设备预知维修的遗传神经网络方法研究

Research on the Methods Based on GNN of Equipment Foreknowable Maintenance

预知维修是设备维修的发展趋势,它已成为人们研究的热点。具有高度非线性和很强的自学习能力的BP神经网络使预知维修成为可能,但由于BP算法存在收敛速度慢、易出现局部极小值等缺陷。遗传算法全局搜索能力强,弥补了BP算法的不足。将两者结合起来,可发挥各自的优势,研究了遗传神经网络的学习算法,构造了时间序列预测和状态预测的预知维修模型。实例分析表明,此种方法科学高效,适合各类复杂设备的预知维修管理。

It is a developing trend for equipment maintenance to carry out foreknowable maintenance, and this is becoming a hot issue currently. With highly nonlinear and a self-learning ability, BP neural network makes it possible, and however, the BP algorithm has a very slow convergence speed and gets into a local minimum easily. Genetic algorithm has a powerful ability of global search, and it can compensate the insufficiency of the BP algorithm. This paper combines the advantages of both the BP algorithm and genetic algorithm, and it researches the learning algorithm of the genetic neural network, and creates foreknowable maintenance models of time sequence prediction and working state prediction. Case analysis shows that this algorithm is scientific and efficient, and adapts to foreknowable maintenance management for any complicated equipment.