Pipeline leakage is a common problem in industrial production, and it is a key factor restricting the safety and reliability of pipeline system, which may lead to safety accidents, environmental polluted and resource waste. Therefore, accurate and rapid detection and location of pipeline leakage points is very important to ensure production safety and environmental protection. A pipeline leak location method based on adaptive median filter algorithm is proposed, and an adaptive median filter model is established, which realizes noise filtering and data adaptive picking, and accurately extracts signal features. The generalized weighted quadratic cross correlation algorithm is used to improve the signal-to-noise ratio, obtain the time delay estimation and locate the leakage point. Subsea Manifolds are used as a case to demonstrate the proposed method. The experimental results show that the method can detect and locate the leakage point of pipeline quickly and accurately, and has high reliability and practicability. This study provides an effective solution for pipeline leakage monitoring and location, and has important engineering application prospects.