Guohai Liu

Modified internal model control of induction motor variable frequency speed control system in v/f mode based on neural network generalized inverse

In order to improve the robustness and anti-interference ability of induction motor variable frequency speed control system (IMVFSCS), a modified internal model control (MIMC) method based on neural network generalized inverse (NNGI) was proposed. On the basis of reversibility analysis of original system, the generalized inverse model approximated by the dynamical BP neural network was cascaded with the original system. Based on the idea of NNGI, linearization and open-loop stability of system can be reached, which benefits the integration of control system. Then the robust stability can be improved by introducing modified internal model control method to generalized pseudo-linear system. The results of experimental researches demonstrate that the linearization of the system can be realized successfully and the high performance of speed control can be ensured when the system has inverse modeling errors and changeable load.

Improved particle swarm optimization algorithm and its global convergence analysis

This paper proposed an novel improved particle swarm optimizer (PSO) algorithm with global convergence performance. The global optimum position is unpredictable, so a random solution is introduced to the improved PSO as the best solution(Pg) in the end of every generation. The novel search strategy enables the improved PSO to make use of the uncertain information, in addition to experience, to achieve better quality solutions. Theoretical proof shows the novel random search strategy enables the improved PSO to own the performance of global convergence. Five of well-known benchmarks used in evolutionary optimization methods are used to evaluate the performance of the improved PSO. From experiments, we observe that the improved PSO significantly improves the PSOs performance and performs better than the basic PSO and other recent variants of PSO.

Robust control of induction motor speed regulation system based on fuzzy neural network generalized inverse

According to the multivariable nonlinear and coupling of the Induction Motor Speed Regulation System, a strategy of robust control based on fuzzy neural network (FNN) generalized inverse system (GIS) is adopted. Being properly designed, a FNN is used to construct the generalized inversion of the induction motors speed regulation system and a pseudo-linear system with open-loop stability is obtained after connecting them. A robust controller is designed based on two-degree of freedom internal model control (IMC) by which the rotator speed can be controlled accurately. Experiment results show that this pseudo-linear system has open-loop stability and good static and dynamic performance and the strong robustness to load torque disturbance and parametric perturbation, un-modeled dynamics et al. can be achieved by using the designed controller.

Improved Particle Swarm Optimization Algorithm Based on Random Perturbations

This paper proposed an novel improved particle swarm optimizer algorithm based on random perturbations (PSORP)with global convergence performance. Random perturbations are introduced to improve the performance of global convergence of the particle swarm optimizer (PSO). The novel search strategy enables the PSO-RP to make use of random information, in addition to experience, to achieve better quality solutions. Simulations show the novel random search strategy enables the PSO-RP to own the performance of global convergence. Five of well-known benchmarks used in evolutionary optimization methods are used to evaluate the performance of the PSO-RP. From experiments, we observe that the PSO-RP significantly improves the PSO’sperformance and performs better than the basic PSO and other recent variants of PSO.

The design of three-motor intelligent synchronous decoupling control system

Aiming at the characteristics of multi-input and multi-output, nonlinearity, time-variation and strong coupling in the three-motor synchronous control system, and on the basis of mathematic model analysis of three-motor synchronous control system, the neural network control system is designed. It is composed of three intelligent PID controllers based on BP neural network arithmetic which adjusts the parameters of PID controllers on-line and neuron decoupling compensator. The control of speed and tension of system is realized by three intelligent PID controllers based on BP neural network, and the decoupling control of coupled variables is achieved by neuron decoupling compensator. Experiment is combined with PLC, and the results indicate that the control system can get some optimal parameters of the PID controllers according to different running state of system. The method is designed to realize better decoupling control between the speed and tension in the system, and it has better dynamic and static characteristics.

Three-motor synchronous decoupling control based on BP neural network

A synchronous control system for three-motor is presented in this paper. The control system includes three intelligent PID controllers based on BP neural network arithmetic which adjusts the parameters of PID controllers on-line, and neuron decoupling compensator fulfilling open loop decoupling of multi-variable. The results of experiment indicates that the control system can get some optimal parameters of the PID controllers according to different running state of system, and has better performances of dynamic and static status comparing to traditional PID, and realizes the better decoupling control of speed and tension in the system.

Simulation of three-motor synchronous control system based on BP neural network

Multi-motor synchronous system is being widely applied in industrial field, in order to ulteriorly improve synchronous performance of multi-motor system, this paper presents a synchronous control system for three-motor which includes three intelligent PID controllers based on BP neural network arithmetic which adjusts the parameters of PID controllers on-line, and neuron decoupling compensator fulfilling open loop decoupling control of multi-variable to reduce mutual effect. The results of simulation indicates that the control system can get the optimal parameters of the PID controllers according to different running state of system, and has better performances of dynamic and static status comparing to traditional PID, and realizes better decoupling control of speed and tension in the system.