Aiming at the problem that it is difficult to extract the early characteristics of pipeline micro-leakage under complex environmental noise, this paper proposed a method based on variational mode decomposition-singular value decomposition(VMD-SVD) self-optimizing pipeline microleakage signal enhancement method. Firstly, the genetic iterative algorithm was used to optimize the VMD parameters [α,k] , and the singular value kurtosis difference spectrum was used to optimize the reconstruction order of SVD. Then, the leakage signals were decomposed by VMD with optimized parameters, and the decomposed modal components were screened and reconstructed by kurtosis analysis. Finally, order optimized SVD is used to nonlinear filter the reconstructed signals, so as to improve the signal-to-noise ratio (SNR) of micro-leakage signals. Simulation and experimental results show that: the signal enhancement method proposed in this paper improves the signal-to-noise ratio of simulation signals by 9. 32 dB, the correlation of pipeline micro-leakage signals has been increased by 5. 92 times, and the relative positioning error of cross-correlation leakage is reduced by 14. 34%.