Industrial data quality evaluation method and system based on machine learning

Abstract

The invention discloses an industrial data quality evaluation method and system based on machine learning. The method comprises the following steps: S1, carrying out the preprocessing of detection data, so as to eliminate the abnormal data of a single detection data point; and S2, constructing an association model, and judging the preprocessed detection data meeting the requirements to determine abnormal detection data which do not meet mutual association. According to the method, the abnormal data which do not meet the requirements obviously are recognized through the preprocessing process, and then the abnormal data which are not associated with one another in the related group are recognized through the association model, so that the data of a plurality of regions in the industrial production process can be conveniently detected, and the abnormal monitoring data can be accurately determined.

Description

technical field [0001] The invention relates to the field of industrial information technology, in particular to a method for evaluating the quality of industrial data based on machine learning. Background technique [0002] In the industrial production process, it is necessary to detect the data of multiple areas, and determine the stability of the equipment in the relevant production process according to the detection results. However, with the increasing number of detection sensors, how to effectively judge the obtained detection data? Accuracy, it is critical to evaluate detection data to find outliers. [0003] In the existing technology, the direct comparison method is mostly used to obtain the data, and the data can be judged well when the amount of data is small. However, as the amount of data continues to increase, it is difficult to evaluate the quality of industrial data in the traditional way. [0004] In addition, the conventional method in the prior art is to ...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the direct comparison method is mostly used to obtain the data, and the data can be judged well when the amount of data is small. However, as the amount of data continues to increase, it is difficult to evaluate the quality of industrial data in the traditional way.

[0004] In addition, the conventional method in the prior art is to establish different data monitoring and quality evaluation models for different specific needs and data types of industrial operations, and lacks a unified data quality evaluation method that does not need to distinguish between operating environments and sensor data types

Images