Assessment of safety culture in the fireworks industry

Comprehensive safety risk evaluation of fireworks production enterprises using the frequency-based ANP and BPNN

The fireworks industry has long struggled with the problem of safety. Scientific, reasonable, and operable evaluation models are prerequisites of reducing risk. Based on the data from over 100 fireworks production safety accidents in China from 2010 to 2022, two evaluation models were established from the perspective of safety risk definition. Firstly, a weight calculation derivative method, the frequency-based analytic network process (ANP), was proposed creatively. This method optimized the importance ranking index calculation process in the ANP by considering the causal frequency of risk factors in the historical accident samples, thus determining how much each indicator affects the likelihood of accidents. Secondly, utilizing the historical accident samples as the dataset, a back propagation neural network (BPNN) model was developed to extract the mathematical relationship between each risk factor and the severity of accident consequence. Finally, the frequency-based ANP and BPNN models were combined to determine the safety risk level of the fireworks production enterprises. Meanwhile, the safety evaluation research samples were used as the comparison set for empirical study with historical accident samples, involving 100 fireworks production enterprises in China evaluated from 2017 to 2020. The significance result of zero shows that there is a statistically significant difference between the likelihood evaluation results of the accident and non-accident companies. Additionally, the severity evaluation model exhibits an excellent result, revealing a classification accuracy of 98.21 %, a mean square error of 8.97 × 10-4, a percent bias of 1.24 %, and a correlation coefficient and Nash-Sutcliffe efficiency coefficient both of 0.96. The frequency-based ANP and BPNN models integrate self-learning, self-adaptive, and fuzzy information processing, obtaining more accurate and objective evaluation results. This work provides a new strategy for the promotion and application of artificial intelligence in the field of safety risk evaluation, thus offering real-time safety risk evaluation and decision support of the safety management for the enterprises.

Integrated Approach for Safety Culture Factor Evaluation from a Sustainability Perspective

Traditionally, sustainable development has been seen as a combination of three pillars: economic, social and environmental development. In recent years, another one has been added to these three pillars, namely culture, as being indispensable in achieving sustainable development. This study proposes an integrated approach for the identification and classification of safety culture factors in the company in a sustainability context. The research design was based on the assumption that safety culture is part of organizational culture that should support the development of corporate sustainability. Firstly, the identification of the safety culture factors (SCFs) based on the literature review was presented. Then, the ISM method was used to identify the interaction between SCFs and to develop the hierarchical structure of these factors. In the next step, ISM was integrated with the MICMAC method to cluster the factors based on driving power and dependence power into four categories. Finally, safety culture factors with high driving power were rated using the fuzzy TOPSIS method from the sustainability dimension perspective. This approach was used in an automotive industry company to improve and develop the company's practices aimed at implementing a sustainable development strategy. A sensitivity analysis was also carried out to monitor the robustness of the approach.