Robust Wheel Wear Monitoring System for Cylindrical Traverse Grinding

Although many advanced signal processing techniques and novel machine learning algorithms have been applied to the monitoring of grinding processes in the literature, most of these techniques and algorithms are only effective under specific conditions and are unusable under other grinding conditions, such as varying wheel types or workpiece materials. This article proposes a robust grinding wheel wear monitoring system to eliminate these restrictions. Physical information generated during the grinding process is collected by a power sensor, accelerometers, and acoustic emission sensors. After the signals are preprocessed, features are extracted via different signal processing techniques, and a novel normalization scheme is applied to make these features independent of the wheel type, workpiece material, and grinding parameters. The features that are most related to wheel wear are selected according to the statistical criterion. An interval type-2 fuzzy basis function network is adopted to develop a wheel wear monitoring model, which is capable of predicting wheel wear under various grinding conditions and generating upper and lower prediction bounds according to the fluctuation of features. Based on the wheel wear model, a robust monitoring scheme to schedule timely wheel dressing and ensure workpiece surface finish could be established.