Method for diagnosis of equipment
First Claim
1. A six sigma method of predicting failures in locomotive equipment including at least one sensor for generating sensor data corresponding to a sensed parameter, the method comprising:
- monitoring the sensor data during normal operation of the equipment;
comparing the sensor data during normal operation to a model prediction of the sensed parameter to determine variance between the sensor data and the model prediction;
calibrating the model to facilitate minimizing the variance between the calibrated model prediction and the sensor data;
generating an alarm if the sensor data exceeds a predetermined limit based on the calibrated model prediction; and
predicting failures in the locomotive equipment based on the generated alarm.
1 Assignment
0 Petitions
Accused Products
Abstract
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.
34 Citations
8 Claims
-
1. A six sigma method of predicting failures in locomotive equipment including at least one sensor for generating sensor data corresponding to a sensed parameter, the method comprising:
-
monitoring the sensor data during normal operation of the equipment;
comparing the sensor data during normal operation to a model prediction of the sensed parameter to determine variance between the sensor data and the model prediction;
calibrating the model to facilitate minimizing the variance between the calibrated model prediction and the sensor data;
generating an alarm if the sensor data exceeds a predetermined limit based on the calibrated model prediction; and
predicting failures in the locomotive equipment based on the generated alarm. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
establishing tolerance levels for the sensor data.
-
-
3. The method of claim 1 wherein:
said determining error includes determining a normalized error in the sensor data and generating the error condition in response to the normalized error.
-
4. The method of claim 3 wherein:
said determining error includes comparing the normalized error to a predetermined limit.
-
5. The method of claim 4 wherein:
the predetermined limit is based on variance of the sensor data during normal operation of the equipment.
-
6. The method of claim 1 wherein:
the sensor data includes a plurality of sensor data corresponding to a plurality of sensed parameters.
-
7. The method of claim 6 wherein:
the predetermined limit includes a plurality of predetermined limits, each predetermined limit corresponding to a respective sensor data.
-
8. The method of claim 1 wherein:
the error condition includes a plurality of error conditions indicating differing levels of failure in the equipment.
Specification