Soft Computing Approaches to Fault Diagnosis for Dynamic Systems

  title={Soft Computing Approaches to Fault Diagnosis for Dynamic Systems},
  author={Jo{\~a}o M. Ferreira Calado and J{\'o}zef Korbicz and Krzysztof Patan and Ron John Patton and Jos{\'e} S{\'a} da Costa},
  journal={Eur. J. Control},
Recent approaches to fault detection and isolation for dynamic systems using methods of integrating quantitative and qualitative model information, based upon soft computing (SC) methods are surveyed and studied in some detail. SC methods are considered an important extension to the quantitative model-based approach for residual generation in fault detection and isolation (FDI). When quantitative models are not readily available, a correctly trained neural network (NN) can be used as a non… 

Figures from this paper

Robust fault detection using analytical and soft computing methods
The main objective is to show how to employ the bounded-error approach to determine the uncertainty of soft computing models (neural networks and neuro-fuzzy networks) and it is shown that based onsoft computing models uncertainty is shown as a confined range for the model output, adaptive thresholds can be described.
Fuzzy model-based fault detection and isolation
  • L. Mendonça, J. Sousa, J. S. D. Costa
  • Computer Science, Engineering
    EFTA 2003. 2003 IEEE Conference on Emerging Technologies and Factory Automation. Proceedings (Cat. No.03TH8696)
  • 2003
The fuzzy model-based FDI system developed in this paper was able to detect and isolate all the simulated faults.
Artificial Neural Networks in Fault Diagnosis
Artificial neural networks seem to be particularly very attractive when designing fault diagnosis schemes and can be effectively applied to both the modelling of the plant operating conditions and decision making.
This paper performs an analysis on the applicability of state-of-the-art fault diagnosis methodologies to both simple and complex systems. Here, a complex system represents a system whose global
Development of a Methodology Using Artificial Neural Network in the Detection and Diagnosis of Faults for Pneumatic Control Valves
A practical and systematic method of how to emulate faults for control valves and the possibility of carrying out an analysis of the data to acquire signatures of the fault behavior is demonstrated and makes it easy to present a fault diagnosis strategy that can be reproduced in other processes.
Fault detection and diagnosis using fuzzy models
In this paper, the successful use of a fuzzy FDI based system, based on dynamic fuzzy models for fault detection and diagnosis of an industrial servo-actuated valve is presented.
Nerual Networks with Decision Trees for Diagnosis Issues
This paper presents a new idea for fault detection and isolation (FDI) technique which is applied to industrial system based on Neural Networks fault-free and Faulty behaviours Models, which requires less computational effort and can be used for on line diagnosis.


Issues of Fault Diagnosis for Dynamic Systems
There is an increasing demand for dynamic systems to become safer, more reliable and more economical in operation. This requirement extends beyond the normally accepted safety-critical systems e.g.,
Analytical and Qualitative Model-based Fault Diagnosis - A Survey and Some New Results
  • P. Frank
  • Computer Science
    Eur. J. Control
  • 1996
Robust residual generation for model-based fault diagnosis of dynamic systems.
This thesis proposes a new full-order unknown input observer structure for robust residual generation and this structure is then used to design directional and minimum variance residuals and studies the design of optimally robust parity relations using multi-criterion optimization.
A Fuzzy FDI Decision Making System for the Support of the Human Operator
Fault diagnosis of machines via parameter estimation and knowledge processing - Tutorial paper
Robustness in Model-Based Fault Diagnosis: The 1995 Situation