Design of training data-based quadratic detectors with application to mechanical systems

Reliable detection of engine knock is an important issue in the design and maintenance of high performance internal combustion engines. Cost considerations dictate the use of vibration signals, measured at the engine block, for knock detection. Conventional techniques use the energy in a bandpass ltered version of the vibration signal as a measure. However, the low signal-to-noise ratio (SNR) in the vibration measurements signiicantly degrades the performance of such bandpass energy detectors. In this paper , we explore the design and application of more general quadratic detection procedures, including time-frequency methods, to this challenging problem. We use statistics estimated from labeled training data to design the detectors. Application of our techniques to real data shows that such detectors, by virtue of their exible structure, improve the eeective SNR, thereby substantially improving the detection performance relative to conventional methods.