Winner take all experts network for sensor validation

The validation of sensor measurements has become an integral part of the op eration and control of modern industrial equipment. The sensor under harsh environment must be shown to consistently provide the correct measurements. Analysis of the validation hardware or software should trigger an alarm wh en the sensor signals deviate appreciably from the correct values, Neural n etwork based models can be used to on-line estimate critical sensor values when neighboring sensor measurements are used as inputs. The underlying ass umption is that the neighboring sensors share an analytical relationship. T he discrepancy between the measured and predicted sensor values may then be used as an indicator fur sensor health. The proposed Winner Take All Exper ts (WTAE) network based on a 'divide and conquer strategy significantly red uces the computational time required to train the neural network;. It emplo ys a growing fuzzy clustering algorithm to divide a complicated problem int o a series of simpler sub-problems and assigns an expert to each of them lo cally. After the sensor approximation, the outputs from the estimator and t he real sensor readings are compared both in the lime domain and the freque ncy domain. Three fault indicators are used to provide analytical redundanc y to detect the sensor failure. In the decision stage, the intersection of three fuzzy sets accomplishes a decision level Fusion, which indicates the confidence level of the sensor health. Two data sets, the Spectra Quest Mac hinery Fault Simulator data set and the Westland vibration data set, were u sed in simulations to demonstrate the performance of the proposed WTAE netw ork. The simulation results show the proposed WTAE is competitive with or e ven superior to the existing approaches. (C) 2001 Elsevier Science Ltd. All rights reserved.