Fault diagnosis can be facilitated by using either quantitative or qualitative information of the system monitored. This paper presents a novel approach to integrate quantitative and qualitative information in fault-diagnosis based on the use of fuzzy-logic systems. In this approach, the diagnostic signals are generated and evaluated via a machine system. The configuration adopted allows the operator to both extract and comprehend system performance from the fuzzy inference system in order to provide reliable diagnostic information. The effectiveness of the proposed diagnosis strategy is illustrated through an evaluation and a validation study of a motor driven centrifugal pump system.