Knowledge-based approaches to fault diagnosis. The development, implementation, evaluation and comparison of knowledge-based systems, incorporating deep and shallow knowledge, to aid in the diagnosis of faults in complex hydro-mechanical devices.

View/ Open
Doherty.pdf (15.14Mb)
Download
Publication date
2010-07-06T15:35:49ZAuthor
Doherty, Neil F.Supervisor
Kochhar, A.K.Keyword
Knowledge-based systemsFault diagnosis
Deep knowledge
Shallow knowledge
Model-based reasoning
Knowledge engineering
System evaluation
Hydro-mechanical devices
Testing, inspection and repair
Rights

The University of Bradford theses are licenced under a Creative Commons Licence.
Institution
University of BradfordDepartment
Department of Mechanical & Manufacturing EngineeringAwarded
1992
Metadata
Show full item recordAbstract
The use of knowledge-based systems to aid in the diagnosis of faults in physical devices has grown considerably since their introduction during the 1970s. The majority of the early knowledge-based systems incorporated shallow knowledge, which sought to define simple cause and effect relationships between a symptom and a fault, that could be encoded as a set of rules. Though such systems enjoyed much success, it was recognised that they suffered from a number of inherent limitations such as inflexibility, inadequate explanation, and difficulties of knowledge elicitation. Many of these limitations can be overcome by developing knowledge-based systems which contain deeper knowledge about the device being diagnosed. Such systems, now generally referred to as model-based systems, have shown much promise, but there has been little evidence to suggest that they have successfully made the transition from the research centre to the workplace. This thesis argues that knowledge-based systems are an appropriate tool for the diagnosis of faults in complex devices, and that both deep and shallow knowledge have their part to play in this process. More specifically this thesis demonstrates how a wide-ranging knowledge-based system for quality assurance, based upon shallow knowledge, can be developed, and implemented. The resultant system, named DIPLOMA, not only diagnoses faults, but additionally provides advice and guidance on the assembly, disassembly, testing, inspection and repair of a highly complex hydro-mechanical device. Additionally it is shown that a highly innovative modelbased system, named MIDAS, can be used to contribute to the provision of diagnostic, explanatory and training facilities for the same hydro-mechanical device. The methods of designing, coding, implementing and evaluating both systems are explored in detail. The successful implementation and evaluation of the DIPLOMA and MIDAS systems has shown that knowledge-based systems are an appropriate tool for the diagnosis of faults in complex hydro-mechanical devices, and that they make a beneficial contribution to the business performance of the host organisation. Furthermore, it has been demonstrated that the most effective and comprehensive knowledge-based approach to fault diagnosis is one which incorporates both deep and shallow knowledge, so that the distinctive advantages of each can be realised in a single application. Finally, the research has provided evidence that the model-based approach to diagnosis is highly flexible, and may, therefore, be an appropriate technique for a wide range of industrial applications.Type
ThesisQualification name
PhDCollections
Related items
Showing items related by title, author, creator and subject.
-
The intranet: a platform for knowledge management systems based on knowledge mapping.Buniyamin, N.; Barber, Kevin D. (2004)This paper presents a discussion based on a literature review and a case study on the suitability of using an intranet as a platform to implement Knowledge Management System (KMS). A description of Knowledge Management (KM) and the current research carried out in this area, with examples of web-based KMS systems currently implemented in organisations, are presented. Further, this paper then describes how knowledge mapping of an organisation's intranet as a form of a KMS can be used to promote the re-utilisation of knowledge, which will contribute to the competitiveness of the organisation. A case study that illustrates and presents evidence of the need and suitability of such a system is provided. The paper ends with a proposal for future research to be carried out in this area.
-
Visualising a knowledge mapping of information systems investment evaluationIrani, Zahir; Sharif, Amir M.; Kamal, M.M.; Love, P.E.D. (01/01/2014)Information systems (IS) facilitate organisations to increase responsiveness and reduce the costs of their supply chain. This paper seeks to make a contribution through exploring and visualising knowledge mapping from the perspective of IS investment evaluation. The evaluation of IS is regarded as a challenging and complex process, which becomes even more difficult with the increased complexity of IS. The intricacy of IS evaluation, however, is due to numerous interrelated factors (e.g. costs, benefits and risks) that have human or organisational dimensions. With this in mind, there appears to be an increasing need to assess investment decision-making processes, to better understand the often far-reaching implications associated with technology adoption and interrelated knowledge components (KC). Through the identification and extrapolation of key learning issues from the literature and empirical findings, organisations can better improve their business processes and thereby their effectiveness and efficiency, while preventing others from making costly oversights that may not necessarily be only financial. In seeking to enlighten the often obscure evaluation of IS investments, this paper attempts to inductively emphasise the dissemination of knowledge and learning through the application of a fuzzy Expert System (ES) based knowledge mapping technique (i.e. Fuzzy Cognitive Map [FCM]). The rationale for exploring knowledge and IS investment evaluation is that a knowledge map will materialise for others to exploit during their specific technology evaluation. This is realised through conceptualising the explicit and tacit investment drivers. Among the several findings drawn from this research, the key resulting knowledge mapping through FCM demonstrated the complex, multifaceted and emergent behaviour of causal relationships within the knowledge area. The principal relationships and knowledge within IS investment evaluation are illustrated as being determined by a blend of managerial and user perspectives.
-
Enhancing university research activities with knowledge management.Chandarasupsang, T.; Harnpornchai, N.; Chakpitak, N.; Dahal, Keshav P. (2006)In the new economy, innovation is regarded as one of the solutions for almost every organisation to survive in the new business era. Universities, especially in terms of research activities, are no difference since they strive for novelties which potentially lead to innovation. An experienced researcher in the university has continually created tacit knowledge in a specific domain, but typically found it difficult to share this tacit knowledge among other researchers for the problem solving purpose. To overcome this problem and to better stimulate knowledge sharing activities among university researchers, Knowledge Management and Knowledge Engineering, particularly KADS, are utilised in this paper to assist a group of different domain researchers in putting their experiences together. In this way, each researcher can make explicit his or her tacit knowledge into KADS task, inference and domain knowledge models. The structured knowledge models captured from different researchers can then be merged together. In this paper, the research in Knowledge Management is selected as a case study, and the results show that the relevant tacit knowledge has been made explicit from a researcher and allow other researchers to share the knowledge as well as to add their own knowledge. Hence, their common research theme is effectively created, and also maintained by a group of researchers.