In order to improve the system performance, reliability, and safety, many researchers have focused their attention on the issues of system identification and fault diagnosis during the last two decades. Nonlinear system identification can improve control performance significantly, especially when the system behaviors are complex, unknown, and with great nonlinearity. In addition, the early detection of faults can prevent the destruction of equipment and avoid great losses. Therefore, the development of effective and robust methods for fault diagnosis has become an important field of research in engineering applications In this dissertation, a novel approach to immune model-based fault diagnosis methodology for nonlinear systems is presented. The diagnosis scheme consists of forward/inverse immune model identification, filtered residual generation method, the fault alarm concentration (FAC) scheme, and the artificial immune regulation (AIR) mechanism. To verify and demonstrate the effectiveness of the proposed schemes, several simulations are employed to validate the effectiveness and robustness of the system identification and diagnosis approach.