Abstract: This series of papers deal with ship-target recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of ship radiated-noise. Based on the studies of a large amount of ship radiated-noise data, which has been collected from actual ships on the seat we extracted effectively recognizable features. Such features include line-spectrum features, stationary and nonstationary spectrum features as well as rhythm features. Finally the categorization are tested by unknown samples on the sea, including, 33 surface ships, 8 underwater targets in 30 operating conditions.Methods for memorization and classification are also explored in the project. Paper (Ⅳ) is the last in the series. It deals with the application of fuzzy neural network to the recognition of targets. The neural network is a multi-layer forward network and the learning algorithm is BP (Error Back Propagation).In the paper, the adjust formula of parameter of fuzzier is given. The paper provides a recognition result which is drawn from 1049 samples gathered from 41 ships in 63 operating conditions, with an original recording time of about 3.5 hours. Over 92 % of recognitions are correct.