Open Access

ARTICLE

Deep Learning-Based Health Assessment Method for Benzene-to-Ethylene Ratio Control Systems under Incomplete Data

Huichao Cao^1,*, Honghe Du¹, Dongnian Jiang¹, Wei Li¹, Lei Du¹, Jianfeng Yang²

1 School of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou, 730050, China
2 Mechanical and Electrical Instrument Operation and Maintenance Center, PetroChina Lanzhou Petrochemical Company, Lanzhou, 730060, China

* Corresponding Author: Huichao Cao. Email:

(This article belongs to the Special Issue: Advanced Detection Technologies and Interpretable Machine Learning Methods in Energy Infrastructure)

Structural Durability & Health Monitoring 2025, 19(5), 1305-1325. https://doi.org/10.32604/sdhm.2025.066002

Received 27 March 2025; Accepted 17 June 2025; Issue published 05 September 2025

Abstract

In the production processes of modern industry, accurate assessment of the system’s health state and traceability non-optimal factors are key to ensuring “safe, stable, long-term, full load and optimal” operation of the production process. The benzene-to-ethylene ratio control system is a complex system based on an MPC-PID double-layer architecture. Taking into consideration the interaction between levels, coupling between loops and conditions of incomplete operation data, this paper proposes a health assessment method for the dual-layer control system by comprehensively utilizing deep learning technology. Firstly, according to the results of the pre-assessment of the system layers and loops by multivariate statistical methods, seven characteristic parameters that have a significant impact on the health state of the system are identified. Next, aiming at the problem of incomplete assessment data set due to the uneven distribution of actual system operating health state, the original unbalanced dataset is augmented using a Wasserstein generative adversarial network with gradient penalty term, and a complete dataset is obtained to characterise all the health states of the system. On this basis, a new deep learning-based health assessment framework for the benzene-to-ethylene ratio control system is constructed based on traditional multivariate statistical assessment. This framework can overcome the shortcomings of the linear weighted fusion related to the coupling and nonlinearity of the subsystem health state at different layers, and reduce the dependence of the prior knowledge. Furthermore, by introducing a dynamic attention mechanism (AM) into the convolutional neural network (CNN), the assessment model integrating both assessment and traceability is constructed, which can achieve the health assessment and trace the non-optimal factors of the complex control systems with the double-layer architecture. Finally, the effectiveness and superiority of the proposed method have been verified by the benzene-ethylene ratio control system of the alkylation process unit in a styrene plant.

---

Keywords

---