A dimensional tolerancing knowledge management system using Nested Ripple Down Rules (NRDR)

This paper proposes to use a knowledge acquisition (KA) approach based on Nested Ripple Down Rules (NRDR) to assist in mechanical design focusing on dimensional tolerancing. A knowledge approach to incrementally model expert design processes is implemented. The knowledge is acquired in the context of its use, which substantially supports the KA process. The knowledge is captured which human designers utilize in order to specify dimensional tolerances on shafts and mating holes in order to meet desired classes of fit as set by relevant engineering standards in order to demonstrate the presented approach. The developed dimensional tolerancing knowledge management system would help mechanical designers become more effective in the time-consuming tolerancing process of their designs in the future.     

The reuse of knowledge: a user-centred approach

The motivation for the work reported in this paper is the belief that not only is it beneficial to reuse knowledge but it is essential if we wish to build knowledge-based systems (KBS) that meet the needs of users. The focus of most KBS research is on complex modelling at the knowledge level which requires a knowledge engineer to act as the intermediary between the expert and the system. The type of reuse primarily considered is the reuse of ontologies or problem-solving methods so that improvements can be made in system quality and development time. However, there is little focus on the needs of users to access the knowledge in a variety of ways according to the individual's decision style or situation. The system described in this paper seeks to support the user in a number of different activities including knowledge acquisition, inferencing, maintenance, tutoring, critiquing, “what-if” analysis, explanation and modelling. The ability to ask different types of questions and to explore the knowledge in alternative ways is a different type of knowledge reuse. The knowledge acquisition and representation technique used as the foundation is known as ripple-down rules (RDR). To support the exploration activities, RDR have been combined with formal concept analysis which automatically generates an abstraction hierarchy from the low-level RDR assertions. The paper suggests that rapid and incremental KA together with retrospective modelling can be used to provide the user with a system that they can own, build and explore without the difficulties associated with capturing and validating the conceptual models of experts via the mediation of a knowledge engineer.     

Dynamic evaluation of the development process of knowledge-based information systems

Codifying expert domain knowledge is a difficult and expensive task. To evaluate the quality of the outcome, often the same domain expert or a colleague of similar expertise is relied on to undertake a direct evaluation of the knowledge-based system or indirectly by preparing appropriate test data. During an incremental knowledge acquisition process, a data stream is available, and the knowledge base is observed and amended by an expert each time it produces an error. Using the kept record of the system’s performance, we propose an evaluation process to estimate its effectiveness as it gets evolved. We instantiate this process for an incremental knowledge acquisition methodology, Ripple Down Rules. We estimate the added value in each knowledge base update. Using these values, the decision makers in the organisation employing the knowledge-based information system can apply a cost-benefit analysis of the continuation of the incremental knowledge acquisition process. They can then determine when this process, involving keeping an expert online, should be terminated. As a result, the expert is not kept on-line longer than it is absolutely necessary. Hence, a major expense in deploying the information system—the cost of keeping a domain expert on-line—is reduced.     

Incorporating prior knowledge into learning by dividing training data

In most large-scale real-world pattern classification problems, there is always some explicit information besides given training data, namely prior knowledge, with which the training data are organized. In this paper, we proposed a framework for incorporating this kind of prior knowledge into the training of min-max modular (M³) classifier to improve learning performance. In order to evaluate the proposed method, we perform experiments on a large-scale Japanese patent classification problem and consider two kinds of prior knowledge included in patent documents: patent’s publishing date and the hierarchical structure of patent classification system. In the experiments, traditional support vector machine (SVM) and M³-SVM without prior knowledge are adopted as baseline classifiers. Experimental results demonstrate that the proposed method is superior to the baseline classifiers in terms of training cost and generalization accuracy. Moreover, M³-SVM with prior knowledge is found to be much more robust than traditional support vector machine to noisy dated patent samples, which is crucial for incremental learning.     

Discrete-event modelling of fire spreading

We deal here with the application of discrete-event System Specification (DEVS) formalism to implement a semi-physical fire spread model. Currently, models from physics finely representing forest fires are not efficient and still under development. If current softwares are devoted to the simulation of simple models of fire spread, nowadays there is no environment allowing us to model and simulate complex physical models of fire spread. Simulation models of such a type of models require being easily designed, modified and efficient in terms of execution time. DEVS formalism can be used to deal with these problems. This formalism enables the association of object-oriented hierarchical modelling with discrete-event techniques. Object-oriented hierarchical programming facilitates construction, maintenance and reusability of the simulation model. Discrete-events reduce the calculation domain to the active cells of the propagation domain (the heated ones).     

An easy-maintenance,reusable approach for building knowledge-based systems: application to landscape assessment

Multiple Classification Ripple-Down Rules (MCRDR) is an extended methodology which allows an expert to build and maintain a knowledge-based system for multiple classification without technical assistance. Current MCRDR knowledge bases do not exhibit an explicit model of the relationships for the domain terms used by the expert. This is a strong impediment for both reusing and sharing of MCRDR knowledge bases, as well as for rapid development and maintenance. In this work, we describe how a domain knowledge ontological framework can be integrated with MCRDR, so providing this with explicit reusable knowledge components.     

A social software/Web 2.0 approach to collaborative knowledge engineering

Expert systems have traditionally captured the explicit knowledge of a single expert or source of expertise in order to automatically provide conclusions or classifications within a narrow problem domain. This is in stark contrast to social software which enables knowledge communities to share implicit knowledge of a more practical or experiential nature to inform individuals and groups to arrive at their own conclusions. Specialists are often needed to elicit and encode the knowledge in the case of expert systems, whereas one of the (claimed) hallmarks of social software and the Web 2.0 trend, such as Wikis and Blogs, is that everyone, anywhere can chose to contribute input. This openness in authoring and sharing content, however, tends to produce unstructured knowledge that is difficult to execute, reason over or automatically validate. This also poses limitations for its reuse. To facilitate the capture of knowledge-in-action which spans both explicit and tacit knowledge types, a knowledge engineering approach which offers Wiki-style collaboration is introduced. The approach extends a combined rule and case-based knowledge acquisition technique known as Multiple Classification Ripple Down Rules to allow multiple users to collaboratively view, define and refine a knowledge base over time and space.     

Declarative representation of strategic control knowledge

Strategic (control) knowledge typically specifies how a target task is solved. Representing such knowledge declaratively remains a difficult and practical knowledge engineering challenge. The key to addressing this challenge rests on two observations. One, strategic knowledge comprises two finer types of knowledge: subgoaling knowledge used to construct the goal structure for each problem situation pertaining to a target task, and goal-sequencing knowledge used to choose which subgoal in this goal structure is to be pursued at any given moment. Second, when subgoaling knowledge is explicit and expressed in declarative ontological terms, it is possible to fully express goal-sequencing knowledge in the same declarative terms. Building on these observations, we achieve three things. First, we analyse several conventional knowledge-based applications whose subgoaling and goal-sequencing knowledge is implicit, showing that making their subgoaling knowledge explicit permits (re)representing their goal-sequencing knowledge declaratively. Among the applications analysed are MORE and NEOMYCIN. Second, upon studying the roles of goal-sequencing knowledge vis-á-vis subgoaling knowledge, we develop a declarative formalism for representing goal-sequencing knowledge. Finally, we discuss and illustrate key benefits from using our declarative formalism, including an enhanced ability to validate and reuse goal-sequencing knowledge.     

AMS: a declarative formalism for hierarchical representation ofprocedural knowledge

This paper presents a domain-independent formalism, called Activity Manager System (AMS), for the explicit, hierarchical representation of procedural knowledge. The formalism is able to: (1) describe procedures at a reasonable level of complexity and completeness; (2) generate dynamically procedures at different levels of abstraction; (3) organize knowledge hierarchies by means of abstract entities; and (4) allow knowledge reusability at different levels of abstraction. AMS uses the notions of activity, activity network, state, and memory organization packet for activities (MOPA) to represent abstractions, and it allows the user to model an application in a hierarchical manner. The advantages and limitations of AMS are also discussed     

Feature Nets: behavioural modelling of software product lines

Software product lines (SPLs) are diverse systems that are developed using a dual engineering process: (a) family engineering defines the commonality and variability among all members of the SPL, and (b) application engineering derives specific products based on the common foundation combined with a variable selection of features. The number of derivable products in an SPL can thus be exponential in the number of features. This inherent complexity poses two main challenges when it comes to modelling: firstly, the formalism used for modelling SPLs needs to be modular and scalable. Secondly, it should ensure that all products behave correctly by providing the ability to analyse and verify complex models efficiently. In this paper, we propose to integrate an established modelling formalism (Petri nets) with the domain of software product line engineering. To this end, we extend Petri nets to Feature Nets. While Petri nets provide a framework for formally modelling and verifying single software systems, Feature Nets offer the same sort of benefits for software product lines. We show how SPLs can be modelled in an incremental, modular fashion using Feature Nets, provide a Feature Nets variant that supports modelling dynamic SPLs, and propose an analysis method for SPL modelled as Feature Nets. By facilitating the construction of a single model that includes the various behaviours exhibited by the products in an SPL, we make a significant step towards efficient and practical quality assurance methods for software product lines.     

Inference in the SOOKAT object-oriented knowledge acquisition tool

The SOOKAT (structured object-oriented knowledge acquisition tool) knowledge acquisition (KA) tool, supporting the SeSKA (seamless structured knowledge acquisition) methodology, integrates phases of KA through seamless transformations between object-oriented (OO) models.The integration of constructing a knowledge base (KB) can be extended beyond the KA process by performing inferences in instantiations of models constructed during the KA process.The models, constructed during the KA process, form a framework for performing inferences in instantiations of the models.Inferences performed in instantiations of OO models are guided by control objects (CO). Messages are sent between COs and components of the inference structure. A specific CO, possibly using subordinate COs, can be specified for each inference strategy.There exists a mutual CO for forward and backward chaining that can also be used when reasoning according to protocols. In addition, COs for problem-solving methods (PSMs), such as cover-and-differentiate or propose-and-revise, can be used.Mechanisms for importing PSMs over the Internet, as well as for generating specific COs for PSMs, are under development.     

RASES: A database supported framework for structured model base management

Structured management of model base has placed demands on some kind of computer based frameworks with highly structured formalisms. This paper proposes a new framework, called the relational algebraic system entity structure (RASES), which is based on the system entity structure (SES) formalism and the relational algebra (RA) formalism. These formalisms provide a conceptual basis for the structured model base management. Within the framework, structural knowledge of a system is represented in a hierarchical structure and saved in a database. Furthermore, several operations can be formulated in terms of relational algebra which can be coded in a standard query language such as the SQL. The framework can be easily implemented on, and fully utilize the functionality of, relational database management system (RDBMS). With the help of the implemented framework, simulation models can be systematically synthesized from the models in the model base through the following processes. First, a family of hierarchical structures of a system is organized in the form of entity structure by the entity structuring process. Then, candidate models of the system which meet design objectives are synthesized from the entity structure through the pruning process. Finally, designers can conduct appropriate experiment with the models for design verification and performance measure.     

Knowledge-based environment for investigating multicomputer architectures

Multicomputers for massively parallel processing will eventually employ billions of processing elements, each of which will be capable of communicating with every other processing element. A knowledge-based modelling and simulation environment (KBMSE) for investigating such multicomputer architecture at a discrete-event system level is described. The KBMSE implements the discrete-event system specification (DEVS) formalism in an object-oriented programming system of Scheme (a dialect), which supports building models in a hierarchical, modular manner, a systems-oriented approach not possible in conventional simulation languages. The paper presents a framework for knowledge-based modelling and simulation by exemplifying modelling a hypercube multicomputer architecture in the KBMSE. The KBMSE has been tested on a variety of domains characterized by complex, hierarchical structures such as advanced multicomputer architectures, local area computer networks, intelligent multi-robot organizations, and biologically based life-support systems.     

Qualitative modelling with imprecise ecological knowledge: a framework for simulation

Ecological understanding is often imprecise and heterogeneous; relationships between different quantities and objects may only be expressed in roughly quantitative or even non-quantitative terms. We argue that there is a need for general time-driven simulation modelling systems capable of utilising these types of understanding, using vegetation dynamics as an example. Although work has gone into developing qualitative models in the past, it has not focussed on the needs of time-driven simulation and there is currently no off-the-shelf solution available. This paper presents a categorisation of the types of knowledge that comprise formal models, then uses the categorisation as the basis for exploring and developing a framework for time-driven simulation modelling with imprecise, heterogeneous knowledge. One of the key concepts presented is the explicit separation of all non-quantitative state variable values from their direction and rate of change. From this concept a general computational method is developed for updating non-quantitative state variables in time-driven simulation. First-order logic is advocated as a suitable representational vehicle and a modelling system that implements the proposed framework is briefly presented. We believe that the framework provides a useful step towards increasing the practical utility of available knowledge.     

基于涟波下降规则的设计知识管理系统

设计过程是一个知识密集型过程.为了向企业提供有效和准确的设计知识,在分析涟波下降规则工作原理的基础上,提出了基于涟波下降规则的设计知识管理系统架构,给出了该系统的定义,进一步研究了该系统的主要功能.依据提出的架构及其主要功能,通过一个应用实例,验证了研究成果的有效性.     

Using MCRDR based Agile approach for expert system development

Various expert system development approaches were proposed but most of them cannot deal with two problems: the difficulty of analysis and maintenance. Rather than to spend time waiting any longer, it is better to find an alternative solution from other research fields. In computer software development area, researchers have been suffering from the difficulty of maintenance and analysis, just as the researchers in the expert system development field. To solve this issue, researchers in the software used both agile software development and business rules approach: agile software development is for overcoming the the difficulty of analysis, and business rules approach is for reducing issues in the maintenance. There is a big opportunity that those two approaches can also be solve the two issues in the expert system development field. The paper describes requirements of the approach based on agile software development and the business rules approach. As a result, we consider and specify why the Multiple Classification Ripple Down Rules is the novel approach for the expert system development.     

Incremental acquisition of search knowledge

The development of highly effective heuristics for search problems is a difficult and time-consuming task. We present a knowledge acquisition approach to incrementally model expert search processes. Though, experts do not normally have complete introspective access to that knowledge, their explanations of actual search considerations seem very valuable in constructing a knowledge-level model of their search processes.Furthermore, for the basis of our knowledge acquisition approach, we substantially extend the work done on Ripple-down rules which allows knowledge acquisition and maintenance without analysis or a knowledge engineer. This extension allows the expert to enter his domain terms during the KA process; thus the expert provides a knowledge-level model of his search process. We call this framework nested ripple-down rules.Our approach targets the implicit representation of the less clearly definable quality criteria by allowing the expert to limit his input to the system to explanations of the steps in the expert search process. These explanations are expressed in our search knowledge interactive language. These explanations are used to construct a knowledge base representing search control knowledge. We are acquiring the knowledge in the context of its use, which substantially supports the knowledge acquisition process. Thus, in this paper, we will show that it is possible to build effective search heuristics efficiently at the knowledge level. We will discuss how our system SmS1.3 (SmS for Smart Searcher) operates at the knowledge level as originally described by Newell. We complement our discussion by employing SmS for the acquisition of expert chess knowledge for performing a highly pruned tree search. These experimental results in the chess domain are evidence for the practicality of our approach.