Genetic Algorithm (GA) is applied to obtain optimal inspection plan for fatigue deteriorating structures. The optimization problem is defined so as to minimize inspection cost in the lifetime of the structure under the constraint that the increment of failure probability in each inspection interval is maintained below a target value. Optimization parameters are the inspection timing and the inspection quality. The inspection timing is selected from the discrete intervals such as one year, two years, three years, etc. The inspection quality is selected from the followings; no inspection, normal inspection, sampling inspection or precise inspection. The applicability of the proposed GA approach is demonstrated through the numerical calculations assuming a structure consisting of four member sets. Influences of the level of target failure probability, initial defect condition and stress increase due to plate thickness reduction caused by corrosion on inspection planning are discussed. Introduction Fatigue is one of the most frequent damage in the use of structures. However, because of the complicated fatigue mechanism and the wide scattering property of fatigue life, accurate life estimation is usually difficult for real structures. Reasonable in-service inspections and succeeding maintenance are thought to be necessary for the safe operation of structures. So far, several methods of inspection planning have been proposed. These are inspection planning controlling the failure probability below certain level (Yang and Trapp, 1974) (Itagaki, Asada, and Itoh, 1982) (Deodatis, Fujimoto, Ito, and Spencer,1992), inspection planning aiming at life time cost minimization (Fujita, Schall and Rackwits, 1989), (Fujimoto, Swilem and Iwata, 1991), cost optimal inspection planning with constraint of failure probability (Fujimoto,1993), etc. Basically, optimization of inspection planning is a dynamic programming problem, where previous inspections influence inspection schedule in the future. Also, inspection plan during service life is so versatile that an optimal plan can't be obtained easily by direct observation.