A mechanism knowledge-driven method for identifying the pseudo dissolution hysteresis coefficient in the industrial aluminium electrolysis process. (September 2020)

• Record Type: Journal Article
• Authors: Zeng, Zhaohui; Gui, Weihua; Chen, Xiaofang; Xie, Yongfang; Wu, Renchao
• Is Part Of: Control engineering practice. Volume 102(2020)
• Publication Date: 2020-09
• Subjects: Process mechanism analysis -- Process semantic embedding -- Explicit representation -- Automatic knowledge acquisition -- Pseudo dissolution hysteresis coefficient -- Aluminium electrolysis -- Bath temperature online recognition -- Alumina concentration abnormality detection; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2020.104533
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: To overcome the difficulties that are associated with the online recognition of the alumina dissolution properties in industrial aluminium electrolysis cells, this paper proposes a method driven by process mechanism knowledge for the identification of a pseudo dissolution hysteresis coefficient (PDHC). The method explicitly represents the process semantemes that are implied in the normalized cell voltage (NCV) and the feed state using the proposed PDHC via process mechanism analysis and process semantic embedding. The PDHC quantifies the online dissolution performance of alumina and, thus, can overcome the inability to express the alumina online dissolution performance in industrial cells. Compared with slope-based methods, the PDHC-based method can not only realize the online recognition of the bath temperature but also detect an abnormal alumina concentration with a lead time of a few integrated feed periods (IFPs), thereby providing a new online basis for the temperature control and feed control of industrial cells. The PDHC identification is an application case of automatic knowledge acquisition in industrial aluminium electrolysis production. Graphical abstract: Highlights: A process mechanism knowledge-driven method is proposed and establishes a bridge between process mechanism research and industrial online application. The empirical knowledge, process mechanism knowledge and data knowledge are explicitly represented by a parameter that can be automatically obtained online. The pseudo dissolution hysteresis coefficient (PDHC) is proposed. The PDHC can overcome the inability to express the online dissolution performance of alumina in industrial cells. The relationship between the PDHC and the online bath temperature is identified. The bath temperature recognition based on the PDHC can alleviate the inability to measure the temperature online. The online alumina concentration anomaly detection base on the PDHC can not only detect concentration anomalies, but also detect the anomalies approximately two hours earlier than the slope-based method. Moreover, the proposed method is simpler than the slope-based method. A PDHC-based feed optimization control framework is developed. In this framework, the feed feedback compensation control loop and the real-time correction of parameters based on online temperature information are incorporated, which are difficult to implement in the slope-based method.