NSG水位特性神经网络辨识方法研究

Neural Network Identification Method for Nuclear Steam Generator Water Level

核动力蒸汽发生器(NSG)是压水堆核动力装置中把一回路冷却剂从反应堆堆芯带出的热量传递给二回路水的关键性设备。在瞬态、启动和低功率下的“收缩”与“膨胀”现象引起的逆动力学效应使核动力蒸汽发生器水位呈现瞬时“虚假水位”现象,并使其水位特性难以辨识。为了提高辨识效果,提出了NSG水位神经网络辨识的新方法。采用串—并联型辨识结构,以保证辨识的收敛性和稳定性。网络训练采用带动量因子与自适应学习率的BP学习算法。仿真结果表明,所提出的方法能够正确地辨识核动力蒸汽发生器的水位特性,且具有较高的辨识精度。

The nuclear steam generator is a key equipment in nuclear power plants, which transfers heat carried by primary loop coolant from reactor core to the secondary one. The false water level, which caused by the reverse thermal -dynamic effects known as ＂shrink＂ and ＂swell＂ effects and occurs during plant transients and is more prominent at start up and low power operation, makes the nuclear steam generator water level difficult to identify. In order to improve the effect of identification, a novel identification method for nuclear steam generator water level is put forward in this paper. The series - parallel model is applied to the identification to assure convergence and stability and the error back propagation algorithm with momentum factor and adaptive learning rate is employed to train the network. The proposed method that can identify the characteristic of NSG water level correctly and has enough precision of identification is demonstrated by computer simulation.