Font Size: a A A

Research On Coal Mine Intelligent Monitoring System Based On Multi-sources Data

Posted on:2017-01-11Degree:MasterType:Thesis
Country:ChinaCandidate:Y ZouFull Text:PDF
GTID:2321330503472444Subject:Control Engineering
Abstract/Summary:PDF Full Text Request
Development of science and technology along with the requirements for efficiency and safety mining make the intelligent monitoring and control system indepensable. Tunnel digging and coal mining are the two most essential parts in mining process. Thus, the collection and management of the spatial data, real-time data, and monitoring data from such process are also consequential. However, current intelligent monitoring system inability to take advantage of aboving data for management. Therefore, the construction of multi-source data mining-based intelligent monitoring system is needed for modern coal mine industry.Multiple sources of data-based intelligent monitoring system is studied in this work. BASIC script language and MySQL SQL language were here used in creating unified variable table, storaging timing critical data, data management, filing data in the history and establishing data access mechanism. All the video and scenes of spatial data, equipment operation real time data, and equipment of vibration monitoring data used here are stored in force control database and the MySQL relational database platforms. In addition, ICONICS Corporation Genesis64 configuration software were used for system development, making a platform possible that could coordinate different functions, control modes, protocols of live video, live scene, and harmonize equipment operation monitor at the same time.Finally, the vibration measure data that resulted from intelligent monitoring system w as analysised. Due to the data from the intelligent monitoring system was scarce, we const ructed the fault simulation experiment platform to stimulate amounts of vibration measure data which was based on model of RBF neural networks fault diagnosis algorithm. Our res ults showed that combined with the failure model of RBF network import feature vector c an effectively improve the accuracy of diagnosis. Our results also suggested that by using t he C++ language, the function module could be easily written into intelligent monitoring system.
Keywords/Search Tags:Multi-source data, Monitoring and control system, Data management, Fault diagnosis, Genesis64
PDF Full Text Request
Related items