A fault detection method which uses a static neuro-fuzzy model to describe the correct operation of the plant is presented. It is shown that a static neuro-fuzzy model can be used to detect faults in nonlinear dynamic...
详细信息
A fault detection method which uses a static neuro-fuzzy model to describe the correct operation of the plant is presented. It is shown that a static neuro-fuzzy model can be used to detect faults in nonlinear dynamic systems. Abnormal operation of the plant is detected when the residuals exceed a variable threshold value which accounts for modelling errors. The fault detection scheme is used to detect two types of faults in the cooling coil subsystem an air-conditioning plant. Results are presented which demonstrate that the scheme can detect abnormal operation, without generating false alarms, even if the fault-free and faulty behaviour are similar at some operating points.
Libraries today are interactive information systems in which a considerable range of services are provided and exploited in different ways and with different results by widely disparate groups of users. There can be a...
详细信息
Libraries today are interactive information systems in which a considerable range of services are provided and exploited in different ways and with different results by widely disparate groups of users. There can be a few libraries of any size which do not provide photocopying facilities but there are many others which offer full photographic services. Many large libraries have bindery and conservation facilities. In addition to the standard reference services which trained library staff provide, the staff who are responsible for the more esoteric or limited services, such as photography and binding, have an experties which interacts with the users, very much to the benefit of the latter.
The main objective of the INSYDE project is to define, implement, and demonstrate a comprehensive methodology for the design of hybrid hardware/software systems. Stages in the INSYDE methodology are analysis, system d...
详细信息
The main objective of the INSYDE project is to define, implement, and demonstrate a comprehensive methodology for the design of hybrid hardware/software systems. Stages in the INSYDE methodology are analysis, system design, detailed design, and validation. The functional requirements analysis results, after some iterations, in a conceptual model in OMT. The system design, which iterates over the OMT structure classification and the transition from OMT to OMT*, produces an OMT* system design model. This system design model is transformed into SDL/VDL automatically as far as possible, and partially by the user. Additional information for the further specification development can be taken from the OMT* system design model.
Hypermedia and hypertext systems have much to offer to the information age. However, hypertext systems reported have been poorly designed, hence, they did not provide information in an appropriate format for users. To...
详细信息
Hypermedia and hypertext systems have much to offer to the information age. However, hypertext systems reported have been poorly designed, hence, they did not provide information in an appropriate format for users. To solve this problem, a radical shift in hypertext design is suggested: rather that using links as programmable features, it is suggested that nodes be made more sophisticated. Nodes ought to be defined in terms of specific properties. The properties of the nodes is then be the links, and exhibit such characteristics as inheritance, membership, etc. Users will allocate certain properties to nodes, and these properties form the basis of links. In practice, it is proposed that the form of interaction with the text would be similar to content analysis techniques. Content analysis is a technique for analyzing the content of documents. This technique is described further in this paper.
The DRIVE II project EDDIT (Elderly and Disabled Drivers' Information Telematics) has evaluated a number of in-vehicle telematic systems in terms of their potential value in extending the safe driving life of the ...
详细信息
The DRIVE II project EDDIT (Elderly and Disabled Drivers' Information Telematics) has evaluated a number of in-vehicle telematic systems in terms of their potential value in extending the safe driving life of the elderly. Among the devices tested have been two reversing aids, three types of route guidance system and a head-up night vision enhancement system. The systems studied lead potentially to an increase in the driver's visual and mental workload. The safety implications of using such devices are very important for elderly people who may have difficulty dealing with the mental and cognitive rigors of driving.
Fault diagnosis of engineering systems requires finding the primary components causing the discrepancies between normal behaviour and observed abnormal behaviour of a system. An approach to diagnosis is based on an un...
详细信息
Fault diagnosis of engineering systems requires finding the primary components causing the discrepancies between normal behaviour and observed abnormal behaviour of a system. An approach to diagnosis is based on an underlying model of a device's structure and behaviour. However, the availability of appropriate system description models that explicitly offer all the information required for diagnosis is the key to the success of this methodology. In this paper, a formal modelling scheme integrating qualitative reasoning with bond graphs is proposed to generate qualitative deep models to represent system structure and to predict system behaviour for diagnosing system failures. Moreover, a universal inference mechanism is developed to locate fault candidates and measurement selection via reasoning from the qualitative proposed system structure and observed abnormal behaviour.
A work in progress on the application of Case Based Reasoning (CBR) to problems of Information Retrieval (IR) is reported. Adaptation and Learning have long been viewed as crucial parts of an IR system, and this alone...
详细信息
A work in progress on the application of Case Based Reasoning (CBR) to problems of Information Retrieval (IR) is reported. Adaptation and Learning have long been viewed as crucial parts of an IR system, and this alone suggests that CBR might prove to be a valuable approach to this area. In this article, a CBR model is proposed as an alternative approach for IR. Emphasis is directed toward what exactly should constitute a case. Finally, a system which starts from a problem description, i.e. a need for information, and a context, which involves both intellectual and institutional features is described.
One of the most common database mining tasks is that of inducing relationships which hold between attributes of a database relation. Rules which are discovered to apply to all of the extensional database are called st...
详细信息
One of the most common database mining tasks is that of inducing relationships which hold between attributes of a database relation. Rules which are discovered to apply to all of the extensional database are called strong rules. Strong rules are useful for decision support and are often used in expert systems and expert database systems. The STRIP algorithm (Strong Rule Induction In Parallel), which discovers strong rules within a database relation using parallel techniques, is presented. How the rules induced using STRIP can be used for implementing a semantic query pre-processor among other potential uses is discussed. How parallel processing can be used to speed up database mining operations is also discussed.
It is important to clearly distinguish knowledge discovery in databases (KDD) from machine learning (ML) in order to focus future research in ML on the extension of current ML techniques aiming at larger KDD problems ...
详细信息
It is important to clearly distinguish knowledge discovery in databases (KDD) from machine learning (ML) in order to focus future research in ML on the extension of current ML techniques aiming at larger KDD problems and for KDD researchers to know which ML techniques are adapted to particular KDD tasks. Machine learning is mainly concerned with the construction or the completion or the correction of a knowledge base, by building rules, domain theories, discovering concepts, and so on, in order for the learner to be able to better solve new problems or to predict new situations. Knowledge discovery in databases, on the other hand, deals with the problems that ML techniques cannot yet solve. Other differences are presented and discussed.
The use of a time headway (TH) feedback system may decrease the TH adopted by a driver, although these behavioral changes are likely to be a reaction to the system implemented, and not due to the general adoption of i...
详细信息
The use of a time headway (TH) feedback system may decrease the TH adopted by a driver, although these behavioral changes are likely to be a reaction to the system implemented, and not due to the general adoption of increased THs. Installation of a PC-driven microwave radar, for example, may be generally accepted by drivers, but the implications of the likely cost of the system are unclear. Its practical value for reducing adopted THs may be limited in traffic conditions where focused attention occurs or a degree of social pressure is imposed upon the driver. As a learning device, the system may not be particularly effective.
暂无评论