A pattern recognition-based methodology is proposed for fault diagnosis of multivariate and dynamic systems. Noisy input patterns, belonging to a class of event(s), are first scaled to unit variance and zero mean. This step, termed as a harmonizing step, reduces magnitude difference amongst patterns belonging to a class of event(s). Existence of low frequency segments, such as ramp-type trends, in a pattern hampers the efficacy of the harmonizing step. In this work, a digital band-pass filter is designed to eliminate the ramp-type segments and decrease noise intensity. Then, the Principal Component Analysis (PCA) technique is applied in order to describe the information space by a Set Of Uncorrelated and fictitious data sources. A wavelet-based methodology is employed for each new sensor to extract pattern features. A binary decision tree is used to classify the extracted features. The outputs of each decision tree are: (1) the a posteriori probabilities that an unlabeled input pattern belongs to different classes of events; and (2) the probability confidence limits that input pattern may be classified to any of known classes. As the last step, any of two consensus theory-based techniques or evidence theory are utilized to combine the outputs of the decision trees and find the best classes of events describing system behavior. The performance of the proposed technique is examined by diagnosis of simulated faulty behavior for the Tennessee Eastman Process.