Application of natural language processing and machine learning for analyzing mining accident reports and automating the process of root cause analysis
Siddhartha Agarwal1
Y.P.Chugh2
Atul Singh1
Vikram Sakinala1
Ayan Mukherjee1
Balbir Prasad1
Cihan Dagli3
Yuhao Zou4
1.Mining Engineering Department,Indian Institute of Technology(ISM),Dhanbad,Jharkhand 826004,India2.Southern Illinois University,Carbondale,IL 62901,USA3.Systems Engineering Department,Missouri Science and Technology,Rolla,MO 65401,USA4.Fintech Leasing Dept,CDB Leasing Co.,Ltd,Shenzhen 518038,Guangdong,China
摘要：Coal mining accidents are a major concern worldwide,necessitating effective safety measures and comprehensive analysis to prevent future accidents.Our proposed solution is the first attempt for Indian mines,inspired by the potential of Natural Language Processing(NLP)that can read and analyze vast repositories of accident records in seconds.In combination with machine learning(ML),NLP algorithms can extract unstructured text by eliminating manual data entry errors,reading poorly scanned reports,and understanding multiple versions of the event and cluster documents based on types that would otherwise take months to collate.In the case of accident records,it can be an asset in capturing recurring issues,contributing factors,and high-risk areas,enabling proactive measures to be taken to prevent future accidents.The heart of the study lies in applying two ML algorithms called latent Dirichlet allocation(LDA)and RAKE(Rapid Automatic Keyword Extraction).LDA is a topic modeling technique for clustering accidents based on descriptions.RAKE generates root cause analysis through keywords from accident descriptions and remedies suggested by inspection officers.Both are unsupervised learning techniques that do not require any training on labeled datasets.AI and NLP can significantly enhance the process of creating Swiss Cheese Models and Logic Sequences of Contributory Factors Diagrams by automating the extraction,classification,and analysis of data from incident reports and other relevant documents.Data for analysis in this study came from the Directorate General of Mines Safety(DGMS),India records from 2010 to 2015.
机标关键词：applicationprocessingreportslanguagenaturallearninganalysiscause
论文发表日期：2025-12-31
在线出版日期：2026-01-30（本平台首次上网日期，不代表文献的发表时间）
页数：33( 194-226 )
英文信息