The loop pipe apparatus are used to simulate the different conditions of the actual pipeline and denoise the original signal by the wavelet method. Kernel⁃based Principal Component Analysis (KPCA) is used to extract the time⁃frequency domain eigenvalues of the leaked signals, and the final input vector of the neural network is obtained. Because the traditional BP neural network is easy to fall into local minimum when it is used to identify working conditions, the BP neural network is optimized by genetic algorithm (GA) and particle swarm optimization (PSO). Compared with the traditional BP neural network,the result show that the two optimized BP neural networks have stronger ability to identify leakage working conditions. Finally, from the two aspects of test accuracy and training time, two different optimization algorithms are compared and their different application situations are proposed.

The actual denoising effect of wavelet denoising methed was studied through pipe flow test apparatus, which simulated the actual pipeline leakage condition. The reason why small leak was not easy to be found was explained from two expects through timefrequency analysis of the leakage signal attenuation process. And the disadvantages of the most commonly used wavelet de-noising method to deal with small leakage signal were also discussed. On this basis, a new threshold function was established to improve the signal reconstruction accuracy and the advantage was analyzed mathematically. Next, a blind source separation algorithm based on maximum signal-to-noise ratio (SNR) was proposed, which integrated wavelet transform with blind source separation. By separating the known structural signal, the applicability of this method was illustrated, and the practical denoising effect and industrial application value of the fusion algorithm were verified.