Abstract: We propose a branch pipeline leakage location based on cyber-physical system (CPS) architecture to solve the problem that the data between multiple pipeline leakage monitoring systems cannot be shared and be located at the same time. Firstly, the singular point of pressure signals at the ends of the pipeline with multibranch was analyzed via the wavelet packet analysis so that the time feature samples could be established. We introduced Fischer-Burmeister function into the learning process of the double support vector machine to avoid the inverse calculation of the matrix when the objective function has been solved. The data sample was, thus, used as the input of the improved twin-support vector machine algorithm for leakage location. The simulation results showed that the method could locate the pipeline leakage point more quickly and accurately than the Back propagation neural network method, the radial basis function neural network method, and the twin support vector machine method.