Automated Recognition Method for Decoupling Situation of Coal Unloading Car Based on Grey Wolf Optimization Algorithm
GUO Jiayu
CHEN Zhenyu
YOU Tianrong
Abstract：Utilizing decoupling historical data to directly identify decoupling trends relies on data quality,and the identification efficiency is relatively low in datasets with a high degree of redundancy.To enhance the automated identification effect of coal unloading car decoupling trends,an automated identification method based on the Grey Wolf Optimization Algorithm for coal unloading car decoupling trends was proposed.The SVM algorithm was employed to classify coal unloading car decoupling trend information based on the difference in decoupling spacing,removing redundant data.The weight and classification basis values were calculated,and preliminary decoupling anomaly identification was completed through similarity sorting.The binary initialization of feature vectors was introduced using the Particle Swarm Optimization Algorithm,and a fitness function was constructed to obtain the optimal fitness value and feature components.Combining the Grey Wolf Algorithm forms the Grey Wolf Optimization Algorithm to dynamically adjust particle positions and optimize feature extraction.Based on the feature results,a recognition framework was set up to determine the probability of decoupling actions and threat levels,and calculate abnormal values for automated identification of decoupling trends.Experimental results showed that the proposed method had a high accuracy rate for car decoupling trend recognition,with a root mean square error of 0.18 and a lower mean error than comparative methods,and the highest recognition efficiency.
Keywords：grey wolf algorithmcoal unloading cardecoupling trendSVM algorithmautomatic identification
Publication Date：2025-12-31
Online Publishing Date：2026-01-29(First online date of this platform, not the publication date of the document)
Pages：5( 63-67 )