Summary: | It is inevitable that machine parts will be worn down in production, causing other mechanical failures. With the appearance of wearing, the accuracy and efficiency of machinery gradually decline. The state between healthy and impaired is defined as sub-health. By recognizing the sub-health state of machinery, accuracy and efficiency can be effectively guaranteed, and the occurrence of mechanical failure can be prevented. Compared with simple fault detection, the identification of s sub-health state has more practical significance. For this reason, the sound characteristics of large-scale reciprocating machinery, combined with the concept of OOD (out-of-distribution) detection, are used, and a model for detecting machinery sub-health state is proposed. A planer sound dataset was collected and collated, and the recognition of mechanical sub-health state was realized by a model combining a VGG network and the threshold setting scheme of OOD detection. Finally, an auxiliary decision-making module was added, and Mahalanobis distance was used to represent spatial relationships among samples, further improving the recognition effect.
|