Main contents


Soft-sensor methods in improving the competitivity of industrial products

Soft sensor or virtual sensor is a common name for software where several measurements are processed together. There may be dozens or even hundreds of measurements. The interaction of the signals can be used for calculating new quantities that need not be measured. Soft sensors are especially useful in data fusion, where measurements of different characteristics and dynamics are combined. It can be used for fault diagnostics as well as control applications.

Well-known software algorithms that can be seen as soft sensors include e.g. Kalman filters. More recent implementations of soft sensors use neural networks or fuzzy computing.

There are plenty of examples of soft sensor techniques:

  • Kalman filters for estimating the location
  • velocity estimators in electric motors
  • estimating process data using self-organizing neural networks
  • fuzzy computing in process control

The SOSE project develops soft sensor based software algorithms for integration with industrial maintenance and intelligent control products.

This project has the following subprojects: Harvester, VÄSY, VAIVI and PIHA.

Our research partners are Tampere University of Technology. Our research is financed by TEKES.


  • Harvester - Intelligent maintenance and performance optimization of forest machines with soft-sensor methods
  • VÄSY - Intelligent, Machine Vision Based Control for a Flotation Process
  • VAIVI - Fault diagnostics of electrical AC machines
  • PIHA - Circuit manufacturing control


(S) File not found or open failed result: raw file: /sovellus/trip_htdocs/tkk/julkaisee/raw.*

Licentiate Theses

(S) File not found or open failed result: list2 file: /sovellus/trip_htdocs/tkk/inssi/list2.*

Master's Theses

(S) File not found or open failed result: list2 file: /sovellus/trip_htdocs/tkk/inssi/list2.*