Study on A Fault Diagnosis Method of Rolling Element Bearing Based on Improved ACO and SVM Model

The vibration signal is nonstationary and it is difficult to acquire the sample with typical fault. An improved ACO algorithm based on adaptive control parameters is introduced into SVM model to propose a new fault diagnosis (IMASFD) method in this paper. In the IMASFD method, the EMD method is used to decompose fault vibration signal into IMF components, the energy of IMF components is selected to construct the fault feature vectors. Then the adaptive controlling pheromone strategy, adaptive controlling stochastic selection threshold strategy and dynamic evaporation rate strategy are used to improve the basic ACO algorithm. The improved ACO algorithm is used to optimize the parameters of SVM model in order to obtain the optimal values of parameter combination in the SVM model. And a new fault diagnosis (IMASFD) method is proposed. Finally, the proposed IMASFD method is applied to the test data from bearing data center of CWRU. The experimental results show that the proposed method can accurately and effectively realize high precision fault diagnosis of rolling bearing, and has strong robustness and generalization ability, provides an effective method for realizing fault diagnosis of rolling bearing.