基于自适应模糊推理系统的柴油机故障诊断

Fault Diagnosis of Diesel Engine Based on ANFIS

为解决柴油机故障诊断问题,采用自适应神经模糊推理系统(ANFIS)建立其故障诊断模型。利用减法聚类方法确定模型初始结构,并采用由梯度下降算法和最小二乘算法所组成的混合学习算法优化模型参数。经文中试验数据检验,所建模型故障识别值与实际值之间的最大误差为10.16%,最小误差为0.115%,平均误差为2.26%,识别精度达到了97.74%。仿真结果表明,与BP网络模型相比,该模型收敛速度快,拟合能力强且诊断识别精度高,能够有效识别柴油机故障。

In order to solve the fault diagnosis problem of diesel engine, Adaptive Neuro-Fuzzy inference system （ANFIS） was applied to build a fault diagnosis model of diesel engine. Subtractive clustering algorithm was used to confirm the original structure of fuzzy inference model, and a hybrid algorithm made up of the least-squares method and the backpropagation gradient descent method was adopted to optimize the model parameters. Through verification of the built diagnosis model with data of engine tests, it has been found that the maximal error between the identification and actual values of fault is 10.16%, the minimal error and the average error is respectively 0.115% and 2.26%, the recognition accuracy is 97.74%. Simulation results show that the fitting ability, convergence speed and recognition accuracy of ANFIS model are all superior to back propagation neural networks （BPNTV）. So a contingent fault of diesel engine can be identified effectively.