Online performance monitoring and diagnosis of multivariate systems

Online performance monitoring can be used to improve the performance of control systems in industry. The purpose of this article is to detect a performance deterioration and determine its cause in a system. In this article, two indices are used for online performance monitoring of a nonlinear multivariate system with optimally tuned proportional integral controllers. The first index is defined based on a squared distance measurement between the closed-loop system outputs and chosen set-points. The second index is a statistical index that uses all the information in the covariance matrices of the closed-loop system output data. Both indices are used and compared for performance monitoring of a quadruple-tank system. Moreover, hypothesis testing method has been used to determine the cause of the performance deterioration, so that appropriate solutions according to the cause can be applied to the system to improve the performance.

Online Performance Monitoring of Grid-Connected Photovoltaic System using Hybrid Improved Fast Evolutionary Programming and Artificial Neural Network

<p>This paper presents the development of online performance monitoring methods for grid-connected photovoltaic (GCPV) system based on hybrid Improved Fast Evolutionary Programming and Artificial Neural Network (IFEP-ANN). The approach has been developed and validated using previous predicted data measurement. Solar radiation (SR), module temperature (MT) and ambient temperature (AT) has been employed as the inputs, and AC output power (PAC) as the sole output to the neural network model. The actual data from the server has been called and uploaded every five minute interval into Matlab by using FTP (File Transfer Protocol) and the predicted AC output power has been produced based on the prediction developed in the training stages. It is then compared with the actual AC output power by using Average Test Ratio, AR. Any predicted AC output power less than the threshold set up, indicates an error has been occurred in the system. The obtained results show that the hybrid IFEP-ANN gives good performance by producing a sufficiently high correlation coefficient, R value of 0.9885. Besides, the proposed technique can analyse and monitor the system in online mode. </p>