Decentralized Diagnosis via Structural Analysis and Integer Programming

Pérez-Zúñiga, Gustavo; Chanthery, Élodie; Travé-Massuyès, Louise; Sotomayor, Javier; Artigues, Christian

doi:10.1016/j.ifacol.2018.09.551

Cited by 11 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first track, we find [3] which presents an approach for decentralized fault-focused residual generation based on structural analysis. The work in [13] is a direct continuation of [3], the diagnostic tests calculated with the decentralized architecture are the same as those computed in a centralized architecture. However, a more efficient algorithm (BILP) is used for test selection.…”

Section: Related Workmentioning

confidence: 99%

“…In several works like [13], it is hypothesized that the decomposition in subsystems is guided by functional constraints. This paper aims at removing this hypothesis and searching for a decomposition that improves the efficiency of the architecture by decreasing the number of interconnections while keeping maximal diagnosability.…”

Section: Definition 4 (Number Of Interconnections Of ϕ In D)mentioning

confidence: 99%

See 1 more Smart Citation

Process Decomposition and Test Selection for Distributed Fault Diagnosis

Chanthery

Sztyber

Travé-Massuyès

et al. 2020

Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices

View full text Add to dashboard Cite

Decomposing is one way to gain efficiency when dealing with large scale systems. In addition, the breakdown into subsystems may be mandatory to reflect some geographic or confidentiality constraints. In this context, the selection of diagnostic tests must comply with decomposition and it is desired to minimize the number of subsystem interconnections while still guaranteeing maximal diagnosability. On the other hand, it should be noticed that there is often some flexibility in the way to decompose a system. By placing itself in the context of structural analysis, this paper provides a solution to the double overlinked problem of choosing the decomposition of the system by leveraging existing flexibility and of selecting the set of diagnostic tests so as to minimize subsystem interconnections while maximizing diagnosability .

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Definition 4 (Number Of Interconnections Of ϕ In D)mentioning

confidence: 99%

Process Decomposition and Test Selection for Distributed Fault Diagnosis

Chanthery

Sztyber

Travé-Massuyès

et al. 2020

Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices

View full text Add to dashboard Cite

show abstract

“…The centralized architecture requires a global model and may be an impractical option (when implementing a global diagnoser) because of the amount of needed communication [23]. Distributed diagnosis using a structural model has been proposed in [26], a distributed diagnosis approach with a set of local diagnosers was presented in [16,17], and, in [27], a decentralized FDI system based on structural analysis of a large distributed plant was designed.…”

Section: Introductionmentioning

confidence: 99%

“…Distributed FDI architecture consists of subsystem models and is implemented with local diagnosers that together guarantee the same diagnosability as a regular centralized architecture, allowing high performance in scalability, reliability, communication, and reduced computation costs [27][28][29]. In this sense, given that oil pipelines are large-scale distributed plants [4,30] with many components, it would be more convenient to apply the distributed FDI approach, in which, unlike centralized approaches, knowing the model of the global plant is not mandatory [17,25,31].…”

Section: Introductionmentioning

confidence: 99%

Distributed Fault Detection and Isolation Approach for Oil Pipelines

et al. 2021

View full text Add to dashboard Cite

Fault detection and isolation (FDI) in oil pipeline systems (OPS) is a very critical issue because faults in these systems such as leaks or equipment malfunctions may cause significant safety accidents and economic losses. These are the challenging factors, along with the environmental regulations for developing efficient FDI approaches for OPS. This paper proposes a model-based distributed FDI approach, which uses a structural model of the system in conjunction with algorithms to generate diagnostic tests that may be implemented in local diagnosers along the OPS. The proposed approach allows detection and isolation of faults in pipeline sections (pipeline segments), pump stations, as well as process control equipment. In this way, simulation of the obtained diagnostic tests in a benchmark application shows that all faults of interest (pipeline segment faults and sensor faults) are detected and isolated.

show abstract

“…The same minimization problem is approached using Linear Matrix Inequalities (LMI) [7], and another common approach is to use observers, such as sliding mode observers [8], Kalman-based fault detection [9], and also residuals generation using parity space relations [10,11]. Likewise, for complex processes with functional constraints, methods have been developed that consider decentralized and distributed diagnostic architectures [12,13].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis via Neural Ordinary Differential Equations

2021

View full text Add to dashboard Cite

Implementation of model-based fault diagnosis systems can be a difficult task due to the complex dynamics of most systems, an appealing alternative to avoiding modeling is to use machine learning-based techniques for which the implementation is more affordable nowadays. However, the latter approach often requires extensive data processing. In this paper, a hybrid approach using recent developments in neural ordinary differential equations is proposed. This approach enables us to combine a natural deep learning technique with an estimated model of the system, making the training simpler and more efficient. For evaluation of this methodology, a nonlinear benchmark system is used by simulation of faults in actuators, sensors, and process. Simulation results show that the proposed methodology requires less processing for the training in comparison with conventional machine learning approaches since the data-set is directly taken from the measurements and inputs. Furthermore, since the model used in the essay is only a structural approximation of the plant; no advanced modeling is required. This approach can also alleviate some pitfalls of training data-series, such as complicated data augmentation methodologies and the necessity for big amounts of data.

show abstract

Decentralized Diagnosis via Structural Analysis and Integer Programming

Cited by 11 publications

References 8 publications

Process Decomposition and Test Selection for Distributed Fault Diagnosis

Process Decomposition and Test Selection for Distributed Fault Diagnosis

Distributed Fault Detection and Isolation Approach for Oil Pipelines

Fault Diagnosis via Neural Ordinary Differential Equations

Contact Info

Product

Resources

About