Intelligent condition monitoring and fault diagnostic system for preventative maintenance

• US 9,104,650 B2
• Filed: 01/11/2013
• Issued: 08/11/2015
• Est. Priority Date: 07/11/2005
• Status: Active Grant

• Current Assignee: Brooks Automation Ltd. (United Kingdom) (Azenta, Inc.)
• Original Assignee: Brooks Automation Incorporated (Azenta, Inc.)
• Inventors: Hosek, Martin, Prochazka, Jan, Krishnasmy, Jayaraman
• Primary Examiner(s): Lottich, Joshua P
• Application Number:
  US13/739,831
• Publication Number:
  US 20140201571A1
• Time in Patent Office: 942 Days
• Field of Search: 714/25, 714/26, 714/47.1
• US Class Current: 1/1
• CPC Class Codes: B25J 9/1674 characterised by safety, monitoring, diagnostic
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• 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 11/2257 using expert systems

Abstract

A system for condition monitoring and fault diagnosis includes a data collection function that acquires time histories of selected variables for one or more of the components, a pre-processing function that calculates specified characteristics of the time histories, an analysis function for evaluating the characteristics to produce one or more hypotheses of a condition of the one or more components, and a reasoning function for determining the condition of the one or more components from the one or more hypotheses.

Claims

1. A system for condition monitoring and fault diagnosis of a machine comprising:

a control system operably coupled to the machine having a hierarchical arrangement of controllers, each comprising a processor and a memory, the hierarchical arrangement of controllers configured to implement;

a data collection function that acquires time histories of selected variables for one or more machine components according to specified sampling parameters;

a preprocessing function that calculates specified characteristics of each of the time histories individually;

an analysis function for evaluating the specified characteristics of each of the individual time histories to produce one or more hypotheses of a condition of the one or more machine components; and

a reasoning function for determining the condition of the one or more machine components from the one or more hypotheses,

wherein at least one of the functions resides in a higher level of the hierarchical arrangement of controllers such that condition monitoring and fault diagnosis data are used at a level where intelligence to process the data is present.

2. The system of claim 1, wherein the specified sampling parameters include a sampling period, trigger mode, and number of samples to be recorded for the selected variables.

3. The system of claim 1, wherein the pre-processing function calculates the specified characteristics of the time histories by performing mathematical operations on the time histories.

4. The system of claim 1, wherein the analysis function produces the one or more hypotheses by applying one or more algorithms and analysis techniques to the calculated specified characteristics of the time histories.

5. The system of claim 1, wherein the reasoning function includes an expert diagnostic system for determining a condition of the one or more components from the one or more hypotheses.

6. A method of component condition monitoring and fault diagnosis of a machine comprising:

operably coupling a control system to the machine, having a hierarchical arrangement of controllers, each controller comprising a processor and a memory; and

configuring the controllers to;

acquire time histories of selected variables for one or more machine components according to specified sampling parameters using a data collection function;

calculate specified characteristics of each of the time histories individually using a preprocessing function;

evaluate the specified characteristics of each of the individual time histories to produce one or more hypotheses of a condition of the one or more machine components using an analysis function; and

determine the condition of the one or more machine components from the one or more hypotheses and utilize the determined condition of the one or more machine components to determine if preventative maintenance or service is required for the one or more machine components, using a reasoning function;

the method further comprising implementing at least one of the functions in a higher level of the hierarchical arrangement of controllers such that condition monitoring and fault diagnosis data are used at a level where intelligence to process the data is present.

7. The method of claim 6, wherein the specified sampling parameters include a sampling period, trigger mode, and number of samples to be recorded for the selected variables.

8. The method of claim 6, comprising configuring the controllers to calculate specified characteristics of the time histories by performing mathematical operations on the time histories.

9. The method of claim 6, comprising configuring the controllers to produce the one or more hypotheses by applying one or more algorithms and analysis techniques to the calculated specified characteristics of the time histories.

10. The method of claim 6, comprising configuring the controllers to implement an expert diagnostic system for determining a condition of the one or more machine components from the one or more hypotheses.

11. A non-transitory computer readable storage medium encoded with a computer program for component condition monitoring and fault diagnosis, that when run on a computer, causes the computer to:

implement a component condition monitoring and fault diagnosis for a machine comprising a hierarchical arrangement of controllers; and

configure the controllers to;

use a data collection function to acquire time histories of selected variables for one or more machine components according to specified sampling parameters;

use a preprocessing function to calculate specified characteristics of each of the time histories individually;

use an analysis function to evaluate the specified characteristics of each of the individual time histories to produce one or more hypotheses of a condition of the one or more machine components; and

use a reasoning function to determine the condition of the one or more machine components from the one or more hypotheses and to utilize the determined condition of the one or more machine components to determine if preventative maintenance or service is required for the one or more machine components,

wherein the computer program further causes the computer to implement at least one of the functions in a higher level of the hierarchical arrangement of controllers such that condition monitoring and fault diagnosis data are used at a level where intelligence to process the data is present.

12. The non-transitory computer readable storage medium of claim 11, wherein the specified sampling parameters include a sampling period, trigger mode, and number of samples to be recorded for the selected variables.

13. The non-transitory computer readable storage medium of claim 11, wherein the computer program configures the controllers to calculate the specified characteristics of the time histories by performing mathematical operations on the time histories.

14. The non-transitory computer readable storage medium of claim 11, wherein the computer program configures the controllers to produce the one or more hypotheses by applying one or more algorithms and analysis techniques to the calculated specified characteristics of the time histories.

15. The non-transitory computer readable storage medium of claim 11, wherein the computer program configures the controllers to implement an expert diagnostic system for determining a condition of the one or more machine components from the one or more hypotheses.