• This is an article from the journal, Proceedings of the In-
Abstract:The growing demands for high-quality products with improved speci®cations increase the requirements for condition monitoring and quality evaluation to ensure that no defective or belowspeci®cation products reach the customer. This paper presents a low-cost condition-monitoring system using acoustics to evaluate the quality of mechanically driven automotive speedometers during manufacture. Signal conditioning methods employ discrete cosine transformation to simplify the frequency spectrum of the signals. A novelty detection approach is optimized to characterize thè normal' conditions of the speedometers and to reject any speedometers that are not so categorized on the basis of the sound waves produced from experimental running of the speedometers. The suggested techniques are found useful in developing an automated condition-monitoring system for deselecting low-quality automotive speedometers.