CAJ | 학술논문

为了解决 RBF神经网络的参数选择问题，以便提高柴油机故障诊断的精度，提出了一种基于引力搜索算法和 RBF神经网络相结合的智能故障诊断方法。该方法首先采用减聚类算法确定网络隐层单元数，然后提出改进引力搜索算法优化 RBF神经网络的参数。利用国际标准样本集对该方法进行分类测试，并将该方法应用于柴油机故障的诊断，仿真实验验证了该方法对柴油机故障的分类和诊断效果。
위료해결 RBF신경망락적삼수선택문제，이편제고시유궤고장진단적정도，제출료일충기우인력수색산법화 RBF신경망락상결합적지능고장진단방법。해방법수선채용감취류산법학정망락은층단원수，연후제출개진인력수색산법우화 RBF신경망락적삼수。이용국제표준양본집대해방법진행분류측시，병장해방법응용우시유궤고장적진단，방진실험험증료해방법대시유궤고장적분류화진단효과。
In order to solve the optimization of the parameters of RBF neural network to improve the accuracy of fault diagnosis of diesel engine,an intelligent fault diagnosis method based on the combination of gravitational search algorithm and RBF neural network is proposed.At first,the subtractive clustering algorithm is used to determine the number of hidden layer units,then the improved gravitational search algorithm is adopted to optimize the parameters of RBF neural net-work.UCI testing data sets are used to check the classification accuracy of the proposed method, and the proposed method is applied to fault diagnosis of diesel engine.Simulation results show that the proposed method is effective in classification and diagnosis of the faults of diesel engine.