Search

Safety production is important for power grid enterprises. It is not only related to enterprise factors, but also closely related to the individual behavior of employees. Among them, employee job satisfaction is significantly related to work safety. Therefore, to realize the timely perception of the psychological state and emotion of staff in the operation is of great importance to the information-based safe management. In this study, the research object is the staff involved in power distribution and operation in the power grid. Through the analysis of audio characteristics and job satisfaction, this research attempts to explore and establish its internal relationship, which provides a reference for predicting job satisfaction from the perspective of voice.

Prediction of cognitive needs using voice signals is an important subject in information science, management science and sociology, and it is also a very potential research direction. The paper is about the regression prediction of cognitive needs by using speech signal modeling. Its purpose is to find a new cognitive needs assessment model that enables rapid, accurate and non-intrusive assessment of individuals, making up for the lack of timeliness and limited application scope. We obtained the voice data of 240 participants and their cognitive needs scale evaluation results. Then, we use principal component analysis to reduce the dimension of speech features, and use support vector machine, random forest and neural network models to predict cognitive needs. We find that the neural network model not only has the highest prediction accuracy, but also has the most uniform distribution of prediction errors. Through the research, we put forward our own suggestions and prospects for the future research direction of cognitive needs.

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.

This paper presents a method to identify individual coping styles based on gait information extracted by OpenPost. By recruiting 414 front-line employees of power distribution posts, psychological index evaluation and gait data acquisition experiments were completed. After preprocessing the gait data, the time domain and frequency domain features are extracted, and the support vector machine is used to train the classification model for identifying the types of coping styles. The correlation between the predictive score of regression model and the score of self-report scale reached a medium level: in the dimension of self-blame, the correlation coefficient between the predictive score of regression model and the score of self-report scale reached 0.52; in the three dimensions of “problem solving”, “help seeking” and “rationalization”, the correlation coefficient could reach 0. The correlation coefficients of avoidance and fantasy were 0.48. The accuracy of the classification model in predicting coping style types (“mature”, “immature” and “mixed”) reached 83%. The results show that by machine learning method, the type of coping style of employees in power grid enterprises can be identified based on gait data.

Characterization of residential and occupational exposures was undertaken in different phases. A survey of the background and equipment-generated power frequency electromagnetic fields was carried out in various locations throughout the utilities facilities. A comparison of electromagnetic field is described in this paper, which is used for analysis of occupational and general public exposure. The electromagnetic field intensity around the electrical equipment depends on the distribution of equipment. The maximum electric field and magnetic field value appeared in busbar and 35kV shunt reactor of 500kV substation, which were 12.133 kV/m and 1267.79 μT. Moreover, The individual exposure of magnetic field was tested. Results indicate that individual professional exposure of magnetic field in 500 kV substation can reach (8.2±11.9) μT, which is considerably higher than in office and at home. But for all that, the power frequency electromagnetic field isn't enough to cause long-term health effects.