This paper presents a method that generalizes various conditions in plate finned-tube cooling and heating coils. An artificial neural network (ANN) with principal component analysis (PCA) has been used as an inverse plant identifier. A correlation among input and output temperatures of dry and wet air and water temperatures through the plate finned-tube coils has been modeled by an ANN. A self-organized principal component analysis network (SOPCAN) was used as a preprocessing technique for the feature extraction. Eighty percent of the data were evaluated for the training and the remaining for the test using a multilayer perceptron network (MLPN) with back-propagation algorithm. Principal components that had small variance were discarded, and the reduced number of uncorrelated variables were applied to the MLPN. The effects of discarding these components on the convergence of the algorithm were investigated. Also, a weight decay procedure has been developed for the elimination of less informative principal components not before but during training. Consequently, quite good generalization between input and output was obtained in this work.