SIGDIG - Signal Discrimination for Condition Monitoring

Signal discrimination analysis UI Signal classification UI


Condition monitoring and diagnosis are important tasks in modern industrial systems having a high degree of automation. Existing industrial systems already have a variety of sensor and control signals that can be used for monitoring. Of particular importance would be automatic detection and recognition of faults, such as motor failures, where an early warning of failure can prevent escalation of the problem and larger damages.

The main objective of this project is to develop general and automatic methods for condition monitoring and diagnosis. Methods should be able to automatically find discriminative information between measurements from different conditions of industrial systems, e.g., what stator current frequencies may reveal bearing damages in electric motors.

The project is conducted in collaboration with
  1. Laboratory of Digital and Computer Electronics, Lappeenranta University of Technology (professor Jero Ahola's research group.



First version of the signal diagnosis software is ready.

Contact information

Pasi Saarinen E-mail - Industry coordinator (industrial contacts)
Jarmo Ilonen E-mail WWW Graduate researcher, Information Technology
Joni Kämäräinen E-mail WWW Post-doc researcher, Information Technology
Jero Ahola E-mail WWW Professor, Electrical Engineering
Heikki Kälviäinen E-mail WWW Professor, Information Technology
Tuomo Lindh E-mail WWW Post-doc researcher, Electrical Engineering
Ville Kyrki E-mail WWW Post-doc researcher, Information Processing Lab
Jarmo Partanen E-mail WWW Professor, Electrical Engineering



  1. Introduction slides:
    1. Finnish - Powerpoint (700k) PDF (700k)
    2. English - Powerpoint (600k) PDF (700k)

Demo software

  1. SIGDIG Matlab demo software
    VersionTested Matlab DistributionTested OSFileFile size
    V0.1R13,R14Unix (Linux), WinXP smoott_demo.tar.gz340kB
    V0.2R13,R14Unix (Linux), WinXP smoott_demo-v0.2.tar.gz340kB
  2. User's Guide (PDF, 150k)

Source code

  1. -

Data sets

  1. Stator current measurements (tar.gz 65M) - see also

Links to other resources


Do not hesitate to to contact authors (e-mail, etc.) in order to retrieve copies or reprints of the following publications.

  1. Articles in international scientific journals with referee practice
    1. Ilonen, J., Kamarainen, J.-K., Lindh, T., Ahola, J., Kälviäinen, H., Partanen, J., Diagnosis Tool for Motor Condition Monitoring, IEEE Transactions on Industry Applications 41, 4 (2005) 963-971.
  2. Articles in international compilation works and in international scientific conference proceedings with referee practice
    1. Kamarainen, J.-K., Kyrki, V., Lindh, T., Ahola, J., Partanen, J., Statistical Signal Discrimination for Condition Diagnosis, In Proc. of the Finnish Signal Processing Symp. (Tampere, Finland, 2003), pp. 195-198.
    2. Lindh, T., Ahola, J., Kamarainen, J.-K., Kyrki, V., Partanen, J., Bearing Damage Detection Based on Statistical Discrimination of Stator Current, In Proc. of the 4th IEEE Int. Symp. on Diagnostics for Electric Machines, Power Electronics and Drives (Atlanta, Georgia, USA, 2003), pp. 177-181.
    3. Ilonen, J., Paalanen, P., Kamarainen, J.-K., Lindh, T., Ahola, J., Kälviäinen, H., Partanen, J., Toward Automatic Motor Condition Diagnosis, In Proc. of the 14th Scandinavian Conf. of Image Processing (Joensuu, Finland, 2005), pp. 971-977.
  3. Scientific monographs
    1. -
  4. Other scientific publications
    1. Kämäräinen, J.-K., Kyrki, V., Lindh, T., Signal Discrimination Based on Power Spectrum of Filter Response, Research Report 80, Lappeenranta University of Technology, Department of Information Technology, 2002. (PDF 290k)