Intelligent detection system for scraper based on YOLOV5 neural network
ZHAI Shanfa
SONG Wenqing
LUO Senhan
WANG Yixiao
Abstract：To improve the production efficiency of scraper in coal bunker groups and reduce operation and maintenance costs,an intelligent detection system for scraper is designed.The system adopts machine vision-based image processing and image segmentation technologies to evaluate the no-load status of scraper and conduct anomaly detection on the operating status.A YOLOV5 neural network fault detection model is established in the system.By detecting and calculating the technical parameters of the scraper,including scraper speed,inclination,chain,unit chain length,and chain link pitch,the system realizes intelligent detection of anomalies and faults in the key components(scrapers and chains)of the scraper.The system false detection rate is effectively reduced from four aspects:data optimization,model improvement,training strategy adjustment and post-processing optimization in the process of production practice.The manual operation and maintenance costs are reduced and the intelligence level of the system is improved.
Keywords：machine visionscraperneural networkanomaly detectionfalse detection
Publication Date：2026-02-28
Online Publishing Date：2026-03-19(First online date of this platform, not the publication date of the document)
Pages：5( 98-102 )