Neural network based data validation algorithm for pressure processes

Effective Control of Complex process in power generation industries is a challenge to instrumentation engineers. Most importantly coordination of sensor functioning should be monitored regularly. So, a sensor validation and data reconciliation methods are adopted for monitoring the data and faulty data are replaced. In this paper neural network based data validation method is developed and tested for pressure sensor. For neural networks, back propagation algorithm is applied for obtaining an estimated value and then a fault detection method called SPRT (Sequential probability ratio test) is applied to identify the trueness of the sensor.