Translation. Region: Russian Federal
Source: Peter the Great St Petersburg Polytechnic University – Peter the Great St Petersburg Polytechnic University –
In June, Peter the Great St. Petersburg Polytechnic University successfully registered a computer program developed by employees of the Civil Engineering Institute.
The program was developed by the director of the Higher School of Technosphere Safety Andrey Andreev, assistants of the Higher School of Technosphere Safety Alexander Doronin and Valeria Kachenkova.
The program for analyzing and predicting human factor risks in production using neural networks was created using the Python programming language and applies LSTM neural network technologies. It is designed to analyze and predict the probability of errors caused by the human factor. The program takes into account a wide range of parameters, such as attention level, reaction speed, employee responsibility and production environment factors, which allows for a comprehensive risk assessment.
Functionality includes risk factor analysis and visualization, building predictive models based on historical data, real-time error probability assessment, creating heat maps of hazardous areas, monitoring employee performance dynamics, and generating reports and recommendations for risk reduction.
The software can be used in manufacturing plants, in occupational health and safety management systems, industrial safety services, as well as in personnel training and assessment to prevent emergency situations.
Technical requirements include the use of an IBM PC based on an Intel Pentium processor or higher, Windows 7 operating system or higher, and the Python programming language. The program size is 150 MB.
Currently, the team of the Higher School of Technosphere Safety continues to work on creating software in the field of labor protection. It will be intended for use in production and in the educational process for training future specialists.
Please note: This information is raw content directly from the source of the information. It is exactly what the source states and does not reflect the position of MIL-OSI or its clients.