Ying Chen , Peishuo Chai , Qinghua Gu , Yuehan Liu , Shengwei Li , Yuan Zou
{"title":"Research on the effects of operational fatigue and bagging-SVM recognition of deep coal mine workers","authors":"Ying Chen , Peishuo Chai , Qinghua Gu , Yuehan Liu , Shengwei Li , Yuan Zou","doi":"10.1016/j.jlp.2024.105508","DOIUrl":null,"url":null,"abstract":"<div><div>As the extraction of mineral resources gradually progresses to deeper levels, the thermal and humidity conditions in mine tunnels have significantly worsened, increasing the intensity of work and accelerating the accumulation of fatigue among miners, leading to the greater degree of fatigue. This study aims to analyze the impact and relationship of fatigue in deep mine environments, summarize physiological, psychological, and safety behavior indicators affecting miner fatigue, and develop a conceptual model of miners' safety behavior capabilities. To effectively identify work fatigue among miners, a deep mine thermal and humidity environment was simulated, replicating the tasks of loading and unloading coal gangue. Data on skin temperature and electrocardiogram features were collected using the BIONOMADIX dual-channel skin temperature transmitter and BIOPAC multi-lead physiological signal acquisition instrument. Features related to fatigue, such as electrocardiogram and skin temperature indicators, were extracted. The Bootstrap Aggregating algorithm was used to optimize the Support Vector Machine (SVM) classification model, leveraging the Bagging framework to enhance the prediction accuracy and stability of fatigue state classification, thereby constructing a Bagging-SVM model for identifying fatigue in deep mine operations. The research results indicate that electrocardiogram signals and skin temperature are positively correlated with fatigue, with the correlation strength decreasing in the following order: cheek temperature > heart rate > nasal temperature > root mean square of the difference between adjacent normal heartbeats (RMSSD). The Bagging-SVM ensemble classifier achieved an accuracy rate of 91.6% in identifying the fatigue state of miners. Therefore, the Bagging-SVM identification model effectively recognizes fatigue in deep mine operations, providing significant theoretical and practical value in mine accident prevention, on-site safety, and management in non-high-risk areas.</div></div>","PeriodicalId":16291,"journal":{"name":"Journal of Loss Prevention in The Process Industries","volume":"94 ","pages":"Article 105508"},"PeriodicalIF":3.6000,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Loss Prevention in The Process Industries","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950423024002663","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
As the extraction of mineral resources gradually progresses to deeper levels, the thermal and humidity conditions in mine tunnels have significantly worsened, increasing the intensity of work and accelerating the accumulation of fatigue among miners, leading to the greater degree of fatigue. This study aims to analyze the impact and relationship of fatigue in deep mine environments, summarize physiological, psychological, and safety behavior indicators affecting miner fatigue, and develop a conceptual model of miners' safety behavior capabilities. To effectively identify work fatigue among miners, a deep mine thermal and humidity environment was simulated, replicating the tasks of loading and unloading coal gangue. Data on skin temperature and electrocardiogram features were collected using the BIONOMADIX dual-channel skin temperature transmitter and BIOPAC multi-lead physiological signal acquisition instrument. Features related to fatigue, such as electrocardiogram and skin temperature indicators, were extracted. The Bootstrap Aggregating algorithm was used to optimize the Support Vector Machine (SVM) classification model, leveraging the Bagging framework to enhance the prediction accuracy and stability of fatigue state classification, thereby constructing a Bagging-SVM model for identifying fatigue in deep mine operations. The research results indicate that electrocardiogram signals and skin temperature are positively correlated with fatigue, with the correlation strength decreasing in the following order: cheek temperature > heart rate > nasal temperature > root mean square of the difference between adjacent normal heartbeats (RMSSD). The Bagging-SVM ensemble classifier achieved an accuracy rate of 91.6% in identifying the fatigue state of miners. Therefore, the Bagging-SVM identification model effectively recognizes fatigue in deep mine operations, providing significant theoretical and practical value in mine accident prevention, on-site safety, and management in non-high-risk areas.
期刊介绍:
The broad scope of the journal is process safety. Process safety is defined as the prevention and mitigation of process-related injuries and damage arising from process incidents involving fire, explosion and toxic release. Such undesired events occur in the process industries during the use, storage, manufacture, handling, and transportation of highly hazardous chemicals.