Citation

Verma A, Dhalmahapatra K, Maiti J. Safety Sci. 2023; 159: e106014.

Copyright

(Copyright © 2023, Elsevier Publishing)

DOI

10.1016/j.ssci.2022.106014

PMID

unavailable

Abstract

Occupational incidents are a major concern in steel industries due to the complex nature of job activities. Forecasting incidents caused by various activities and determining the root cause might aid in implementing appropriate interventions. Thus, the purpose of this study is to investigate the future trend and identify the pattern of contributing factors of incident occurrences. The study focuses on an integrated steel plant where different steel-making-related operations are carried out in separate units. The incident data of 45 months is used. Initially, a unit-wise trend of incidents (e.g., injury, near-miss and property damage) is forecasted using the autoregressive integrated moving average (ARIMA) model to determine the near-future incident trends and to identify the most incident-prone unit of the plant. The model is validated using six-month holdout data, and the predicted number of incidents is compared with the actual counts. The ARIMA model indicates that the safety performance of the iron making unit is found to be underperforming. In the second phase, meaningful association rules are extracted from text data using the apriori algorithm for the underperforming unit to discover the incident-causing factors.

RESULTS from text mining-based association mining suggest that bike and car-related incidents are the leading causes of injury. Similarly, gas leakage, slag spillage, and coke-oven door malfunctioning are causing near-miss incidents. The majority of property damage incidents are reported due to derailment, loading/ unloading and dashing of the dumper vehicle. Effective implementation of the study's specified rules can aid plant administration in formulating policies to improve safety performance by designing focused interventions.

Language: en

Keywords

ARIMA model; Association rule mining; Forecasting; Incident data analysis; Text mining