The paper describes preliminary investigations into the application of RAM-based neuralnetworks to image reconstruction for tomographic systems. Amenability to hardware implementation and the trivial mathematics invo...
详细信息
The paper describes preliminary investigations into the application of RAM-based neuralnetworks to image reconstruction for tomographic systems. Amenability to hardware implementation and the trivial mathematics involved in recall suggest that the RAM-based approach may allow for high speed reconstruction of images at a fraction of the cost of traditional reconstruction methods. Simulated data for a 12 electrode capacitance tomography system, with a 2-phase flow regime, have been generated using finite element modelling. Through extensive software simulations, image flows have been reconstructed from capacitance measurements. Results for two flow regimes (stratified and bubble) are presented. Careful selection of the training patterns and network parameters reveals that high fidelity images can be reconstructed.
High speed manufacturing systems require continuous operation with minimal disruption for repairs and service. A good way of achieving this is through the use of an intelligent diagnostic system. This report provides ...
详细信息
High speed manufacturing systems require continuous operation with minimal disruption for repairs and service. A good way of achieving this is through the use of an intelligent diagnostic system. This report provides a system capable of detecting a number of faults. By using this system, maintenance can be scheduled in advance of sudden failure, and the necessity to replace parts at intervals based on mean time between failures can be reduced. Instead, parts will need to be replaced only when necessary.
The basic concepts of PID control can be generalized within the same structure but allowing for the control of complicated dynamic systems using advanced control design algorithms. This structure arises naturally from...
详细信息
The basic concepts of PID control can be generalized within the same structure but allowing for the control of complicated dynamic systems using advanced control design algorithms. This structure arises naturally from the system description and does not need to be imposed artificially. Recent advances in Local Model networks give a neat extension of the basic (generalized) PID structure to handle nonlinear or time-varying systems.
Databases are complex structures that may conceal implicit patterns of information that cannot be easily discovered by conventional analysis and interrogation methods. This situation can be exacerbated as the database...
详细信息
Databases are complex structures that may conceal implicit patterns of information that cannot be easily discovered by conventional analysis and interrogation methods. This situation can be exacerbated as the database grows in size, and the data therein grows in complexity. Discovery of patterns and trends in such cases requires database query methods more advanced than those traditionally used. Such databases may be analyzed using a set of techniques often collectively referred to as knowledge discovery. Knowledge discovery may be performed effectively using neuralnetworks. The use of neural network techniques for knowledge discovery in an infertility database is described.
Simulations of fuzzy logic and neural network based control algorithms show some useful insights into the potential of soft computing in the control regime of electrical motor servos and drives. Results show that soft...
详细信息
Simulations of fuzzy logic and neural network based control algorithms show some useful insights into the potential of soft computing in the control regime of electrical motor servos and drives. Results show that soft computing offers robustness to a conventional PI controller, and can overcome positional steady state error due to the system's nonlinearities. Design procedures are more straightforward as stringent mathematical models and analysis are usually not involved. Formulation of membership functions and tuning the boundaries of these functions are, however, time-consuming, and solutions may not be guaranteed.
Artificial neuralnetworks have shown good capabilities in medical diagnostic applications. They offer the advantage that they are able to learn the representation by examples, which is of great benefit when the natur...
详细信息
Artificial neuralnetworks have shown good capabilities in medical diagnostic applications. They offer the advantage that they are able to learn the representation by examples, which is of great benefit when the nature of the process is unknown or is difficult to characterise. On the other hand, the hardware implementation of the parallel network structure can dramatically improve the network efficiency. In this paper, A hardware implementation of neural network based ballistocardiogram (BCG) classification system with field programmable gate arrays(FPGAs) technology is presented. The specific trained neural network is implemented in Xilinx XC4000 series FPGAs.
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.< >
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 paper proposes a novel adaptive three-phase autoreclosure technique for double circuit systems using a neural network approach. Based on the investigation of digital simulation of various types of fault on such sy...
详细信息
The paper proposes a novel adaptive three-phase autoreclosure technique for double circuit systems using a neural network approach. Based on the investigation of digital simulation of various types of fault on such systems, some salient features are summarized and extracted which are then used as the inputs of neuralnetworks. A three-layer neural network is constructed, trained and tested. The results indicate that the proposed approach is very reliable.
Hypersonic aircraft require a high degree of system integration. Design tools are needed that can provide rapid, accurate calculations of complex fluid flow. Existing methods are slow. The goal of this project was to ...
详细信息
Hypersonic aircraft require a high degree of system integration. Design tools are needed that can provide rapid, accurate calculations of complex fluid flow. Existing methods are slow. The goal of this project was to apply neuralnetworks to the calculation of fluid flow and heat transfer in a heat exchanger panel for the National AeroSpace Plane (NASP).< >
暂无评论