Exergy-related Operating Performance Assessment for Hot Rolling Process Based on Multiple imputation and Multi-class Support Vector Data Description

In process industry, operating performance assessment (OPA) is important for ensuring production efficiency. With the development of modern information technology, the collection, storage and transmission of information in the process industry has been gaining popularity. However, the massive streaming industrial data obtained in real time has some non-ideal characteristics, such as missing values, which greatly increases the difficulty of OPA. Besides, traditional data-driven methods pay more attention to the utilization of process data and ignore the process mechanism. It is necessary to consider the energy flow of the process. As the unity of quality and quantity of energy, exergy contains the performance change information of the process and can be used as another way of achieving the required dimensionality reduction. To handle above issues, a novel exergy-related OPA based on multiple imputation (MI) and multi-class support vector data description (SVDD) is proposed in this paper. First, the initial incomplete process data are imputed by MI. Second, exergy efficiency are calculated and exergy-related process variables are obtained by the minimal redundancy maximal relevance (mRMR). Then, the exergy-related assessment model are developed. Finally, case study on a real hot rolling process (HRP) is given to illustrate the effectiveness of the proposed method.