Study On Prediction System Of Mine Fan Fault Based On Multivariate Data

Mine main fan is the core of the respiratory system of mine, the safety and not directly related to the life safety of the working personnel in mine. In recent years, the main mine fan fault have occurred, and the existing fan alarm system can achieve fault prediction, in order to ensure the safety of mine production, reduce wind machine breakdown maintenance cost, improve mine fan service life. The purpose of this paper is to study a kind of fault prediction system for mine fans, which is suitable for production.This study to mine explosion proof counter rotating axial flow fan as the research object, the research of the active mine ventilation machine type and ventilation, using CAD, Pro/E software of wind turbine were 2D drawing and 3D modeling and simulation, to study the structure and design principle of each part of the fan. By combining the operation principle of the sensor and the long-term monitoring condition,the failure of the system, hardware and software of the wind turbine system are studied.Provide the fault database suitable for production and monitoring for fan fault prediction system.This paper analyzes the fault diagnosis method of the existing fan system, and deeply studies the application of the fault diagnosis method based on the analytical model and artificial neural network in the mine fan. In combination with the production practice, a new method of mine fan fault prediction based on multi variable data is proposed.According to the requirement of the system, the hardware and software of the original monitoring system are improved, and the new network printer, web page and data server are added. Use Kingview software to reconstruct the monitoring interface,through the Kingview software and SQL Server database links, the realization of the data storage and query. With the powerful data processing capability of Matlab, the integrated forecasting mechanism is established through the real-time transmission and processing and feedback of the monitoring data.In this paper, the research results have been tested by link, which can effectively predict the fault of mine fan system.