Dong Ze

Controller design for networked control systems based on neural network prediction

To the networked control systems in which network-induced delay is time-vary and less than one sample time, a neural network predictive control method is presented to compensate the random delays in this paper. Genetic algorithm is used to optimize parameters. Neural network is introduced to do prediction and optimization calculation. And the uncertainty of the delay is transformed to parametrical uncertainties. Simulation result shows that this control method can evidently improve the control quality with increasing time delay, and has stronger adaptability.

PID-NN decoupling control of CFB boiler combustion system based on PSO method

Circulating fluidized bed (CFB) is becoming the main coal combustion technique all over the world for its high combustion efficiency, low pollution, fuel flexibility and good load-following capability, but its combustion process characteristic is highly non-linear, time-varying, large time delay and multi-variable strong coupling. The conventional control proposal divides the bed temperature control system and main steam pressure control system into two separate PID single-loops without consideration of inter-circuit coupling, which results in low automatism operation rate and often manual operation required. To solve this problem, a multi-variable adaptive neural network decoupling controller with PID structure is introduced based on the principle of NN control and decoupling compensation. The decoupling and control capability of PID NN decoupling controller are from the NN cross-tie structure and the nonlinear mapping properties, as well as the PID style processing of the hidden layer node. The weights of the NN are learned and optimized by the particle swarm optimization (PSO) algorithm, which is known for its searching ability in the total parameter space concurrently and efficiently. These NN weights will not only eliminate the coupling relations between circuits, but also strengthen the PID-NN controllers adaptability. This multivariable decoupling control method is used to control the two-dimensional transfer function matrix of the bed temperature and main steam pressure system in the CFB combustion system. Simulation results show that the new control strategy could overcome nonlinear and strong coupling features of CFB combustion system in a wide range and is expected to have great potential for engineering application.

CFB boiler bed temperature's improved fuzzy control

Keeping the regular bed temperature is the key point of making the circulating fluidized bed boiler work stably. The difficult part of the CFB bed temperature control system lies in: there are many influence factors, little tunable factors, large time delay, big inertia and strong coupling between bed temperature and the main steam pressure. According to the feature of CFB boiler, this paper analyzed the dynamic characteristic of bed temperature control system and the reasons leading to low automation utilization ratio of the combustion system, and designed a bed temperature control system which takes advantage of feed coal quantity for rough tone, primary air flow for precision adjust, by using the cooperation of feed coal and primary air flow times without number to achieve the goal of stabilize the bed temperature. Base on the limitations of fuzzy controller for large time delay system, using controllers output history to replace the deviation change ratio as one of the inputs of the fuzzy controller, the new controller reduces the overshoot of the system, speeds up the settling time, gets better suitability for the changed parameters and solves the CFB bed temperature control problem well. Circulating Fluidized Bed