Wavelet-based analysis for fouling diagnosis of an aircraft heat exchanger

Patent metadata

Field	Value
Publication number	US-10288548-B2
Application number	US-201514689467-A
Country	US
Kind code	B2
Filing date	Apr 17, 2015
Priority date	Apr 17, 2015
Publication date	May 14, 2019
Grant date	May 14, 2019

Abstract

A method and apparatus for estimating a fouling state of a heat exchanger of an aircraft. Training sensor measurements are obtained of a parameter related to operation of the heat exchanger and a wavelet transform is applied to the training sensor measurements to obtain wavelet data. Data reduction is performed on the wavelet data to obtain representative features indicative of the training sensor measurements. A classifier is then trained to assign suitable fouling classes to the representative features. The trained classifier is used on testing sensor measurements from the heat exchanger to assign a fouling class to the testing sensor measurements in order to estimate the fouling state of the heat exchanger.

First claim

The invention claimed is:

1. A method of estimating a fouling state of a heat exchanger of an aircraft, comprising:
receiving, at a heat exchanger, at least one of bleed air or ram air from an aircraft engine;
coupling one or more sensors to the heat exchanger, wherein the one or more sensors include a pressure sensor configured to measure an input pressure of the bleed air to the heat exchanger, a temperature sensor configured to measure a temperature associated with the heat exchanger, and an angular speed sensor configured to measure a speed of a shaft of an air cycle machine of the aircraft;
obtaining training sensor measurements of a parameter related to operation of the heat exchanger;
applying a wavelet transform to the training sensor measurements to obtain wavelet data;
performing data reduction on the wavelet data to obtain a representative feature indicative of the training sensor measurements;
training a classifier to assign a suitable fouling class to the representative feature;
applying the trained classifier to testing sensor measurements from the heat exchanger to assign a fouling class to the testing sensor measurements in order to estimate the fouling state of the heat exchanger; and
evaluating a performance of the classifier to reduce a number of false alarms and missed detections by training the classifier, wherein the evaluation includes:
partitioning the training sensor measurements into a plurality of groups;
using a first portion of the plurality of groups to train the classifier and using a second portion of the plurality of groups to test the classifier;
generating a confusion matrix, the confusion matrix based at least in part on the testing of the classifier and which includes information associated with the performance of the classifier;
outputting the evaluation to a display;
determining at least one of a maintenance schedule or in-flight action based at least in part on the evaluation; and
performing maintenance of the heat exchanger based at least in part on a condition of the heat exchanger.

2. The method of claim 1 , wherein the heat exchanger is included in an environmental control system having an air cycle machine, and the parameter further comprises at least one of: (i) heat exchanger output temperature; (ii) condenser inlet temperature; (iii) Environmental Control System output temperature; (iv) Environmental Control System input pressure; and (v) an angular speed of an Air Cycle Machine.

3. The method of claim 1 , wherein the fouling class of the heat exchanger is known a priori.

4. The method of claim 3 , further comprising classifying the representative feature using a pattern classification algorithm.

5. The method of claim 4 , wherein training the classifier further comprises applying a cross-validation algorithm to test the ability of the classifier to correctly classify the representative feature.

6. The method of claim 1 , further comprising obtaining the training sensor measurements from a model of the heat exchanger under different fouling conditions.

7. The method of claim 6 , wherein training the classifier further comprises establishing fouling classification categories.

8. A method of estimating a fouling state of a heat exchanger of an aircraft, comprising:
receiving, at a heat exchanger, at least one of bleed air or ram air from an aircraft engine;
coupling one or more sensors to the heat exchanger, wherein the one or more sensors include a pressure sensor configured to measure an input pressure of the bleed air to the heat exchanger, a temperature sensor configured to measure a temperature associated with the heat exchanger, and an angular speed sensor configured to measure a speed of a shaft of an air cycle machine of the aircraft;
obtaining training sensor measurements of a parameter related to operation of the heat exchanger;
applying a wavelet transform to the training sensor measurements to obtain wavelet data;
performing data reduction on the wavelet data to obtain a representative feature indicative of the training sensor measurements;
training a classifier to assign a suitable fouling class to the representative feature;
applying the trained classifier to testing sensor measurements from the heat exchanger to assign a fouling class to the testing sensor measurements in order to estimate the fouling state of the heat exchanger;
evaluating a performance of the classifier to reduce a number of false alarms and missed detections;
outputting the evaluation to a display;
determining at least one of a maintenance schedule or in-flight action based at least in part on the evaluation; and
performing maintenance of the heat exchanger based at least in part on a condition of the heat exchanger.

9. An apparatus for estimating a fouling state of a heat exchanger of an aircraft, comprising:
a heat exchanger that is configured to receive at least one of bleed air or ram air from an aircraft engine, wherein the heat exchanger is coupled to one or more sensors;
a model of the heat exchanger;
one or more sensors configured to obtain training sensor measurements of a parameter related to an operation of the model of the heat exchanger, wherein the one or more sensors include a pressure sensor configured to measure an input pressure of the bleed air to the heat exchanger, a temperature sensor configured to measure a temperature associated with the heat exchanger, and an angular speed sensor configured to measure a speed of a shaft of an air cycle machine of the aircraft; and
a processor configured to:
apply a wavelet transform to the training sensor measurements to obtain wavelet data;
perform data reduction on the wavelet data to obtain a representative feature,
train a classifier to assign a suitable fouling class to the representative feature,
apply the trained classifier to testing sensor measurements from the heat exchanger to assign a fouling class to the testing sensor measurements in order to estimate the fouling state of the heat exchanger;
evaluate a performance of the classifier to reduce a number of false alarms and missed detections by training the classifier, wherein the evaluation includes:
partition the training sensor measurements into a plurality of groups;
use a first portion of the plurality of groups to train the classifier and using a second portion of the plurality of groups to test the classifier;
generate a confusion matrix, the confusion matrix based at least in part on the testing of the classifier and which includes information associated with the performance of the classifier;
output the evaluation to a display;
determine at least one of a maintenance schedule or in-flight action based at least in part on the evaluation; and
performing maintenance of the heat exchanger based at least in part on a condition of the heat exchanger.

10. The apparatus of claim 9 , wherein the heat exchanger is included in an Environmental Control System having an air cycle machine and the parameter further comprises at least one of: (i) heat exchanger output temperature; (ii) condenser inlet temperature; (iii) Environmental Control System output temperature; (iv) Environmental Control System input pressure; and (v) an angular speed of an air cycle machine.

11. The apparatus of claim 9 , wherein the processor is further configured to estimate the fouling state by performing a pattern classification algorithm on the representative feature to classify the representative feature.

12. The apparatus of claim 9 , wherein the fouling class of the heat exchanger is known a priori.

13. The method of claim 12 , wherein training the classifier further comprises apply

Assignees

• Hamilton Sundstrand Corp

Inventors

• Silva Andre A
• Najjar Nayeff A
• Gupta Shalabh
• D'Orlando Paul M
• Walthall Rhonda Dawn

Classifications

• G01N25/18

  by investigating thermal conductivity (by calorimetry G01N25/20; by measuring change of resistance of an electrically-heated body G01N27/18) · CPC title

• F28F27/00

  Control arrangements or safety devices specially adapted for heat-exchange or heat-transfer apparatus (control arrangements in general G05) · CPC title

• G01N17/008 Primary

  Monitoring fouling · CPC title

• G06F17/148

  Wavelet transforms · CPC title

• G05B23/0283

  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 title