基于数值优化的改进BP算法在旋转机械故障诊断中的应用

机械设备的安全运行对企业的现代化生产至关重要,因而对故障机械的诊断近年来受到了普遍关注,而神经网络具有分辨原因及故障类型的能力,在故障诊断领域中得到了广泛应用.本文针对传统BP算法存在的收敛速度慢以及容易陷入局部最小点等问题,给出了两种基于数值优化方法的改进BP算法,应用改进的BP算法对旋转机械故障进行诊断研究,结果表明,加快了网络的收敛速度.证明该算法比BP算法精度更高且收敛速度更快.

Application of Improved BP Algorithm Based on Numerical Optimization to Fault Diagnosis of Rotating Machinery

The safety of machine equipment running is very important to modern production of corporation,so fault machinery diagnosis is paid more attention to in recent years.Neural networks have the ability of distinguishing the types and reason of faults,so it's widely applied in the area of fault diagnosis.Aiming at the problems that BP algorithm has slow convergence rate and is likely to fall into local minimum point,this paper presents two improved BP algorithm methods based on numerical optimization.The research result of applying the improved BP algorithm to the fault diagnosis of rotating machinery shows that it can make convergence rate of network faster.It is proved that the method has higher precision and faster convergence rate than the BP algorithm.