The use of non linear partial least square methods for on-line process monitoring as an alternative to artificial neural networks

摘要

On-Line monitoring evaluates instrument channel performance by assessing its consistency with other plant indications. Industry and EPRI experience at several plants has shown this overall approach to be very effective in identifying instrument channels that are exhibiting degrading or inconsistent performance characteristics. On-Line monitoring of instrument channels provides information about the condition of the monitored channels through accurate, more frequent monitoring of each channel's performance over time. This type of performance monitoring is a methodology that offers an alternate approach to traditional time-directed calibration. On-line monitoring of these channels can provide an assessment of instrument performance and provide a basis for determination if adjustments are necessary. Elimination or reduction of unnecessary field calibrations can reduce associated labour costs, reduce personnel radiation exposure and reduce the potential for miscalibration. PEANO is a system for on-line calibration monitoring developed in the years 1995-2000 at the Institutt for energiteknikk (IFE), Norway, which makes use of Artificial Intelligence techniqoes for its purpose. The system has been tested successfully in Europe in off-line tests with EDF (Prance), Tecnatom (Spain) and ENEA (Italy). PEANO is currently installed and used for on-line monitoring at the HBWR reactor in Halden. A major problem in the use of Artificial Neural Networks, as in PEANO, is its limited retraining capability (which is necessary whenever process component changes occur) and its exponential complexity increase with the number of monitored signals. To overcome these limitations, an approach based on Non Linear Partial Least Square, an extension of the well-known PLS method, is proposed. In this work the NLPLS algorithm will be implemented in the PEANO architecture and its performance will be compared with the current PEANO version, based on ANN. For this purpose, real data from an operating PWR will be used for testing both systems.