Hierarchical Multiblock T-PLS Based Operating Performance Assessment for Plant-Wide Processes

Abstract

With the pursuit of profit, the operating performance assessment of industrial processes has gradually attracted attention and concentration in modern industrial production. However, owing to the complexity of plant-wide processes, many existing operating performance assessment techniques are lacking in interpretation of the assessment result, and the cause identification is also difficult for the nonoptimal operating performance. In this study, a new operating performance assessment method is proposed for plant-wide processes based on hierarchical multiblock total projection to latent structures (T-PLS). The proposed approach divides the process variables into several conceptually meaningful blocks and incorporates block information into high level for operating performance assessment of plant-wide processes. With the new method, the assessment task can be greatly reduced and the interpretability of the assessment models are greatly improved. Once the process operating performance is nonoptimal, the responsible block is first located by the block assessment result, and then the variable contributions are calculated in the corresponding block so as to narrow the search and improve the accuracy of the cause identification result. A case study of the gold hydrometallurgy process evaluates the feasibility and efficiency of the proposed method.

Neural Component Analysis for Key Performance Indicator Monitoring

“…It should be noted that process data contain two types of information: key performance indicator (KPI)-related and KPI-unrelated, where KPIs are indicators of product quality or process safety that must be emphasized in process monitoring . Partial least squares (PLS), − as a commonly used KPI-related performance monitoring method, can maximize the variation between process variables and KPI-related variables and use KPI-related information to detect faults. As such, PLS is more sensitive to abnormal changes in KPI-related components, and hence, it is suitable for monitoring the industrial process with clear KPI indices.…”

Distributed Operating Performance Assessment of the Plant-Wide Process Based on Data-Driven Hybrid Characteristics Decomposition

“…Because the data is collected from different procedures with different characteristics in the plant-wide process, the traditional data-based centralized model , may not be suitable for the modern large-scale industrial production with long processes and multiple procedures. Therefore, many scholars are concerned about the research results of distributed (or multiblock) models. − Liu et al proposed a distributed assessment method based on total projection to latent structures, in which the decomposition of plant-wide processes depended on prior knowledge. As the first step as well as the key step in developing a distributed assessment model, process decomposition could be implemented through process topology or prior knowledge; however, process knowledge was incomplete when it came to large-scale and high-complexity industrial processes .…”

“…Therefore, many scholars are concerned about the research results of distributed (or multiblock) models. 19−27 Liu et al 19 proposed a distributed assessment method based on total projection to latent structures, in which the decomposition of plant-wide processes depended on prior knowledge. As the first step as well as the key step in developing a distributed assessment model, process decomposition could be implemented through process topology or prior knowledge; however, process knowledge was incomplete when it came to large-scale and high-complexity industrial processes.…”

Data-Driven Plant-Wide Control Performance Monitoring

“…Several modifications have appeared in the last decades, which include adaptive/recursive approaches, − nonlinear strategies, , and dynamic extensions as summarized in Qin (2012) and Ge (2017) . Recently, a hierarchical multiblock total PLS based monitoring was presented in Liu et al (2018) . This work suggests a methodology for on-line process operation monitoring based on the user-defined benchmark approach.…”

“…15 Recently, a hierarchical multiblock total PLS based monitoring was presented in Liu et al (2018). 16 This work suggests a methodology for on-line process operation monitoring based on the user-defined benchmark approach. In addition, a contribution analysis is suggested for abnormal operation diagnosis.…”