Search Results

Conventional fixed controllers in combination with adaptive neural networks provide a powerful controller architecture. By utilizing the existing controller designs and augmenting them with adaptive neural networks engineers may exploit the merits of both control approaches. By adding on an adaptive component to the existing controller the range of operating conditions is increased and robustness to system degradation is improved. One of the simplest neural network controllers is the adaptive linear combiner. In this paper the adaptive linear combiner is described and the controller architecture is applied to an engine rpm controller. Results are given.

Optimization for control system design or testing is commonly used. Most of the optimization approaches are based on simplex or gradient descent. If the system is complex these approaches are susceptible to being caught in local minimums. Particle swarm optimization (PSO) is a subset of evolutionary computation, which includes genetic algorithms. Evolutionary search techniques have been introduced as a means of detecting global minimums within a parameter range. PSO has been presented by a number of researchers, with applications in function optimization and neural network training. In this study PSO theory and equations will be detailed. The procedure will be applied to an engine rpm control system and results will be presented. The optimization procedure is used to minimize cumulative error and select parameters for a lead-lag plus integral control system. The simulation was coded in simulink and is shown in the figures.

This paper presents an implementation of Hopfield and a modified Hopfields Neural Network that solves a binary (0-1) decision making problem. It discusses techniques for formulating this problem as a discrete neural network and then describes it as an nxn matrix of 1's and 0's. The two methods are compared for different sizes of matrices.

This paper addresses the problem of real time assessment or evaluation of an adaptive neural network controller performance. Complex control systems require robust controllers that handle a large variety of operating conditions. In these circumstances controllers must be adaptive or robust with respect to inaccurate plant models and changes in the plant dynamics. One of the major difficulties in adaptive controller is proof of stability of the update mechanism. In the case where a conventional controller is available it is convenient to toggle it based on controller performance. This paper presents a proposed approach to evaluate the performance of an adaptive sigma pi neural network controller.