|
1. |
Adaptive filtering and neural networks for realisation of internal model control |
|
Intelligent Systems Engineering,
Volume 2,
Issue 2,
1993,
Page 67-76
K.J.Hunt,
D.Sbarbaro,
Preview
|
PDF (1488KB)
|
|
摘要:
We show that adaptive inverse control is a further member of the class of control design techniques with an internal model control structure. By implication, therefore, adaptive inverse control is supported by the firm analytical foundation on which internal model control is now based. In a further contribution, we present artificial neural network architectures for the implementation ofnon-linearinternal model control. This approach can be viewed as a non-linear analogue of adaptive inverse control; the network models used are nothing more than non-linear adaptive filters. We use two separate networks in the implementation of non-linear IMC; one network models the plant, and the second network models the plant inverse. We conclude with a simulation example demonstrating non-linear IMC using neural networks.
DOI:10.1049/ise.1993.0008
出版商:IEE
年代:1993
数据来源: IET
|
2. |
A review of techniques for machine learning of real-time control strategies |
|
Intelligent Systems Engineering,
Volume 2,
Issue 2,
1993,
Page 77-90
RanjanVepa,
Preview
|
PDF (2222KB)
|
|
摘要:
In this paper, techniques for machine learning of real-time control strategies are presented and reviewed from a control engineer's point of view. The objective is to present a consolidated view, both in the context of classical control theory and modern artificial intelligence practice. The review seeks to present the principal contributions to the field and the impact of these contributions on control engineering, particularly from the machine learning point of view.
DOI:10.1049/ise.1993.0009
出版商:IEE
年代:1993
数据来源: IET
|
3. |
An integrated project planning environment |
|
Intelligent Systems Engineering,
Volume 2,
Issue 2,
1993,
Page 91-106
GrahamWinstanley,
Michael A.Chacon,
Raymond E.Levitt,
Preview
|
PDF (2130KB)
|
|
摘要:
The life-cycle of complex engineering products involves many disciplines, each of which is responsible for a stage, or phase, in the design-to-production process. Concurrent engineering principles are capable of bringing together the traditionally disparate groups involved. However, in order to facilitate the essential sharing of product and process information, there is a need to provide a common environment capable of supporting the various requirements of designers, production workers and managers while ensuring that communication and appropriate support is maintained. This paper describes model-based planning research in the construction industry. At the heart of the system are a central generic computer model of a certain type of construction and a knowledge-based system able to apply engineering knowledge in the constraint satisfaction process, leading to a planned sequence of construction activities. The environment comprises the central representation and reasoning mechanism, a symbolic computer-aided design facility, and a commercial project planning and management system. The paper details our experiences in developing and applying the environment in the planning of ‘real-life’ construction projects.
DOI:10.1049/ise.1993.0010
出版商:IEE
年代:1993
数据来源: IET
|
4. |
Efficient model-based diagnosis |
|
Intelligent Systems Engineering,
Volume 2,
Issue 2,
1993,
Page 107-118
NicoRoos,
Preview
|
PDF (1697KB)
|
|
摘要:
In this paper, an efficient model-based diagnostic process is described for systems whose components possess a causal relation between their inputs and their outputs. In this diagnostic process, a set of focuses on likely broken components is first determined. Secondly, for each focus, the most informative probing point within the focus can be determined. Both these steps have a worst-case time complexity of O(n2), wherenis the number of components. If the connectivity of the components is low, however, the diagnostic process shows a linear time complexity. We also show how the described diagnostic process can be applied in dynamic systems and systems containing loops. When diagnosing dynamic systems, it is possible to choose between detecting intermittent faults or improving the diagnostic precision by assuming non-intermittency.
DOI:10.1049/ise.1993.0011
出版商:IEE
年代:1993
数据来源: IET
|
5. |
Automating the FMEA process |
|
Intelligent Systems Engineering,
Volume 2,
Issue 2,
1993,
Page 119-132
J.E.Hunt,
C.J.Price,
M.H.Lee,
Preview
|
PDF (1913KB)
|
|
摘要:
Failure mode and effects analysis (FMEA) is a design analysis procedure involving the investigation and assessment of the effects of all possible failure modes on a system. This kind of analysis is of growing importance in the automotive, aerospace and other advanced manufacturing industries, where increasingly complex electrical, electronic and mechanical systems are being combined in safety-critical applications. FMEA is an extremely tedious process because it demands detailed and systematic examination of the operation of all aspects of the design. However, this work must be carried out by professional engineers as it requires extensive experience of the domain. These two factors, painstaking work and expert judgment, indicate the great benefits that automated help will provide for design engineers. This paper describes a program which automates the prediction of the effect of failure modes for electrical systems. This is the most challenging task in FMEA and can only be fully achieved by integrating multiple models in a distributed reasoning architecture. The architecture is open-ended, and the paper shows how the present program can be extended to encompass the full FMEA process.
DOI:10.1049/ise.1993.0012
出版商:IEE
年代:1993
数据来源: IET
|
|