Description:TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of Cyber-Physical Systems (CPS) and ontologies, and more particularly to a system and method for development of a unified ontology for managing and optimising structural, environmental and operational conditions in polyhouse systems.

BACKGROUND
[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Food preservation is essential for post-harvest handling to minimise spoilage and maintain the quality of agricultural produce. In many regions, particularly in developing and rural areas, traditional sun drying is still a prevalent method due to its low operational cost and simplicity. However, this method is susceptible to environmental factors, hygiene issues, and inconsistencies in the drying process, which can impact the quality of the preserved food.
[0004] Polyhouse Solar Dryers (PSDs) provide an improved alternative by enclosing drying environment in a protective structure that retains heat and limits external exposure. This enables more efficient moisture removal and reduces weather-related interruptions. Despite these benefits, many PSDs rely on manual monitoring and control, which may result in variations in drying performance. Efforts to automate PSDs through the integration of sensors and actuators have introduced basic Cyber Physical Systems (CPS) features, enabling better control of temperature, humidity, and airflow. Nonetheless, many of these systems depend on predefined configurations, static data models, and tightly coupled software, making adaptation to changing requirements more difficult. For instance, the addition or modification of sensors may require extensive code and schema changes.
[0005] There is, therefore, a need for a flexible and scalable solution that supports seamless integration of diverse data sources and components to enhance effectiveness of CPS-based solar drying setups.
OBJECTS OF THE PRESENT DISCLOSURE
[0006] A general object of the present disclosure is to provide a unified ontology for polyhouse Cyber-Physical Systems (CPS) that integrates diverse data sources for seamless data management and enhanced system optimisation.
[0007] An object of the present disclosure is to facilitate automated optimisation of drying process by utilising the unified ontology to which reasoning techniques are applied.
[0008] Another object of the present disclosure is to provide real-time contextual awareness for controlling environmental conditions within the polyhouse, based on dynamic data processing.
[0009] Another object of the present disclosure is to provide federated querying capabilities that dynamically connect to external data sources, facilitating efficient decision-making for market operations.
[0010] Another object of the present disclosure is to provide a flexible ontology framework that allows for easy integration of new devices and sensors, reducing system configuration overhead.
[0011] Another object of the present disclosure is to provide semantic handling of data inconsistencies across multiple polyhouses, enabling smooth aggregation of heterogeneous data.
[0012] Another object of the present disclosure is to provide an extensible querying interface that retrieves information from unified ontology without requiring prior knowledge of its schema or vocabulary.

SUMMARY
[0013] Aspects of the present disclosure relate to Cyber-Physical Systems (CPS) and ontologies, specifically a system and method for developing a unified ontology to manage and optimise polyhouse operations. This integrates diverse data sources, through which facilitates automates drying process optimisation, and real-time environmental control. Additionally, the proposed system and method support federated querying, easy device integration, and seamless data aggregation across polyhouses, all while offering an extensible querying interface.
[0014] An aspect of the present disclosure pertains to a system and method for managing and optimising environmental and operational conditions in a polyhouse solar dryer using a Cyber-Physical System (CPS). The system includes a processor configured to implement a unified ontology for polyhouse CPS, which is operatively coupled to a plurality of data sources and sensors that collect data, such as polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications. A memory is coupled to the processor, storing instructions that, when executed, enable the processor to: create a unified ontology integrating the collected data; apply reasoning techniques to identify relationships among the data, allowing for automated optimisation of the drying process; generate contextual awareness for real-time environmental control in the polyhouse; generate instructions for actuation units within the polyhouse based on inferences from the ontology; facilitate communication of the processed data to at least one computing device; and perform federated querying by dynamically connecting to external data sources for market-related decision-making, without requiring prior configuration or schema integration.
[0015] In addition, to generate the unified ontology, the processor is further configured to receive a CPS-enabled polyhouse use case description, generate a polyhouse ontology requirement specification, reference physical, cyber, and meta ontologies for semantic alignment, construct a lightweight ontology based on the specification, and integrate it using one or more ontology design patterns to form the unified ontology.
[0016] In an aspect, the processor is also configured to classify food characteristics based on parameters such as moisture content, texture, or perishability, using predefined ontological classes. This applies semantic reasoning to infer optimal drying schedules based on food characteristics and environmental conditions.
[0017] In an aspect, the processor enables a querying interface to retrieve data without prior knowledge of the ontology schema or vocabulary and updates the unified ontology upon the automatic registration of new sensors and devices, without requiring manual additional configuration.
[0018] In an aspect, the processor resolves data format incompatibilities from various polyhouses by using ontology-defined semantics to aggregate the collected data.
[0019] Another aspect of the present disclosure relates to a method for managing and optimising environmental and operational conditions in a polyhouse solar dryer using a Cyber-Physical System (CPS). The method includes receiving data from a plurality of data sources and sensors, where the data includes polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications. A processor creates a unified ontology that integrates the collected data from the various sources and sensors. The processor applies reasoning techniques to the unified ontology to identify relationships between different types of data, which enables the automated optimisation of the drying process.
[0020] The method also includes generating contextual awareness for real-time control of the polyhouse's environmental conditions based on the collected data. The processor generates instructions for controlling one or more actuation units within the polyhouse, using inferences derived from the unified ontology and the automated optimisation of the drying process. Additionally, the processor facilitates communication of the processed data to at least one computing device. The processor performs federated querying by dynamically connecting to external data sources, retrieving data without prior configuration or schema integration, to support decision-making for market-related operations.
[0021] Further, the method includes the dynamic updating of the unified ontology upon the automatic registration of new sensors and devices without requiring manual configuration. The process of creating the unified ontology further includes receiving a CPS-enabled polyhouse use case description, generating a polyhouse ontology requirement specification based on the use case description, referencing physical, cyber, and meta ontologies for semantic alignment, constructing a lightweight ontology based on the requirement specification and the referenced ontologies, and integrating the lightweight ontology with one or more ontology design patterns to generate the unified ontology.

BRIEF DESCRIPTION OF DRAWINGS
[0022] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. The diagrams are for illustration only, which is thus not a limitation of the present disclosure.
[0023] FIG. 1 illustrates an exemplary block diagram for proposed system to manage and optimise environmental and operational conditions in a polyhouse solar dryer, in accordance with an embodiment of the present invention.
[0024] FIGs. 2A and 2B illustrate exemplary outer and inner views of a polyhouse, in accordance with an embodiment of the present invention.
[0025] FIG. 3 illustrates an exemplary architecture of proposed system, in accordance with an embodiment of the present invention.
[0026] FIG. 4 illustrates an exemplary flow diagram of polyhouse ontology construction process, in accordance with an embodiment of the present invention.(It is adopted from other paper and not sure we can include as part of our invention)
[0027] FIG. 5 illustrates an exemplary flow diagram of interoperable polyhouse ontology, in accordance with an embodiment of the present invention.
[0028] FIG. 6 illustrates an exemplary semantic representation of polyhouse, in accordance with an embodiment of the present invention.
[0029] FIG. 7 illustrates an exemplary flow diagram of a method for managing and optimising environmental and operational conditions in a polyhouse solar dryer using a cyber-physical system (CPS), in accordance with an embodiment of the present invention.
[0030] FIG. 8 illustrates an exemplary computer system in which or with which embodiments of the present disclosure are utilized in accordance with some embodiments of the present disclosure.
DETAILED DESCRIPTION OF THE PRESENT INVENTION
[0031] The following is a detailed description of embodiments of the disclosure represented in the accompanying drawings. The disclosed embodiments are merely exemplary of the invention, which may be embodied in various forms. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0032] Embodiment of the present disclosure polyhouse, specifically a system and method for developing a unified ontology to manage and optimise polyhouse operations. This integrates diverse data sources, automates drying process optimisation, and provides real-time environmental control.
[0033] An embodiment of the present disclosure relates to a system and method for managing and optimising environmental and operational conditions in a polyhouse solar dryer using a Cyber-Physical System (CPS). The system comprises a processor configured to implement a unified ontology for the polyhouse CPS. The processor is operatively coupled to a plurality of data sources and sensors configured to collect data including polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications. A memory is coupled to the processor and is configured to store instructions that, when executed by the processor, enable the processor to create a unified ontology integrating the collected data. The processor is further configured to apply reasoning techniques to identify relationships among the data to enable automated optimisation of the drying process. The processor is also configured to generate contextual awareness to support real-time environmental control within the polyhouse. Based on inferences drawn from the ontology and optimisation logic, the processor is configured to generate instructions for one or more actuation units located within the polyhouse. The processor is additionally configured to facilitate communication of the processed data to at least one computing device. The processor is further configured to perform federated querying by dynamically connecting to external data sources to support market-related decision-making, without requiring prior configuration or schema integration.
[0034] Referring to FIG. 1 an exemplary block diagram (100) for proposed system (102) to manage and optimize environmental and operational conditions in a polyhouse solar dryer (104) (interchangeably referred to as polyhouse (104), hereinafter), as shown in FIGs. 2A and 2B. The system (102) is using a cyber-physical system (CPS) (ontology) to manage polyhouse (104). The system (102) includes a processor (106) (also referred to as microcontroller, herein), configured to implement a unified ontology for polyhouse (104). The processor (106) is operatively coupled to a plurality of data sources and sensors (302) (as shown in FIG. 3), also referred to as end/edge devices and a camera (304). These data sources and sensors being configured to collect data including such as but not limited to polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications. This processor (106) also aggregates the data from the plurality of data sources and sensors of one or more polyhouses by resolving data format incompatibilities using ontology-defined semantics.
[0035] In an exemplary implementation of proposed system with polyhouse (104), three end nodes and edge node (302) are mounted at in dependent logical grid positions within the polyhouse (104). These nodes are responsible for sensing, processing, and executing activation operations in the polyhouse. The end nodes primarily monitor physical conditions of the designated grid positions using temperature and humidity sensors mounted on them. Additionally, the end nodes (302) analyse the current state of the food items drying in the polyhouse (104) using image data captured through camera units, alongside the other physical parameters observed. The edge node (302) coordinates operations among the end nodes and maintains communication with a server (not shown). The server is configured to receive external knowledge sources (314) and is communicatively coupled with a user interface (316). The server is also responsible for making centralized decisions within the polyhouse (104) and for triggering one or more actuation units (306). For instance, an exhaust fan is considered as the actuation unit (306), used to control physical conditions of the polyhouse (104). For instance, each end/edge node (302) is hosted on microcontroller, which is configured and developed by Sony. The microcontroller includes a CXD5602 chip, which runs on six ARM Cortex-M4F cores. In the polyhouse ontology, this microcontroller (106) is represented as an instance of classes ’Controller’, ’Device’, ’Element’, ’IoT Entity’, and ’Platform’. Temperature and humidity of the polyhouse (104) are monitored using the SHT25 sensor. The edge node utilizes SIM7600 (308), a 4G LTE module, to establish communication with the centralized server. In addition, ESP32 (310) is used for Wi-Fi communication between the end and edge nodes (302), and a power bank (312) is incorporated to supply power to multiple components of the system.
[0036] In an embodiment, the processor (106) may also include an interface(s) (110). The interface(s) (110) may include a variety of interfaces, for example, interfaces for data input and output devices, referred to as Input/Output (I/O) devices, storage devices, and the like. The interface(s) (110) may provide a communication pathway for one or more components of the vehicle. Examples of such components include but are not limited to, processing engine(s) (114) and a database (112).
[0037] In an embodiment, the processing engine(s) (114) may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) (114). The database (112) may include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) (114). In some embodiments, the processing engine(s) (114) may include an ontology creation module (116), a drying process optimisation module (118), a contextual awareness generation module (120), a query management module (122), and other module(s) (124). The other module(s) (124) may implement functionalities that supplement applications/functions performed by the system (102).
[0038] In an embodiment, the ontology creation module (116) may be configured to create the unified ontology that integrates the collected data from the end/edge devices (302) and the camera (304), as shown in FIG. 3. The ontology creation module (116) also classifies the food characteristics based on one or more parameters. These parameters include any or a combination of moisture content, texture, or perishability using predefined ontological classes.
[0039] In addition, to generate the unified ontology, the ontology creation module (116) is further configured to perform various steps as shown in FIG. 4. A flow diagram (400) depicting the polyhouse CPS ontology construction process, emphasizing both reuse of well-established ontologies and the development of new Ontology Design Patterns (ODPs). The ontology creation module (116) is further configured to execute a series of structured steps to generate the unified ontology. At block (402), the processor receives a CPS-enabled polyhouse use case description, which informs development of the ontology requirement specification, as shown in block (404). Referenced ontologies from physical, cyber, and meta domains are received from block (406) to ensure semantic alignment, and at block (408), a lightweight ontology is constructed based on this specification received from the block (404) and the referenced ontologies received from the block (406). Subsequently, at block (412), this constructed lightweight ontology with one or more ontology design patterns (received from block (410)) to build an interoperable polyhouse ontology. Finally, the unified ontology is generated at block (414).
[0040] This construction process adheres to the guidelines set by the Semantic Web Best Practices and Deployment Working Group (SWBP) and the Ontology Engineering and Patterns Task Force (OEP), resulting in an ontology that is reusable, interoperable, and semantically coherent, particularly suited for CPS applications.
[0041] In an exemplary implementation, initially, domain-specific information related to Polyhouse Solar Dryers (PSDs), including their structural, functional, and physical characteristics is collected. Using this information, a requirement specification document is created, defining the core objectives of the ontology and framing competency questions in natural language. These questions help clarify the scope of knowledge the ontology must capture and the types of queries it may support. Further, existing ontologies from related domains are identified and evaluated to ensure they satisfy the defined requirements and can address the competency questions effectively.
[0042] In an embodiment, the drying process optimisation module (118) may be configured to apply reasoning techniques to the unified ontology to identify relationships between different types of the collected data, enabling automated optimisation of a drying process. In addition, the semantic reasoning is applied to infer optimal drying schedules based on the food characteristics and the environmental conditions.
[0043] In an embodiment, the contextual awareness generation module (120) may be configured to generate contextual awareness for real-time control of the environmental conditions of the polyhouse (104) from the collected data. In addition, the contextual awareness generation module (120) may generate instructions for one or more actuation units (304) (as shown in FIG. 3) within the polyhouse (104), based on inferences drawn from the unified ontology and the automated optimisation of the drying process. Further, facilitate communication of the processed data to at least one computing device (not shown) communicatively coupled to the processor (106) through communication units including NodeMCU Wi-Fi and 4G (SIM7600EI) (312).
[0044] In an embodiment, the query management module (122) may be configured to perform federated querying by dynamically connecting to external data sources (not shown) to retrieve data without prior configuration or schema integration, for decision-making for market-related operations. In addition, the query management module (122) enables a querying interface configured to retrieve information without requiring prior knowledge of ontology schema or vocabulary.
[0045] Further, the processor (106) dynamically updates the unified ontology upon registration of new sensors and devices without requiring additional configuration.
[0046] In an exemplary embodiment, the polyhouse ontology facilitates the aggregation of data from diverse sources and automatically resolves incompatibilities across data variants. For example, the AgroESP project involves three different polyhouses. The first polyhouse is located within the university campus and uses SHT25 sensor (314) in a sensor node to measure relative humidity. In contrast, the other two polyhouses are located approximately 3 km and 25 km from the university campus and use DHT11 sensors for measuring relative humidity. In this context, two different types of humidity sensors are employed, DHT11 provides measurements in integer values, while SHT25 offers measurements with floating-point precision. These variations are effectively managed by the polyhouse ontology, as the semantics of sensor observations are explicitly annotated in the form of Resource Description Framework (RDF) representations.
[0047] In an exemplary embodiment, any combination of polyhouse-related knowledge can be effectively inferred from the knowledge base using the available information by leveraging the proposed polyhouse ontology. Advantage of this querying system is that prior knowledge of the ontology's schema or vocabulary is not required to formulate a query. By matching known terms with external knowledge sources such as WikiData, DBpedia, or other related repositories, it becomes possible to extract any relevant information pertaining to the polyhouse.
[0048] Referring to FIG. 5, an exemplary flow diagram (500) of polyhouse knowledge graph generation is disclosed. The system (102) adopts a structured approach by utilizing established ontologies to represent various aspects of a smart polyhouse environment. The ontology is configured to capture interconnected components that collectively influence both the food drying process and the operational behavior of the polyhouse. This includes definition and description of relevant concepts, relationships, and constraints that exist in such an environment. The major areas represented in this ontology include structural details, environmental parameters, food-related attributes, control mechanisms, sensor-generated data, time-based factors, and external contextual influences. To represent structural information of the polyhouse, the Building Topology Ontology (BOT) is employed, enabling formal annotation of architectural elements. Details pertaining to food items being dried are described using the FoodOn ontology, which supports classification and annotation of food types, processing stages, ingredients, and biological origins. The data generated from various sensors and actuators embedded in the polyhouse is managed using the FIESTA-IoT ontology. This ontology provides a framework for representing IoT devices, their observations, spatial and temporal contexts, and services.
[0049] The communication infrastructure within the polyhouse, including the interaction among edge devices, end nodes, actuators, and external systems, is captured using the ToCo ontology. This supports detailed modeling of network topology, channels, services, and user roles. The ML Schema ontology is used to annotate the deployment and configuration of machine learning tasks executed on embedded systems. User-specific access control and resource interactions are described through dedicated segments of the ontology, allowing efficient management and organization of the system. These individual ontologies are semantically aligned and integrated to form a unified lightweight polyhouse ontology that ensures consistency across diverse components. This integrated model supports annotation of various entities and facilitates the generation of a comprehensive knowledge graph.
[0050] To meet the requirements aligned with Building Information Modeling (BIM) Maturity Level 3, topological data of the polyhouse is represented using Semantic Web and Linked Data techniques. The BOT ontology, recommended by the W3C Linked Building Data Community Group (LBD CG), provides a high-level framework to represent architectural structures. To enhance detail, the Building Element Ontology (BEO) is used for elements like doors, ramps, and roofs, while the Distribution Element Ontology (DEO) is applied to represent services such as electrical wiring and airflow distribution. An additional object property, bot:has3DModel, is incorporated to associate geometric information with building entities, allowing reconstruction of 3D views at various levels of detail. These ontologies together support the representation and querying of structural elements, fulfilling competency requirements related to information modeling and retrieval within the polyhouse system.
[0051] Referring to FIG. 7, an exemplary semantic representation 600 of polyhouse discloses outlines process of converting the structural elements of a polyhouse into a semantic, machine-readable format that enables interoperability across systems. A core objective in this stage is the creation of a 3D model of the polyhouse using a modeling tool that supports rendering and exporting in Building Information Modeling (BIM) format. The resulting 3D model not only represents the structural framework of the polyhouse but also captures the logical grid layout where food drying activities take place. In the AgroESP setup, the drying area of the polyhouse was segmented into three logical grid units, each monitored by sensors and microcontroller units strategically mounted for optimal data collection. Although the polyhouse structure is initially treated as a unified model, it comprises various distinct elements constructed from different materials. For meaningful semantic representation and efficient data querying, these elements must be manually grouped into logical sets. This enables differentiation between individual components, making it possible to assign unique identities and extract specific attributes for each element. The 3D model, once developed, is exported into the Industry Foundation Classes (IFC) format, a globally recognized standard for data exchange in construction and facility management.
[0052] Subsequently, an IFC-based BIM model is transformed into a BOT-OWL format, allowing semantic annotation of building components. The object property "bot:has3DModel" is employed to associate geometric details with corresponding entities in the ontology. These geometric details are stored in the wavefront OBJ format. Due to the substantial file sizes of OBJ models, direct integration into the ontology is impractical. To overcome this, the OBJ files are hosted on a GitHub repository and linked to relevant polyhouse entities in the ontology using defined individuals, ensuring both scalability and maintainability of the semantic model.
[0053] Referring to FIG. 7, a method 700 for managing and optimising environmental and operational conditions in a polyhouse solar dryer using a cyber-physical system (CPS) using unified ontology is disclosed. At step (702), the method (700) includes receiving data, by a processor (106), from a plurality of data sources and sensors (702). The data includes polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications.
[0054] Continuing further, at step (704), the method (700) includes creating by the processor (106), a unified ontology that integrates the collected data from the data sources and sensors (302). In addition, creating the unified ontology further includes receiving a CPS-enabled polyhouse use case description, generating a polyhouse ontology requirement specification based on the use case description, referencing physical, cyber, and meta ontologies for semantic alignment, constructing a lightweight ontology based on the requirement specification and the referenced ontologies, and constructing an interoperable polyhouse ontology by integrating the lightweight ontology with one or more ontology design patterns to generate the unified ontology.
[0055] Continuing further, at step (706), the method (700) includes applying by the processor (106), reasoning techniques to the unified ontology to identify relationships between different types of data from the collected data, enabling automated optimisation of a drying process.
[0056] Continuing further, at step (708), the method (700) includes generating by the processor, contextual awareness for real-time control of environmental conditions in the polyhouse based on the collected information.
[0057] Continuing further, at step (710), the method (700) includes generating, by the processor (106), instructions for controlling one or more actuation units (304) within the polyhouse (104), based on inferences drawn from the unified ontology and automated optimisation of the drying process.
[0058] Continuing further, at step (712), the method (700) includes facilitating by the processor (106), communication of the processed data to at least one computing device.
[0059] Continuing further, at step (714), the method (700) includes performing by the processor (106), federated querying by dynamically connecting to external data sources to retrieve data without prior configuration or schema integration, to support decision-making for market-related operations.
[0060] Further, the processor (106) dynamically updates the unified ontology upon registration of new sensors and devices without requiring additional configuration.
[0061] In an exemplary implementation, proposed polyhouse ontology is configured to incorporate various structural and functional aspects of every possible entity in the smart PSD. This ontology can be employed as a turnkey framework to capture the knowledge aspects of other types of solar dryers like step-type dryers, cabinet dryers, rack dryers, greenhouse dryers, multi-rack dryers and flat plate air-heater.
[0062] In an exemplary implementation, logical consistency of the polyhouse ontology and property constraints such as domain, range, cardinality, and data type restrictions are verified using the HermiT reasoner. The quality of the ontology is evaluated based on both functional and non-functional requirements. Ontology-based metrics offer insights into the ontology's size, including the number of axioms, classes, and properties, considering only elements explicitly defined within the ontology and excluding those imported from external sources. The base metric values demonstrate a rich set of axioms used to represent polyhouse-specific knowledge. Schema metrics highlight the depth and breadth of the ontology's structure, with Table 1 and Table 2 presenting the evaluated schema metrics and their values. The inheritance richness score of 0.8 reflects the average number of subclasses per class, while the axiom-to-class ratio of 10.5 indicates a well-structured and detailed representation per class. However, schema metrics alone do not provide insights into domain coverage or semantic correctness. Knowledgebase metrics, such as average population and class richness, reflect the distribution of instances, showing that the AgroESP knowledgebase utilizes around 30% of the classes defined in the polyhouse ontology.
[0063] Table 1: Ontology base metric values

[0064] Table 2: Schema metrics

[0065] The non-functional assessment of the polyhouse ontology focuses on maintainability, interoperability, and reusability characteristics using the metrics defined by OQuaRE. Table 3 presents the scores for these aspects, ranging from 1 to 5, where 1 denotes minimally acceptable and 5 denotes highly acceptable characteristics. The reusability score of 3.16 indicates moderate support for reuse of the defined terminologies in other ontologies. In contrast, the scores for consistent search and query, knowledge reuse, controlled vocabulary, and guidance and decision tree metrics are maximally accepted, indicating that the polyhouse ontology supports efficient querying and searching, exhibits a high level of semantic interoperability, and is designed with a strong modular structure.
[0066] Table 3: Model functional adequacy

[0067] FIG. 8 illustrates a block diagram of an example computer system (800) in which or with which embodiments of the present disclosure may be implemented.
[0068] As shown in FIG. 8, the computer system (800) may include an external storage device (810), a bus (820), a main memory (830), a read-only memory (840), a mass storage device (850), communication port(s) (860), and a processor (870). A person skilled in the art will appreciate that the computer system (800) may include more than one processor and communication ports. The processor (870) may include various modules associated with embodiments of the present disclosure. The communication port(s) (860) may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fibre, a serial port, a parallel port, or other existing or future ports. The communication port(s) (860) may be chosen depending on a network, such as a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system (800) connects. The main memory (830) may be random access memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory (840) may be any static storage device(s) including, but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or basic input/output system (BIOS) instructions for the processor (870). The mass storage device (850) may be any current or future mass storage solution, which may be used to store information and/or instructions.
[0069] The bus (820) communicatively couples the processor (870) with the other memory, storage, and communication blocks. The bus (820) can be, e.g., a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), universal serial bus (USB), or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor (870) to the computer system (800).
[0070] Optionally, operator and administrative interfaces, e.g. a display, keyboard, and a cursor control device, may also be coupled to the bus (820) to support direct operator interaction with the computer system (800). Other operator and administrative interfaces may be provided through network connections connected through the communication port(s) (860). In no way should the aforementioned exemplary computer system (800) limit the scope of the present disclosure.
[0071] Thus, the present disclosure provides the system (102) and method (400) to model complex polyhouse CPS ontology, aiming to address semantic interoperability issues and streamline data integration across various domains.
[0072] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions, or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.

ADVANTAGES OF THE PRESENT DISCLOSURE
[0073] The present disclosure provides a unified ontology for polyhouse Cyber-Physical Systems (CPS) that integrates various data sources, enabling seamless data management and optimised system performance.
[0074] The present disclosure provides automated optimisation of the drying process by applying reasoning techniques to the unified ontology.
[0075] The present disclosure provides real-time contextual awareness for controlling environmental conditions within the polyhouse based on dynamic data obtained from the ontology.
[0076] The present disclosure facilitates automatic generation of instructions for actuation units, ensuring optimised polyhouse operations without requiring manual intervention.
[0077] The present disclosure provides federated querying capabilities that dynamically connect to external data sources, supporting efficient decision-making for market-related operations.
[0078] The present disclosure provides a flexible ontology framework that facilitates the easy integration of new devices and sensors, reducing configuration overhead.
[0079] The present disclosure provides semantic handling of data inconsistencies across multiple polyhouses, ensuring smooth aggregation and analysis of heterogeneous data.
[0080] The present disclosure provides an extensible querying interface that retrieves information from the unified ontology without requiring prior knowledge of its schema or vocabulary.
, Claims:1. A system (102) to manage and optimise environmental and operational conditions in a polyhouse solar dryer (104) using an ontology, the system (102) comprising:
a processor (106), configured to implement a unified ontology for polyhouse solar dryer (104), wherein the processor is operatively coupled to a plurality of data sources and sensors, the plurality of data sources and sensors being configured to collect data including polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications; and
a memory (108) coupled to the processor (106), wherein the memory (108) stores instructions that, when executed by the processor (106), cause the processor (106) to:
create the unified ontology that integrates the collected data from the plurality of data sources and sensors;
apply reasoning techniques to the unified ontology to identify relationships between different types of the collected data, enabling automated optimisation of a drying process;
generate contextual awareness for real-time control of the environmental conditions of the polyhouse from the collected data;
generate instructions for one or more actuation units within the polyhouse, based on inferences drawn from the unified ontology and the automated optimisation of the drying process;
facilitate communication of the processed data to at least one computing device; and
perform federated querying by dynamically connecting to external data sources to retrieve data without prior configuration or schema integration, for decision-making for market-related operations.
2. The system (102) as claimed in claim 1, wherein to generate the unified ontology, the processor is further configured to:
receive a CPS-enabled polyhouse use case description;
generates a polyhouse ontology requirement specification based on the use case description;
reference physical, cyber, and meta ontologies for semantic alignment;
construct a lightweight ontology based on the requirement specification and the referenced ontologies; and
construct an interoperable polyhouse ontology by integrating the lightweight ontology with one or more ontology design patterns, to generate the unified ontology.
3. The system (102) as claimed in claim 1, wherein the processor (106) is configured to classify the food characteristics based on one or more parameters, wherein the one or more parameters comprise any or a combination of moisture content, texture, or perishability using predefined ontological classes.
4. The system (102) as claimed in claim 1, wherein the processor (106) applies the semantic reasoning to infer optimal drying schedules based on the food characteristics and the environmental conditions.
5. The system (102) as claimed in claim 1, wherein the processor (106) enables a querying interface configured to retrieve data without requiring prior knowledge of ontology schema or vocabulary.
6. The system (102) as claimed in claim 1, wherein the processor (106) dynamically updates the unified ontology upon registration of new sensors and devices without requiring additional configuration.
7. The system (102) as claimed in claim 1, wherein the processor (106) aggregates the data received from the plurality of data sources and sensors of one or more polyhouses by resolving data format incompatibilities using ontology-defined semantics.
8. A method (700) for managing and optimising environmental and operational conditions in a polyhouse solar dryer using an ontology, the method (800) comprising:
receiving data (702), by a processor, from a plurality of data sources and sensors, wherein the data comprising polyhouse structural attributes, environmental conditions, food characteristics, sensor observations, control parameters, spatial and temporal aspects, and communication specifications;
creating (704), by the processor, a unified ontology that integrates the collected data from the plurality of data sources and sensors;
applying (706), by the processor, reasoning techniques to the unified ontology to identify relationships between different types of data from the collected data, enabling automated optimisation of a drying process;
generating (708), by the processor, contextual awareness for real-time control of environmental conditions in the polyhouse based on the collected information;
generating (710), by the processor, instructions for controlling one or more actuation units within the polyhouse, based on inferences drawn from the unified ontology and automated optimisation of the drying process;
facilitating (712), by the processor, communication of the processed data to at least one computing device; and
performing (714), by the processor, federated querying by dynamically connecting to external data sources to retrieve data without prior configuration or schema integration, to support decision-making for market-related operations.
9. The method (700) as claimed in claim 8, wherein the processor dynamically updates the unified ontology upon registration of new sensors and devices without requiring additional configuration.
10. The method (700) as claimed in claim 8, wherein creating the unified ontology further comprises: receiving a CPS-enabled polyhouse use case description;
generating a polyhouse ontology requirement specification based on the use case description;
referencing physical, cyber, and meta ontologies for semantic alignment;
constructing a lightweight ontology based on the requirement specification and the referenced ontologies; and
constructing an interoperable polyhouse ontology by integrating the lightweight ontology with one or more ontology design patterns to generate the unified ontology.