Proceedings of the colloquium on Computing and control Division 'neural and fuzzy systems: design, hardware and applications' (9 May 1997, Savoy Place, London) are presented. Nine reports were discussed. The m...
详细信息
Proceedings of the colloquium on Computing and control Division 'neural and fuzzy systems: design, hardware and applications' (9 May 1997, Savoy Place, London) are presented. Nine reports were discussed. The main topics were the following ones: neural network and fuzzy system hardware implementation, multilayer feedforward neuralnetworks, hardware implementation of neuro-fuzzy systems;neuralnetworks with intrinsic learning behaviours;neuro-fuzzy network applications.
Applications of neuro-fuzzy systems have provided advances in the ability to deal with abrupt fault conditions and incorporate multiple fault conditions. The support for ambiguities or approximate information implicit...
详细信息
Applications of neuro-fuzzy systems have provided advances in the ability to deal with abrupt fault conditions and incorporate multiple fault conditions. The support for ambiguities or approximate information implicit in fuzzy systems modelling provides the basis for teleological modelling. Finally, we draw attention to recent advances to the integration of fuzzy systems and Dempster-Shafer belief structures. The ensuing fuzzy system is better able to explicitly represent the characteristics of noise sources, therefore improving false alarm rates.
The modelling and generalization abilities of a class of neural algorithms called neurofuzzy networks are investigated. Neurofuzzy networks try to combine the vague linguistic representation of fuzzy logic with the le...
详细信息
The modelling and generalization abilities of a class of neural algorithms called neurofuzzy networks are investigated. Neurofuzzy networks try to combine the vague linguistic representation of fuzzy logic with the learning abilities of neuralnetworks. Also discussed is the Cerebellar model articulation controller (CMAC) which is a tabular look-up table for generalizations.
Instead of modeling complicated processes by mathematical formulas, neuralnetworks learn this tasks autonomously and is suited for modeling, optimization, forecasting, and control of multidimensional nonlinear system...
详细信息
Instead of modeling complicated processes by mathematical formulas, neuralnetworks learn this tasks autonomously and is suited for modeling, optimization, forecasting, and control of multidimensional nonlinear systems and processes. This high potential for applications of neural nets are realized in the corporate research divisions of Siemens in Munich (ZFE) and Princeton (SCR). The broad range of applications on which the central research division cooperates with the business units are presented. These include ideas for steel solutions for metals, neuralnetworks in water business, smoke detection, Simulation Environment for neural nets (SEneuralnetworks) and weather forecasting.
Inferential estimation involves the determination of difficult to measure process variables from easily accessible secondary information. In addition to the capital costs of instrumentation, the downward pressure on m...
详细信息
Inferential estimation involves the determination of difficult to measure process variables from easily accessible secondary information. In addition to the capital costs of instrumentation, the downward pressure on manpower costs and overheads involved in maintenance make soft sensing attractive for industrial applications. Viscosity control in a polymerization reactor is addressed. The neural network based inferential estimation, where the network is trained to predict the polymer viscosity from past torque and viscosity data, is investigated. Results from the offline training of a feedforward network are presented and new work on online viscosity estimation using B-Spline networks is described.
The proceedings contain nine papers on unmanned and remotely operated vehicles. Topics include unmanned submarines and aircraft, remote control, controlsystems, neuralnetworks, flight dynamics, and navigation systems.
The proceedings contain nine papers on unmanned and remotely operated vehicles. Topics include unmanned submarines and aircraft, remote control, controlsystems, neuralnetworks, flight dynamics, and navigation systems.
This paper describes the forward-backward module: a simple building block that allows the evolution of neuralnetworks with intrinsic supervised learning ability. This expands the range of networks that can be efficie...
详细信息
This paper describes the forward-backward module: a simple building block that allows the evolution of neuralnetworks with intrinsic supervised learning ability. This expands the range of networks that can be efficiently evolved compared to previous approaches, and also enables the networks to be invertible i.e. once a network has been evolved for a given problem domain, and trained on a particular dataset, the network can then be run backwards to observe what kind of mapping has been learned, or for use in control problems. A demonstration is given of the kind of self-training networks that could be evolved.
The proceedings contains 7 papers on nonlinear control. Some of the topics discussed include control system synthesis and analysis, neuralnetworks, mathematical models, system stability, optimal controlsystems, unce...
详细信息
The proceedings contains 7 papers on nonlinear control. Some of the topics discussed include control system synthesis and analysis, neuralnetworks, mathematical models, system stability, optimal controlsystems, uncertainty, adaptive control, fuzzy sets, state estimation and control theory.
The work reported here is concerned with research carried out at the University of Birmingham, UK and funded by London Underground Limited (LUL) into early-failure warning systems for safety-critical railway signallin...
详细信息
The work reported here is concerned with research carried out at the University of Birmingham, UK and funded by London Underground Limited (LUL) into early-failure warning systems for safety-critical railway signalling equipment. The paper outlines the motivation for the research, a brief overview of the requirements for condition monitoring systems, a summary of various condition monitoring and fault diagnosis used in the study. The process of laboratory tests and field trials which led to the development of ideas and techniques for the employment of intelligent neural network-based sensors for on-line condition monitoring of railway equipment are briefly reported. Problems still to be tackled will be addressed.
暂无评论