Description:FIELD OF INVENTION
The present disclosure generally relates to the field of optimization dwell time in superfinishing or microfinishing. More particularly, the present disclosure relates to a system for optimizing the dwell time of a finishing module in a machining unit.
DEFINITIONS
As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used to indicate otherwise.
Dwell Time: The term ‘Dwell Time’ hereinafter refers to a time required to process a component. The process may include surface finishing, Surface finishing, free belt grinding.
Machine operating rules: The term ‘machine operating rules’ is hereinafter refers to an elementary operation based on a set of rules or instruction which is designed and built to perform particular operation.
Set of machine learning rules: The term ‘set of machine learning rules’ is a set of instruction that provides a process of creating rules from pre-trained data, and/or existing rules or machine learning models.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Dwell time optimization in machining for finishing operations is a crucial aspect of the manufacturing industry, particularly in the field of metalworking. Machining refers to the process of shaping and transforming raw materials, typically metals, into desired components or products through various cutting, drilling, and grinding techniques. Finishing operations, on the other hand, focus on refining the surface quality and dimensional accuracy of the workpiece.
In finishing, dwell time refers to the period during which the finishing tool remains in contact with the workpiece for finishing or grinding. The dwell time plays a significant role in determining the final surface finish and the overall efficiency of the machining process. Optimizing the dwell time is essential to achieve the desired surface quality while minimizing production time and cost.
One of the key objectives in dwell time optimization is to ensure that the machining process removes the appropriate amount of material from the workpiece, to generate surface with high precision and surface quality, for aerospace, automotive, and medical device manufacturing application.
Traditionally, the dwell time optimization was primarily based on empirical knowledge and the experience of machinists. Further, it is very difficult to predict accurately dwell time in plunge finishing operation, as a result, the current dwell times for plunge superfinishing component tend to be excessively long. Therefore, there is felt a need for a system for optimizing the dwell time of a finishing module during machine-finishing that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
An object of the present disclosure is to provide a system for optimizing the dwell time of a finishing module during machine-finishing.
Another object of the present disclosure is to provide a system to capture an input roughness value of a component to be machine-finish.
Still another object of the present disclosure is to provide a system for crawling and extracting dwell time from a historical pre-trained data.
Yet another object of the present disclosure is to provide a system to capture the actual roughness value of the component to be machine-finish.
Still another object of the present disclosure is to provide a system to provide a data signal to the crawler-extractor pair to extract the closest dwell time corresponding to the pair of the actual roughness value and the user-defined desired output roughness value.
Yet another object of the present disclosure is to provide a system for optimizing cycle time.
Still another object of the present disclosure is to provide a system to increase finishing accuracy.
Yet another object of the present disclosure is to provide a system for adjusting the dwell time as per user requirement.
Still another object of the present disclosure is to provide a system for adaptability to changes in finishing conditions.
Yet another object of the present disclosure is to provide a system for generating deviation for machine-finishing of the component to obtain the desired output roughness.
Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure envisages a system for optimizing the dwell time of a finishing module. The system comprises a control unit, at least one data repository unit, at least one comparator, an input unit, and an optimizer unit.
The control unit includes a processor, which is configured with a machine learning rule and a machine operating rules and commands.
At least one data repository unit is communicatively connected to the control unit. The data repository is configured to store, in a table a set of pre-defined pre-trained data containing in connection with pre-finishing roughness values, desired roughness values, and dwell times for converting the pre-finishing roughness of a component to the desired roughness.
At least one comparator is communicatively connected to the control unit and the data repository unit. The comparator provided with a crawler-extractor pair. The crawler-extractor pair is configured to crawl on the data and an extract dwell time corresponding to a pair of pre-finishing roughness values and desired roughness values.
The input unit is in communication with the control unit and the crawler-extractor pair. The input unit is configured to capture an actual roughness value of a component to be machined and to receive a user-defined desired output roughness value for the component to be machined. The input unit is configured to provide a data signal to the crawler-extractor pair to extract at least one dwell time corresponding to the pair of the actual surface roughness value and the user-defined desired output roughness value.
The optimizer unit is in communication with the input unit and the crawler-extractor pair is configured to receive the extracted dwell time’s. The optimizer unit is configured to compute and display an optimized dwell time for carrying out the machine-finishing operation.
In an aspect, the system includes at least one sensing unit. The sensing unit is configured to periodically sense actual output surface roughness after each pass of machine-finishing. The sensing unit is configured to generate at least one corresponding actual output sensed roughness signal.
In an aspect, the control unit includes an analogue-to-digital converter, communicating with the sensing unit.
In an aspect, the analogue-to-digital converter is being configured to receive the actual output sensed roughness signal. The analogue-to-digital converter is configured to convert the actual output sensed roughness signal to actual output digital sensed roughness value.
In an aspect, the comparator is configured to be in communication with the analogue-to-digital converter to compare the actual output digital sensed roughness value with the desired output roughness value to generate deviation in the desired output surface roughness value.
In an aspect, the system includes an error module in communication with the comparator to receive the generated deviation.The error module is configured with a set of machine learning rules in connection with error correction. The error module is configured to generate a required target output surface roughness value (TRa) corresponding to the generated deviation for machine-finishing the component to obtain the desired output roughness by the finishing module.
In an aspect, the system includes an editor unit is in communication with the control unit and the data repository unit. The editor unit is configured to erase the pre-installed pre-trained data of the repository unit to free-up the memory of the repository unit to receive a pre-defined historical data in connection with surface roughness for different components.
In an aspect, the system includes a data loading unit is in communication with the control unit and the repository unit. The data loading unit is configured to load the pre-defined data for different components in connection with a component to be machine-finishing.
In an aspect, the system further includes a trained module in connection with the control unit and the data repository unit to back-test and examine the pre-defined data before feeding to the control unit or the comparator.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
A system for optimizing dwell time of finishing module during machine-finishing will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram of a system for optimizing the dwell time of a finishing module in accordance with an embodiment of the present disclosure;
Figure 2 illustrates a flow chart depicting the steps involved instruction flow of the system for optimizing dwell time during the machine-finishing of a component in accordance with an embodiment of the present disclosure;
Figure 3A and Figure 3B illustrate the architecture of the machining unit of the system for superfinishing and microfinishing between center in accordance with an embodiment of the present disclosure;
Figure 4 illustrates the architecture of the machining unit of the system for superfinishing centerless in accordance with an embodiment of the present disclosure; and
Figure 5 illustrates a plot showing the dwell time and ‘Ra’ difference in accordance with an embodiment of the present disclosure.
LIST OF REFERENCE NUMERALS
100 - System
102 - Control Unit
102a - Analog-to-Digital Converter
104 - Data Repository Unit
106 - Comparator
108 - Input Unit
110 - Optimizer Unit
112 - Sensing Unit
114 - Error Module
116 - Data Loading Unit
118 - Trained Module
120 - Component
122 - Machining Unit
124 - Finishing Module
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details, are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a,” "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms “including,” and “having,” are open ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
When an element is referred to as being “engaged to,” "connected to," or "coupled to" another element, it may be directly engaged, connected, or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
In finishing, dwell time refers to the period during which the finishing tool remains in contact with the workpiece for finishing or grinding. The dwell time plays a significant role in determining the final surface finish and the overall efficiency of the machining process. Optimizing the dwell time is essential to achieve the desired surface quality while minimizing production time and cost.
One of the key objectives in dwell time optimization is to ensure that the Finishing process removes the appropriate amount of material from the workpiece, to generate surface with high precision and surface quality, for aerospace, automotive, and medical device manufacturing application.
Traditionally, dwell time optimization was primarily based on empirical knowledge and the experience of machinists. Superfinishing is the process of finishing rotating workpieces with a fairly soft stone that oscillates parallel to the surface of the workpiece. Amorphous layers left over from previous processes are removed by superfinishing. In superfinishing, there are three types: through-feed, plunge, and wheel. Surfaces with irregular shapes are finished with plunge types. Workpieces are rotated while abrasives are plunged onto desired surfaces.
Conventionally, it is very difficult to predict accurately dwell time in plunge finishing operation, as a result, the current dwell times for plunge superfinishing component tend to be excessively long. To address the aforementioned drawbacks of the conventional systems, the present disclosure envisages a system (hereinafter referred to as “system 100”) for optimizing the dwell time of a finishing module during machine-finishing. The system 100 will now be described with reference to Figure 1.
Referring to Figure 1, the system 100 comprises a control unit 102, at least one data repository unit 104, at least one comparator 106, an input unit 108, and an optimizer unit 110. The different units are connected operatively to a machining unit to machine-finish a component by a finishing module. In the present disclosure, superfinishing is performed by an abrasive film or a polishing film. The machining unit is configured with a head stock and a tail stock to receive the component therebetween.
In an embodiment, the component is selected from a group consisting of steel component, alloy component, a polymeric component or a combination thereof to be machined.
The control unit 102 includes a processor. The processor is configured with a machine learning rule and a machine operating rules and commands. The data repository unit 104 is communicatively connected to the control unit 102. The data repository unit 104 is configured to store, in a table a set of pre-defined pre-trained data containing in connection with 1) pre-finishing roughness values, 2) desired roughness values, and 3) dwell times to convert the pre-finishing roughness of a component to be machined to the desired roughness.
The comparator 106 is communicatively connected to the control unit 102 and the data repository unit 104. The comparator 106 is provided with a crawler-extractor pair. The crawler-extractor pair is configured to crawl on the data of the repository unit and an extract dwell time corresponding to a pair of pre-finishing roughness values and desired roughness values.
The input unit 108 is in communication with the control unit 102 and the crawler-extractor pair. The input unit 108 is configured to capture an actual roughness value of a component to be machined and to receive a user-defined desired output roughness value for the component to be machined. The input unit 108 is configured to provide a data signal to the crawler-extractor pair to extract at least one dwell time corresponding to the pair of the actual surface roughness value and the user-defined desired output roughness value.
The optimizer unit 110 is in communication with the input unit 108 and the crawler-extractor pair. The optimizer unit is configured to receive the extracted dwell time’s and is further configured to compute and display an optimized dwell time for carrying out the machine-finishing operation.
Further, the system 100 includes at least one sensing unit 112, is configured to periodically sense actual output surface roughness after each pass of machine-finishing. The sensing unit 112 is configured to generate at least one corresponding actual output sensed roughness signal.
In an aspect, the control unit 102 includes an analogue-to-digital converter 102a, communicating with the sensing unit 112. the analogue-to-digital converter is being configured to receive the actual output sensed roughness signal. The analogue-to-digital converter is configured to convert the actual output sensed roughness signal to the actual output digital sensed roughness value.
Further, the comparator 106 is configured to be in communication with the analogue-to-digital converter 102a to compare the actual output digital sensed roughness value with the desired output roughness value to generate deviation in the desired output surface roughness value.
The system 100 includes an error module 114 in communication with the comparator 106. The error module is configured to receive the generated deviation from the comparator 106.The error module 114 is configured with a set of machine learning rules in connection with error correction. The error module is configured to generate a required target output surface roughness value (TRa) corresponding to the generated deviation for machine-finishing the component to obtain the desired output roughness by the finishing module.
Further, the system 100 includes an editor unit 104 in communication with the control unit 102 and the data repository unit 104. The editor unit 104 is configured to erase the pre-installed pre-trained data of the repository unit to free-up the memory of the repository unit to receive a pre-defined historical data in connection with surface roughness for different components.
In an aspect, the system includes a data loading unit 116 is in communication with the control unit 102 and the repository unit 104. The data loading unit 116 is configured to load the pre-defined data for different components in connection with a component to be machine-finishing.
In an aspect, the system 100 further includes a trained module 118 in connection with the control unit 102 and the data repository unit 104 to back-test and examine the pre-defined data before feeding to the control unit 102 or the comparator 106.
In an embodiment, the system 100 measures the input Ra of the component in microns. The input roughness of many components was measured and tabulated. The random dwell times were set for each component to ensure data collection across a wider spectrum of dwell times and input roughness. The components were held between a headstock and tailstock while an oscillating superfinishing unit processed them. The output surface roughness of each component was measured and tabulated against dwell times and input roughness. Table 1 shows the values captured from a test conducted. The process configuration includes defining the oscillation rate, film feed rate, rotation speed, etc. The target output surface finish “x2” is updated after each cycle based on the learning equation.
In an aspect, the system 100, each cycle, one or more output surface roughness values were determined by the individual input surface roughness’s 'Ra'. For any cycle for which dwell time is calculated, the input surface roughness 'Ra' can be used to determine the output surface roughness 'Ra’.
In an aspect, the input surface roughness and output surface roughness values are adjusted to optimize dwell times in order to determine the accuracy of the system. In this case, the crawler-extractor crawls through the data of the repository unit and extracts a dwell time based on the pre-finished surface roughness and desired roughness values.
In an aspect, a finishing test conducted on a component with the following operational parameters,
the Input Surface Roughness 'Ra' (microns): 0.45-1.21
Output Surface Roughness 'Ra' (microns): 0.10-0.22
Variation of Output from Target (microns): 0.1-0.2
Calculated Dwell Time (sec): 1.5-5.9
Target Ra x2: 0.31-0.33
In an aspect, the system 100 reduces the dwell time by deciding the one or more dwell time as a target variable. The following are the steps used to determine the error in predicted output and actual output.
• The input surface roughness and output surface roughness was set as independent variables.
• A model equation was generated with the above variables.
• For validation, the input roughness of another set of components was measured, and an output roughness Ra value of 0.3 microns was set.
• Based on a set of machine operating rules and commands to evaluate the regression function, the dwell times were calculated, and the part was processed accordingly.
• The output surface roughness was measured.
• Error in Predicted Output and actual output was minimized based on a set of machine learning rules in connection with error correction to finalize the model.
In an aspect, the system 100 describes the set of machine learning rules and a machine operating rules and commands, a suitable regression equation is generated to calculates the dwell time for the Target Ra as:
..… (1)
Where,
y= Dwell Time
x1=Input Ra
x2=Output Ra
b0, b1, b2, b3, b4, b5 = Coefficients/Weights
In an aspect, the learning function was introduced to reduce the error between target output surface roughness and actual output surface roughness. The learning function considers the variation of the difference between the actual output surface roughness and the target output surface roughness of the past 10 observations. The target output surface roughness was then continuously adjusted by the learning function. This adjusted the dwell times which in turn reduced the error in output surface roughness.
Additional, calculating the learning rate (Error Rate) for target output x2 based on a set of machine learning rules in connection with error correction:
……………………….(2)
Where,
x2 = Output Ra
x2target = Target output Ra
x2new = new target Ra
x = mean output Ra of past 10 observations
a = Learning rate
In an aspect, the system 100 determines the dwell time for a component by calculating the total cycle time without using a machine learning algorithm and with using a machine learning algorithm.
In an aspect, without a machine learning implementation, the plunge dwell time for all components would be set to the worst input component i.e. 8.909 seconds. The total cycle time would be 1514.53 seconds for 170 components. The total cycle time using the ML algorithm is 794.754 seconds. Table 2 shows the total cycle time saving while using a machine learning algorithm. This saving will increase with the number of components processed with large input variations.
Table 2: Total time saving by using Machine Learning
Max Dwell time 8.9090
Total time (Seconds)
pre-ML 1514.5300
Total Time (Seconds)
Post-ML 794.7540
Time-saving in % 47.52%
In an aspect, the shafts-like components are typically processed in grinding machines which provide an output surface finish Ra of 0.4 to 1.2 microns. These components are then sent to the superfinishing/microfinishing machines for finishing to achieve an output surface finish Ra of 0.1 to 0.3 microns. The superfinishing process is with contact rollers and superfinishing films. The microfinishing process is with scissor arms and contact shoes with superfinishing films. The finishing module is actuated to plunge onto the component for a pre-set dwell time. Oscillation at a constant rate is provided either to the job or to the unit.
The dwell time set for this plunge is typically the dwell time required to process a component with an input Ra of 1.2 microns (which is considered the worst input condition) down to an Output Ra of 0.3 microns. However, since the input varies from Ra 0.4 to 1.2 microns when components with lower input Ra are processed, the dwell time is still set to what was required for the worst input condition to ensure that the required output finish is still met.
In an aspect, the following example shows the time saving in percentage for the total dwell time required to get the target x2.
The given inputs are as follows:
• Film Grit: Ranging from 3, 5, 9, 15, 20, 30, 40, 60, 80;
• RPM: Ranging from 70 - 1000;
• Oscillation: Ranging from 200-500;
• Film Feed: Ranging from 10-150;
• Tolerance: Less than 0.4;
In an aspect, the following results are obtained for the given input and output of surface roughness’s:
• Input roughness (microns) in the range of: 0.6-1.2
• Output roughness (microns) in the range of: 0.1-0.3
• Variation of Output (microns) from Target in the range of: 0.1-0.3
• Calculated Dwell Time (sec.) in the range of: 1-6
• Calculated Dwell Time (sec.) Equation in the range of: 1-6
• Target (microns) in the range of: 0.25-0.36
The calculated Standard Deviation, Max Difference, Total dwell time, Max dwell time, Total Dwell time in Non-Adaptive, Time Saving in % are as follows:
Standard Deviation of variation of output (microns) from Target: 0.030195852
Maximum variation of output (microns) from target: 0.204
Total dwell time of calculated Dwell Time (sec) 92.862
Max optimized dwell time (sec) for 20 records: 5.686
Min. optimized dwell time (sec) for 20 records: 1.733
Total Dwell time (sec) in Non-Adaptive: 113.72
Time Saving in %: 18.34%
and the Target finish (x2) is calculated by equation (2) that recites:

??????2??????<0.36:??2=??2??????;
????(??2??????>0.36:??2=0.36;
where,
??2 = output Ra
??2?????? = new target Ra
In an aspect, the system 100 may include a processor. The processor may be implemented as microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor may fetch and execute computer-readable instructions stored in a memory. The functions of the processor may be provided through the use of dedicated hardware as well as hardware capable of executing machine-readable instructions. The processor may be configured to execute functions of various modules of the system 100 such as the control unit 102, the comparator 106, the input unit 108, the optimizer unit 110, the sensing unit 112, an error module 114, the data loading unit 116, and the trained module 118.
Figure 2 illustrates a flow chart depicting the steps involved instruction flow of the system for optimizing dwell time during the machine-finishing of a component in accordance with an embodiment of the present disclosure. The new component is loaded onto the machine for machine-finishing. The input unit measures the input roughness Ra of the component. The machine learning algorithm calculates the dwell time for the component for each pass of machine-finishing starts and stops, where the actual output surface roughness is sensed periodically for each pass of machine-finishing. The target output ‘TRa’ is compared with the actual measured output ‘Ra’ to determine the error correction in each pass. Further, update the target output surface roughness value (TRa) corresponding to the generated deviation for machine-finishing the component to obtain the desired output roughness. The deviation is determined by comparing the actual output digital sensed roughness value with the desired output roughness value.
Figure 3A and Figure 3B illustrate the architecture of the machining unit of the system for superfinishing and microfinishing between centers in accordance with an embodiment of the present disclosure. Figure 3A headstock with a motor drive and a pneumatic tailstock was used to drive and clamp the component between the center. The finishing module having an oscillating assembly, contact wheel, and superfinishing film was set up. The finishing module was mounted on a slide to control the approach and retract plunge operations.
In an operative configuration, the system 100 comprises a control unit 102 is configured with a set of machine learning rules. at least one data repository unit 104 communicatively connected to the control unit 102 and configured to store in a table a set of pre-defined pre-trained data in connection with pre-finishing roughness values, desired roughness values, and dwell times for converting the pre-finishing roughness to the desired roughness of components. At least one comparator 106 is communicatively connected to the control unit 102 and the data repository unit 104, the comparator 106 is configured with a crawler-extractor pair, and the crawler extractor pair is configured to crawl in the data of the repository unit and extract a dwell time corresponding to a pair of the pre-finished surface roughness and the desired roughness values. The input unit 108 is in communication with the control unit 102 and the crawler-extractor pair, the input is configured to capture an actual roughness value of the component and receive a user-defined desired output roughness value for the component and is further configured to provide a data signal to the crawler-extractor pair to extract closest dwell time corresponding to the pair of the actual roughness value and the user-defined desired output roughness value. The optimizer unit 110 is in communication with the input unit 108 and the crawler-extractor pair to receive the dwell time and configured to compute and display an optimized dwell time to be fed to the finishing module in relation to the user-defined desired output roughness value
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of a system for optimizing the dwell time of a finishing module during machine-finishing, that:
• optimize the dwell time;
• effectively capture an input roughness value of a component to be machine-finish;
• facilitates the crawling and extracting of dwell time from a historical pre-trained data;
• increase finishing accuracy;
• adjusts the dwell time as per user requirement;
• guaranteed consistent results despite variation in the input are scalable;
• adaptability to changes in finishing conditions;
• saving film consumption/usage;
• optimise the cycle time of machine-finishing the component; and
• parameters are updated and optimal.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
The use of the expression “at least” or “at least one” suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation. , Claims:WE CLAIM:
1. A system (100) for optimizing the dwell time of a finishing module (124) during the machine-finishing of a component by a machining unit (122), said system comprising:
• a control unit (102) includes a processor, said processor configured with a machine learning rule and a machine operating rules and commands;
• at least one data repository unit (104) communicatively connected to said control unit (102) and configured to store, in a table a set of pre-defined pre-trained data containing in connection with pre-finishing roughness values, desired roughness values, and dwell times for converting the pre-finishing roughness of a component to the desired roughness;
• at least one comparator (106) communicatively connected to said control unit (102) and said data repository unit (104), said comparator (106) provided with a crawler-extractor pair, configured to crawl on the data and extract dwell times corresponding to a pair of pre-finishing roughness values and desired roughness values;
• an input unit (108) in communication with said control unit (102) and said crawler-extractor pair, said input configured to capture an actual roughness value of a component to be machined and to receive a user-defined desired output roughness value for the component to be machined, and further configured to provide a data signals to said crawler-extractor pair to extract at least one dwell time corresponding to the pair of the actual surface roughness value and the user-defined desired output roughness value; and
• an optimizer unit (110) in communication with said input unit (108) and said crawler-extractor pair configured to receive the extracted dwell time’s and further configured to compute and display an optimized dwell time for carrying out the machine-finishing operation.
2. The system (100) as claimed in claim 1, wherein said system (100) includes at least one sensing unit (112), is configured to periodically sense actual output surface roughness after each pass of machine-finishing and is further configured to generate at least one corresponding actual output sensed roughness signal.
3. The system (100) as claimed in claim 2, wherein said control unit (102) includes an analog-to-digital converter (102a), communicating with said sensing unit.
4. The system (100) as claimed in claim 3, wherein said analog-to-digital converter is being configured to receive said actual output sensed roughness signal and is further configured to convert said actual output sensed roughness signal to actual output digital sensed roughness value.
5. The system (100) as claimed in claim 4, wherein said comparator (106) is configured to be in communication with said analog-to-digital converter (102a) to compare said actual output digital sensed roughness value with said desired output roughness value to generate deviation in the desired output surface roughness value.
6. The system (100) as claimed in claim 5, wherein said system (100) includes an error module (114) in communication with said comparator (106) to receive said generated deviation.
7. The system (100) as claimed in claim 6, wherein said error module (114) is configured with a set of machine learning rules in connection with error correction and is further configured to generate a required target output surface roughness value (TRa) corresponding to said generated deviation for machine-finishing the component to obtain said desired output roughness by the finishing module.
8. The system (100) as claimed in claim 1, wherein said system (100) includes an editor unit in communication with said control unit (102) and said data repository unit (104), said editor unit (104) is configured to erase the pre-installed pre-trained data of said repository unit to free-up the memory of said repository unit to receive a pre-defined historical data in connection with surface roughness for different components.
9. The system (100) as claimed in claim 8, wherein said system includes a data loading unit (116) in communication with said control unit and said repository unit, said data loading unit (116) is configured to load said pre-defined data for different components in connection with a component to be machine-finishing.
10. The system (100) as claimed in claim 9, wherein said system (100) further includes a trained module (118) in connection with said control unit (102) and said data repository unit (104) to back-test and examine said pre-defined data before feeding to said control unit (102) or said comparator (106).
Dated this 26th day of July, 2023

_______________________________
MOHAN RAJKUMAR DEWAN, IN/PA – 25
of R.K.DEWAN & CO.
Authorized Agent of Applicant

TO,
THE CONTROLLER OF PATENTS
THE PATENT OFFICE, AT MUMBAI