The Prediction and Evaluation of Manufacturing Technology innovation based on Machine Learning and Big Data Analysis

Abstract

A data anomaly detection method was designed based on chemical manufacturing and oil refining units. Massive data storage and calculation are used in the cloud computing framework for petrochemical enterprises, refineries, and other large enterprises. The massive data is segmented based on the modified time series method, and the anomaly analysis is carried out. Thus, the abnormal data of the chemical manufacturing and oil refining units can be monitored. The practice proves that the algorithm proposed in this paper is a feasible, simple and effective data correction scheme.