Managing qualitative simulation in knowledge‐based chemical diagnosis

“…Two methods of system decomposition for fault diagnosis have been developed. One is a two-step diagnostic strategy that narrows the diagnostic focus to a particular decomposed subsystem and performs diagnosis on this subsystem. − In the other method, a diagnosis knowledge base is developed separately for each subsystem, and diagnostic results are collected from all of the subsystems before the final conclusion is drawn. , System decomposition has the advantages of providing flexible diagnosis throughout operating condition changes, reducing the size of the knowledge base, and simplifying the understanding of complex process to process interactions.…”

Section: Diagnosis Strategymentioning

confidence: 99%

Multiple-Fault Diagnosis Based on System Decomposition and Dynamic PLS

Lee

Song

Yoon

2003

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

This study suggests a hybrid method of signed digraph and partial least squares for the fault diagnosis of chemical processes. Using the local qualitative relationships of each variable in a signed digraph, a process is decomposed into subprocesses to allow for the reliable diagnosis of multiple faults. A partial least-squares model is built for the estimation of each measured variable in each decomposed subprocess. To handle the process dynamics accurately, the input of the partial least-squares model uses both the current values and the past values of the process variables. In each case, the measured and estimated values are compared to diagnose the fault. A case study of a continuously stirred tank reactor illustrates the conclusion that the proposed method greatly improves the accuracy, resolution, and reliability of the diagnosis.

show abstract

“…Using the hybrid approach can take advantage of the efficiency of compiled knowledge in rapidly focusing on the solution, while retaining the robustness of models when confronted with the need for behavioral detail. Several recent research papers in the chemical engineering literature have explored this hybrid problem-solving notion (42,43). For more information on model-based reasoning in general see References 44 and 45.…”

Section: Model-based Reasoningmentioning

confidence: 99%

Expert Systems

Ramesh

2000

Kirk-Othmer Encyclopedia of Chemical Technology

View full text Add to dashboard Cite

Expert systems, or more appropriately knowledge‐based systems, are essentially computer programs that encode the expertise of human problem solvers in some well‐defined domain. A practical offshoot of the field of artificial intelligence, knowledge‐based technology has emerged as an important area of computer applications, with significant business impact on the industry. This is because knowledge‐based systems can automate problem‐solving tasks that hitherto could not be computerized by conventional, numeric modeling techniques. In the domain of chemical engineering, knowledge‐based systems have been used to automate such tasks as equipment and process design, control of complex processes, troubleshooting process operations, scheduling batch processes under uncertain conditions, and simulation of discrete event operations. This article discusses the motivations and benefits of knowledge‐based technology as applied to chemical engineering problems; the differences between knowledge‐based systems and quantitative, numerical techniques; the theoretical underpinnings of the technology; approaches to selecting, designing, and implementing knowledge‐based system applications; and some of the tools available to implement such systems. Alternatives to expert systems such as neural networks (nets) and case‐based reasoning are also briefly discussed. Throughout, the concepts are illustrated using examples from chemical engineering.

show abstract

Managing qualitative simulation in knowledge‐based chemical diagnosis

Abstract: Deep knowledge about process behaviorsplays an important role in the diagnosis

Cited by 15 publications

References 23 publications

Qualitative-model simplification with an application to multistage separation processes

Qualitative-model simplification with an application to multistage separation processes

Multiple-Fault Diagnosis Based on System Decomposition and Dynamic PLS

Expert Systems

Contact Info

Product

Resources

About