In this study, the system identification based fault tolerant control of an unmanned underwater vehicle (UUV) dynamics is presented. The proposed fault tolerant control approach is robust to control surface failures which cause different control effectiveness factors for the actuator. The least squares method (LSM) is used in order to identify the control distribution matrix elements, that correspond to the faulty actuator and the control reconfiguration is carried out using this identified control distribution matrix. Data needed for the system identification is created from the simulation model of the baseline underwater vehicle. This data is treated as real cruise data and by the LSM, model parameters are estimated. A linear quadratic optimal controller (LQR) is designed for the modeled underwater vehicle. A fault in the control surfaces is identified by the parameter identification method and LQR controller is reconfigured for the identified model. In simulations, the linearized model of dynamics of REMUS UUV is considered, and the performance of the proposed actuator failure identification and reconfigurable control techniques are examined for this model.