A real-time expert data filtering system for industrial plant environments Original Research Article

This paper presents an Expert Data Rejection (EDR) system, developed to accompany a real-time data acquisition tool for industrial plants. The EDR system is an integrated software tool responsible for the first stage process of multiple raw measurements coming from the plant. It provides different algorithms, which operate in real time, recognizing faulty patterns according to the user requirements. For each specific measurement the user may define a different way of treatment. The system checks the signal values and filters the incoming data. Various adaptive techniques have been adopted, such as digital filtering and variations of the recursive least-squares algorithm, as well as the neural network based algorithms. The system was applied and tested in a subprocess of a refinery plant in Athens. The EDR system removes the measurement noise and provides reliable data for further processing. It also gives information about the existence of faulty instruments monitoring the operation of the industrial process.