基于神经网络和过程机理特性的锅炉蒸发系统仿真

BOILER EVAPORATION SYSTEM SIMULATION BASED ON NEURAL NETWORK AND PROCESS MECHANISM CHARACTERISTIC

文中构建了一种基于神经网络和过程机理特性的自然循环锅炉蒸发系统仿真模型。该模型在型式上为混合人工神经网络模型 ,具有十分理想的仿真速度 ;在网络模型的设计上 ,较好地考虑了系统及网络输入与输出间的物理基础 ,网络模型在一定程度上由常规的黑箱模型转化为“灰箱模型”。与常规的神经网络模型相比 ,该网络模型的训练除了具有通常的输入输出间纯数值映射关系学习功能之外 ,还较为充分地体现了系统输入与输出间的物理机理学习 ,从而保基金项目 :教育部高校骨干教师资助计划资助项目 (GG 470 10 188 10 42 )。证了网络模型的联想能力、对系统过渡过程的预报能力和外推效果。同时 ,利用前述的仿真方法还能够实现锅炉蒸发系统的在线建模 ,加强了模型对实际系统的描述能力。文中通过仿真试验结果证明了上述建模方法的有效性。

A simulation model of a natural circulation boiler evaporation system is presented, which is based on neural network (NN) and process mechanism charac teristics. The main characteristic of the model is that it is the hybrid artific ial neural network (HANN) model, thus its ideal simulation speed is assured. On network model design, the system and the physical basis of the network between i nput and output were well considered. The network model was transformed from 'bl ack box model' to 'gray box model' to a certain degree. Compared with ordinary A NN, the training of this network model fully reflects physical mechanism learnin g on system input and output, besides basic function of learning pure numeric ma pping relations between input and output. Therefore, the association ability of, the prediction ability and the extrapolation effect on system transition proces s of the network model were well assured. At the same time, on-line modeling of boiler evaporation system can be realized by using the simulation method. This m odel strengthens the description capability on real system. The validity of the modeling method was proved by the simulation test result.