提出基于知识参量的数据标准化处理方法,介绍了知识参量的构成以及故障征兆的隶属度表示方法。根据功率相等的原则提出了传感器数据中的野值滤波方法。运用神经网络和最小二乘法加权的方法对缺损数据进行填充,并分别与最小二乘法和BP网络的处理结果进行比较。仿真结果表明,运用该方法进行数据处理,可以在保证数据完整准确的情况下,有效地弥补原始数据的缺陷,提高了数据的准确性和可信度。 A data standardization method based on knowledge parameters was proposed. The composition of knowledge parameters and the membership method of fault symptom were introduced. According to the principle of equal power, the outlier filtering method in sensor data is proposed. The defect data is filled by using the method of neural network and least square method and compared with the result of least square method and BP network respectively. Simulation results show that using this method for data processing can effectively make up for the defects of the original data and improve the accuracy and reliability of the data while ensuring complete and accurate data.