Evaluation and prediction of the safety management efficiency of coal enterprises based on a DEA-BP neural network

Abstract

With the development of big data technology, big data have gradually become the main driving force of safety management. To effectively predict and evaluate the changes in the safety management efficiency of coal enterprises under big data technology, the model-driven DEA method and the data-driven BP neural network method are combined. A DEA-BP neural network hybrid-driven model, in which safety management efficiency is considered, is constructed for coal enterprise evaluation and prediction. The data of 20 coal enterprises from 2015 to 2020 are used for empirical research. The results indicate that the static analysis shows a fluctuating upwards trend in the level of safety management of coal enterprises. The dynamic analysis shows that the decline in the technical efficiency change is mainly caused by the decline in the pure technical efficiency change. In terms of improving safety management efficiency, coal enterprises mainly target a single aspect of technical progress efficiency, without realizing that the improvement of safety efficiency is the result of the combined effect of technical efficiency and technical progress efficiency. An accuracy of 90% can be achieved using the BP neural network prediction based on the addition of new indicators, demonstrating that the evaluation and prediction model has good adaptability.