A Fault Identification Method in Distillation Process Based on Dynamic Mechanism Analysis and Signed Directed Graph

Tian, Wende; Cui, Zhe; Liu, Zijian; Wang, Shaochen; Zhao, Yingjie; Zou, Hao

doi:10.3390/pr9020229

Cited by 8 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And there are two types of SDG edges, solid lines and dashed lines, which indicate the positive and negative correlations between the changing trends of the starting point and the end point, respectively [128] . Figure 5 [129] shows a simple SDG model structure, which means that an increase in A leads to an increase in B, and then leads to a decrease in C.…”

Section: Knowledge-driven Methodsmentioning

confidence: 99%

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Yang

Lei

et al. 2023

Big Data Min. Anal.

View full text Add to dashboard Cite

Fluidic Catalytic Cracking (FCC) is a complex petrochemical process affected by many highly non-linear and interrelated factors. Product yield analysis, flue gas desulfurization prediction, and abnormal condition warning are several key research directions in FCC. This paper will sort out the relevant research results of the existing Artificial Intelligence (AI) algorithms applied to the analysis and optimization of catalytic cracking processes, with a view to providing help for the follow-up research. Compared with the traditional mathematical mechanism method, the AI method can effectively solve the difficulties in FCC process modeling, such as high-dimensional, nonlinear, strong correlation, and large delay. AI methods applied in product yield analysis build models based on massive data. By fitting the functional relationship between operating variables and products, the excessive simplification of mechanism model can be avoided, resulting in high model accuracy. AI methods applied in flue gas desulfurization can be usually divided into two stages: modeling and optimization. In the modeling stage, data-driven methods are often used to build the system model or rule base; In the optimization stage, heuristic search or reinforcement learning methods can be applied to find the optimal operating parameters based on the constructed model or rule base. AI methods, including data-driven and knowledge-driven algorithms, are widely used in the abnormal condition warning. Knowledge-driven methods have advantages in interpretability and generalization, but disadvantages in construction difficulty and prediction recall. While the data-driven methods are just the opposite. Thus, some studies combine these two methods to obtain better results.

show abstract

Section: Knowledge-driven Methodsmentioning

confidence: 99%

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Yang

Lei

et al. 2023

Big Data Min. Anal.

View full text Add to dashboard Cite

show abstract

“…The reverse search strategy based on the fault propagation matrix is adopted to judge the compatible paths, obtain the candidate fault source set, and use the availability to objectively evaluate the influence of multiple fault sources, so as to improve the efficiency of troubleshooting. Tian et al (2021) proposed a new identification method combining two-step cluster analysis and signed directed graph (TSCA-SDG) for the problem that abnormal working conditions are difficult to identify in industrial production. First, variables are efficiently selected and extracted through correlation analysis and R-type cluster analysis.…”

Section: Related Workmentioning

confidence: 99%

Research on the uncertainty problem of SDG fault diagnosis based on information flow

Huang

Liu²,

Yang³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Accurate and complete diagnosis of nuclear accidents is the primary link to nuclear emergencies. The signed directed graph (SDG), as a common method of fault diagnosis, has good completeness. However, if there are feedforward and negative feedback control loops, compensation response and reverse response will be generated in the process of fault occurrence and propagation, which makes the state of the compensation variable and reverse variable uncertain, thus destroying the compatibility of the fault propagation path, leading to incomplete SDG reverse reasoning. In order to solve this problem, this paper proposes a SDG fault diagnosis method based on information flow. This method first finds out all the directed edges with the compensation variable or inverse variable node as the endpoint. By comparing the goodness of fit between the information flow on these directed edges and their total information flow curves, the path that contained the directed edge represented by sub-information flow with the highest R2 is obtained, and it is used as the fault propagation path with the maximum probability to determine the state of the compensation variable or inverse variable and fault location. At the same time, this paper extends the SDG model from the structure to build an FR-SDG model that can intuitively describe the node steady-state information under the final response and the fault propagation path with the maximum probability, which improves the diagnosis resolution. Finally, this paper carried out the relevant experiments in the subsystem of the nuclear reactor primary loop by using the simulation system PCTran AP1000, which verified the feasibility of this method.

show abstract

“…The states of M, N and P are "+", "+" and "•" respectively. The relationship between M and N is represented by a solid arrow, while the relationship between N and P is represented by a dashed arrow, meaning that an increase in M will lead to an increase in N and then a decrease in P [32]. The sample of SDG model γ = (G_0，φ) is a function of node state value 𝜓: 𝐴 → +,0, − .…”

Section: Sdg Modelmentioning

confidence: 99%

Identification of Unknown Abnormal Conditions in Catalytic Cracking Process Based on Two-Step Clustering Analysis and Signed Directed Graph

Hong

Tian

et al. 2021

Processes

Self Cite

View full text Add to dashboard Cite

There are many unknown abnormal working conditions in industrial production. It is difficult to identify unknown abnormal working conditions because there are few relative sample and experience in this field. To solve this problem, a new identification method combining two-step clustering analysis and signed directed graph (TSCA-SDG) is proposed. Firstly, through correlation analysis and R-type clustering analysis, the variables are effectively selected and extracted. Then, a two-step clustering analysis was carried out on the selected variables to obtain the cluster results. Through the establishment of the signed directed graph (SDG) model, the causes of abnormal working conditions and their mutual influence are deduced from the mechanism. The application of the TSCA-SDG method in the catalytic cracking process shows that this method has good performance for abnormal condition identification.

show abstract

A Fault Identification Method in Distillation Process Based on Dynamic Mechanism Analysis and Signed Directed Graph

Cited by 8 publications

References 25 publications

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Artificial Intelligence Methods Applied to Catalytic Cracking Processes

Research on the uncertainty problem of SDG fault diagnosis based on information flow

Identification of Unknown Abnormal Conditions in Catalytic Cracking Process Based on Two-Step Clustering Analysis and Signed Directed Graph

Contact Info

Product

Resources

About