Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Driven Supervision of a Thermal-Hydraulic Process Towards a Physics-Based Digital Twin

Osimone Imhogiemhe, Yoann Jus, Hubert Lejeune, Saïd Moussaoui

TL;DR

A digital twin dedicated to fault detection and diagnosis in the context of a thermal-hydraulic process supervision is proposed and validated on a specific test scenario, with single one-off parameter change occurrences in the system.

Abstract

The real-time supervision of production processes is a common challenge across several industries. It targets process component monitoring and its predictive maintenance in order to ensure safety, uninterrupted production and maintain high efficiency level. The rise of advanced tools for the simulation of physical systems in addition to data-driven machine learning models offers the possibility to design numerical tools dedicated to efficient system monitoring. In that respect, the digital twin concept presents an adequate framework that proffers solution to these challenges. The main purpose of this paper is to develop such a digital twin dedicated to fault detection and diagnosis in the context of a thermal-hydraulic process supervision. Based on a numerical simulation of the system, in addition to machine learning methods, we propose different modules dedicated to process parameter change detection and their on-line estimation. The proposed fault detection and diagnosis algorithm is validated on a specific test scenario, with single one-off parameter change occurrences in the system. The numerical results show good accuracy in terms of parameter variation localization and the update of their values.

Data-Driven Supervision of a Thermal-Hydraulic Process Towards a Physics-Based Digital Twin

TL;DR

A digital twin dedicated to fault detection and diagnosis in the context of a thermal-hydraulic process supervision is proposed and validated on a specific test scenario, with single one-off parameter change occurrences in the system.

Abstract

The real-time supervision of production processes is a common challenge across several industries. It targets process component monitoring and its predictive maintenance in order to ensure safety, uninterrupted production and maintain high efficiency level. The rise of advanced tools for the simulation of physical systems in addition to data-driven machine learning models offers the possibility to design numerical tools dedicated to efficient system monitoring. In that respect, the digital twin concept presents an adequate framework that proffers solution to these challenges. The main purpose of this paper is to develop such a digital twin dedicated to fault detection and diagnosis in the context of a thermal-hydraulic process supervision. Based on a numerical simulation of the system, in addition to machine learning methods, we propose different modules dedicated to process parameter change detection and their on-line estimation. The proposed fault detection and diagnosis algorithm is validated on a specific test scenario, with single one-off parameter change occurrences in the system. The numerical results show good accuracy in terms of parameter variation localization and the update of their values.
Paper Structure (18 sections, 7 equations, 8 figures, 3 tables)

This paper contains 18 sections, 7 equations, 8 figures, 3 tables.

Table of Contents

  1. Introduction
  2. General Framework
  3. Digital Twin
  4. The Physical Process
  5. The Virtual Twin
  6. Input-Output Parameters
  7. Fault Detection and Diagnosis Approach
  8. Monitoring principle
  9. Fault Detection
  10. Fault Localization
  11. Parameter Estimation
  12. Parameter Validation
  13. Experiments
  14. Database
  15. Localization
  16. ...and 3 more sections

Figures (8)

  • Figure 1: Photo of the closed hydraulic loop
  • Figure 2: The CAD of the closed hydraulic loop
  • Figure 3: The 1D model of the closed hydraulic loop on Simcenter Flomaster software
  • Figure 4: The simplified monitoring principle using the DT
  • Figure 5: The FDD Algorithm
  • ...and 3 more figures