skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Observer and data-driven-model-based fault detection in power plant coal mills

Abstract

This paper presents and compares model-based and data-driven fault detection approaches for coal mill systems. The first approach detects faults with an optimal unknown input observer developed from a simplified energy balance model. Due to the time-consuming effort in developing a first principles model with motor power as the controlled variable, data-driven methods for fault detection are also investigated. Regression models that represent normal operating conditions (NOCs) are developed with both static and dynamic principal component analysis and partial least squares methods. The residual between process measurement and the NOC model prediction is used for fault detection. A hybrid approach, where a data-driven model is employed to derive an optimal unknown input observer, is also implemented. The three methods are evaluated with case studies on coal mill data, which includes a fault caused by a blocked inlet pipe. All three approaches detect the fault as it emerges. The optimal unknown input observer approach is most robust, in that, it has no false positives. On the other hand, the data-driven approaches are more straightforward to implement, since they just require the selection of appropriate confidence limit to avoid false detection. The proposed hybrid approach is promising for systems where a firstmore » principles model is cumbersome to obtain.« less

Authors:
; ;  [1]
  1. University of Aalborg, Aalborg (Denmark). Dept. of Electrical Systems
Publication Date:
OSTI Identifier:
21059027
Resource Type:
Journal Article
Journal Name:
IEEE Transactions on Energy Conversion
Additional Journal Information:
Journal Volume: 23; Journal Issue: 2; Journal ID: ISSN 0885-8969
Country of Publication:
United States
Language:
English
Subject:
01 COAL, LIGNITE, AND PEAT; MILLING MACHINES; PULVERIZERS; FOSSIL-FUEL POWER PLANTS; COAL; DEFECTS; DETECTION; ENERGY BALANCE; NUMERICAL SOLUTION; REGRESSION ANALYSIS

Citation Formats

Odgaard, P F, Lin, B, and Jorgensen, S B. Observer and data-driven-model-based fault detection in power plant coal mills. United States: N. p., 2008. Web. doi:10.1109/TEC.2007.914185.
Odgaard, P F, Lin, B, & Jorgensen, S B. Observer and data-driven-model-based fault detection in power plant coal mills. United States. https://doi.org/10.1109/TEC.2007.914185
Odgaard, P F, Lin, B, and Jorgensen, S B. 2008. "Observer and data-driven-model-based fault detection in power plant coal mills". United States. https://doi.org/10.1109/TEC.2007.914185.
@article{osti_21059027,
title = {Observer and data-driven-model-based fault detection in power plant coal mills},
author = {Odgaard, P F and Lin, B and Jorgensen, S B},
abstractNote = {This paper presents and compares model-based and data-driven fault detection approaches for coal mill systems. The first approach detects faults with an optimal unknown input observer developed from a simplified energy balance model. Due to the time-consuming effort in developing a first principles model with motor power as the controlled variable, data-driven methods for fault detection are also investigated. Regression models that represent normal operating conditions (NOCs) are developed with both static and dynamic principal component analysis and partial least squares methods. The residual between process measurement and the NOC model prediction is used for fault detection. A hybrid approach, where a data-driven model is employed to derive an optimal unknown input observer, is also implemented. The three methods are evaluated with case studies on coal mill data, which includes a fault caused by a blocked inlet pipe. All three approaches detect the fault as it emerges. The optimal unknown input observer approach is most robust, in that, it has no false positives. On the other hand, the data-driven approaches are more straightforward to implement, since they just require the selection of appropriate confidence limit to avoid false detection. The proposed hybrid approach is promising for systems where a first principles model is cumbersome to obtain.},
doi = {10.1109/TEC.2007.914185},
url = {https://www.osti.gov/biblio/21059027}, journal = {IEEE Transactions on Energy Conversion},
issn = {0885-8969},
number = 2,
volume = 23,
place = {United States},
year = {Sun Jun 15 00:00:00 EDT 2008},
month = {Sun Jun 15 00:00:00 EDT 2008}
}