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
Selection schemes and neural networks in adaptive real-time control: predictive simulation adaptive control
Linköping University, Department of Mechanical Engineering, Fluid and Mechanical Engineering Systems. Linköping University, The Institute of Technology.
2005 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

The vision of self-aware machines was the starting point of this work. The idea is a machine having knowledge about itself and its surrounding environment, being able to react to changes in the environment. To support this vision, a number of engineering disciplines need to be merged and the control strategy "predictive simulation adaptive control'', PSAC, developed.

The focus of the thesis is the synthesis of a number of algorithms and ideas from different engineering disciplines and fields. The main disciplines that the work is based on are simulation techniques, selection schemes and neural networks; all of these combined with the constraints imposed by the real-time demands of control systems.

Selection schemes, or optimisation algorithms, are introduced here and used directly for real-time control of the test system, a rod-less pneumatic cylinder. The selection process is primarily based on genetic algorithms and the outcome of numerous simulations of the system for different possible control signals.

Neural networks in general, and the version used here in particular, the Kohonen self-organising map, is widely used for classification and storage of information. Here it is used first to approximate friction in a rod-less pneumatic cylinder, and later on, possible ways to utilise this technique for condition monitoring are briefly discussed.

Real-time systems and programming are a necessity when designing modern control systems. From the real-time constraints, special demands are put on the implemented algorithms and ideas.

By bringing all this together, piece by piece, the vision comes a little bit closer. One step on the path, is the PSAC control concept proposed here. The control concept is successfully implemented and tested on a position servo consisting of a pneumatic rod-less cylinder controlled by on/off-valves.

Place, publisher, year, edition, pages
Linköping: Linköpings universitet , 2005. , 62 p.
Series
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1187
Keyword [en]
Adaptive Control, Real-Time, Self-Organizing Feature Maps, Pneumatic, Neural Networks, Evolutionary Algorithms
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-29324Local ID: 14645ISBN: 91-85457-11-6 (print)OAI: oai:DiVA.org:liu-29324DiVA: diva2:250136
Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2013-11-21
List of papers
1. Simulation and selection schemes for real-time control of a pneumatic cylinder
Open this publication in new window or tab >>Simulation and selection schemes for real-time control of a pneumatic cylinder
2003 (English)In: The Bath Workshop on Power Transmission & Motion Control, PTMC' 03 / [ed] C. R. Burrows & K. A. Edge, London, Bury St Edmunds, UK: Professional Engineering Publishing , 2003, 307-318 p.Conference paper, Published paper (Other academic)
Abstract [en]

Simulation techniques are used in this project to predict the dynamic behaviour of a rod-less pneumatic cylinder in real-time. This forms a controller for position control of the cylinder using selection and optimisation methods based on simulation results. This paper reports on the current state of ongoing research, emphasising extending the use of simulation techniques within real-time applications. A test setup is presented with a pneumatic cylinder controlled by four 3/2 on/off valves. The valves form a modulating energy input to the cylinder. The valve switch timing is established by short simulations of different possible scenarios. A selection scheme is then applied and the most suitable simulation forms the control signals for the valves. Experimental results together with the corresponding simulations are presented.

The presented setup uses the real-time operating system Linux/RTAI to host the simulation, selection and control software.

Place, publisher, year, edition, pages
London, Bury St Edmunds, UK: Professional Engineering Publishing, 2003
Keyword
Pneumatic, simulation, selection scheme, control, real-time
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-24282 (URN)3898 (Local ID)3898 (Archive number)3898 (OAI)
Conference
The Bath Workshop on Power Transmission & Motion Control, PTMC' 03, Bath, United Kingdom, 10th-12th September, 2003
Available from: 2009-10-07 Created: 2009-10-07 Last updated: 2013-11-21
2. Simulation and Selection Schemes in Machine Self-Awareness, a Position Control Case Study
Open this publication in new window or tab >>Simulation and Selection Schemes in Machine Self-Awareness, a Position Control Case Study
2004 (English)In: Power Transmission and Motion Control. PTMC 2004 / [ed] C R Burrows, K A Edge, D N Johnston, London, Bury St Edmunds, UK: Professional Engineering Publishing , 2004, 307-318 p.Conference paper, Published paper (Other academic)
Abstract [en]

Simulation techniques for numerical prediction of dynamic behaviour of a sub-system may be combined with different types of selection schemes at a controller loop level. This constitutes a way of using physical simulation models as a prediction scheme for machine control. This is similar to model-based control techniques but introduces the flexibility of switching control objectives and limitations on the fly. Such a control strategy may be of interest in applications where the environment is not fully identified or may change in an unpredictable way. A sudden change in working conditions due to a failure in the system or component itself is an example. The machine then needs to have some degree of readiness for unforeseen conditions. This is a typical scenario in remote mobile robotics and machinery in hazardous environments. Some level of self-awareness in the controller of the machine is desirable.

This paper describes a case study of techniques suitable for such machine self awareness. Simulation techniques are used in this project to predict the dynamic behaviour of a rod-less pneumatic cylinder in real-time. This forms a controller for position control of the cylinder using selection and optimisation methods based on simulation results. Previous work has shown that the method works when using grid selection schemes of a reduced set of control signals. In this paper this is further extended using genetic algorithm selection schemes.

Possible applications for the proposed scheme are discussed and a simple selection scheme based upon genetic algorithms is proposed.

Place, publisher, year, edition, pages
London, Bury St Edmunds, UK: Professional Engineering Publishing, 2004
Keyword
Machine Self-Awareness, simulation
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-23249 (URN)2666 (Local ID)9781860584664 (ISBN)2666 (Archive number)2666 (OAI)
Conference
The Bath Workshop on Power Transmission & Motion Control, PTMC' 04, Bath, United Kingdom, 1st-3rd September, 2004
Available from: 2009-10-07 Created: 2009-10-07 Last updated: 2013-11-21
3. Self-Organising Maps for Illustration of Friction in a Pneumatic Cylinder
Open this publication in new window or tab >>Self-Organising Maps for Illustration of Friction in a Pneumatic Cylinder
2005 (English)In: 9th Scandinavian International Conference on Fluid Power, SICFP’05, 2005, 80-81 p.Conference paper, Published paper (Other academic)
Abstract [en]

Friction exists in virtually every mechanical system. A great many models for prediction and simulation of friction exist. However, due to the high non-linear nature of friction, especially stick-slip friction, there exists a trade-off between simplicity and accuracy in the predictions, also due to difficulties in building an accurate model.

Here an approach to estimation of friction based on accumulated knowledge, using previous measurements and estimations based on these measurements, is discussed. In this approach, a special kind of neural networks, is used. The type of neural network used here is a Kohonen self-organising map. Results from the trained map are used to illustrate how friction relates to states in the pneumatic cylinder. The structure in the map resulting from the different states is also discussed, interpreted and illustrated.

Keyword
Self-organizing maps, friction, pneumatic
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-12975 (URN)
Conference
9th Scandinavian International Conference on Fluid Power, SICFP’05, Linköping, Sweden, 1st-2nd June, 2005
Available from: 2008-02-26 Created: 2008-02-26 Last updated: 2013-11-21

Open Access in DiVA

No full text

Authority records BETA

Zachrison, Anders

Search in DiVA

By author/editor
Zachrison, Anders
By organisation
Fluid and Mechanical Engineering SystemsThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 78 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