Research And Design Of High Precision Ultrasonic Anemometer For Mine

The accurate measurement of wind speed in coal mine roadway is not only one of the necessary guarantees for safety production,but it’s also the basic work to realize the goal of "reliable ventilation".Traditional anemometers are used widely.However,in the complex environment of high humidity and high dust in the coal mine,the accuracy of traditional anemometers is low.The ultrasonic anemometer has many advantages,such as no rotating parts and stable performance.There is no need to consider the interference of temperature and humidity in the coal mine roadway on the measurement results.The ultrasonic anemometer can well adapt to the working environment in the field of coal mines.However,the shadow effect caused by the structural characteristics of the ultrasonic anemometer will affect its measurement accuracy.To improve the measurement accuracy of the ultrasonic anemometer,the paper focuses on the error compensation model for the wind speed of the ultrasonic anemometer based on computational fluid dynamics(CFD)and machine learning.In the paper,the experiment of the ultrasonic anemometer in the wind tunnel is simulated by FLUENT software,the influence of the shadow effect on the measurement accuracy of the ultrasonic anemometer is analyzed,and the wind speed data of the error compensation model is obtained.The paper studies the error compensation model for the wind speed based on Extreme Learning Machine(ELM),Kernel Extreme Learning Machine(KELM),Support Vector Regression(SVR),and Back-Propagation Neural Networks(BPNN),and selects Particle Swarm Optimization(PSO),Moth-Flame Optimization(MFO),and Grid Search algorithms to optimize the parameters of each model,and compare the error compensation effects of the above models.The experimental results show that the overall time of the MFO-KELM model is no more than 0.1 s,and the Mean Absolute Percentage Error(MAPE)of the MFO-KELM model is 0.043%.The error compensation effect of the MFO-KELM model is the best in the paper.To verify the accuracy of the MFO-KELM model,the paper makes a statistical test on each error compensation model and uses the wind tunnel experimental data to test the MFO-KELM model.The experimental results show that after the error compensation of the MFO-KELM model,the relative error of wind speed remains between-0.3% and + 10%,which are lower than the relative error before error compensation.The MFO-KELM model can effectively reduce the error of the wind speed caused by the shadow effect.Based on the research of the ultrasonic time-difference method and wind speed error compensation model,the paper designs and develops the ultrasonic anemometer,and selects STM32 as the control core.The ultrasonic anemometer is equipped with many functional modules,such as Ultrasonic transmitting and receiving,Frequency output,LCD,Communication,etc.At the same time,the system is designed to compensate for the error of the wind speed,and transmit and store accurate data.The research of the error compensation method based on the experiment in the wind tunnel has a complex operation,and the time cost is high.Considering this,the paper provides a new idea for the error compensation of ultrasonic anemometer.The MFO-KELM model proposed in the paper can effectively compensate for the error of wind speed and has a certain reference value for the development of mining high-precision ultrasonic anemometer and the accurate measurement of wind speed in the coal mine roadway.Figure [68] Table [8] Reference [101]...