liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Probabilistic Fault Diagnosis with Automotive Applications
Linköping University, Department of Electrical Engineering, Vehicular Systems. Linköping University, The Institute of Technology.
2009 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The aim of this thesis is to contribute to improved diagnosis of automotive vehicles. The work is driven by case studies, where problems and challenges are identified. To solve these problems, theoretically sound and general methods are developed. The methods are then applied to the real world systems.

To fulfill performance requirements automotive vehicles are becoming increasingly complex products. This makes them more difficult to diagnose. At the same time, the requirements on the diagnosis itself are steadily increasing. Environmental legislation requires that smaller deviations from specified operation must be detected earlier. More accurate diagnostic methods can be used to reduce maintenance costs and increase uptime. Improved diagnosis can also reduce safety risks related to vehicle operation.

Fault diagnosis is the task of identifying possible faults given current observations from the systems. To do this, the internal relations between observations and faults must be identified. In complex systems, such as automotive vehicles, finding these relations is a most challenging problem due to several sources of uncertainty. Observations from the system are often hidden in considerable levels of noise. The systems are complicated to model both since they are complex and since they are operated in continuously changing surroundings. Furthermore, since faults typically are rare, and sometimes never described, it is often difficult to get hold of enough data to learn the relations from.

Due to the several sources of uncertainty in fault diagnosis of automotive systems, a probabilistic approach is used, both to find the internal relations, and to identify the faults possibly present in the system given the current observations. To do this successfully, all available information is integrated in the computations.

Both on-board and off-board diagnosis are considered. The two tasks may seem different in nature: on-board diagnosis is performed without human integration, while the off-board diagnosis is mainly based on the interactivity with a mechanic. On the other hand, both tasks regard the same vehicle, and information from the on-board diagnosis system may be useful also for off-board diagnosis. The probabilistic methods are general, and it is natural to consider both tasks.

The thesis contributes in three main areas. First, in Paper 1 and 2, methods are developed for combining training data and expert knowledge of different kinds to compute probabilities for faults. These methods are primarily developed with on-board diagnosis in mind, but are also applicable to off-board diagnosis. The methods are general, and can be used not only in diagnosis of technical system, but also in many other applications, including medical diagnosis and econometrics, where both data and expert knowledge are present.

The second area concerns inference in off-board diagnosis and troubleshooting, and the contribution consists in the methods developed in Paper 3 and 4. The methods handle probability computations in systems subject to external interventions, and in particular systems that include both instantaneous and non-instantaneous dependencies. They are based on the theory of Bayesian networks, and include event-driven non-stationary dynamic Bayesian networks (nsDBN) and an efficient inference algorithm for troubleshooting based on static Bayesian networks. The framework of nsDBN event-driven nsDBN is applicable to all kinds of problems concerning inference under external interventions.

The third contribution area is Bayesian learning from data in the diagnosis application. The contribution is the comparison and evaluation of five Bayesian methods for learning in fault diagnosis in Paper 5. The special challenges in diagnosis related to learning from data are considered. It is shown how the five methods should be tailored to be applicable to fault diagnosis problems.

To summarize, the five papers in the thesis have shown how several challenges in automotive diagnosis can be handled by using probabilistic methods. Handling such challenges with probabilistic methods has a great potential. The probabilistic methods provide a framework for utilizing all

information available, also if it is in different forms and. The probabilities computed can be combined with decision theoretic methods to determine the appropriate action after the discovery of reduced system functionality due to faults.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press , 2009. , 44 p.
Series
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 1288
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-51931ISBN: 978-91-7393-493-0 (print)OAI: oai:DiVA.org:liu-51931DiVA: diva2:278142
Public defence
2009-12-18, Visionen, Hus B, Campus Valla, Linköpings universitet, Linköping, 10:15 (English)
Opponent
Supervisors
Available from: 2009-11-30 Created: 2009-11-24 Last updated: 2010-11-23Bibliographically approved
List of papers
1. Bayesian Fault Diagnosis for Automitive Engines by Combining Data and Process Knowledge
Open this publication in new window or tab >>Bayesian Fault Diagnosis for Automitive Engines by Combining Data and Process Knowledge
2009 (English)In: IEEE Transactions on Systems, Man and Cybernetics, ISSN 0018-9472, E-ISSN 2168-2909Article in journal (Other academic) Submitted
Abstract [en]

We consider fault diagnosis of complex systems, motivated by the problem of fault diagnosis of an automotive diesel engine. Previous fault diagnosis algorithms are typically based either on process knowledge, for example a Fault Signature Matrix (FSM), or on training data. Both these methods have their advantages and drawbacks.

The main contribution in the present work is that we show how to integrate process knowledge and training data to improve fault diagnosis for automotive processes. We carefully investigate the characteristics of our motivating application, and we derive a new method for fault diagnosis based Bayesian inference.

To illustrate the new fault diagnosis method we have applied it to the diagnosis of the gas flow of an automotive engine using data from real driving situations. It is shown that diagnosis performance is improved compared to previous methods using solely data or process knowledge. Finally we study the relation between the new method and previous state of the art methods for fault diagnosis.

Place, publisher, year, edition, pages
IEEE, 2009
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-51922 (URN)
Available from: 2009-11-24 Created: 2009-11-24 Last updated: 2017-12-12Bibliographically approved
2. Bayesian Inference by Combining Training Data and Background Knowledge Expressed as Likelihood Constraints
Open this publication in new window or tab >>Bayesian Inference by Combining Training Data and Background Knowledge Expressed as Likelihood Constraints
2009 (English)In: International Journal of Approximate Reasoning, ISSN 0888-613X, E-ISSN 1873-4731Article in journal (Other academic) Submitted
Abstract [en]

Bayesian inference, or classification, from data is a powerful method for determining states of process when no detailed physical model of the process exists. However, the performance of Bayesian inference from data is dependent on the amount of training data available. In many real applications the amount of training data is limited, and inference results become insufficient. Thus it is important to take other kinds of information into account in the inference as well. In this paper, we consider a general type of background knowledge that appears in many real applications, for example medical diagnosis, technical diagnosis, and econometrics. We show how it can be expressed as constraints on the likelihoods, and provide detailed description of the computations. The method is applied to a diagnosis example, where it is clearly shown how the integration of background knowledge improves diagnosis when training data is limited.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-51926 (URN)
Available from: 2009-11-24 Created: 2009-11-24 Last updated: 2017-12-12Bibliographically approved
3. Non-stationary Dynamic Bayesian Networks in Modeling of Troubleshooting Process
Open this publication in new window or tab >>Non-stationary Dynamic Bayesian Networks in Modeling of Troubleshooting Process
2009 (English)In: International Journal of Approximate Reasoning, ISSN 0888-613X, E-ISSN 1873-4731Article in journal (Other academic) Submitted
Abstract [en]

In research and industry, decision theoretic troubleshooting of complex automotive systems has recently gained increased interest. With suitable troubleshooting, uptime can be increased and repair times shortened. To perform decision theoretic troubleshooting, probability computations are needed. In this work we consider computation of these probabilities under external interventions, which changes dependency relations. We apply a non-stationary dynamic Bayesian network (nsDBN), where the interventions so called events. The events change dependency relations, and drive the nsDBN forward. In the paper, we present how to build models using event driven nsDBN, how to perform inference, and how to use the method in troubleshooting. Event driven nsDBN can be used to model any process subject to interventions, and in particular it opens for solving more general troubleshooting problems than previously presented in literature.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-51927 (URN)
Available from: 2009-11-24 Created: 2009-11-24 Last updated: 2017-12-12Bibliographically approved
4. Modeling and Efficient Inference for Troubleshooting Automotive Systems
Open this publication in new window or tab >>Modeling and Efficient Inference for Troubleshooting Automotive Systems
2009 (English)Report (Other academic)
Abstract [en]

We consider computer assisted troubleshooting of automotive vehicles, where the objective is to repair the vehicle at as low expected cost as possible.

The work has three main contributions: a troubleshooting method that applies to troubleshooting in real environments, the discussion on practical issues in modeling for troubleshooting, and the efficient probability computations.

The work is based on a case study of an auxiliary braking system of a modern truck.

We apply a decision theoretic approach, consisting of a planner and a diagnoser.

Two main challenges in troubleshooting automotive vehicles are the need for disassembling the vehicle during troubleshooting to access parts to repair, and the difficulty to verify that the vehicle is fault free. These facts lead to that probabilities for faults and for future observations must be computed for a system that has been subject to external interventions that cause changes the dependency structure. The probability computations are further complicated due to the mixture of instantaneous and non-instantaneous dependencies.

To compute the probabilities, we develop a method based on an algorithm, updateBN, that updates a static BN to account for the external interventions.

Place, publisher, year, edition, pages
Linköping: Linköpings universitet, 2009
Series
LiTH-ISY-R, ISSN 1400-3902 ; 2921
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-51928 (URN)LiTH-ISY-R-2921 (ISRN)
Available from: 2009-11-24 Created: 2009-11-24 Last updated: 2011-02-27Bibliographically approved
5. A Comparison of Baysian Approaches to Learning in Fault Isolation
Open this publication in new window or tab >>A Comparison of Baysian Approaches to Learning in Fault Isolation
Show others...
2009 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344Article in journal (Other academic) Submitted
Abstract [en]

Fault isolation is the task of localizing faults in a process, given observations from it. To do this, a model describing the relations between faults and observations is needed.

In this paper we focus on learning such models both from training data and from prior knowledge. There are several challenges in learning for fault isolation.

The number of data and the available computing resources are often limited. Furthermore, there may be previously unobserved fault patterns.

To meet these challenges we take on a Bayesian approach.

We compare five different approaches to learning for fault isolation, and evaluate their performance on a real application, namely the diagnosis of an automotive engine.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-51930 (URN)
Available from: 2009-11-24 Created: 2009-11-24 Last updated: 2017-12-12Bibliographically approved

Open Access in DiVA

Probabilistic Fault Diagnosis with Automotive Applications(746 kB)669 downloads
File information
File name FULLTEXT02.pdfFile size 746 kBChecksum SHA-512
21159efad9fe74f35d90f0bee54cbc6f1b666a6f47d0fae4ce815bd16f2531a538d454ea9b1165878281c4b1b2f8a8a29c0d089ed1de382452b530eca6baa8a8
Type fulltextMimetype application/pdf
Cover(230 kB)119 downloads
File information
File name COVER01.pdfFile size 230 kBChecksum SHA-512
ea650921cff6af87efd45c7d64cf2c49c169bf873fec08510a7f1be71f24b4257667afa423df61585f006c8eafb9317bb0003ee12168c3d0bddd2ea79a457ce2
Type coverMimetype application/pdf

Authority records BETA

Pernestål, Anna

Search in DiVA

By author/editor
Pernestål, Anna
By organisation
Vehicular SystemsThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 792 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 2629 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf