The problem of fault detection and isolation (FDI) in cooperative manipulators is addressed here. Four faults are considered: free-swinging joint faults, locked joint faults, incorrect measured joint position, and incorrect measured joint velocity. Free-swinging and locked joint faults are isolated using neural networks. For each arm, a Multilayer Perceptron (MLP) is used to reproduce the dynamics of the fault-free robot. The outputs of each MLP are compared to the real joint velocities in order to generate a residual vector that is then classified by a RBF network. The sensor faults are isolated based on the kinematic constraints imposed on the system. Simulations and a real application are presented indicating the efectiveness of the FDI system.