Big data-driven correlation analysis based on clustering for energy-intensive manufacturing industries.

In Industry 4.0, the production data obtained from the Internet of Things has reached the magnitude of big data with the emergence of advanced information and communication technologies. The massive and low-value density of big data challenges traditional clustering and correlation analysis. To solve this problem, a big data-driven correlation analysis based on clustering is proposed to improve energy and resource utilisation efficiency in this paper. In detail, the production units with abnormal and energy-intensive consumption can be classified by using clustering analysis. Additionally, feature extraction is carried out based on clustering analysis and the same cluster data is migrated to the training data set to improve correlation analysis accuracy. Then, correlation analysis can balance the relationship between energy supply and demand, which can reduce carbon emission and enhance sustainable competitiveness. The sensitivity analysis results show that the feature extraction method can improve the correlation analysis accuracy compared to the original analysis model. In conclusion, the big data-driven correlation analysis based on clustering can uncover the potential relationship between energy consumption and product yield, thus improving the efficiency of energy and resources. • An architecture of big data clustering and correlation analysis is proposed. • A PCA-guided ISODATA is proposed for data pre-processing and processing. • The feature extraction method has been proposed based on clustering. • A correlation analysis model is established for data mining. • The models can improve the scheduling efficiency of energy and resources. [ABSTRACT FROM AUTHOR]