Analyzing equipment degradation for maintaining equipment

Patent metadata

Field	Value
Publication number	US-10067038-B2
Application number	US-201514913222-A
Country	US
Kind code	B2
Filing date	Mar 24, 2015
Priority date	Mar 24, 2015
Publication date	Sep 4, 2018
Grant date	Sep 4, 2018

Abstract

A method and system for analyzing equipment degradation for maintaining the equipment are provided. The method and system receive and store equipment and sensor data associated with operational equipment, generate a display signal to display a relationship analysis window, a residual error window, a performance condition window, and a maintenance trigger window, and evaluate a coordinated relationship between the equipment sensor data and the environmental data, determine residual errors and determine a Historical Health Condition Index (HHCI) for the operational equipment and generate a Future Health Condition Index (FHCI) from the HHCI, and generate an equipment maintenance trigger for the operational equipment by establishing a trigger threshold for maintenance.

First claim

What is claimed is:

1. A system comprising:
a communication interface circuitry configured to receive:
equipment sensor data time series from a sensor disposed inside an operational equipment representing an equipment performance parameter from among multiple different performance parameters associated with the operational equipment; and
environmental data time series representing an environmental characteristic of a location where the operational equipment is located;

a measurement database configured to store the equipment sensor data time series and the environmental data time series received from the communication interface circuitry;
display generation circuitry configured to generate a display signal comprising:
a relationship analysis window;
a residual error window;
a performance condition window; and
a maintenance trigger window; and

equipment analysis circuitry in communication with the measurement database and the display generation circuitry, the equipment analysis circuitry configured to:
select, among the equipment sensor data time series and environmental data time series in the measurement database, a subset of historical equipment sensor data and a corresponding subset of historical environmental data obtained when the operational equipment was running during a time period of healthy condition;
evaluate a coordinated healthy condition relationship between the selected subset of historical equipment sensor data and the selected subset of historical environmental data to obtain a relationship output, and provide the relationship output for display in the relationship analysis window;
determine a calculated equipment sensor data time series based on the coordinated healthy condition relationship and the environmental data time series stored in the measurement database;
determine residual error time series showing differences between the calculated equipment sensor data time series and the equipment sensor data time series stored in the measurement database, and provide the residual errors for display in the residual error window;
determine that the residual error time series follow a normal distribution by:
dividing the residual errors into groups according to time windows of a predetermined time unit; and
determining that the residual error time series follow a normal distribution in each of the time windows based on comparing calculated quantiles of the residual error time series in each time window and a set of norm quantiles;

upon determining that the residual error time series follow a normal distribution:
use the residual error time series as a Historical Health Condition Index (HHCI) for the operational equipment; and
generate a Future Health Condition Index (FHCI) from the HHCI by:
calculating a mean and a standard deviation for the residual error time series for each time window;
training a predictive model for future mean and standard deviation for residual error based on the calculated means and standard deviation for the residual error time series; and
determining the FHCI based on the predictive model;

provide the HHCI and the FHCI for display in the performance condition window; and
generate an equipment maintenance trigger for the operational equipment by establishing a maintenance trigger threshold for a limit violation probability for a predetermined HCI limit based on the predictive model, and provide the equipment maintenance trigger for display in the maintenance trigger window.

2. The system of claim 1 , wherein the coordinated healthy condition relationship comprises a linear regression.

3. The system of claim 1 , wherein the environmental data represent an ambient temperature.

4. The system of claim 1 , wherein the equipment analysis circuitry is further configured to generate the FHCI for future time according to the HHCI.

5. The system of claim 1 , wherein the equipment analysis circuitry is further configured to apply a smooth function to the HHCI and the FHCI to filter out noise, local fluctuation or both to obtain an overall trend of HCI.

6. The system of claim 1 , wherein the limit violation probability for a future residual error is determined by the equipment analysis circuitry based on the predetermined HCI limit, a mean and standard deviation of the future residual error predicted by the predictive model.

7. The system of claim 1 , wherein the equipment analysis circuitry is further configured to generate a maintenance notification and send the maintenance notification to a recipient by using the communication interface circuitry when the trigger threshold is exceeded.

8. The system of claim 1 , wherein the display signal further comprises an informational window for the operational equipment, wherein the informational window comprises an image of the operational equipment and a description of the operational equipment.

9. A method comprising:
receiving, from a communication interface circuitry, equipment sensor data time series from an sensor disposed inside an operational equipment representing an equipment performance parameter from among multiple different performance parameters associated with the operational equipment;

receiving, from the communication interface circuitry, environmental data time series representing an environmental characteristic of a location where the operational equipment is located;
storing the equipment sensor data time series and the environmental data time series received from the communication interface circuitry into a measurement database;
generating, by display generation circuitry, a display signal to display: a relationship analysis window, a residual error window, a performance condition window, and a maintenance trigger window;
selecting, by equipment analysis circuitry, among the equipment sensor data time series and environmental data time series in the measurement database, a subset of historical equipment sensor data and a corresponding subset of historical environmental data obtained when the operational equipment was running during a time period of healthy condition;
evaluating, by the equipment analysis circuitry that is in communication with the measurement database and the display generation circuitry, a coordinated healthy condition relationship between the selected subset of historical equipment sensor data and the selected subset of historical environmental data to obtain a relationship output, and providing the relationship output for display in the relationship analysis window;
determining, by the equipment analysis circuitry, a calculated equipment sensor data time series based on the coordinated healthy condition relationship and the environmental data time series stored in the measurement database;
determining, by the equipment analysis circuitry, residual error time series showing differences between the calculated equipment sensor data time series and the equipment sensor data time series stored in the measurement database, and providing the residual errors for display in the residual error window;
determine that the residual error time series follow a normal distribution by:
dividing the residual errors into groups according to time windows of a predetermined time unit; and
determining that the residual error time series follow a normal distribution in each of the time windows based on comparing calculated quantiles of the residual error time series in each time window and a set of norm quantiles;

upon determining that the residual error time series follow a normal distribution:
using, by the equipment analysis circuitry, the residual error time series as a Historical Health Condition Index (HHCI) for the operational equipment; and

Assignees

• Accenture Global Services Ltd

Inventors

• Hou Fang
• Gao Yan
• Cheng Xiaopei

Classifications

• G06T11/26

  Drawing of charts or graphs · CPC title

• G16Z99/00

  Subject matter not provided for in other main groups of this subclass · CPC title

• G06Q10/20

  Administration of product repair or maintenance · CPC title

• F04B51/00

  Testing machines, pumps, or pumping installations · CPC title

• G01M99/008 Primary

  by doing functionality tests · CPC title