A Data-Driven Identification Method for Actuator Fault Factors in Nonlinear Systems

Abstract

The invention discloses a data-driven identification method for a failure factor of a nonlinear system actuator, which belongs to the field of intelligent control. Under the data-driven framework, for the fault failure factor identification problem of nonlinear systems with actuator faults, the identification method is as follows: establish a nonlinear system; dynamically linearize the nonlinear system into equivalent linear data with actuator fault failure factors model; design an update algorithm to estimate the pseudo partial derivative in the linear data model; design a state observer to estimate the system state; design an online estimation algorithm for the fault factor to realize the estimation of the fault factor. The data-driven nonlinear system actuator failure factor identification method disclosed in the present invention can estimate the actuator failure factor in the nonlinear system online, using the data-driven method, which can not rely on specific model information, and has good Under the premise of adaptability, the requirement of actuator fault estimation is met.

Description

technical field [0001] The invention belongs to the technical field of intelligent control, and more specifically relates to an online identification method of data-driven actuator fault factors for nonlinear systems with actuator faults. Background technique [0002] With the rapid development of modern economy, the scale and complexity of modern industrial systems are constantly increasing. Once such systems fail, it may cause huge economic losses. The fault identification method can estimate the fault factors in the system, and then reduce the impact of faults on the control. [0003] For the research on actuator fault factor identification method, the following two issues need to be considered: 1. The current control system is becoming more and more diverse and complex, and the actuator fault factor identification method can be effectively applied to various systems; 2. , It can guarantee the adaptability and achieve the purpose of estimating the fault factors in the sy...

AI Technical Summary

Problems solved by technology

Methods based on artificial intelligence include expert systems, neural networks, etc., which are suitable for systems that cannot obtain detailed mathematical models, but require a lot of production experience and process knowledge, and have poor versatility

[0005] In order to overcome the "unmodeled dynamic" problem of the fault identification method based on the mathematical model method and the poor versatility of the artificial intelligence method, it is necessary to design a method that does not rely on the system model and does not require a lot of production experience and technology Knowledge-based data-driven fault identification method to achieve the purpose of estimating actuator fault factors in the system

Images