Soft sensor or virtual sensor is a common name for software where several measurements are processed together. Commonly soft sensors are based on control theory and also receive the name of state observer. 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 diagnosis as well as control applications.

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

Examples of soft sensor applications:

• Kalman filters for estimating the location
• Velocity estimators in electric motors
• Estimating process data using self-organizing neural networks
• Fuzzy computing in process control
• Estimators of food quality^[1]

• Virtual sensing
• State observer

• Fortuna, Luigi; Graziani, Salvatore; Rizzo, Alessandro; Xibilia, M. Gabriella (2007), Soft Sensors for Monitoring and Control of Industrial Processes, Springer-Verlag, ISBN 978-1-84628-479-3
• Kadlec, Petr; Gabrys, Bogdan; Strandt, Sybille (2009), "Data-driven Soft Sensors in the Process Industry" (PDF), Computers and Chemical Engineering, 33 (4): 795–814, doi:10.1016/j.compchemeng.2008.12.012
• Karri, Rama Rao; Damaraju, Phaneswara Rao; Venkateswarlu, Chimmiri (2009), "Soft Sensor Based Nonlinear Control of a Chaotic Reactor", Intelligent Control Systems and Signal Processing, 2 (1): 537–543, doi:10.3182/20090921-3-TR-3005.00093
• Venkatasubramanian, V.; Rengaswamy, R.; Yin, S.; Kavuri (2003), "A review of process fault detection and diagnosis, three Parts", Computers and Chemical Engineering, 27 (3): 293–326, CiteSeerX 10.1.1.91.2319, doi:10.1016/S0098-1354(02)00161-8

• Helsinki University of Technology
• Soft Sensors for process applications in gas industry