Research of Ultrasonic Flow Measurement and Temperature Compensation System Based on Neural Network

In traditional ultrasonic flow measurement, temperature has great great influence on the speed of sound. To insure high accuracy and sensitivity measurement of ultrasonic flow meter, on the basis of nonlinear compensation method, temperature compensating model of ultrasonic flow measurement is established by the application of BP (Back Propagation) neural network. The system hardware structure design of ultrasonic flow measurement system with temperature compensation is completed, doing analysis and research to some circuits of system and work process. The network was trained using the measured samples by using MATLAB software, based on this compensating the temperature of the ultrasonic flow measurement system. By using neural network technique, the precision of the ultrasonic flow measurement is improved greatly, and the accurate intelligent temperature compensation of the ultrasonic flow measurement is made.