학술논문
Construction of Safety Psychological Model for Power Distribution Operational Maintenance Posts of Power Grid Enterprises Based on Fully Connected Neural Network
Document Type
Conference
Author
Source
2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC) Technology and Mechatronics Engineering Conference (ITOEC), 2020 IEEE 5th Information. :1345-1348 Jun, 2020
Subject
Language
Abstract
In power grid enterprises, a series of unsafe behaviors, such as violation of labor discipline, operating rules and methods, are easy to cause power safety accidents. Therefore, it is particularly important to predict the risks of unsafe behaviors of employees. Firstly, this paper uses the methods of literature review and questionnaire survey to explore the psychological factors related to the safety behavior of employees in specific positions in power grid enterprises, and obtains five indicators: personality quality, cognitive ability, work values, mental health and social environment. Then the method of fully connected neural network is adopted to finally obtain the safety psychological model. The average absolute value loss of this model is 0.049512, which can predict unsafe behaviors of employees well in specific positions.