Cause analysis of hot work accidents based on text mining and deep learning

A comprehensive risk assessment method for hot work in underground mines based on G1-EWM and unascertained measure theory

A risk assessment method for hot work based on G1-EWM and unascertained measurement theory was proposed to prevent hot work accidents in underground mines. Firstly, based on the risk influencing factors and classification criteria for underground hot work operations in mines, a single indicator measurement matrix was constructed using unascertained measurement theory; Secondly, a risk assessment index system for mine underground hot work operations was established. The combination weight coefficient of each index was determined using the order relationship analysis method (G1) and entropy weight method (EWM) and coupled with the single index measurement evaluation vector to calculate the multi-index comprehensive evaluation vector of the evaluation object; Finally, the model was validated and examined using engineering examples, and the evaluation level was determined using confidence identification criteria. The results showed that the proposed method, when used to evaluate the risk of hot work operations in tunnels and vertical shafts in metal mines, produces risk levels that are in line with reality III (Moderate Risk) for the vertical shaft and IV (High Risk) for the tunnels. The evaluation model results are consistent with the risk evaluation results the whole process of on-site hot work, which verifies the model feasibility. A unique strategy and method for risk management in hot work operations in underground mines is provided by the combination of weighting and unascertained measure models, which has theoretical and practical value. Future research could focus on refineing this model by exploring the applicability in diverse mining environments and integrating advanced analytical techniques to enhance the predictive accuracy and operational efficiency.

Co-occurrence word model for news media hotspot mining-text mining method design

Currently, with the rapid growth of online media, more people are obtaining information from it. However, traditional hotspot mining algorithms cannot achieve precise and fast control of hot topics. Aiming at the problem of poor accuracy and timeliness in current news media hotspot mining methods, this paper proposes a hotspot mining method based on the co-occurrence word model. First, a new co-occurrence word model based on word weight is proposed. Then, for key phrase extraction, a hotspot mining algorithm based on the co-occurrence word model and improved smooth inverse frequency rank (SIFRANK) is designed. Finally, the Spark computing framework is introduced to improve the computing efficiency. The experimental outcomes expresses that the new word discovery algorithm discovered 16871 and 17921 new words in the Weibo Short News and Weibo Short Text datasets respectively. The heat weight values of the keywords obtained by the improved SIFRANK reaches 0.9356, 0.9991, and 0.6117. In the Covid19 Tweets dataset, the accuracy is 0.6223, the recall is 0.7015, and the F1 value is 0.6605. In the President-elects Tweets dataset, the accuracy is 0.6418, the recall is 0.7162, and the F1 value is 0.6767. After applying the Spark computing framework, the running speed has significantly improved. The text mining news media hotspot mining method based on the co-occurrence word model proposed in this study has improved the accuracy and efficiency of mining hot topics, and has great practical significance.

Characteristics and Statistical Analysis of Large and above Hazardous Chemical Accidents in China from 2000 to 2020

To investigate the occurrence and development pattern of large-scale hazardous chemicals emergencies, a statistical analysis of 195 large and above accidents of hazardous chemicals in China during 2000-2020 was conducted. A general description of the characteristics of larger and above accidents based on statistical data was analyzed, and then the system risk of the hazardous chemical industry was calculated and evaluated by the entropy weight method and the TOPSIS method comprehensively. Results show that: (1) The geographical distribution of large and above hazardous chemical accidents (LAHCA) varies significantly; (2) The high-temperature season has high probabilities of having large and above accidents; (3) Human factors and management factors are the main causes of LAHCA; (4) During the period from 2000 to 2020, due to the rapid development of the chemical industry, the overall risk of accidents involving hazardous chemicals were upswing accompanied by volatility, and the risk of serious accidents remains high. The development history of safety regulations in China's hazardous chemical sector and the industry's projected course for future growth were then discussed. Finally, based on the findings of the aforementioned statistics and research, specific recommendations were provided for the safety management of the hazardous chemical sector. This study expects to provide a practical and effective reference for the construction of safety management as well as accident prevention in the hazardous chemical industry.

Big Data-Based Early Fault Warning of Batteries Combining Short-Text Mining and Grey Correlation

Considering the battery-failure-induced catastrophic events reported frequently, the early fault warning of batteries is essential to the safety of electric vehicles (EVs). Motivated by this, a novel data-driven method for early-stage battery-fault warning is proposed in this paper by the fusion of the short-text mining and the grey correlation. In particular, the short-text mining approach is exploited to identify the fault information recorded in the maintenance and service documents and further to analyze the categories of battery faults in EVs statistically. The grey correlation algorithm is employed to build the relevance between the vehicle states and typical battery faults, which contributes to extracting the key features of corresponding failures. A key fault-prediction model of electric buses based on big data is then established on the key feature variables. Different selections of kernel functions and hyperparameters are scrutinized to optimize the performance of warning. The proposed method is validated with real-world data acquired from electric buses in operation. Results suggest that the constructed prediction model can effectively predict the faults and carry out the desired early fault warning.