Danling Yuan

A large amount of traffic safety information has been generated. This will further promote the sustainable development of transport. However, its content, form, and structure are complex and scattered, lacking effective information integration and a comprehensive framework. Combined with the concept of safety analysis, a traffic safety management knowledge graph was designed for structured data, which include 54 types of node entities and 14 types of relationship entities. Six types of information were collected and imported, including illegal acts, vehicle failure, emergency response, legal norms, organization information, and road-related information. Ultimately, a knowledge query function was realized using Cypher, and an automatic Q&A function was created based on rule matching. A traffic accident knowledge graph was constructed for unstructured data, with people and institutions involved, vehicles involved, and accidents as the core, including 21 types of node entities and 22 types of relationship entities. Comparing the node entity extraction performance of Bert, Bert-CRF, Bert-BiLSTM, and Bert-BiLSTM-CRF models, Bert BiLSTM-CRF performs the best. The Bert model was used for relationship entity extraction. The traffic accident knowledge graph can structurally display accident information and support a query function to facilitate safety analysis.

To study the occurrence characteristics of hazardous chemical accidents in China, mathematical analysis methods were used to study hazardous chemical fatalities (HCFs) in recent years. This research focused on selecting seven accident characteristics including time characteristics, geographical characteristics, accident type characteristics, hazardous chemical types, hazardous chemical production links, accident cause characteristics, and accident classification. The research results show that: (1) the occurrence of HCFs has obvious time-domain and regional characteristics, the number of casualties on Wednesday working days is the largest, 9:00–11:00 (inclusive) and 15:00–16:00 (inclusive) in a day are the two time periods with the largest number of incidents, the number of hazardous chemical accidents and deaths in economically developed coastal provinces is relatively high; (2) Analyze according to the type of accident statistics, the number of accidents and deaths caused by explosions, poisoning, asphyxiation, and fire are the largest; (3) Analyze according to the type of hazardous chemicals, drugs, compressed gas and liquefied gas, flammable solids, and spontaneous combustion materials, as well as flammable materials when wet are the types of hazardous chemicals that cause the most casualties; (4) Analyze according to the type of hazardous chemical accidents, the number of accidents and deaths caused in the production process is the largest; (5) Analyze according to the type of unsafe behavior by personnel, operator errors, the ignorance of safety, and the ignorance of warnings are the main causes of injuries and deaths caused by hazardous chemicals.; (6) Through single-factor feature analysis and multi-feature comprehensive cross-discussion, countermeasures, and suggestions for preventing and controlling accidents in hazardous chemical enterprises are put forward according to the characteristics of accidents caused by different accident characteristics.