基于ANN-PSO的造球机故障诊断

Fault Diagnosis of Pelletizer Based on ANN-PSO

对机械设备的监控和故障诊断是重要而困难的,神经网络能够用来检测设备故障,但其训练方法容易陷入局部最优。粒子群算法具有全局搜索能力,将免疫系统中的抗体抑制机理引入粒子群算法以保持粒子多样性,采用免疫粒子群算法(ImPso)与LM(levenberg-marguardt)算法,结合训练前向神经网络。计算机仿真结果显示,训练后的网络性能优于使用一般BP算法训练的网络,将其应用于造球机故障诊断的准确度高于单纯BP算法训练的网络。

It is difficult and important to monitor and find possible fault for machine. FeedForward Neural Network can be used to detect these faults, but the gradient descent method in traditional BP algorithm is vulnerable to local optimum. Particle Swarm Optimizer （PSO） can be capable of searching optimum in global scope,by introducing Clone Suppression in Immune Systems into PSO to maintain the diversity of Particles. The hybrid algorithm （ImPso） can be used to train FeedForward Neural Network. The computer simulation results show that the performance of neural network with the hybrid algorithm （ImPso） combine with LM algorithm is better than the performance with traditional gradient descent method. And it is more effective to put it into fault diagnosis of pelletizer.