Common rail oil injector fault signal preprocessing method based on IWOA-SVR-EEMD

The invention aims to provide an IWOA-SVR-EEMD-based common-rail oil injector fault signal preprocessing method. The method comprises the following steps: acquiring a pressure signal of a high-pressure oil pipe, and performing signal continuation by using support vector regression optimized by an improved whale optimization algorithm; then carrying out ensemble empirical mode decomposition on the extended signal to obtain a plurality of intrinsic mode components; and finally, calculating the Pearson product-moment correlation coefficient of each intrinsic mode component, and leaving components with large correlation with the original signal for component synthesis. And after the preprocessing is finished, the denoised high-pressure oil pipe pressure signal is obtained. Compared with an original ensemble empirical mode decomposition method, the method has a better inhibition effect on the endpoint effect problem; compared with a traditional signal denoising method, the signal-to-noise ratio of the denoised sig