Data Mining Implementations for Determining Root Causes and Precautions of Occupational Accidents in Underground Hard Coal Mining

Abstract

Background

Nowadays, as in every branch of industry, a large amount of data can be collected in mining, both in productivity and occupational safety. It is increasingly essential to transform this data into useful information for enterprises. Data mining is very useful in processing and extracting useful information from the processed data. This study aims to analyze the data of occupational accidents with injuries between 2010 and 2021 in an underground hard coal mine by data mining.

Methods

The injured accident data for the relevant years were organized and analyzed using data mining algorithms. These algorithms were implemented with the WEKA data mining program, an open-source application.

Results

According to different test methods, k-Nearest Neighborhood and Support Vector Machine algorithms succeeded in classification and prediction. The k-Nearest Neighborhood and Support Vector Machine algorithms achieved 100% (training set) and 66% (cross-validation) performance, respectively, according to two different test methods. One of the critical phases of the study is the determination of the attributes and subclasses that are effective in the origin of accidents by association rules mining. Thus, more detailed information was obtained about the root causes of the accidents. A result of Apriori and Predictive Apriori implementations revealed that the root causes of occupational accidents according to the accident locations are the worker experience, the working hours in the shift, and the worker position. In addition, shifts, accident causes, especially monthly production, and monthly wages were also influential.

Conclusions

These results are also in accordance with the actual situation in the enterprise. As a result of the research, practical suggestions were presented for evaluating occupational accidents and taking precautions.