Fault Diagnosis of Heavy-duty Scraper Conveyor Using Fuzzy C-means Clustering

Heavy scraper conveyor is a key transportation equipment in coal mine comprehensive mining face, and its operating status directly affects production safety and efficiency. This paper proposes a fault diagnosis method based on fuzzy C-means (FCM) clustering algorithm to address the problem of complex fault characteristics and difficult diagnosis. Firstly, the operation data of the scraper conveyor is collected through multiple sensors such as vibration, temperature, and current, and the time-domain and frequency-domain features are extracted to construct high-dimensional feature vectors. Then, the FCM algorithm is used to perform unsupervised clustering on the feature vectors, dividing the operating state into typical fault modes such as normal, sprocket wear, chain breakage, and scraper deformation. To verify the effectiveness of the proposed method, a scraper conveyor experimental platform was built and data was collected under real working conditions. The experimental results show that compared with traditional support vector machines (SVM), backpropagation neural networks (BPNN), and K-means clustering methods, our method has significantly improved diagnostic accuracy, robustness, and generalization ability, with an average diagnostic accuracy of 96.7%. This provides a reliable technical means for the intelligent operation and maintenance of scraper conveyors.