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

Direct link
Cite
Citation style
  • apa
  • 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
A fusion toolbox for sensor data fusion in industrial recycling
Linköping University, The Institute of Technology. Linköping University, Department of Physics, Chemistry and Biology.
Linköping University, The Institute of Technology. Linköping University, Department of Physics, Chemistry and Biology.
IEEE, Department of Technology and Science, Örebro University, Örebro, SwedenDepartment of Technology and Science, Örebro University, Örebro, Sweden,.
2002 (English)In: IEEE Transactions on Instrumentation and Measurement, ISSN 0018-9456, E-ISSN 1557-9662, Vol. 51, no 1, p. 144-149Article in journal (Refereed) Published
Abstract [en]

Information from different sensors can be fused in various ways. It is often difficult to choose the most suitable method for solving a fusion problem. In a measurement situation, the measured signal is often corrupted by disturbances (noise, etc.). It is, therefore, meaningless to compare crisp values without the corresponding uncertainty intervals. This paper describes a toolbox including nine different fusing methods. All methods are applied on training data, and the most suitable method is then used for solving the real fusion problem. In the example, fusion is performed on data for classification in an industrial recycling operation. The data is from different vision systems and an eddy current system. The fusion methods included in the toolbox are fuzzy logic with triangular and Gaussian shaped membership functions, fuzzy measures with triangular and Gaussian shapes, Bayes' statistics, artificial neural networks, multivariate analysis (PCA), a knowledge-based system, and a neuro-fuzzy system.

Place, publisher, year, edition, pages
2002. Vol. 51, no 1, p. 144-149
Keywords [en]
AC motors, DC motors, Fuzzy logic, Fuzzy neural networks, Neural networks, Robot vision systems
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-47112DOI: 10.1109/19.989918OAI: oai:DiVA.org:liu-47112DiVA, id: diva2:268008
Available from: 2009-10-11 Created: 2009-10-11 Last updated: 2021-12-16
In thesis
1. A Toolbox for Sensor Data Fusion in Industrial Automation
Open this publication in new window or tab >>A Toolbox for Sensor Data Fusion in Industrial Automation
1999 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The work is focused on measurement for support in industrial automation and especially around industrial robots. The main thread in the work is the combination (fusion) of information from different sensors. The applications are disassembly of electrical motors, sensor fusion in industrial safety applications and a new method for calibration of industrial robots.

When working with worn out products e.g. electrical motors, there are many different sources of uncertainty. To be able to perform operations on the products a method that can work under uncertainty are needed. It can be hard to decide which method works best in a specific situation. To make it easier a sensor fusion toolbox including different methods can be used. Typical data are tested by the toolbox and the method giving the best result is then used in the specific situation. One possible method is fuzzy measures: statistics and operator knowledge are combined forming possibility measures. These are then fused to give a decision regarding which operation to perform.

In the work with disassembly of electrical motors we have studied both commercial sensors, such as vision, accelerometers, current probes and speed counters, and sensors developed at the department, i.e. eddy current probes. One part of the work has been to make the different sensors co-operate, both with each other and with the rest of the system.

Safety is important when working with industrial automation. However, a problem with the safety systems of today is that they reduce the flexibility in the work cell. To avoid that we use new sensing methods, which can monitor the critical area and combine their output by sensor fusion. When an intruder is entering the working area, the speed of the equipment is reduced and when the intruder is close to the equipment it will stop.

To make general off-line programming of industrial robots possible there is a need of high absolute accuracy. Absolute accuracy here means that different robots reach the same position with sufficient precision when the same robot program controls them. The industrial robots of today have a good relative accuracy, in the sense that a specific robot always reaches the same position as before when controlled by the same program. However, the absolute accuracy is not so high due to insufficient robot mechanics. ABB Robotics has, in co-operation with the division of measurement technology, worked with a concept based on a calibration stick equipped within clinometers and a LVDT. The stick measures, from a carefully determined point in the floor and to different robot positions, the distance using a LVDT, and the angle of inclination using inclinometers.

Place, publisher, year, edition, pages
Linköping: Linköping University, 1999. p. 89
Series
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 601
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:liu:diva-181866 (URN)9172195568 (ISBN)
Public defence
1999-10-15, Schrödinger (E324), Fysikhuset, Linköpings universitet, Linköping, 13:15
Opponent
Note

All or some of the partial works included in the dissertation are not registered in DIVA and therefore not linked in this post.

Available from: 2021-12-16 Created: 2021-12-16 Last updated: 2025-02-10Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records

Karlsson, BeatriceJärrhed, Jan-Ove

Search in DiVA

By author/editor
Karlsson, BeatriceJärrhed, Jan-Ove
By organisation
The Institute of TechnologyDepartment of Physics, Chemistry and Biology
In the same journal
IEEE Transactions on Instrumentation and Measurement
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 148 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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