For the covertness in modern anti-submarine warfare (ASW), a sonar system has been evolved to the bi-static type. However, it is difficult to get the recognizable error coefficients at any time with clear mathematical definition for the sonar model. To resolve the dynamics accompanied with the error component, we should deal with heterogeneous, complementary fusion of information in order to enable robust target detection, classification, localization, and tracking. In the tracking point of view, we concentrate on the increment of tracking error occurred from the target's maneuvering owing to the acceleration. From the measurement residual, compensating acceleration by merging the filter with fuzzy c-means (FCM) clustering is proposed. Finally, a example is provided to show the effectiveness of the proposed algorithm.