Machinery fault diagnosis and prognosis: application of advanced signal processing techniques

Machinery health prediction based on process models and/or process parameters is an important function in automated manufacturing set-ups. Sensor data is collected and used to indirectly model the equipment. Due to the short response times required it is important to investigate robust sensor data representation schemes. Traditional Fourier Analysis is not sufficient to preserve the information in both frequency and time domains. In this paper we describe the use of wavelets, both continuous and discrete, for equipment diagnosis and prognosis. We detail wavelet-based techniques for gear fault diagnosis and prognosis.