Application of an algorithm of neural network generalized predictive control for generating unit

Large-scale generating unit in heat power plant is a system which is complex, nonlinear time-variant with long-time delay and difficulty to establish accurate model, and etc. So it is hard to make system gain optimum running effect with conventional control strategy. However, neural network generalized predictive control strategy has some beneficial characteristics such as wide application and strong robustness, which can compensate the limitation said above effectively. It establishes the math model with BP arithmetic which combines changing step and inducting momentum and achieves predictive control with online rolling optimization and real time feedback revision. The results of the emulation show the availably of it.