processor-executable instructions, on execution, may further cause the processor to automatically generate, via a ML model, a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values. For each DFX rule of the set of DFX rules, the processor-executable instructions, on execution, may further cause the processor to validate the DFX rule based on at least one of the confidence score or a user validation. The processor-executable instructions, on execution, may further cause the processor to generate a DFX checklist for the CAD model corresponding to the physical product based on the comparing. It should be noted that the DFX checklist may include one or more validated DFX rules from the set of DFX rules.
[008] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
BRIEF DESCRIPTION OF THE DRAWINGS
[009] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles.
[010] FIG. 1 is a block diagram of an exemplary system for automatically generating Design for Excellence (DFX) checklists for Computer-Aided Design (CAD) models, in accordance with some embodiments of the present disclosure.
[011] FIG. 2 illustrates a functional block diagram of a system for automatically generating DFX checklists for CAD models, in accordance with some embodiments of the present disclosure.
[012] FIG. 3 illustrates a flow diagram of an exemplary process for automatically generating DFX checklists for CAD models, in accordance with some embodiments of the present disclosure.
[013] FIG. 4 illustrates a flow diagram of a detailed exemplary process for automatically generating DFM checklists for CAD models, in accordance with an embodiment of the present disclosure.
[014] FIG. 5 illustrates an exemplary Graphical User Interface (GUI) representing validation results of a CAD model with respect to rules of a DFX checklist, in accordance with an embodiment of the present disclosure.
[015] FIG. 6 is a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.
DETAILED DESCRIPTION
[016] Exemplary embodiments are described with reference to the accompanying drawings. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.
[017] Referring now to FIG. 1, an exemplary system 100 for automatically generating Design for Excellence (DFX) checklists for Computer-Aided Design (CAD) models is illustrated, in accordance with some embodiments of the present disclosure. The system 100 may include a computing device 102. The computing device 102 may be, for example, but may not be limited to, server, desktop, laptop, notebook, netbook, tablet, smartphone, mobile phone, or any other computing device, in accordance with some embodiments of the present disclosure. The computing device 102 may automatically generate DFX rules for a CAD model based on manufacturing feedback data for a physical product corresponding to that CAD model using a Generative Artificial Intelligence (GenAI) model.
[018] As will be described in greater detail in conjunction with FIGS. 2 – 6, the computing device 102 may receive feedback data for a physical product corresponding to a CAD model from one or more data sources. The computing device 102 may further analyze, via a GenAI model, the feedback data to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model. The computing device 102 may further automatically generate, via a Machine Learning (ML) model, a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values. For each DFX rule of the set of DFX rules, the computing device 102 may further validate the DFX rule based on at least one of the confidence score or a user validation. The computing device 102 may further generate a DFX checklist for the CAD model corresponding to the physical product based on the comparing. It should be noted that the DFX checklist may include one or more validated DFX rules from the set of DFX rules.
[019] In some embodiments, the computing device 102 may include one or more processors 104 and a memory 106. Further, the memory 106 may store instructions that, when executed by the one or more processors 104, may cause the one or more processors 104 to automatically generate DFX checklists for CAD models, in accordance with aspects of the present disclosure. The memory 106 may also store various data (for example, feedback data, one or more DFX parameters, one or more corresponding DFX parameter values, a set of DFX rules, a confidence score, a DFX checklist, and the like) that may be captured, processed, and/or required by the system 100.
[020] The system 100 may further include a display 108. The system 100 may interact with a user interface 110 accessible via the display 108. The system 100 may also include one or more external devices 112. In some embodiments, the computing device 102 may interact with the one or more external devices 112 over a communication network 114 for sending or receiving various data. The communication network 114 may include, for example, but may not be limited to, a wireless fidelity (Wi-Fi) network, a light fidelity (Li-Fi) network, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a satellite network, the internet, a fiber optic network, a coaxial cable network, an infrared (IR) network, a radio frequency (RF) network, and a combination thereof. The one or more external devices 112 may include, but may not be limited to, a remote server, a laptop, a netbook, a notebook, a smartphone, a mobile phone, a tablet, or any other computing device. The system 100 may further include a Human-In-The-Loop (HITL) intelligent decision making 116. The HITL intelligent decision making 116 may be a hybrid decision architecture in which AI model may generate outputs and a human agent participates in validation to improve reliability, safety, and contextual appropriateness.
[021] Referring now to FIG. 2, a functional block diagram of a system 200 for automatically generating DFX checklists for CAD models is illustrated, in accordance with some embodiments of the present disclosure. FIG. 2 is explained in conjunction with FIG. 1. The system 200 may be analogous to the system 100. The system 200 may implement the computing device 102. The system 200 may include, within the memory 106, a receiving module 202, an analyzing module 204, a Design for Excellence (DFX) rule generating module 206, a validating module 208, a comparing module 210, a DFX checklist generating module 212, a reinforcement learning (RL) module 214, a GenAI module 216, and a Machine Learning (ML) module 218. The GenAI module 216 may include a GenAI model 220. The ML module 218 may include an ML model 222.
[022] Initially, the receiving module 202 may receive feedback data 224 for a physical product corresponding to a CAD model from one or more data sources. For example, the one or more data sources may be, but may not be limited to, a user (e.g., operator, technicians, engineers, or the like), sensors, images, or the like. The feedback data 224 may include at least one of shop-floor quality check (QC) logs, user feedback data (in natural language), image-based feedback data, or material-based feedback data. The shop-floor QC logs may include design features of the physical product that cause defects (or rework) in production. For example, the shop-floor QC logs may include, but may not be limited to, rework actions, rework (or scrap) reasons, QC reports on failure types and frequencies, defects linked to product features (or materials), or the like. The user feedback data may provide practical and experience-based insights from real machining. For example, the user feedback data may include, but may not be limited to, hard to clamp due to rounded base, drill gets stuck near thin webs, special setup required due to awkward geometry, or the like.
[023] For example, the image-based feedback data may include, but may not be limited to, surface finish issues, cracks, warping, tool marks, visual comparison of failed parts with good parts using an AI vision, or the like. The material-based feedback data may capture how different materials behave during manufacturing and identify unsuitable material-feature combinations. For example, the material-based feedback data may include, but may not be limited to, tool wear and breakage frequency across materials, burr formation (or chipping) by material type, scrap rate linked to materials, dimensional accuracy due to thermal expansion, vibration (or spindle load spikes) for harder material, or the like. For example, the physical product may be, but may not be limited to, smartphone cases, automobile parts (e.g., engine components, body panels, or the like), medical devices, prosthetics, or the like.
[024] Further, the receiving module 202 may send the feedback data 224 to the analyzing module 204. Further, the analyzing module 204 may analyze, via the GenAI model 220, the feedback data 224 to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model. For example, the DFX parameters may include, but may be limited to, Design for Manufacturing (DFM) (e.g., number of parts, tolerance complexity, material selection suitability, tool accessibility, wall thickness, or the like), Design for Assembly (DFA) (e.g., number of assembly steps, fastener count and type, symmetry of parts, or the like), Design for cost (DFC) (e.g., material cost, labor cost, tooling cost, or the like), or the like.
[025] Further, the DFX rule generating module 206 may automatically generate, via the ML model 222, a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values.
[026] Further, for each DFX rule of the set of DFX rules, the validating module 208 may validate the DFX rule based on at least one of the confidence score or a user validation. To validate the DFX rule, the comparing module 210 may compare the confidence score with a predefined threshold score. Further, the DFX checklist generating module 212 may generate a DFX checklist 226 for the CAD model corresponding to the physical product based on the comparing. The DFX checklist 226 may include one or more validated DFX rules from the set of DFX rules.
[027] In some embodiments, when the confidence score is greater than the predefined threshold, the DFX checklist generating module 212 may add the DFX rule to the DFX checklist. In some other embodiments, when the confidence score is less than the predefined threshold, the receiving module 202 may receive a user feedback corresponding to the DFX rule. The user feedback may include a modification to the DFX rule, a data label corresponding to the modification, and context corresponding to the modification. Further, the receiving module 202 may send the user feedback to the DFX rule generating module 206. Further, the DFX rule generating module 206 may modify the DFX rule based on the user feedback. Upon modification, the DFX checklist generating module 212 may add the modified DFX rule to the DFX checklist 226. Simultaneously, the RL module 214 may perform RL on the ML model 222 using the user feedback.
[028] It should be noted that all such aforementioned modules 202 – 222 may be represented as a single module or a combination of different modules. Further, as will be appreciated by those skilled in the art, each of the modules 202 – 222 may reside, in whole or in parts, on one device or multiple devices in communication with each other. In some embodiments, each of the modules 202 – 222 may be implemented as dedicated hardware circuit comprising custom application-specific integrated circuit (ASIC) or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. Each of the modules 202 – 222 may also be implemented in a programmable hardware device such as a field programmable gate array (FPGA), programmable array logic, programmable logic device, and so forth. Alternatively, each of the modules 202 – 222 may be implemented in software for execution by various types of processors (e.g., processor 104). An identified module of executable code may, for instance, include one or more physical or logical blocks of computer instructions, which may, for instance, be organized as an object, procedure, function, or other construct. Nevertheless, the executables of an identified module or component need not be physically located together but may include disparate instructions stored in different locations which, when joined logically together, include the module and achieve the stated purpose of the module. Indeed, a module of executable code could be a single instruction, or many instructions, and may even be distributed over several different code segments, among different applications, and across several memory devices.
[029] As will be appreciated by one skilled in the art, a variety of processes may be employed for automatically generating DFX checklists for CAD models. For example, the exemplary system 100 and the associated computing device 102, may automatically generate DFX checklists for CAD models, by the processes discussed herein. In particular, as will be appreciated by those of ordinary skill in the art, control logic and/or automated routines for performing the techniques and steps described herein may be implemented by the system 100 and the associated computing device 102 either by hardware, software, or combinations of hardware and software. For example, suitable code may be accessed and executed by the one or more processors on the system 100 to perform some or all of the techniques described herein. Similarly, application specific integrated circuits (ASICs) configured to perform some or all of the processes described herein may be included in the one or more processors on the system 100.
[030] Referring now to FIG. 3, an exemplary process 300 for automatically generating DFX checklists for CAD models is illustrated via a flow chart, in accordance with some embodiments of the present disclosure. FIG. 3 is explained in conjunction with FIGS. 1 and 2. The process 300 may be implemented by the computing device 102 of the system 100. In some embodiments, the process 300 may include receiving, by a receiving module (such as the receiving module 202), feedback data (such as the feedback data 224) for a physical product corresponding to a CAD model from one or more data sources, at step 302. The feedback data may include at least one of quality check (QC) logs, user feedback data, image-based feedback data, or material-based feedback data.
[031] Upon receiving the feedback data, the process 300 may include analyzing, by an analyzing module (such as the analyzing module 204) via a GenAI model (such as the GenAI model 220), the feedback data to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model, at step 304.
[032] Further, the process 300 may include automatically generating, by a DFX rule generating module (such as the DFX rule generating module 206) via a ML model (such as the ML model 222), a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values, at step 306.
[033] Once the set of DFX rules are generated, for each DFX rule of the set of DFX rules, the process 300 may include validating, by a validating module (such as the validating module 208), the DFX rule based on at least one of the confidence score or a user validation, at step 308. To validate the DFX rule, the process 300 may include comparing, by a comparing module (such as the comparing module 210), the confidence score with a predefined threshold score, at step 310.
[034] Further, the process 300 may include generating, by a DFX checklist generating module (such as the DFX checklist generating module 212), a DFX checklist (such as the DFX checklist 226) for the CAD model corresponding to the physical product based on the comparing, at step 312. The DFX checklist may include one or more validated DFX rules from the set of DFX rules. The step 312 may include steps 314, 316, 318, and 320.
[035] When the confidence score is greater than the predefined threshold, the process 300 may include adding, by the DFX checklist generating module, the DFX rule to the DFX checklist, at step 314.
[036] When the confidence score is less than the predefined threshold, the process 300 may include initiating a HITL intelligent decision-making procedure. Once the HITL intelligent decision-making procedure is initiated, the process 300 may include receiving, by the receiving module, a user feedback corresponding to the DFX rule, at step 316. It should be noted that the user feedback may include a modification to the DFX rule, a data label corresponding to the modification, and context corresponding to the modification. Upon receiving the user feedback, the process 300 may include modifying, by the DFX rule generating module, the DFX rule based on the user feedback, at step 318. Once the DFX rule is modified, the process 300 may include adding, by the DFX checklist generating module, the modified DFX rule to the DFX checklist, at step 320. Simultaneously, the process 300 may include performing, by a RL module (such as the RL module 214), RL on the ML model using the user feedback, at step 322.
[037] Referring now to FIG. 4, a detailed exemplary process 400 for automatically generating DFM checklists for CAD models is illustrated via a flow chart, in accordance with some embodiments of the present disclosure. FIG. 4 is explained in conjunction with FIGS. 1, 2, and 3. The process 400 may be implemented by the computing device 102 of the system 100. The receiving module 202 may receive shop-floor quality logs 402 (i.e., the shop-floor QC logs) corresponding to a Computer Numerical Control (CNC)-margined motor housing from one or more data sources for a CAD model. The CNC-machined motor housing may include deep pockets, internal ribs, and angled features. The CNC-machined motor housing may require tight tolerance for component alignment (or fit) (e.g., bearings, shafts, or the like). For example, the CNC-machined motor housing may be used in automotives, robotics, pumps, or the like.
[038] For example, the shop-floor quality logs 402 may include “Frequent dimensional errors in internal ribs and the deep pockets”, “Tool deflection causing tapered walls (or incomplete cleaning) of corners”, “3 parts out of 20 parts scrapped in a final inspection”, and an “AI links tight internal rib spacing and a deep geometry with poor tool access and quality issues”.
[039] Additionally, the receiving module 202 may receive operator feedback (analogous to the user feedback data) 404 corresponding to the CNC-machined motor housing from an operator. For example, the operator feedback 404 may include several comments of the operator in natural language. The comments may be “The tool cannot fully reach to a bottom of angled pockets”, “I had to use a custom long tool (i.e., part vibrated)”, “internal ribs are too close together to clean burrs”, and “the AI confirms that geometry makes standard tooling impractical”.
[040] Additionally, the receiving module 202 may receive image-based feedback 406 corresponding to the CNC-machined motor housing from one or more data sources (e.g., images of CNC-machined motor housing parts, or the like). Also, the receiving module 202 may receive material-based feedback 408 corresponding to the CNC-machined motor housing from one or more data sources. For example, the material-based feedback 408 may include a cast iron (i.e., brittle, chatter during deep cuts, and edge chipping on tight angles), an aluminium (i.e., flexible but requires reinforcement in thin features, can handle deeper pockets), and a general insight (i.e., tool wear and vibration increases with deeper pockets and closer internal ribs in harder materials).
[041] Further, the receiving module 202 may send the shop-floor quality logs 402, the operator feedback 404, the image-based feedback 406, and the material-based feedback 408 to a proactive Artificial Intelligence (AI) engine 410. In an embodiment, the proactive AI engine 410 is a combination of the GenAI module 216 and the ML module 218. Further, the proactive AI engine 410 may aggregate (or combine) each of the shop-floor quality logs 402, the operator feedback 404, the image-based feedback 406, and the material-based feedback 408 to obtain combined feedback. Further, the proactive AI engine 410 may detect one or more key patterns (analogous to the DFX parameters) causing manufacturing errors based on the combined feedback.
[042] For example, the detected key patterns may include “the pockets deeper than ‘40’ mm with width less than ‘12’ mm, which may result in tool access limitations, deflection, or poor finish”, “the internal ribs spaced less than ‘10’ mm, which may cause machinery difficulty, inadequate burr removal, and vibration during the tool movement”, and “the angled features with included angles less than 45 degree which require special tooling (or cause tool deflection and surface quality issues)”.
[043] Upon detecting the one or more key patterns, the proactive AI engine 410 may automatically generate, via the ML model 222, a set of DFM rules (analogous to the DFX rules) corresponding to tool accessibility based on the one or more key patterns. The set of DFM rules may be used to check whether a cutting tool may reach properly to a machine surface without any collision or interference from adjacent features (or walls) (e.g., deep pockets, angle walls, holes, or the like). Additionally, the proactive AI engine 410 may generate one or more reasons for the DFM rule generation based on the one or more key patterns.
[044] For example, three DFM rules (e.g., a first DFM rule 412, a second DFM rule 414, and a third DFM rule 416) may be generated based on each key pattern. The first DFM rule 412 may be “Avoid pockets deeper than ‘40’ mm, if the access width is less than ‘12’ mm, especially in the aluminium and the cast iron materials”. A reason for generating the first DFM rule 412 may be “Reduces tool deflection and ensures proper machining”.
[045] The second DFM rule 414 may be “Maintain internal rib spacing of at least ‘10’ mm to ensure tool clearance and enable effective burr removal”. A reason for generating the second DFM rule 414 may be “Improves tool path accessibility and prevent post-processing issues”.
[046] The third DFM rule 416 may be “Angled walls should be below 45 degrees, flag the features for review as standard end-mills may not reach effectively”. A reason for generating the third DFM rule 416 may be “Reduces chatter, edge damage, and ensures correct tool engagement”.
[047] Once the set of DFM rules are generated, the proactive AI engine 410 may send the set of DFM rules to a tool accessibility section in a software application (i.e., a DFMPro® software application) for validation based on historical part repository, via a design engineers (or operator). For example, when a designer models a new CNC-machined motor housing, the DFMPro software application may apply the set of DFM rules on the new CNC-machined motor housing to evaluate the rib spacing, the pocket depth versus tool access width, and the wall angles and material combination.
[048] In some embodiments, if any of the DFM rules are violated (or not aligned with the parts of the new CNC-machined motor housing), in such cases, the DFMPro application may flag a tool accessibility issue. For example, the tool accessibility issue may include “Rib spacing less than ‘10’ mm (i.e., require a custom tool and increate machining time)”, “Pocket depth exceeds ‘40’ mm, (i.e., consider widening or adjusting design to avoid tool deflection)”, and “Wall angle less than 45 degrees in brittle material (i.e., check if standard end-mill can reach this feature)”.
[049] Further, the proactive AI engine 410 may modify the set of DFM rules based on the tool accessibility issues. For example, an original rule instruction may be “Cutting tools should have accessibility to features in a preferred machining orientation”. A revised rule instruction may be “Ensure tool access to all features, considering material-specific and geometric constraints”. Upon modification, the proactive AI engine 410 may add modified tool accessibility rules in a DFM checklist. For example, the DFM checklist may include “For cast iron, avoid pockets > 40 mm deep, if width < 12 mm”, “Maintain rib spacing ≥ 10 mm for tool clearance and burr removal”, “Flag angled walls < 45° in brittle materials to avoid risk of tool deflection”, and “Use feedback from QC logs and operator inputs to validate access”.
[050] Referring now to FIG. 5, an exemplary GUI 500 representing validation results of a CAD model 502 with respect to rules of a DFX checklist is illustrated, in accordance with some embodiments of the present disclosure. FIG. 5 is explained in conjunction with FIGS. 1, 2, 3, and 4. The GUI 500 may present the CAD model 502 in a three-dimensional view, allowing a user (e.g., a design engineer, an operator, or the like) to visually inspect geometric features of the CAD model 502 that may be subject to DFM validation. The CAD model 502 may correspond to a machined part.
[051] The GUI 500 may further include a section for recommendations 506 for various instances of DFM checklists (for example, “instance 1”, “instance 2” and “instance 3”). For each instance, DFM validation results of the CAD model 502 may be shown in a rules section 506 of the GUI 500. The user may select one instance at a time for the DFM validation. For example, when the user selects the “instance 1”, DFM validation may be automatically performed for the CAD model 502 based on the DFM checklist created for the “instance 1”. Subsequently, the rules section 506 may enlist the DFM validation results for each rule in the DFM checklist.
[052] The rules section 506 may represent the various DFM rule categories and their corresponding validation results in an expandable tree format. For example, the rules section 506 may include drilling rules with subcategories for issues such as entry and exit surface for holes, standard hole sizes, and holes intersecting cavities. Each subcategory may display a count of flagged instances relative to total instances checked during the validation process.
[053] The rules section 506 may further include categories for flat bottom holes with different severity levels (e.g., high, medium, and low). The rules section 506 may also include milling rules with subcategories for tool accessibility, displaying severity classifications to help the user prioritize design modifications. The GUI 500 may enable the user to expand or collapse rule categories to view detailed validation results for specific DFM rules.
[054] Each of the DFM rules in the rules section 506 is selectable by the user. The GUI 500 may highlight specific features on the CAD model 502 that correspond to flagged instances in a selected DFM rule from the rules section 506. This visual correlation may assist the user in identifying and addressing design issues that may cause manufacturing problems. The GUI 500 may also provide options for the user to accept, modify, or reject flagged instances, and such user feedback may be used for reinforcement learning on the ML model 222 as described with respect to step 322 of the process 300.
[055] As will be also appreciated, the above-described techniques may take the form of computer or controller implemented processes and apparatuses for practicing those processes. The disclosure can also be embodied in the form of computer program code containing instructions embodied in tangible media, such as floppy diskettes, solid state drives, CD-ROMs, hard drives, or any other computer-readable storage medium, wherein, when the computer program code is loaded into and executed by a computer or controller, the computer becomes an apparatus for practicing the invention. The disclosure may also be embodied in the form of computer program code or signal, for example, whether stored in a storage medium, loaded into and/or executed by a computer or controller, or transmitted over some transmission medium, such as over electrical wiring or cabling, through fiber optics, or via electromagnetic radiation, wherein, when the computer program code is loaded into and executed by a computer, the computer becomes an apparatus for practicing the invention. When implemented on a general-purpose microprocessor, the computer program code segments configure the microprocessor to create specific logic circuits.
[056] The disclosed methods and systems may be implemented on a conventional or a general-purpose computer system, such as a personal computer (PC) or server computer. Referring now to FIG. 6, an exemplary computing system 600 that may be employed to implement processing functionality for various embodiments (e.g., as a SIMD device, client device, server device, one or more processors, or the like) is illustrated. Those skilled in the relevant art will also recognize how to implement the invention using other computer systems or architectures. The computing system 600 may represent, for example, a user device such as a desktop, a laptop, a mobile phone, personal entertainment device, DVR, and so on, or any other type of special or general-purpose computing device as may be desirable or appropriate for a given application or environment. The computing system 600 may include one or more processors, such as a processor 602 that may be implemented using a general or special purpose processing engine such as, for example, a microprocessor, microcontroller or other control logic. In this example, the processor 602 is connected to a bus 604 or other communication medium. In some embodiments, the processor 602 may be an Artificial Intelligence (AI) processor, which may be implemented as a Tensor Processing Unit (TPU), or a graphical processor unit, or a custom programmable solution Field-Programmable Gate Array (FPGA).
[057] The computing system 600 may also include a memory 606 (main memory), for example, Random Access Memory (RAM) or other dynamic memory, for storing information and instructions to be executed by the processor 602. The memory 606 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processor 602. The computing system 600 may likewise include a read only memory (“ROM”) or other static storage device coupled to bus 604 for storing static information and instructions for the processor 602.
[058] The computing system 600 may also include a storage devices 608, which may include, for example, a media drive 610 and a removable storage interface. The media drive 610 may include a drive or other mechanism to support fixed or removable storage media, such as a hard disk drive, a floppy disk drive, a magnetic tape drive, an SD card port, a USB port, a micro USB, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive. A storage media 612 may include, for example, a hard disk, magnetic tape, flash drive, or other fixed or removable medium that is read by and written to by the media drive 610. As these examples illustrate, the storage media 612 may include a computer-readable storage medium having stored therein particular computer software or data.
[059] In alternative embodiments, the storage devices 608 may include other similar instrumentalities for allowing computer programs or other instructions or data to be loaded into the computing system 600. Such instrumentalities may include, for example, a removable storage unit 614 and a storage unit interface 616, such as a program cartridge and cartridge interface, a removable memory (for example, a flash memory or other removable memory module) and memory slot, and other removable storage units and interfaces that allow software and data to be transferred from the removable storage unit 614 to the computing system 600.
[060] The computing system 600 may also include a communications interface 618. The communications interface 618 may be used to allow software and data to be transferred between the computing system 600 and external devices. Examples of the communications interface 618 may include a network interface (such as an Ethernet or other NIC card), a communications port (such as for example, a USB port, a micro USB port), Near field Communication (NFC), etc. Software and data transferred via the communications interface 618 are in the form of signals which may be electronic, electromagnetic, optical, or other signals capable of being received by the communications interface 618. These signals are provided to the communications interface 618 via a channel 620. The channel 620 may carry signals and may be implemented using a wireless medium, wire or cable, fiber optics, or other communications medium. Some examples of the channel 620 may include a phone line, a cellular phone link, an RF link, a Bluetooth link, a network interface, a local or wide area network, and other communications channels.
[061] The computing system 600 may further include Input/Output (I/O) devices 622. Examples may include, but are not limited to a display, keypad, microphone, audio speakers, vibrating motor, LED lights, etc. The I/O devices 622 may receive input from a user and also display an output of the computation performed by the processor 602. In this document, the terms “computer program product” and “computer-readable medium” may be used generally to refer to media such as, for example, the memory 606, the storage devices 608, the removable storage unit 614, or signal(s) on the channel 620. These and other forms of computer-readable media may be involved in providing one or more sequences of one or more instructions to the processor 602 for execution. Such instructions, generally referred to as “computer program code” (which may be grouped in the form of computer programs or other groupings), when executed, enable the computing system 600 to perform features or functions of embodiments of the present invention.
[062] In an embodiment where the elements are implemented using software, the software may be stored in a computer-readable medium and loaded into the computing system 600 using, for example, the removable storage unit 614, the media drive 610 or the communications interface 618. The control logic (in this example, software instructions or computer program code), when executed by the processor 602, causes the processor 602 to perform the functions of the invention as described herein.
[063] Various embodiments provide method and system for automatically generating DFX checklists for CAD models. The disclosed method and system may receive feedback data for a physical product corresponding to a CAD model from one or more data sources. Further, the disclosed method and system may analyze, via a GenAI model, the feedback data to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model. Further, the disclosed method and system may automatically generate, via a ML model, a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values. Moreover, for each DFX rule of the set of DFX rules, the disclosed method and system may validate the DFX rule based on at least one of the confidence score or a user validation. Thereafter, the disclosed method and system may generate a DFX checklist for the CAD model corresponding to the physical product based on the comparing. The DFX checklist may include one or more validated DFX rules from the set of DFX rules.
[064] Thus, the disclosed method and system try to overcome the technical problem of automatically generating DFX checklists for CAD models. The disclosed method and system may automatically generate a set of DFM rules based on real production data using AI model. Further, the disclosed method and system may replace manually created rule libraries with dynamic data-driven logic. This may ensure that the DFM rules are tailored to specific processes, material, and production environments. Further, the disclosed method and system may continuously adapt the DFM rules based on production variability. For example, the disclosed method and system may monitor ongoing changes in manufacturing conditions (e.g., material performance, tool wear, or the like). Additionally, the disclosed method and system may automatically refine the existing DFM rules (or add new DFM rules in the existing DFM rules as needed). This may keep the DFM system with shop-floor realities without requiring manual updates. Further, the disclosed method and system may identify manufacturing issues early in a design stage. This may lead to prevent costly rework, tooling modifications, and production delays. Further, the disclosed method and system may use streamline product development cycles to improve efficiency and time-to-market. Further, the disclosed method and system may flag design geometries likely to cause machining (or quality problems). Additionally, the disclosed method and system may support engineers (i.e., operator) by providing design alerts during concept (or prototyping). This may enable corrective actions before parts move into production and improve yield. Further, the disclosed method and system may provide closed-loop feedback between design and manufacturing. For example, the disclosed method and system may establish a continuous learning loop between the CAD environment and shop floor. Also, the disclosed method and system may integrate real-time feedback into the CAD environment to guide future design decisions. This may lead to enhance collaboration between design and production teams, reduce disconnect and errors.
[065] In light of the above mentioned advantages and the technical advancements provided by the disclosed method and system, the claimed steps as discussed above are not routine, conventional, or well understood in the art, as the claimed steps enable the following solutions to the existing problems in conventional technologies. Further, the claimed steps clearly bring an improvement in the functioning of the device itself as the claimed steps provide a technical solution to a technical problem.
[066] It will be appreciated that, for clarity purposes, the above description has described embodiments of the invention with reference to different functional units and processors. However, it will be apparent that any suitable distribution of functionality between different functional units, processors or domains may be used without detracting from the invention. For example, functionality illustrated to be performed by separate processors or controllers may be performed by the same processor or controller. Hence, references to specific functional units are only to be seen as references to suitable means for providing the described functionality, rather than indicative of a strict logical or physical structure or organization.
[067] Although the present invention has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Rather, the scope of the present invention is limited only by the claims. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognize that various features of the described embodiments may be combined in accordance with the invention.
[068] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[069] It is intended that the disclosure and examples be considered as exemplary only. , Claims:CLAIMS
I/We claim:
1. A method (300) for automatically generating Design for Excellence (DFX) checklists for Computer-Aided Design (CAD) models, the method (300) comprising:
receiving (302), by a computing device (102), feedback data (224) for a physical product corresponding to a CAD model from one or more data sources;
analyzing (304), by the computing device (102) via a Generative Artificial Intelligence (GenAI) model (220), the feedback data (224) to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model;
automatically generating (306), by the computing device (102) via a Machine Learning (ML) model (222), a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values;
for each DFX rule of the set of DFX rules, validating (308), by the computing device (102), the DFX rule based on at least one of the confidence score or a user validation; and
generating (312), by the computing device (102), a DFX checklist (226) for the CAD model corresponding to the physical product based on the comparing, wherein the DFX checklist (226) comprises one or more validated DFX rules from the set of DFX rules.

2. The method (300) as claimed in claim 1, wherein the feedback data (224) comprise at least one of quality check (QC) logs, user feedback data, image-based feedback data, or material-based feedback data.

3. The method (300) as claimed in claim 1, wherein validating the DFX rule comprises:
for each DFX rule of the set of DFX rules, comparing (310) the confidence score with a predefined threshold score.

4. The method (300) as claimed in claim 3, comprising:
when the confidence score is greater than the predefined threshold, adding (314) the DFX rule to the DFX checklist (226).

5. The method (300) as claimed in claim 3, comprising:
when the confidence score is less than the predefined threshold,
receiving (316) a user feedback corresponding to the DFX rule, wherein the user feedback comprises a modification to the DFX rule, a data label corresponding to the modification, and context corresponding to the modification;
modifying (318) the DFX rule based on the user feedback; and
adding (320) the modified DFX rule to the DFX checklist (226).

6. The method (300) as claimed in claim 5, comprising performing (322) reinforcement learning (RL) on the ML model (222) using the user feedback.

7. A system (100) for automatically generating DFX checklists for CAD models, the system (100) comprising:
a processor (104); and
a memory (106) communicatively coupled to the processor (104), wherein the memory (106) stores processor executable instructions, which, on execution, causes the processor (104) to:
receive (302) feedback data (224) for a physical product corresponding to a CAD model from one or more data sources;
analyze (304), via a GenAI model (220), the feedback data (224) to identify one or more DFX parameters and one or more corresponding DFX parameter values for the CAD model;
automatically generate (306), via a ML model (222), a set of DFX rules for the CAD model and a confidence score associated with each of the set of DFX rules based on the one or more DFX parameters and the one or more corresponding DFX parameter values;
for each DFX rule of the set of DFX rules, validate (308) the DFX rule based on at least one of the confidence score or a user validation; and
generate (312) a DFX checklist (226) for the CAD model corresponding to the physical product based on the comparing, wherein the DFX checklist (226) comprises one or more validated DFX rules from the set of DFX rules.

8. The system (100) as claimed in claim 7, wherein the feedback data (224) comprise at least one of quality check (QC) logs, user feedback data, image-based feedback data, or material-based feedback data.

9. The system (100) as claimed in claim 7, wherein to validate the DFX rule, the processor executable instructions cause the processor (104) to:
for each DFX rule of the set of DFX rules, compare (310) the confidence score with a predefined threshold score.

10. The system (100) as claimed in claim 9, wherein the processor executable instructions cause the processor (104) to:
when the confidence score is greater than the predefined threshold, add (314) the DFX rule to the DFX checklist (226).

11. The system (100) as claimed in claim 9, wherein the processor executable instructions cause the processor (104) to:
when the confidence score is less than the predefined threshold,
receive (316) a user feedback corresponding to the DFX rule, wherein the user feedback comprises a modification to the DFX rule, a data label corresponding to the modification, and context corresponding to the modification;
modify (318) the DFX rule based on the user feedback; and
add (320) the modified DFX rule to the DFX checklist (226).

12. The system (100) as claimed in claim 11, wherein the processor executable instructions cause the processor (104) to perform RL on the ML model (222) using the user feedback.