A virtual level temperature compensation system based on information fusion technology

The output of ultrasonic object-location meter changes with the environmental temperature. In order to eliminate such a situation, a new information fusion algorithm based on neural network is presented. A virtual ultrasonic object-location measurement temperature compensation system is realized based on a method of the hybrid programming of MATLAB and LabVIEW with MATLAB Script node. A improved BP algorithm - LM algorithm is used to train the neural network, it can improve the data's convergent speed. Experimental results show that the method can eliminates impacts of temperature to object-location and improves the accuracy of sensor. This virtual object-location measurement system based on BP neural network is of wide and factual application value.