In this study, an intelligent diagnosis systems have been developed and applied for classifying six types of cooling radiator conditions by means of infrared thermal images; namely, radiator tube blockage, radiator fin blockage, loose connections between fins and tubes, radiator door failure, coolant leakage and normal. The proposed system is consisted of several subsequent procedures including thermal image acquisition, preprocessing, of images via two dimensional discrete wavelet transform (2D-DWT), feature extraction, feature selection, and classification. The 2D-DWT was implemented to decompose the thermal images. Subsequently, statistical texture features were extracted from the original and decomposed thermal images. Consequently, statistical texture features are extracted from the original and decomposed thermal images to develop ANFIS classifiers. In this paper, the significant and relevant features are selected based on genetic algorithm (GA) in order to enhance the performance of ANFIS classifier. For evaluating ANFIS classifier performance, the values of the confusion matrix, such as specificity, sensitivity, precision and accuracy were computed. The overall accuracy of the classifier was 94.11 %. The results demonstrated that this system can be employed satisfactorily as an intelligent condition monitoring and fault diagnosis for a class of cooling radiator.