Method for processing abnormal data of real-time data acquisition system in real time

Abstract

The invention relates to a data processing method and discloses a method for processing abnormal data of a real-time data acquisition system in real time. The method comprises the steps of (1) initializing sample data and selecting an even number of normally operating sample data; (2) adopting 1 / 2 of the sample data to act as the moving step by using a single exponential smoothing method, and predicting the latter half part of the sample data by using a single exponential smoothing recurrence method; (3) the residual of a prediction result is calculated according to a prediction value and a measured value of the latter half part; (4) carrying out anomaly analysis on the residual sequence according to a Pauta criterion to confirm whether the measured value is abnormal data or not; and (5) replacing the measured value with the prediction value if the measured value is abnormal data. The method disclosed by the invention is mainly advantageous in that a prediction algorithm coefficient is adjusted in an adaptive mode, the error is analyzed by adopting a mobile exponential smoothing method, and the anomaly judging method better conforms to use conditions of the Pauta criterion, thereby improving the accuracy in judgment for the abnormal data, and preventing false judgment and missing judgment to a certain degree.

Description

technical field [0001] The invention relates to a data processing method, in particular to a processing method for abnormal data in an industrial real-time data acquisition system. Background technique [0002] At present, in the field of industrial informatization, it basically includes industrial real-time data acquisition systems. In the process of data acquisition, there are many situations, especially due to the instantaneous occurrence of data acquisition due to the ambient temperature, humidity, dust, magnetic field, and signal interference of acquisition components. In abnormal situations, this kind of data cannot reflect the real situation, and will cause false alarms, abnormal fluctuations in real-time production curves in the operating system, etc., affecting production operations, and will cause calculation errors in the later data summary analysis, etc. This requires processing such abnormal data during data collection to avoid erroneous data. [0003] However,...

AI Technical Summary

Problems solved by technology

[0010] As for the real-time data processing method of one-time exponential smoothing prediction, it has also been mentioned in papers and invention patent documents before, but the coefficient of the exponential smoothing method used in the paper does not change dynamically, and the error is counted from the initial point of the model, due to the prediction error of exponential smoothing It is related to initial value selection, coefficient selection and iteration steps, so the statistical error results do not conform to the prediction model of each data. The error of the predicted data points at the beginning of the model is generally greater than the error of the predicted data points at the end of the model, resulting in abnormal judgments. Wrong; there is no exponential smoothing forecast error in the patent literature, using the Raida criterion to judge, but the difference between the current collection value and the previous collection value using the Raida criterion, which directly uses the data difference result to judge the abnormality of the data The algorithm uses the differential data of the collected data as the object of abnormal judgment, and does not fully meet the prerequisites for the use of the Raida criterion, that is, equal precision measurement

There are only two options for the coefficient of the exponential smoothing algorithm, and there is no recursive exponential smoothing method, and the prediction accuracy is not high

Especially for some delayed industrial collection data such as temperature and pressure, it is easy to cause misjudgment

Images