A knowledge-driven approach for process supervision in chemical plants

Musulin, Estanislao; Roda, Fernando; Basualdo, Marta

doi:10.1016/j.compchemeng.2013.06.009

Cited by 14 publications

(11 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed system can also be integrated with the current systems through and interface. Other approaches of ontology and MAS-based process supervision have been developed using a conceptualisation of equipment, control systems and hazards, or to demonstrate how description logic (DL) reasoning could be used to detect and diagnose faults, without the help of external agents (Musulin et al, 2013). For the management of abnormal situations, an agentbased approach called ENCORE, using OntoSafe, explicitly captures the hierarchy of the offshore platform, comprising the entire process at the highest level and the individual instruments and equipment at the lowest (Natarajan & Srinivasan, 2014).…”

Section: Multi-agent Systems and Ontology For Fault Detectionmentioning

confidence: 99%

Towards fault detection and self-healing of chemical processes over wireless sensor networks

Dorneanu¹,

Ruan²,

Mohamed³

et al. 2020

Industry 4.0 – Shaping the Future of the Digital World

View full text Add to dashboard Cite

show abstract

Section: Multi-agent Systems and Ontology For Fault Detectionmentioning

confidence: 99%

Towards fault detection and self-healing of chemical processes over wireless sensor networks

Dorneanu¹,

Ruan²,

Mohamed³

et al. 2020

Industry 4.0 – Shaping the Future of the Digital World

View full text Add to dashboard Cite

show abstract

“…The usage of ontologies for HAZOP studies has already been proposed by Batres [20] and Daramola et al [21]. Other research groups have used ontologies for decision support in [22] and process supervision in [23].…”

Section: Technical Basismentioning

confidence: 99%

Computer-Aided Hazop Studies: Knowledge Representation and Algorithmic Hazard Identification

Single¹,

Schmidt²,

Denecke³

2019

WIT Transactions on the Built Environment

View full text Add to dashboard Cite

Safety assessments are conducted to identify and assess the risks that arise from processes, process plants or technical systems in general. This includes the identification of potential hazards posed by plants. One recognized and generally accepted method for this is the hazard and operability (HAZOP) method. It is a human-centered process that is time-and labor-intensive. In the presented research approach, the structure of a computer-aided HAZOP system is described. The identification of hazards and malfunctions within technical systems is knowledge-intensive. Within this research approach, it transpired that the semantically correct and detailed modeling of deviation cause and effect relationships in the form of ontologies are of particular importance to draw correct conclusions. Thus, the guiding principles of a knowledge representation framework are described from a process safety perspective, and serve as a basis for the automatic identification of hazards. An integral understanding of the process, process plant and involved substances requires extensive knowledge. The way in which this knowledge is used and the search for hazards is conducted has an influence on the completeness of the results. Within this approach, the hazard/malfunction identification is conducted on different layers of abstraction to improve the efficiency of the search algorithm. The proposed methodology is applied within a case study to a technical system that consists of a compressor, vessel and valve. The first results demonstrate that the proposed method is well-suited to understand and identify the context of hazards and malfunctions. Thus, a system for computer-aided HAZOP studies can be used to assist HAZOP conductors in performing hazard analysis while increasing the speed of safety assessments and serving as a decision support system.

show abstract

“…Step of size = +3 IDV (2) Drift fault, of slope = 0.03 IDV (3) Noise increased by 50% IDV (4) Noise reduced by 20% IDV (5) Two consecutive steps, +3 at t=101 and -6 at t=201 Figure 4 shows the monitoring results for the step disturbance IDV(1). PCA detects the fault at time 107 (three consecutive T 2 samples out of the 99% limit).…”

Section: Disturbance Description Idv(1)mentioning

confidence: 99%

“…In the last years, many process monitoring methods have been developed to timely detect process disturbances. [1][2][3][4] In particular data driven techniques have attracted the greatest interest due to the high availability of on-line data. [5][6][7][8][9] Many process monitoring applications relies on dimensionality reduction techniques; process measurements are projected into a low-dimension space where most of the normal data variability is contained.…”

Section: Introductionmentioning

confidence: 99%

Spectral Graph Analysis for Process Monitoring

Musulin

2014

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

Process monitoring is a fundamental task to support operator decisions under abnormal situations. Most process monitoring approaches, such as Principal Components Analysis and Locality Preserving Projections, are based on dimensionality reduction.In this paper Spectral Graph Analysis Monitoring (SGAM) is introduced. SGAM is a new process monitoring technique that does not require dimensionality reduction techniques. The approach it is based on the spectral graph analysis theory. Firstly, a weighted graph representation of process measurements is developed. Secondly, the process behavior is parameterized by means of graph spectral features, in particular the graph algebraic connectivity and the graph spectral energy. The developed methodology has been illustrated in autocorrelated and non-linear synthetic cases, and applied to the well known Tennessee Eastman process benchmark with promising results.

show abstract

A knowledge-driven approach for process supervision in chemical plants

Cited by 14 publications

References 49 publications

Towards fault detection and self-healing of chemical processes over wireless sensor networks

Towards fault detection and self-healing of chemical processes over wireless sensor networks

Computer-Aided Hazop Studies: Knowledge Representation and Algorithmic Hazard Identification

Spectral Graph Analysis for Process Monitoring

Contact Info

Product

Resources

About