Identifying patterns of safety related incidents in a steel plant using association rule mining of incident investigation reports

•Association rule mining of incident data is done using apriori algorithm.•Work flow diagram of incident investigation is proposed.•843 incidents are analyzed from a steel manufacturing company.•Both single to multiple loop learning are explored.•35 meaningful rules are generated. The aim of this paper is to find out the patterns of incidents in a steel plant in India. Occupational incidents occur in steel plant mainly in form of injury, near miss, and property damage or in combination. Different factors are responsible for such incidents to occur. An incident investigation scheme is proposed. Association rule mining approach is used to discover cause-and-affect patterns (rules) using 843 incidents. Thirty-five meaningful association rules are extracted using three criteria, support (S), confidence (C) and lift (L). For example, the results show that unsafe acts done by others are more frequent in injury cases (S=4.86%, C=78.8%, L=2.3). Similarly, one of the SOP (standard operating procedures) related rule: ‘SOP required, available, adequate but not complied’ led to property damage (S=11.03%, C=49.2%, L=1.525). Another useful rule ‘SOP required, available but inadequate, followed’ led to near miss (S=1.66%, C=38.89%, L=1.163). It is also found that for slip, trip and fall incidents, workers working alone (S=3.91%, C=76.74%, L=2.239) or in a group (S=3.20%, C=75.00%, L=2.188) does not make much difference. The findings pinpoint the areas of improvement such as inadequate SOPs, non-compliance of SOPs, training, and slip, trip and fall prevention to minimize incidents.