The general principles of neural and hybrid architectures for multimedia in general are discussed. From the perspective of knowledge engineering, hybrid symbolic/neural agents are advantageous since different mutually...
详细信息
The general principles of neural and hybrid architectures for multimedia in general are discussed. From the perspective of knowledge engineering, hybrid symbolic/neural agents are advantageous since different mutually complementary properties can be combined. Symbolic representations have advantages with respect to easy interpretation, explicit control, fast initial coding, dynamic variable binding and knowledge abstraction. neural agents show advantages for gradual analog plausibility, learning, robust fault-tolerant processing, and generalization to similar input. Since these advantages are mutually complementary, a hybrid symbolic neural architecture can be useful if different processing strategies have to be supported.
Recent developments in the instrumentation of plants has led to multivariate statistical process control (MSPC) techniques becoming increasingly popular for process monitoring in the chemical industry over the last fe...
详细信息
Recent developments in the instrumentation of plants has led to multivariate statistical process control (MSPC) techniques becoming increasingly popular for process monitoring in the chemical industry over the last few years. This paper examines one such algorithm, Partial Least Squares (PLS), and shows how the basic principles of this linear technique can be extended into the nonlinear domain via the application of Radial Basis Function (RBF) neuralnetworks. Results showing the successful application of these methods to fault detection in a validated model of an industrial overheads condenser and reflux drum plant are also given.
Although a large number of neural architectures exist and are applied to a wide range of problems, there continues a need for fast real-time neural network classifiers, especially in the area of sensor interpretation....
详细信息
Although a large number of neural architectures exist and are applied to a wide range of problems, there continues a need for fast real-time neural network classifiers, especially in the area of sensor interpretation. This paper describes a novel neural network architecture and implementation, which has the potential to eventually lead to a system that will be able to satisfy the above needs. A modified Radial Basis Function (RBF) neural network algorithm has been presented, that uses several methods to gain a speed advantage over the original RBF algorithm. A hardware platform has also been proposed, using PIC 16V84 micro-controllers for the implementation of the algorithm. An application has also been discussed, for the above system. This was the real-time condition monitoring and control in an automotive spark-ignition engine. A neural network system as described above can also be applied to a number of other problems, where output classes are limited and response time is important.
The application of artificial neural network techniques to the diagnosis of non-catastrophic faults in the integrated dry route (IDR) process of British Nuclear Fuels are described. It was shown through simulation and...
详细信息
The application of artificial neural network techniques to the diagnosis of non-catastrophic faults in the integrated dry route (IDR) process of British Nuclear Fuels are described. It was shown through simulation and with real IDR process data that one neural network trained with data from a primary operating points are conditioned using the same data pre-processing methods. These data pre-processing methods enable the secondary operating point data to be converted as close to the primary operating point as possible. This is useful if there are not enough data available from different operating points to train separate neuralnetworks for each point.
Quick-Response Excitation (QRE), Dynamic Resistance Braking (DRB) and Fast Valving (FV) are all the important measures to improve the stability of power systems. All the time it is a difficult problem to coordinate th...
详细信息
Quick-Response Excitation (QRE), Dynamic Resistance Braking (DRB) and Fast Valving (FV) are all the important measures to improve the stability of power systems. All the time it is a difficult problem to coordinate the three kinds of nonlinear controllers. In this paper, a cooperative control of QRE, DRB and FV based on artificial neuralnetworks (ANN) is proposed. Both the steady-state stability limits and the transient stability limits of the power system have been improved greatly.
In this paper a method for expanding the limited vocabulary of neural-network based language systems is introduced. The proposed method draws on developmental constraints observed in human language acquisition, to gen...
详细信息
In this paper a method for expanding the limited vocabulary of neural-network based language systems is introduced. The proposed method draws on developmental constraints observed in human language acquisition, to generate increasingly specialist feature maps in linked orthogonal spaces. Each space acts as a semantic filter, channelling words to more specialist spaces. The resultant trace through each space corresponds to a full feature list for the word, which can be manipulated symbolically or by another network. This approach allows arbitrary feature accuracy for any word, whilst limiting input dimensionality to the minimum required to uniquely specify the word in the relevant specialist space. Consequently crossover between unrelated words is also minimised, so avoiding the n-squared relation between computation and vocabulary size found in fully connected networks. The resultant topology of spaces also suggests that complex inferences are possible, and the use of a perception-based feature set allows a common knowledge base to be shared between languages.
This paper describes a neural network and its simulation results for fault diagnosis in HVDC systems. Fault diagnosis is carried out by mapping input data patterns, which represent the behaviour of the system, to one ...
详细信息
This paper describes a neural network and its simulation results for fault diagnosis in HVDC systems. Fault diagnosis is carried out by mapping input data patterns, which represent the behaviour of the system, to one or more fault conditions. The behaviour of the converters is described in terms of the time varying patterns of conducting thyristors and ac & dc fault characteristics. A three-layer neural network consisting of 20 input nodes, 12 hidden nodes and 2 output nodes is used. This paper will describe the performance of the network for ac and dc faults due to changes in number of hidden layers, number of neurons in the layer, learning rate and momentum. Dynamic characteristics of networks for different configurations are studied too. The time performance of the network is also included. neuralnetworks provide an effective way for fault diagnosis and identification. Simulation data obtained from the EMTP will be used to test the performance of this network. The comparison will be given and the result is promising.
Neurofuzzy modelling combines the attractive attributes of fuzzy systems and neuralnetworks, and is ideally suited to data modelling. The resulting models possess the ability to learn empirical data, and their behavi...
详细信息
Neurofuzzy modelling combines the attractive attributes of fuzzy systems and neuralnetworks, and is ideally suited to data modelling. The resulting models possess the ability to learn empirical data, and their behaviour can be described by a series of humanly understandable fuzzy rules. However, conventional neurofuzzy modelling is essentially restricted to low dimensional problems for which good quality expert knowledge and empirical data are available. This observation has motivated the development of constructive neurofuzzy modelling techniques, which iteratively identify parsimonious neurofuzzy models based on a combination of available a priori knowledge and empirical data. Bayesian inferencing techniques are adapted to perform local regularisation producing a method for successfully controlling superfluous model parameters, further improving model generalisation and data interpretation by the generation of valid models. This paper examines the merits of this approach by applying the techniques to a real world data set. The technique successfully produces an accurate transparent model and highlights inadequacies in the data.
Provision of reliability of the walking robots is complex problem. Application of soft computing allows to provide the reliability of robots. Soft-computing is new discipline that bring together all features of fuzzy-...
详细信息
Provision of reliability of the walking robots is complex problem. Application of soft computing allows to provide the reliability of robots. Soft-computing is new discipline that bring together all features of fuzzy-logic, genetic programming, and neuralnetworks. The main peculiarity of soft-computing is capability to treat with uncertain systems that cannot be easily modelled an controlled by using the classical approaches. The walking robots are typical example of systems affected by uncertainty: leg kinematic is often non-linear and known with low accuracy. Overview of soft-computing techniques developed that have been applied to several walking robots is given.
The paper deals with new developments of interpolating memories as the basic element of learning control and with their possible application. It discusses learning control, interpolating memories, characteristic manif...
详细信息
The paper deals with new developments of interpolating memories as the basic element of learning control and with their possible application. It discusses learning control, interpolating memories, characteristic manifolds for automotive control, and possible future developments.< >
暂无评论