WO2016051338A1

WO2016051338A1 - Model driven knowledge engineering framework for computational engineering

Info

Publication number: WO2016051338A1
Application number: PCT/IB2015/057445
Authority: WO
Inventors: Raghavendra Reddy Yeddula; Sushant S Vale; Sreedhar S REDDY; Gautham Purushottham Basavarsu; Amarendra Kumar Singh
Original assignee: Tata Consultancy Services Limited
Priority date: 2014-04-04
Filing date: 2015-09-29
Publication date: 2016-04-07
Also published as: IN2014MU01274A

Abstract

In an embodiment, method(s) and system(s) for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component is disclosed.

Description

MODEL DRIVEN KNOWLEDGE ENGINEERING FRAMEWORK FOR COMPUTATIONAL ENGINEERING

TECHNICAL FIELD

The present invention relates to methods and systems for knowledge engineering frameworks and, particularly but not exclusively, to methods and systems for manufacturing of a component using knowledge engineering frameworks.

DEFINITIONS OF TERMS USED IN THE COMPLETE SPECIFICATION

The expression 'stresses and strains' used hereinafter in this specification refers to effects of different environmental conditions. Environment conditions include normal wear and tear, interactions with other components, atmosphere etc. due to these, component develops "stresses and strains" including stress, strain, fatigue, cracks, etc.

The expression 'experts' used hereinafter in this specification refers to machines including artificial intelligence based machines, expert systems and human experts having knowledge/skill in particular fields of interest.

These definitions are in addition to those expressed in the art. BACKGROUND

Materials engineering is a knowledge-intensive activity. Knowledge plays a key role in all aspects such in selecting a right material composition for a given engineering problem, in selecting right processes and parameters related thereto in order to achieve required properties of a material, in selecting right simulation tools and control parameters if simulation is required during process design, and the like. This knowledge is provided by a knowledge engineering framework associated with a platform that is actually dealing with an engineering problem. A knowledge engineering framework acts as an interface between a user and the platform.

Knowledge Engineering (KE) was initially considered equivalent to transferring expert knowledge into a knowledge base. Drawbacks in this approach led to usage of modeling frameworks for KE. In these frameworks the construction of knowledge based system means building a computer model with the aim of realizing problem-solving capabilities that are comparable to a domain expert. The knowledge acquisition process is considered as a model construction process. Conventional knowledge engineering frameworks such as CommonKADs, Protege-II and Knowledge Based Engineering are very generic in nature. They provide a set of models that are very generic in nature. They provide a broad road map for carrying out knowledge engineering projects in a pre-determined manner. Conventional knowledge engineering frameworks facilitates analysis of a product, manufacturing of a product based on best practices determined by evaluating a stored experience, data and geometry in relation to product family.

Further, conventional CommonKADS proposes organization model, task model, agent model, communication model, knowledge/expertise model and design model. The organization model is meant for modeling the organization structure of an enterprise and the processes carried out in the enterprise. Task model specifies tasks performed to carry out organizational processes and assignment of agents to tasks. Agent model specifies capabilities, preferences, and permissions of agents. Expertise model categorizes knowledge into three types - Domain knowledge, Inference knowledge containing reasoning steps that can be performed on the domain knowledge and applied to tasks, and Task Knowledge which specifies the goals and decomposition of tasks into subtasks.

Furthermore, Knowledge Based Engineering (KBE) is another methodology with its roots in computer-aided design (CAD) and product lifecycle management (PLM) systems. KBE's focus is on product engineering design activities such as analysis, manufacturing etc. It facilitates the creation of a product design based on best practice by storing the experience, geometry and data that relate to a product family. While KBE appears to cover some of the subject areas of interest to us, it lacks in several respects and several problems are associated with this approach.

However, conventional knowledge engineering frameworks as described herein above are unable to deal with different kind of problems related to different aspect of engineering. Conventional knowledge engineering frameworks are limited by their functionality and are unable to be adapted for a variety of engineering problems. Further, conventional knowledge engineering frameworks are not flexible enough to deal with engineering problems effectively and are inefficient.

Hence, there is a need for a knowledge engineering framework that alleviates problems associated with conventional knowledge engineering frameworks. OBJECTS

Some of the objects of the framework of the present invention are aimed to ameliorate one or more problems of the prior art or to at least provide a useful alternative and are listed herein below.

An object of the present invention is to provide a model driven knowledge engineering framework for computational engineering.

Another object of the present invention is to provide a model driven knowledge engineering framework that is adaptable for different kind of engineering problems.

Another object of the present invention is to provide a model driven knowledge engineering framework that effectively and efficiently deals with different kind of engineering problems.

Another object of the present invention is to provide a model driven knowledge engineering framework that is extensible.

Another object of the present invention is to provide a model driven knowledge engineering framework that is intelligent.

Other objects and advantages of the present invention will be more apparent from the following description when read in conjunction with the accompanying figures, which are not intended to limit the scope of the present disclosure.

SUMMARY

This summary is provided to introduce concepts related to manufacturing of a component using knowledge engineering frameworks. This summary is neither intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the present disclosure.

In an embodiment, method(s) and system(s) for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component is disclosed. The method includes capturing a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to the components during their use, a variety of desirable properties and parameters of the components, a variety of simulation models defining the inter-relationship between each of the materials, the material structures, the suitable geometry and manufacturing process steps. Further, the method includes storing the knowledge elements in a knowledge repository. In this respect, the method includes receiving inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters. The method further includes processing the inputs using the rules and commands and the plurality of knowledge elements to obtain the appropriate knowledge elements at each stage of the processes. To this end, the method includes processing the obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component. Subsequently, the method includes simulating the optimum processes using the identified optimum material, material structure, and component geometry to obtain properties and parameters of the component. Further, the method includes comparing the obtained properties and parameters of the component with the desired properties and parameters; and reiterating the method until the obtained properties and parameters of the component conform to the desired properties and parameters.

BRIEF DESCRIPTION OF ACCOMPANYING DRAWINGS

The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to reference like features and modules.

Fig. 1 illustrates an architecture of a model driven knowledge engineering framework, according to an implementation of the present disclosure.

Fig. 2 illustrates a block diagram of a knowledge element adaptor generation of the model driven knowledge engineering framework, according to an implementation of the present disclosure.

Fig. 3 illustrates a network implementing a model driven computing system for selecting a material, a material structure and a suitable geometry of and a process for manufacturing of a component, according to an implementation of the present disclosure.

Fig. 4 illustrates a method for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component, according to an implementation of the present disclosure. It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION

The present disclosure relates to a system and a method for manufacturing of a component using knowledge engineering frameworks.

Unless specifically stated otherwise as apparent from the following discussions, it is to be appreciated that throughout the present disclosure, discussions utilizing terms such as "capturing" or "storing" or "receiving" or "processing" or "simulating" or "comparing" or "reiterating" or the like, refer to the action and processes of a computer system, or similar electronic activity detection device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.

The systems and methods are not limited to the specific embodiments described herein. In addition, modules of each system and each method can be practiced independently and separately from other modules and methods described herein. Each module and method can be used in combination with other modules and other methods.

According to an implementation, the present invention discloses a system and method for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component in a model driven approach.

The model driven knowledge engineering framework of the present invention systematically guides the knowledge capture process by facilitating the determination of different problem contexts that is to be modeled, the kind of knowledge that is to be captured in different problem contexts and the determination of a manner in which the captured knowledge is to be represented to a user. The model driven framework of the present invention provides a semantic foundation for retrieving and applying right knowledge elements in a given problem solving context. Further, the model driven framework of the present invention enables learning generalizations from the captured knowledge relevant to the captured problems. The model driven framework of the present invention possess the capability of extending its abilities on itself by adding new subject areas, new problem solving contexts and knowledge pertaining to the new problem solving contexts. The model driven framework of the present invention has the ability to add new knowledge representation and reasoning mechanisms.

In another implementation, the model driven knowledge engineering framework provides a means that systematically guides the knowledge capture process by providing a clear conceptual map by specifying how different problem contexts may be modeled, what kinds of knowledge may be captured in those problem contexts and how the captured knowledge should be represented. Further, the model driven knowledge engineering framework provides a semantic foundation for retrieving and applying right knowledge elements in a given problem solving context. Subsequently, the model driven knowledge engineering framework provides learning generalizations from the captured knowledge. The model driven knowledge engineering framework may have extending capabilities that includes the ability to add new subject areas, new problem solving contexts and knowledge pertaining to the present model and the ability to add new knowledge representation and reasoning mechanisms.

In another implementation, the model driven knowledge engineering framework provides for capturing a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to the components during their use, a variety of desirable properties and parameters of the components, a variety of simulation models defining the inter-relationship between each of the materials, the material structures, the suitable geometry and manufacturing process steps.

The plurality of knowledge elements may represents the importance and role of knowledge in their respective fields such as the knowledge elements may provide the knowledge of a material. For example, the material knowledge may include knowledge about various material properties such as what kind of properties, such as strength, hardness, ductility, fatigue life, etc., may be achieved with a given material composition and under what conditions, such as manufacturing and/or processing steps, are these properties achieved. The knowledge elements may also belong to the knowledge about material structure. For example, the knowledge about material structure includes knowledge about the kind of structural configurations of a material. Further, material properties may also indicate its microstructure. Some examples of features such as crystal structure, crystal grain sizes, defects such as dislocations, inclusions, etc., provides an important knowledge while determining a material's properties. Thus, the knowledge about the structural features of the materials indicates to what kind of properties is important which may be included while selecting appropriate materials. Further, the knowledge elements may also belong to the knowledge about process-structure -property relationships. For example, a material's structure may be changed by manufacturing processes, so what process causes what kind of changes to the structure and thereby its properties is important for selecting right process steps. Similarly, knowledge of how variations in composition have influence on variations in structure in a given process and therefore properties is also important for selecting right compositions.

Further, the knowledge elements may also provide the manufacturing process knowledge. The manufacturing process knowledge provides the knowledge of different manufacturing processes and their simulation. In this respect, it provides the knowledge of process capabilities, i.e. which process is capable of transforming a material from a given source state to a desired target state, and the material classes to which the process is applicable. Furthermore, it provides the process-structure knowledge, more specifically the knowledge of what a process does to the structure of a material. Furthermore, it provides the process- property knowledge, more specifically the knowledge of what a process does to the properties of a material. Similarly, it provides the process parameter selection knowledge, more specifically the knowledge of how the parameters of a process should be selected to achieve a certain effect. On a similar note, it also provides the knowledge of physical phenomena, more specifically the knowledge of what physical phenomena underlie a process and how these phenomena interact with each other. For example, in casting heat-transfer and fluid-flow interact with each other, so they have to be co-simulated. Further, the knowledge of how governing equations may be selected for a phenomenon. For instance in fluid flow, the selection of a laminar flow model or a turbulent flow model based on parameters such as velocity, density, viscosity, etc. On a similar note, the knowledge of selecting boundary conditions for solving these equations, which depends on a number of conditions such as symmetry of the component, process parameters such as external forces, etc.

Further, the knowledge elements may also provide the product knowledge. More specifically, the product knowledge which may consist of product design knowledge, material selection knowledge, manufacturing process knowledge, and so on. For instance, which functional and structural features to choose for the product configuration to satisfy a given set of requirements, what material to select to meet the given performance and cost requirements, what unit processes to choose so that the material obtains the required properties, and so on.

Furthermore, the knowledge elements may also provide the simulation knowledge. More specifically, the simulation knowledge may provide the simulation parameter knowledge, such as success of simulation depends on setting right values to simulation control parameters such as time step, convergence criteria, etc. Further, the time step may depend on mesh parameters such as mesh element size and material properties. Similarly, the convergence control parameter may depend on mesh parameters and the phenomenon being simulated.

In another implementation, the capturing of a plurality of knowledge elements may include different representational forms such as rules, decision trees, cases, models of different kinds, documents, etc. In this respect, some of these are formal and machine interpre table, others (e.g. documents) are meant purely for human consumption, to be interpreted by a human reader. Further, a knowledge element may also have additional attributes such as an applicability condition, cost and a confidence level. The applicability conditions of the knowledge element may refer to a set of conditions on elements in its context. For example, a set of rules for empirical relations used for computing diffusion coefficient such as a material property parameter, while simulating carburization process being applicable only when the chemistry of material is in a certain range. Further, the cost attributes of the knowledge element may refer to an idea of the computational cost associated with the knowledge element. Furthermore, the confidence level attributes of the knowledge element may refer to an indication of the reliability of the knowledge element in a given context.

In another implementation, the capturing of a plurality of knowledge elements may include mining of the knowledge elements from variety of sources including literatures, machine learning, generalized captured knowledge and the information obtained from experts. The term data mining may include a process of analyzing variety of data from different perspectives and summarizing it into useful information. The data mining in the present invention may refer to all variety of means through which the information may be captured. Further, the capturing of a plurality of knowledge elements may also include capturing the knowledge from a domain expert including direct capture from experts and a mining the decision traces. In another implementation, the capturing of a plurality of knowledge elements may be guided by a knowledge meta model. The knowledge meta model may include a model of the topics about which knowledge needs to be captured. The knowledge meta model may also include a model of the kinds of knowledge that can be captured about a topic. The knowledge meta model may also include a model of the context in which a given piece of knowledge (about a topic) is applicable.

In another implementation, the model driven knowledge engineering framework provides for storing the knowledge elements in a knowledge repository. Further, the model also provides for storing a set of rules and commands in a memory in relation to a given relationship conditions.

In another implementation, the model driven knowledge engineering framework provides for receiving inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters. Further, the received inputs may be understand as the requirement and a problem context on which the selection of material, the selection of material structure, the selection of suitable geometry and a process for manufacturing of a component is based. The received inputs may also refer to inputs received from the user, inputs received for the machine/process, inputs received after deriving knowledge at a certain stage of a process.

In another implementation, the model driven knowledge engineering framework provides for processing the inputs using the rules and commands and the knowledge elements to obtain the appropriate knowledge elements at each stage of the processes. Further, the obtaining / selection of the appropriate knowledge elements at each stage of the processes may also refer to a process of selecting the appropriate or right knowledge elements for a given knowledge requirement in a given problem solving context, by matching the requirement against information captured in the knowledge model and selecting the elements that best meet the requirement. It may also be understood that there may be a case where no knowledge elements matches the requirement exactly. In such scenario, the system may select an element that is the best approximate match as measured along the context and topic dimensions. In another implementation, where in a contexts where meta knowledge is explicitly captured, the meta knowledge element may be used to select the right knowledge elements. In another implementation, the model driven knowledge engineering framework provides for processing the obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component.

In another implementation, the model driven knowledge engineering framework provides for simulating the optimum processes using the identified optimum material, material structure, and component geometry to obtain properties and parameters of the component. Subsequently, the obtained properties and parameters of the component are compared with the desired properties and parameters and the method is reiterated until the obtained properties and parameters of the component conform to the desired properties and parameters.

Throughout the description and claims of this complete specification, the word "comprise" and variations of the word, such as "comprising" and "comprises," means "including but not limited to," and is not intended to exclude, for example, other additives, components, integers or steps. "Exemplary" means "an example of and is not intended to convey an indication of a preferred or ideal embodiment. "Such as" is not used in a restrictive sense, but for explanatory purposes.

For a firmware and/or software implementation, the methodologies can be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. Any machine readable medium tangibly embodying instructions can be used in implementing the methodologies described herein. For example, software codes and programs can be stored in a memory and executed by a processor.

In another firmware and/or software implementation, the functions may be stored as one or more instructions or code on a non-transitory computer-readable medium. Examples include computer-readable media encoded with a data structure and computer-readable media encoded with a computer program. The computer-readable media may take the form of an article of manufacturer. The computer-readable media includes physical computer storage media. A storage medium may be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer; disk and disc, as used herein, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blue-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

It should be noted that the description merely illustrates the principles of the present subject matter. It will thus be appreciated that those skilled in the art will be able to devise various arrangements that, although not explicitly described herein, embody the principles of the present subject matter and are included within its spirit and scope. Furthermore, all examples recited herein are principally intended expressly to be only for pedagogical purposes to aid the reader in understanding the principles of the invention and the concepts contributed by the inventor(s) to furthering the art, and are to be construed as being without limitation to such specifically recited examples and conditions. Moreover, all statements herein reciting principles, aspects, and embodiments of the invention, as well as specific examples thereof, are intended to encompass equivalents thereof.

The manner, in which the system and method for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component in a model driven approach shall be implemented, has been explained in details with respect to the Fig. 1, 2, 3 and 4.

Fig. 1 illustrates an exemplary layout of a model incorporated by a framework 100 of the present invention includes a topic meta model 102, a context meta model 104 and a knowledge element meta model 106. The topic meta model 102 specifies a hierarchy of topics of interest about which knowledge needs to be captured. The hierarchy specifies generalization/specialization relations among topics such as material selection, process selection, process parameter selection, mesh transformation, and the like. A topic may have different knowledge elements in different contexts. For example material selection knowledge of a gear may be different from that of a clutch.

As illustrated by Fig. 1, the knowledge has a certain context in which it is applicable. The context meta model 104 enables the classification of context along several dimensions such as material, process, phenomenon and component. These context elements come from the domain ontology 202, each with its own classification hierarchy as known in the art. The knowledge element meta model 106 capturing of knowledge in different representational forms such as rules, decision trees, cases, models of different kinds, documents and the like. While some of these are formal and machine interpre table, others are meant purely for human consumption, to be interpreted by a human reader. In an exemplary embodiment, a knowledge element may include additional attributes such as applicability conditions. For instance, a set of rules for empirical relations used for computing diffusion coefficient (a material property parameter) while simulating carburization process being applicable only when the chemistry of material is in a certain range. The knowledge element may include cost associated with the knowledge element. Further, the knowledge element may include confidence level which is an indication of the reliability of the knowledge element in a given context.

The knowledge element meta model 106 further includes a meta knowledge element 204 which is a special knowledge element that possesses knowledge about other knowledge elements in a given context. For instance, knowledge about what rules to use and what models to use in different situations, say in the space of steels. The meta knowledge element 204 captures this kind of knowledge, and helps in selecting right knowledge elements for a given requirement in a given application context. The knowledge may be captured as a set of rules, a decision tree or a document that guides a human expert. The knowledge may be captured in many ways such as a direct capture with the help of experts. Knowledge model can serve as the reference for building a suitable interface that systematically guides an expert in capturing the knowledge in the right form, in the right context. Further, knowledge may be extracted indirectly from experts by mining the decision traces left behind by them when they solve design problems. PREMAP as known in the art, records these traces in a component called global state 206. Global state 206 also records the problem context in terms of the component being designed, material being used, process step being performed and so on. This enables us to place the knowledge extracted in its right context in the knowledge repository. Furthermore, knowledge may be extracted from published literature. A typical publication has the following structure such as material compositions experimented with, processes tried out, models used and results obtained. Results have to be extracted and placed in their right context, such as the right material composition, right process parameters and so on. This is a challenging information extraction problem as these things are presented in different sections spread across a -publication. The knowledge element meta model 106 and the associated domain ontology 202 play a useful role in the extraction process. They together provide a high-level map of what to look for in a publication. Data produced in experiments and simulations can be mined to learn rules, decision trees, and so on. To place these knowledge elements in their right context, we have to know the context in which data is produced. This requires the data extraction process to be context-aware as discussed in aforementioned models. Determining the context of data produced during simulations is relatively simpler as the problem context in which a simulation is carried out is explicitly recorded in the global state. This enables us to place the mined knowledge in its right context in a knowledge repository.

The model driven knowledge engineering framework 100 provides generalization of the captured knowledge, context dimensions, context hierarchies and features of context elements provide a means for generalizing the knowledge captured in a given context - basically it generalize a knowledge element to all similar contexts that have similar features. As illustrated in Fig. 1, the knowledge retrieval is the process of selecting right knowledge elements for a given knowledge requirement in a given problem solving context, by matching the requirement against information captured in the knowledge model and selecting the elements that best meet the requirement. There may be no knowledge elements that match the requirement exactly. The system then selects an element that is the best approximate match as measured along the context and topic dimensions. In contexts where meta knowledge is explicitly captured, we can use the meta knowledge element to select the right knowledge elements. Further, a knowledge service is the means by which knowledge is accessed and applied while carrying out a design process. Knowledge services are invoked when executing the process model of a design process. The knowledge service then looks up the global state to retrieve the problem context and the current process step. Based on this the knowledge service retrieves the applicable knowledge elements from the knowledge repository and executes them. An executing knowledge element accesses the global state to read data relevant to the problem, and after solving the problem writes the results back to the global state, which will then be shown to the designer for his consideration. The designer may accept them or override them. If the knowledge element in question is a document, it will simply be displayed to the user.

As illustrated by Fig. 2, global state 206 serves as the 'fact base' for an executing knowledge element 204. Facts of interest are specified by the context model of the knowledge element. Taking rule base as an example, the antecedent part of a rule may specify conditions on material composition, material properties, process parameters and so on, and the consequent part may change some of these values. However, different knowledge element types typically have different execution engines. Some of these execution engines have their own internal representations of the fact bases they operate on. For example, a rule engine uses working memory (essentially a set of tuples) as its internal representation. In such cases, data from the global state has to be made available to the engine in an engine specific form, and after the engine completes it execution, the solution has to be reflected back into the global state. This is done by a knowledge element adapter that sits between the knowledge element and the global state. Such adapters are automatically generated from the interface specifications of knowledge elements, using model driven techniques, as shown in Fig. 2. An interface 204 specifies the ontology objects 202 the element needs as input and the ontology objects the element updates as output.

Knowledge engineering frameworks of prior art are general purpose in nature and are meant to provide a broad road map for how knowledge engineering projects should be implemented, whereas the model driven knowledge engineering framework of the present invention proposes a knowledge modeling framework that is specifically meant for capturing the structure and properties of the knowledge relevant for computational engineering of material, manufacturing processes and products in an integrated manner, thereby being adaptable for different kind of problems and are able to deal effectively and efficiently with different kind of problems.

Fig. 3 illustrates a network implementing a model driven computing system 302 for selecting a material, a material structure and a suitable geometry of and a process for manufacturing of a component. The model driven computing system 302 can be implemented as a variety of communication devices, such as a laptop computer, a notebook, a workstation, a mainframe computer, a server and the like. The model driven computing system 302 described herein, can also be implemented in any network environment comprising a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.

In one implementation, the model driven computing system 302 is connected to one or more computing devices 304-1, 304-2...304-N, individually and commonly hereinafter referred to as device(s) 304, and a knowledge repository 308, through a network 306. The devices 304 may be implemented as, but are not limited to, hand-held devices, laptops or other portable computers, tablet computers, mobile phones, personal digital assistants (PDAs), Smartphone, and the like. The devices 304 may be located within the vicinity of the model driven computing system 302 or may be located at different geographic location as compared to that of the model driven computing system 302. Further, the devices 304 may themselves be located either within the vicinity of each other, or may be located at different geographic locations.

The network 306 may be a wireless or a wired network, or a combination thereof. The network 306 can be a collection of individual networks, interconnected with each other and functioning as a single large network (e.g., the internet or an intranet). The network 306 can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 306 may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), etc., to communicate with each other.

The knowledge repository 308 may be implemented as, but not limited to, enterprise database, remote database, local database, and the like. The knowledge repository 308 may be located within the vicinity of the model driven computing system 302 and devices 304 or may be located at different geographic location as compared to that of the model driven computing system 302 and devices 304. Further, the knowledge repository 308 may themselves be located either within the vicinity of each other, or may be located at different geographic locations. Furthermore, the knowledge repository 308 may be implemented inside the device 204 or inside the activity detection system 202 and the knowledge repository 308 may be implemented as a single database.

In one implementation, the model driven computing system 302 includes processor(s) 312. The processor 312 may be implemented as one or more 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(s) is configured to fetch and execute computer- readable instructions stored in a memory.

The functions of the various elements shown in the figure, including any functional blocks labeled as "processor(s)", may be provided through the use of dedicated hardware as well as hardware capable of executing software in association with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, by a single shared processor, or by a plurality of individual processors, some of which may be shared. Moreover, explicit use of the term "processor" should not be construed to refer exclusively to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), read only memory (ROM) for storing software, random access memory (RAM), non-volatile storage. Other hardware, conventional and/or custom, may also be included.

Also, the model driven computing system 302 includes interface(s) 310. The interfaces 310 may include a variety of software and hardware interfaces that allow the model driven computing system 302 to interact with the entities of the network 306, or with each other. The interfaces 310 may facilitate multiple communications within a wide variety of networks and protocol types, including wire networks, for example, LAN, cable, etc., and wireless networks, for example, WLAN, cellular, satellite-based network, etc.

The model driven computing system 302 may also include a memory 314. The memory 314 may be coupled to the processor 312. The memory 314 can include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.

Further, the model driven computing system 302 may include module(s) 316 and data 318. The modules 316 may be coupled to the processors 312 and amongst other things, include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types. The modules 316 may also be implemented as, signal processor(s), state machine(s), logic circuitries, and/or any other device or component that manipulate signals based on operational instructions. Further, the modules 316 can be implemented in hardware, instructions executed by a processing unit / processor, or by a combination thereof. In another aspect of the present subject matter, the modules 316 may be machine -readable instructions (software) which, when executed by a processor/processing unit, perform any of the described functionalities.

In an implementation, the modules 316 may include a knowledge capture module 320, a component design module 322, a knowledge retrieval module 324, a knowledge execution module 326, a process execution module 328 and other module(s) 330. The other module(s) 330 may include programs or coded instructions that supplement applications or functions performed by the model driven computing system 302. Further, the data 318 may include global state data 332, knowledge retrieval data 334, and other data 336. The other data 336, amongst other things, may serve as a repository for storing data that is processed, received, or generated as a result of the execution of one or more modules in the modules 316. Although the data 318 is shown internal to the model driven computing system 302, it may be understood that the data 318 can reside in an external repository, which may be coupled to the model driven computing system 302.

In one implementation, the model driven computing system 302 may select a material, a material structure, a suitable geometry and a process for manufacturing of a component. The model driven computing system 302 may include the knowledge capture module 320 to capture a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to said components during their use, a variety of desirable properties and parameters of said components, a variety of simulation models defining the inter-relationship between each of the materials, material structures, suitable geometry and manufacturing process steps. Further, the knowledge capture module 320 is configured to store the knowledge elements in a knowledge repository in the memory. The knowledge capture module 320 is further configured to store a set of rules and commands in said memory in relation to said relationship conditions.

According to the present implementation, the model driven computing system 302 may include the component design module 322 to receive inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters.

According to the present implementation, the model driven computing system 302 may include the knowledge retrieval module 324 to process the inputs using the rules and commands and the plurality of knowledge elements to obtain the appropriate knowledge elements at each stage of the processes.

According to the present implementation, the model driven computing system 302 may include the knowledge execution module 326 to process the obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component. According to the present implementation, the model driven computing system 302 may include the process execution module 328 to simulate the optimum processes using the identified optimum material, material structure, and component geometry to obtain properties and parameters of the component.

According to the present implementation, the model driven computing system 302 which already includes the component design module 322, the component design module 322 is further configured to compare the obtained properties and parameters of the component with the desired properties and parameters and reiterate the method until the obtained properties and parameters of the component conform to the desired properties and parameters.

In another implementation, the knowledge capture module 320 is further configured to capture and store said knowledge elements that is guided by a knowledge meta model. Further, the knowledge capture module 320 is configured to capture said knowledge elements including mining of said knowledge elements from variety of sources including literatures and obtaining information from experts.

In another implementation, the knowledge capture module 320, having the knowledge meta model, is further configured to include a context meta model, a topic meta model, and a knowledge element meta model. Further, the knowledge capture module 320 is configured to include additional attributes related to applicability conditions, cost, and confidence level.

In another implementation, the knowledge retrieval module 324, having the appropriate knowledge elements, is further configured to select to a knowledge element that is best match as measured along the context and topic dimensions. Further, the knowledge retrieval module 324 is configured to execute a meta knowledge element.

Fig. 4 illustrates a method 400 for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component according to an embodiment of the present subject matter. The method 400 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, and modules, functions, which perform particular functions or implement particular abstract data types. The method 300 may also be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communication network. In a distributed computing environment, computer executable instructions may be located in both local and remote computer storage media, including memory storage devices. The order in which the method 400 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 400, or alternative method. Additionally, individual blocks may be deleted from the method 400 without departing from the spirit and scope of the subject matter described herein. Furthermore, the method 400 can be implemented in any suitable hardware, software, firmware, or combination thereof. In an example, the method 400 may be implemented in a computing system, such as a model driven computing system 302.

Referring to method 400, at bock 402, capturing a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to said components during their use, a variety of desirable properties and parameters of said components, a variety of simulation models defining the interrelationship between each of the materials, the material structures, the suitable geometry and manufacturing process steps. In an implementation, the knowledge capture module 320 capture a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to said components during their use, a variety of desirable properties and parameters of said components, a variety of simulation models defining the inter-relationship between each of the materials, material structures, suitable geometry and manufacturing process steps.

At block 404, storing said knowledge elements in a knowledge repository in said memory. In an implementation, the knowledge capture module 320 store said knowledge elements in a knowledge repository in said memory.

At block 406, storing a set of rules and commands in said memory in relation to said relationship conditions. In an implementation, the knowledge capture module 320 store a set of rules and commands in said memory in relation to said relationship conditions.

At block 408, receiving inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters. In an implementation, the component design module 322 receive inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters. At block 410, processing said inputs using said rules and commands and said plurality of knowledge elements to obtain the appropriate knowledge elements at each stage of said processes. In an implementation, the knowledge retrieval module 324 store a set of rules and commands in said memory in relation to said relationship conditions.

At block 412, processing said obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component. In an implementation, the knowledge execution module 326 processes said obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component.

At block 414, simulating said optimum processes using said identified optimum material, material structure, and component geometry to obtain properties and parameters of said component. In an implementation, the process execution module 328 simulate said optimum processes using said identified optimum material, material structure, and component geometry to obtain properties and parameters of said component.

At block 416, comparing the obtained properties and parameters of said component with the desired properties and parameters. In an implementation, the component design module 322 compares the obtained properties and parameters of the said component with the desired properties and parameters.

At block 418, reiterating the method until the obtained properties and parameters of said component conform to the desired properties and parameters. In an implementation, the component design module 322 reiterates the method until the obtained properties and parameters of said component conform to the desired properties and parameters.

Although implementations for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component have been described in language specific to structural features and/or method, it is to be understood that the appended claims are not necessarily limited to the specific features or method described. Rather, the specific features and method are disclosed as exemplary implementations for determining human activity using the smart meter data.

Claims

CLAIMS:

1. A model driven method for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component, the method to be executed on a computer, the computer including a memory, the method comprising:

capturing a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to said components during their use, a variety of desirable properties and parameters of said components, a variety of simulation models defining the inter-relationship between each of the materials, the material structures, the suitable geometry and manufacturing process steps; storing said knowledge elements in a knowledge repository in said memory;

storing a set of rules and commands in said memory in relation to said relationship conditions;

receiving inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters;

processing said inputs using said rules and commands and said plurality of knowledge elements to obtain the appropriate knowledge elements at each stage of said processes;

processing said obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component;

simulating said optimum processes using said identified optimum material, material structure, and suitable geometry to obtain properties and parameters of said component; comparing the obtained properties and parameters of said component with the desired properties and parameters; and

reiterating the method until the obtained properties and parameters of said component conform to the desired properties and parameters.

2. The method as claimed in claim 1 , wherein capturing and storing of said knowledge elements is guided by a knowledge meta model.

3. The method as claimed in claim 1, wherein capturing said knowledge elements includes mining of said knowledge elements from variety of sources including literatures and obtaining information from experts.

4. The method as claimed in claim 2, wherein said knowledge meta model comprises a context meta model, a topic meta model, and a knowledge element meta model.

5. The method as claimed in claim 4, wherein said context meta model comprises context along several dimensions including materials, process, phenomenon, and component, and wherein each of said dimensions being derived from a domain ontology.

6. The method as claimed in claim 4, wherein said topic meta model comprises a classification of topics about which knowledge needs to be captured.

7. The method as claimed in claim 4, wherein said knowledge element meta model comprises classification of types of said knowledge elements.

8. The method as claimed in claim 7, wherein said types includes both machine interpreted knowledge elements and human interpreted knowledge elements.

9. The method as claimed in claim 1, wherein said knowledge elements includes additional attributes related to applicability conditions, cost, and confidence level.

10. The method as claimed in claim 7, wherein said knowledge element meta model includes meta knowledge elements having knowledge about other knowledge elements in a given context.

11. The method as claimed in claim 1, wherein obtaining the appropriate knowledge elements includes selecting a knowledge element that is best match as measured along the context and topic dimensions.

12. The method as claimed in claim 1, wherein obtaining the appropriate knowledge elements includes executing a meta knowledge element.

13. The method as claimed in claim 1, wherein processing said obtained appropriate knowledge elements includes composing a plurality of knowledge services that execute the knowledge elements in an appropriate sequence, and wherein executing the knowledge elements includes generating a knowledge execution engine specific adapter.

14. The method as claimed in claim 1, wherein data generated during method re-iterations is mined to update said knowledge repository.

15. A model driven computing system for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component, the computing system comprising:

a processor;

a knowledge capture module coupled to the processor, the knowledge capture module is configured to:

capture a plurality of knowledge elements relating to a variety of materials, a variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to said components during their use , a variety of desirable properties and parameters of said components , a variety of simulation models defining the inter-relationship between each of the materials, material structures, suitable geometry and manufacturing process steps;

store said knowledge elements in a knowledge repository in said memory; store a set of rules and commands in said memory in relation to said relationship conditions;

a component design module coupled to the processor, the component design module is configured to:

receive inputs in connection with a component for which a material, its structure, a suitable geometry and a plurality of processes for its manufacture are to be selected including its desired properties and parameters;

a knowledge retrieval module coupled to the processor, the knowledge retrieval module is configured to:

process said inputs using said rules and commands and said plurality of knowledge elements to obtain the appropriate knowledge elements at each stage of said processes; a knowledge execution module coupled to the processor, the knowledge execution module is configured to:

process said obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component;

a process execution module coupled to the processor, the process execution module is configured to:

simulate said optimum processes using said identified optimum material, material structure, and suitable geometry to obtain properties and parameters of said component; and

the component design module is further configured to:

compare the obtained properties and parameters of the said component with the desired properties and parameters;

reiterate the method until the obtained properties and parameters of said component conform to the desired properties and parameters.

16. The system as claimed in claim 15, wherein the knowledge capture module is further configured to capture and store said knowledge elements that is guided by a knowledge meta model.

17. The system as claimed in claim 15, wherein the knowledge capture module is further configured to capture said knowledge elements and includes mining of said knowledge elements from variety of sources including literatures and obtaining information from experts, said knowledge capture module is further configured to update said knowledge repository by mining data generated during the re-iterations.

18. The system as claimed in claim 16, wherein the knowledge capture module, having the knowledge meta model, is further configured to includes a context meta model, a topic meta model, and a knowledge element meta model.

19. The system as claimed in claim 15, wherein the knowledge capture module having said knowledge elements is further configured to includes additional attributes related to applicability conditions, cost, and confidence level.

20. The system as claimed in claim 15, wherein the knowledge retrieval module is further configured to select to a knowledge element that is best match as measured along the context and topic dimensions.

21. The system as claimed in claim 15, wherein the knowledge retrieval module, having the appropriate knowledge elements, is further configured to execute a meta knowledge element.

22. The system as claimed in claim 15, wherein said knowledge execution module is configured to compose a plurality of knowledge services that execute the knowledge elements in an appropriate sequence, and wherein executing the knowledge elements includes generating a knowledge execution engine specific adapter.

23. A non-transitory computer-readable medium having embodied thereon a computer readable program code for executing a model driven method for selecting a material, a material structure, a suitable geometry and a process for manufacturing of a component, the method comprising:

capturing a plurality of knowledge elements relating to variety of materials, variety of material structures, a variety of manufacturing processes, a variety of manufacturing process conditions, a variety of components, a variety of stresses and strains applicable to said components during their use , a variety of desirable properties and parameters of said components , a variety of simulation models defining the inter-relationship between each of the materials, the material structures, the suitable geometry and manufacturing process steps; storing said knowledge elements in a knowledge repository in said memory;

processing said inputs using said rules and commands and said plurality of knowledge elements to obtain the appropriate knowledge elements at each stage of said processes; processing said obtained appropriate knowledge elements to identify an optimum material, material structure, a suitable geometry and one or more optimum processes of manufacture of the component;