Generating optimal overlapping subsystems for distributed statistical fault detection subject to constraints

Khatib, Shaaz; Daoutidis, Pródromos

doi:10.1016/j.jprocont.2019.05.008

Cited by 9 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three additional features are added to the implementation of the forward selection algorithm that was described above to make it computationally efficient. First, a performance-based stopping criterion is included in the algorithm in which the algorithm stops when the MCR of the initial decomposition in an iteration is a certain predefined fraction (ζ) higher than the MCR of the decomposition with the lowest MCR up until that iteration . Second, in calculating the MCRs of the candidate decompositions, the computations involved in simulating the first stage of the distributed pattern recognition method will be minimized.…”

Section: Forward Selection For Distributed Pattern Recognitionmentioning

confidence: 99%

“…These subsystems must satisfy the cannot-link constraints encoded in A M . A decomposition that satisfies all the constraints and yields near optimal performance for distributed fault detection can be found using the PDAC method . The decomposition used for fault diagnosis via a distributed pattern recognition method can be selected using the FSDPR method.…”

Section: Subsystem and Sensor Allocationmentioning

confidence: 99%

“…PDAC is a method that uses the wrapper approach to select a decomposition for distributed fault detection by minimizing the fraction of undetected faulty samples subject to the cannot-link and other constraints. It can be modified to select a decomposition for distributed pattern recognition by simply using MCR as the objective function.…”

Section: Case Studymentioning

confidence: 99%

“…Besides the decomposition selected by FSDPR for implementing the distributed pattern recognition method, a decomposition with nine subsystems ( S 1 det , S 2 det , ···, S 9 det ) is selected for distributed fault detection using PDAC . The specific form of this decomposition is given in the Supporting Information.…”

Section: Case Studymentioning

confidence: 99%

“…It uses a greedy search strategy based on clustering algorithms from graph theory to generate the set of candidate decompositions. In ref 30, we extended PDAC to allow sensors to be allocated to multiple subsystems and to incorporate cannot-link and certain other constraints (cannot-link constraints define the pairs of sensors that cannot be placed into the same subsystem in the selected decomposition). The software for PDAC is available at http://license.umn.edu/technologies/20180385_ performance-driven-agglomerative-clustering-software.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Optimal Feature Selection for Distributed Data-Driven Process Monitoring

Khatib

Daoutidis

2019

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

Two methods are proposed in this article to address distributed data-driven process monitoring. The first method selects sensors and allocates these sensors among subsystems with the objective of optimizing the diagnostic performance of a pattern recognition method when it is implemented in a distributed configuration subject to constraints that are imposed to meet operational requirements. The second method finds the minimum number of monitoring computers required to implement the methods used for fault detection and diagnosis in a distributed configuration subject to certain operational constraints. It also finds the sensors that need to be transmitted to each of the monitors. The proposed methods rely on concepts and algorithms from graph theory and optimization, and their efficiency is shown through a case study on the benchmark Tennessee Eastman Process.

show abstract

Section: Forward Selection For Distributed Pattern Recognitionmentioning

confidence: 99%

Section: Subsystem and Sensor Allocationmentioning

confidence: 99%

Section: Case Studymentioning

confidence: 99%

Section: Case Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimal Feature Selection for Distributed Data-Driven Process Monitoring

Khatib

Daoutidis

2019

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

show abstract

Community detection based process decomposition and distributed monitoring for large‐scale processes

et al. 2022

View full text Add to dashboard Cite

Distributed architectures wherein multiple decision-making units are employed to coordinate their decision-making/actions based on real-time communication have become increasingly important for monitoring processes that have large scales and complex structures. Typically, the development of a distributed monitoring scheme involves two key steps, that is, the decomposition of the process into subsystems, and the design of local monitors based on the configured subsystem models. In this article, we propose a distributed process monitoring approach that tackles both steps for large-scale processes. A data-driven process decomposition approach is proposed by leveraging community structure detection to divide variables into subsystems optimally via finding a maximal value of the metric of modularity. A two-layer distributed monitoring scheme is developed where local monitors are designed based on the configured subsystems of variables using canonical correlation analysis. Innersubsystem interactions and inter-subsystem interactions are tackled by the two layers separately, such that the sensitivity of this monitoring scheme to certain types of faults is improved. We utilize a numerical example to illustrate the effectiveness and superiority of the proposed method. It is then applied to a simulated wastewater treatment process.

show abstract

A New Distributed BRB-Based Fault Diagnosis Method for Multi-Agent Systems

Wang

Yang

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Generating optimal overlapping subsystems for distributed statistical fault detection subject to constraints

Cited by 9 publications

References 27 publications

Optimal Feature Selection for Distributed Data-Driven Process Monitoring

Optimal Feature Selection for Distributed Data-Driven Process Monitoring

Community detection based process decomposition and distributed monitoring for large‐scale processes

A New Distributed BRB-Based Fault Diagnosis Method for Multi-Agent Systems

Contact Info

Product

Resources

About