Research on Multi-sensors Data Fusion of Large Diameter Measurement System Using Rollers

To improve the measurement accuracy while measuring large diameters using rollers, the errors which affect measurement precision should be corrected such as that caused by the distortion of the rollers and temperature fluctuation etc. So five kinds of sensors, such as inductance displacement sensors, pressure sensors, temperature sensors, circular raster sensors and photoelectric sensors, more than thirty sensors in number totally are used in the large diameter measuring system. Through data fusion, the big diameter can be measured in high precision. The model of data fusion system, which consists of the information level fusion and the character level fusion, is presented emphatically. In information level fusion, abnormal measurement data of three rollers´ rotating angles is found and mended, and the locality of skidding can be identified by the correlation analysis of large-diameter measurement based on multiple rolling-wheel method. In feature level fusion, through the method of backpropagation neural network, three groups measurement datum are fused and a group result is got. The results of simulation experiments show the method can gain precision measurement.