Light rail vehicle having predictive diagnostic system for motor driven automated doors

• US 6,636,814 B1
• Filed: 08/22/2002
• Issued: 10/21/2003
• Est. Priority Date: 11/05/1999
• Status: Expired due to Fees

• Current Assignee: Bombardier Transportation GmbH (Bombardier Incorporated)
• Original Assignee: Bombardier Transportation GmbH (Bombardier Incorporated)
• Inventors: Karg, Kenneth A., McCullers, Curtis W., Campbell, Dean J., Smith, Alice E., Etzel, Andreas H.
• Primary Examiner(s): SHAH, KAMINI S
• Application Number:
  US10/111,926
• Time in Patent Office: 425 Days
• Field of Search: 702/34, 701/19, 701/29, 701/34, 701/40, 701/79, 700/83, 709/318
• US Class Current: 702/34
• CPC Class Codes: B61D 19/02 for carriages B61D19/003 takes precedence
• CPC Class Codes: G05B 23/0281 Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G06F 11/2263 using neural networks

Abstract

Disclosed is a light rail vehicle having a predictive diagnostic system for a motor driven automated door (100) to enable condition-based maintenance. The light rail vehicle (110) has an automated door system (112), at least one data acquisition board (114), a data collection program (116), an exponential smoothing algorithm (118), and a neural network (120). The need for maintenance is identified through the collection of various door system (112) parameters, calculating current energy and time consumption from these parameters, and determining the rate of degradation based on current energy and time consumption of the door system (112) as compared with historical energy and time consumption. From the rate of degradation, maintenance can be scheduled as needed.

Claims

1. A method for identifying when maintenance is required on a light rail vehicle motor driven automated door system, comprising the steps of:

a) collecting data from the door system;

b) calculating current energy and time consumption values for the door system based on the data;

c) producing a set of energy and time consumption values based on the current energy and time consumption values and historical energy and time consumption values;

d) generating a degree of degradation of the system based on the set of energy and time consumption values;

e) generating an estimated time to failure of the system based on the degree of degradation and a known point where the system requires maintenance; and

e) identifying maintenance needs based on the estimated time to failure.

2. The method according to claim 1, wherein the data collected in step a) includes motor current, motor voltage, and door position at a given time of the door system.

3. The method according to claim 1, wherein door position is determined through data sent from switches fixedly positioned around a cam coupled to a shaft of a motor of the door system.

4. The method according to claim 1, wherein:

at least one data acquisition board electrically connected to the door system collects the data in step a);

a computer electrically connected to the data acquisition board receives the data from the data acquisition board, the computer including a data collection program that calculates the current energy and time consumption values in step b);

an exponential smoothing algorithm produces the set of energy and time consumption values in step c); and

a neural network calculates the rate of degradation and the estimated time to failure and identifies the maintenance needs.

5. The method according to claim 4, wherein the computer also includes the data acquisition board.

6. The method according to claim 3, wherein the neural network is a backpropagation, a cascade correlation, or a radial basis function neural network.

7. An apparatus for identifying when maintenance is required on a light rail vehicle motor driven automated door system, comprising:

means for indicating a position of a door through open and close cycles;

at least one data acquisition board electrically connected to the motor and the means for indicating the position of the door;

at least one computer including a data collection program, an exponential smoothing algorithm, and a neural network,

wherein the data acquisition board collects data from the motor and the means for indicating the position of the door as the door system cycles open and closed, the data collection program and the exponential smoothing algorithm calculate a set of input values based on the data, and the neural network determines a rate of degradation and an estimated time of failure of the door system based on the set of input values and identifies when maintenance is required on the door system.

8. The apparatus according to claim 7, wherein the means for indicating the position of the door is a plurality of switches fixedly positioned around a cam coupled to a shaft of a motor of the door system.

9. The apparatus of claim 7, wherein the data collected includes motor current, motor voltage, and switch signals at a given time of the door system.

10. The apparatus of claim 7, wherein one of the at least one computer is electrically connected to the data acquisition board and includes the data collection program.

11. The apparatus of claim 7, wherein the neural network is a backpropagation, a cascade correlation, or a radial basis function neural network.