Skip to Main Content
Effective control for non-linear MIMO systems with strong couples and time-varying property can not be implemented with traditional decouple and control algorithms. Some currently used algorithms cause problems in real-time control and practical implementation. A kind of fault-tolerant decouple and control algorithm for non-linear and time-varying MIMO systems based on neuron adaptive PID and neural network is proposed. With the proposed algorithm, online control for non-linear and time-varying MIMO systems is implemented by neuron adaptive PID controller and online decouple for non-linear and time-varying MIMO systems is implemented by two-layered neural network based on gradient descent searching algorithms for diagonalization of relative gain sensitivity matrix. Decouple and control are implemented in parallel. Stability analysis for the close loop system with neuron adaptive PID controller, online optimization algorithms for proportional factors and self-learning rates are given. A compensating decoupler with two-layered neural network is constructed. Self-learning algorithm based on diagonalization of relative gain sensitivity matrix is used in decouple network and gradient descent algorithm is used in self-learning process. Real-time simulation results show the proposed algorithms are effective in improving dynamic performance of system and reducing couples between variables greatly. Meanwhile, strong fault-tolerant performance is achieved. Satisfactory control effects are achieved.