Simulation and Application of Soft Measurement Method Based on Process Neural Network

Soft measurement is a method by modeling mathematic model for some undetected parameters in control system A new algorithm of soft measurement based on process neural network (PNN) was studied. A time aggregation operator was introduced to process neuron, and it made the neuron network has the ability to deal with the information of space-time two dimensions at the same time, so the data processing enginery of biological neuron was imitated better than traditional neuron. PNN with the structure of three layers in which hidden layer was process neuron and inputs and output were common neurons was discussed. The soft measurement based on PNN may be used to fulfill measurement of the effluent BOD from wastewater treatment system, and a good training result of soft measurement was obtained by simulation with MATLAB.