Dynamic Weighted Fusion of Multi-source Information for Large Rotating Machinery Fault Prediction
Sun Jianghong, Zuo Yunbo, Xiaoli Xu · 2010
Data process of large rotating machinery is in line with basic features of information fusion. The fault deterioration is extracted from the pattern spectrum as the fault feature, and its trend is predicted by the information fusion which is based on the dynamic weighted method for single-sensor and multi-sensors respectively. Actual example of Beijing Yanshan Petrochemical Co. shows the correction of conclusion.