METHOD FOR DIAGNOSIS OF EQUIPMENT

A method of predicting failures in equipment including at least one sensor for generating sensor data corresponding to a sensed parameter. The method includes monitoring the sensor data during normal operation of the equipment. The sensor data during normal operation is compared to a model prediction of the sensed parameter to determine variance between the sensor data and the model prediction. The model is calibrated to minimize the variance between the model prediction and the sensor data. Error in the sensor data is determined and an error condition is generated upon detection of an error in the sensor data.