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. The closed-loop control loop performance evaluation method comprises the following steps: step 1, acquiring reference data; 2, extracting dynamic information and static information of the reference data by using a slow feature analysis algorithm. The method has the beneficial effects that the dynamic and static information of the operation variables and the controlled variables of the reference data and the to-be-evaluated data is extracted by applying a slow feature analysis(SFA) algorithm, and then the Gaussian mixture model (GMM) of the dynamic and static information is estimated; and finally, the Hellinger distance between the online data and the reference data basedon a Gaussian mixture model are calculated to serve as an evaluation index of the performance of the closed-loop control loop. The problem that control performance evaluation is difficult to accurately carry out due to control logic high coupling and data non-Gaussian distribution in the actual process is solved, the accuracy of dynamic process control performance evaluation is improved, a controlloop can be effectively and timely checked and overhauled, and the reliability of the control loop is improved. Therefore, safe and reliable operation of equipment where the loop is located and the whole industrial process is guaranteed.

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