Research On The Operation Status Monitoring Of Rotary Kilns Based On Wireless Sensor Networks

Rotary kiln is the core equipment of cement production.Rotary kiln works in harsh environment of high temperature and heavy load for a long time,and various faults often occur.If these faults cannot be found in time,it may affect the normal operation of rotary kiln.If a production shutdown accident occurs It will bring huge economic losses to the cement plant,so it is necessary to monitor and study the fault state of the rotary kiln.The displacement signal generated by the rotary kiln supporting roller during the operation process contains important information on the operating status of the rotary kiln.At present,the supporting roller displacement signal is generally collected by wired communication.The wired communication network has stable transmission and is not easily affected by the environment,but requires a lot of Manpower and material resources are required for installation and maintenance,and these additional inputs even exceed the sensor itself.The emergence of wireless sensor networks solves the above problems of wired networks.In addition,wireless sensor networks are widely used in various fields because they have many advantages such as convenient assembly,diverse working environments,and low production and application costs.In this paper,the wireless sensor network technology is used to collect the displacement signal of the rotary kiln supporting roller,and combined with the equipment fault diagnosis technology,the research is carried out on the acquisition of the supporting roller displacement signal,the signal processing,and the identification of the operating state of the rotary kiln.Based on the short-distance wireless communication technology Zig Bee,a set of rotary kiln supporting roller displacement monitoring system is designed.The system completes the hardware and software design of terminal,router and coordinator based on CC2530 which supports Zig Bee protocol,and transmits the displacement signal of the roller collected by the sensor to the coordinator through the wireless Zig Bee network,and then the coordinator transmits it to the host computer through the USB interface.The acquisition of the displacement signal of the supporting roller is completed.The hardware of the system is mainly divided into a wireless transmission part and a data acquisition part.The wireless transmission part is designed with the CC2530 chip as the core,which is responsible for the wireless transmission part of the displacement signal of the supporting roller;a high-precision displacement sensor is selected to complete the displacement of the supporting roller in the system.The acquisition part of the signal.In order to prolong the working time of the terminal node,in addition to the low power consumption design in the sleep mode,special design is also carried out in the two aspects of intelligent management of collecting data and sending data mode.Extracting multiple signal feature quantities that can reflect the fault of the rotary kiln from the supporting roller displacement signal in the time domain,frequency domain,and time-frequency domain to form a feature set,using random forest to analyze the importance of each feature in the initial feature set,combining The forward feature selection method determines the optimal feature subset based on the classification accuracy of random forest under different feature subsets.Using the powerful learning ability of Hidden Markov Model(HMM)for time series data,a recognition model of rotary kiln operating state based on mixed Gaussian Hidden Markov Model was established.Using the collected displacement data of the supporting rollers,the experimental verification of the fault state identification model of the rotary kiln is carried out.The results show that the system can accurately distinguish the operating states of different faults,and the recognition accuracy can reach 97.2%.Therefore,the recognition model can be applied to the actual monitoring of the operating state of the rotary kiln.Based on the fault state recognition model of rotary kiln operation,the application system is designed with the support of MATLAB and QT.The interface of the application system includes the data receiving function,the callback function,etc.,which ensures the coordination and cooperation between the data transmission and the running status recognition.Finally,the monitoring system is debugged under laboratory conditions,which basically meets the overall requirements of the design.