Observer and Data-Driven-Model-Based Fault Detection in Power Plant Coal Mills

2008 ◽  
Vol 23 (2) ◽  
pp. 659-668 ◽  
Author(s):  
P.F. Odgaard ◽  
Bao Lin ◽  
S.B. Jorgensen
Keyword(s):  
Power Plant ◽  
Fault Detection ◽  
Data Driven ◽  
Model Based

Data-Driven Fault Diagnosis for Nuclear Power Plant: The Implicit Model Approach

2018 ◽  
Author(s):  
Zhaoxu Chen ◽  
Xianling Li ◽  
Zhiwu Ke ◽  
Mo Tao ◽  
Yi Feng
Keyword(s):  
Power Plant ◽  
Nuclear Power Plant ◽  
Fault Detection ◽  
Nuclear Power ◽  
Model Identification ◽  
Industrial Process ◽  
Data Driven ◽  
Implicit Model ◽  
Complicated Model ◽  
Model Approach

This paper proposes a data-driven fault detection approach for nuclear power plant. The approach starts from input and output (I/O) data obtained from operating data of industrial process. Due to the model is not explicitly appeared, the proposed approach is named as implicit model approach (IMA). Residual generator is obtained directly from I/O data rather than from the mechanism, based which the algorithm of IMA-based fault detection is proposed. The main advantage of IMA-based fault detection is that it can circumvent complicated model identification. The approach generates parameterized matrices of residual signal inspired by subspace relevant technology without any prior knowledge about mechanisms of the plant. Fault information has been injected to a simulating platform of a compact reactor in the simulation part, by which we verify the effectiveness of IMA-based fault detection.

Mutual Information Based Feature Selection From Data Driven and Model Based Techniques for Fault Detection in Rolling Element Bearings

2011 ◽  
Author(s):  
Karthik Kappaganthu ◽  
C. Nataraj
Keyword(s):  
Fault Detection ◽  
Mutual Information ◽  
Diagnostic System ◽  
Classification Performance ◽  
Data Driven ◽  
Time Frequency ◽  
Bearing Fault ◽  
Model Based ◽  
Rolling Element ◽  
And Performance

This paper proposes a novel technique combining datadriven and model-based techniques to significantly improve the performance in bearing fault diagnostics. Features that provide best classification performance for the given data are selected from a combined set of data driven and model based features. Some of the common data driven techniques from time, frequency and time-frequency domain are considered. For model based feature extraction, recently developed cross-sample entropy is used. The ranking and performance of each of these feature sets are studied, when used independently and when used together. Mutual information based technique is used for ranking and selection of the optimal feature set. Using this method, the contribution to performance and redundancy of each of the data driven features and model based features can be studied. This method can be used to design an effective diagnostic system for bearing fault detection.

Model-Based and Data-Driven Fault Detection Performance for a Small UAV

2013 ◽  
Vol 18 (4) ◽  
pp. 1300-1309 ◽  
Author(s):  
Paul Freeman ◽  
Rohit Pandita ◽  
Nisheeth Srivastava ◽  
Gary J. Balas
Keyword(s):  
Fault Detection ◽  
Detection Performance ◽  
Data Driven ◽  
Model Based ◽  
Small Uav

Model-based and data-driven with multiscale sum of squares double EWMA control chart for fault detection in biological systems

2018 ◽  
Vol 32 (12) ◽  
pp. e3068 ◽  
Author(s):  
Majdi Mansouri ◽  
Mohamed Faouzi Harkat ◽  
Sin Yin Teh ◽  
Ayman Al-khazraji ◽  
Hazem Nounou ◽  
...  
Keyword(s):  
Fault Detection ◽  
Control Chart ◽  
Biological Systems ◽  
Sum Of Squares ◽  
Data Driven ◽  
Model Based ◽  
Ewma Control Chart

scholarly journals Data-driven Residual Generation for Early Fault Detection with Limited Data

2020 ◽  
Vol 12 (1) ◽  
pp. 9
Author(s):  
Hamed Khorasgani ◽  
Ahmed Farahat ◽  
Chetan Gupta
Keyword(s):  
Fault Detection ◽  
Industrial Applications ◽  
Fault Detection And Isolation ◽  
Data Driven ◽  
Practical Reasons ◽  
Traditional Model ◽  
Sources Of Information ◽  
Environment Change ◽  
Model Based ◽  
Systems Model

Traditionally, fault detection and isolation community have used system dynamic equations to generate diagnosers and to analyze detectability and isolability of the dynamic systems. Model-based fault detection and isolation methods use system model to generate a set of residuals as the bases for fault detection and isolation. However, in many complex systems it is not feasible to develop highly accurate models for the systems and to keep the models updated during the system lifetime. Recently, data- driven solutions have received an immense attention in the industrial applications for several practical reasons. First, these methods do not require the initial investment and expertise for developing accurate models. Moreover, it is possible to update and retrain the diagnosers as the system or the environment change over time automatically. Finally, unlike the model-based methods it is straightforward to combine time series measurements such as pressure and voltage with other sources of information such as system operating hours to achieve a higher accuracy. In this paper, we extend the traditional model- based fault detection and isolation concepts such as residuals, and detectable and isolable faults to the data-driven domain. We then propose an algorithm to automatically generate residuals from the normal operating data. We compare the performance of our proposed approach with traditional model-based methods through a case study.

scholarly journals A new model-based approach for power plant Tube-ball mill condition monitoring and fault detection

2014 ◽  
Vol 80 ◽  
pp. 10-19 ◽  
Author(s):  
Shen Guo ◽  
Jihong Wang ◽  
Jianlin Wei ◽  
Paschalis Zachariades
Keyword(s):  
Power Plant ◽  
Fault Detection ◽  
Condition Monitoring ◽  
Ball Mill ◽  
New Model ◽  
Model Based
Sign in / Sign up

Export Citation Format

Share Document