A closed-loop control loop performance evaluation method based on sfa and hellinger distance

Abstract

The invention relates to a closed-loop control loop performance evaluation method based on SFA and Hellinger distance, comprising: step 1, acquiring reference data; step 2, using a slow feature analysis algorithm to extract dynamic information and static information of the reference data. The beneficial effect of the present invention is: use the slow feature analysis (SFA) algorithm to extract the dynamic and static information of the operating variable and the controlled variable of the reference data and the data to be evaluated, and then estimate the Gaussian mixture model (GMM) of the dynamic and static information, and finally based on the Gaussian The hybrid model calculates the Hellinger distance between the online data and the reference data as the evaluation index of the closed-loop control loop performance; it solves the problem that the control logic is highly coupled in the actual process and the control performance evaluation caused by the non-Gaussian distribution of the data is difficult to carry out accurately, and improves the dynamic process control. The accuracy of performance evaluation helps to carry out effective and timely inspection and maintenance of the control loop, so as to ensure the safe and reliable operation of the equipment where the loop is located and the entire industrial process.

Description

technical field [0001] The invention relates to the field of performance evaluation of an analog control system, and particularly includes an online performance evaluation method of a multivariable coupling control system and a non-Gaussian process. Background technique [0002] The control system occupies a very important position in the modern industrial process, and the production quality, operation safety, material energy consumption and other indicators that affect economic benefits are directly or indirectly related to the performance of the control system. In the actual production process, the control system often performs well when it is put into use, but after a period of operation, due to equipment wear, regular maintenance and untimely maintenance, etc., the performance of the control system may decline, and the control performance will deteriorate. It directly affects the quality of production and leads to loss of economic benefits. If it causes production failur...

AI Technical Summary

Problems solved by technology

For the actual industrial process, the control logic of the loop is more or less coupled, and due to factors such as disturbance, load change, and loop nonlinearity, the loop may work at different set values, and it is difficult for the controlled variable to satisfy the Gaussian distribution assumptions

Existing control performance evaluation methods such as minimum variance and covariance-based performance evaluation algorithms are based on the ideal assumption that the working conditions are stable and the data is Gaussian distribution. Therefore, it is applied to the control loop of the actual industrial process , and can not get a good application effect

Images