In view of the problem that the electrical connector is subjected to step stress random vibration during operation, which leads to fretting wear of the electrical connector and the reduction of contact performance, the step stress random vibration test is carried out. The electrical capacitance tomography (ECT) is used to detect the characteristic value of wear debris between the electrical connector contacts in the process of fretting wear. Contact resistivity and the characteristic value of wear debris are used to study the wear degree and degradation law of contact performance under step stress random vibration conditions. The maximal information coefficient (MIC), which has good robustness and can characterize the nonlinear relationship, is introduced to analyze the correlation between the characteristic value of wear debris and contact resistance, and the dimension is reduced through mic screening to improve the prediction accuracy of the model. The findings demonstrate that under the random vibration of step stress, there is a stepped change trend in the contact resistance, the total characteristic values of wear debris, and the characteristic values of wear debris. Through the calculation of the maximum information coefficient, it is found that the total amount of wear debris characteristics is strongly correlated with the contact resistance. The results of energy spectrum analysis are consistent with the test results. The average absolute error of CHIO-Elman neural network performance degradation model optimized by MIC screening is less than 4%.