Method, apparatus, and system for monitoring manufacturing equipment

• US 10,152,879 B2
• Filed: 11/10/2015
• Issued: 12/11/2018
• Est. Priority Date: 11/10/2015
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Chen, Te-Ming, Chang, Sen-Chia, Lai, Chien-Liang, Day, Chi-Ting
• Primary Examiner(s): Lim, Steven
• Assistant Examiner(s): Adnan, Muhammad
• Application Number:
  US14/936,787
• Publication Number:
  US 20170132910A1
• Time in Patent Office: 1,127 Days
• Field of Search: None
• CPC Class Codes: G05B 19/0428 Safety, monitoring G05B19/0423 takes precedence
• CPC Class Codes: G05B 23/00 Testing or monitoring of control systems or parts thereof monitoring of programme-control systems G05B19/048, G05B19/406
• CPC Class Codes: G05B 23/0235 based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
• CPC Class Codes: G05B 23/0272 Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user
• CPC Class Codes: G08B 21/182 Level alarms, e.g. alarms responsive to variables exceeding a threshold
• CPC Class Codes: G08B 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system

Abstract

A method for monitoring a manufacturing apparatus includes collecting a control signal, of a controller and a corresponding sensing signal, of the manufacturing apparatus over a predetermined period of time; segmenting the control signal and the corresponding sensing signal to obtain at least one control step; calculating a character of the controller based on at least one of the control signal, the sensing signal, the at least one control step, or information from a user manual; generating, based on the character, a health index indicating health of the controller; and generating a warning signal when the health index exceeds a predetermined threshold.

Claims

1. A method for monitoring a manufacturing apparatus, comprising:

collecting a control signal, of a controller and a corresponding sensing signal, of the manufacturing apparatus over a predetermined period of time;

segmenting the control signal and the corresponding sensing signal by categorizing change of the control signal and the corresponding sensing signal in time, to obtain at least one control step;

calculating a character of the controller based on at least one of the control signal, the sensing signal, the at least one control step, or information from a user manual;

generating, based on the character, a health index indicating health of the controller; and

generating a warning signal when the health index exceeds a predetermined threshold.

2. The method of claim 1, wherein:

the character includes a character vector, and

calculating the character includes;

calculating a difference between the control signal and the corresponding sensing signal to obtain an offset value; and

calculating the character vector based on the obtained offset value.

3. The method of claim 2, wherein:

the manufacturing apparatus includes at least one valve associated with the controller, and

calculating the character vector based on the obtained offset value includes adjusting the offset value based on a tolerance value, the tolerance value being pre-defined and including error caused by at least one of a response time of the controller, an inaccuracy of the controller, or an opening/closing time of the at least one valve.

4. The method of claim 2, wherein calculating the character vector includes:

calculating at least one of a histogram, a mean, a standard deviation, a maximum value, a minimum value, a range, an interquartile range, a skewness, a kurtosis, a rise time, a fall time, a settling time, an overshoot, an undershoot, or a time to peak of the offset value, and

calculating the character vector based on the at least one of a histogram, a mean, a standard deviation, a maximum value, a minimum value, a range, an interquartile range, a skewness, a kurtosis, a rise time, a fall time, a settling time, an overshoot, an undershoot, or a time to peak.

5. The method of claim 1, wherein:

the character includes a character vector,

the at least one control step includes two or more control steps, and

calculating the character includes;

calculating a difference between the control signal and the corresponding sensing signal, at each of the two or more control steps, to obtain corresponding offset values; and

calculating the character vector based on the obtained offset values.

6. The method of claim 5, wherein:

the manufacturing apparatus includes at least one valve associated with the controller,

calculating the difference includes calculating the difference based on a tolerance value, the control signal, and the sensing signal, and

the tolerance value is pre-defined and includes error caused by at least one of a response time of the controller, an inaccuracy of the controller, or an opening/closing time of the at least one valve.

7. The method of claim 5, wherein calculating the character vector further includes:

calculating at least one of a histogram, a mean, a standard deviation, a maximum value, a minimum value, a range, an interquartile range, a skewness, a kurtosis, a rise time, a fall time, a settling time, an overshoot, an undershoot, or a time to peak of the offset value, and

calculating the character vector based on the at least one of a histogram, a mean, a standard deviation, a maximum value, a minimum value, a range, an interquartile range, a skewness, a kurtosis, a rise time, a fall time, a settling time, an overshoot, an undershoot, or a time to peak.

8. The method of claim 5, wherein calculating the character vector includes:

categorizing each of the two or more control steps and the corresponding offset values, each category having at least one offset value;

calculating, for each category, a histogram of the at least one offset value;

calculating, for each category, a categorized-character vector based on the histogram to obtain a plurality of categorized-character vectors; and

calculating the character vector based on the plurality of categorized-character vectors.

9. The method of claim 1, further comprising:

generating a health model for the controller according to the character of the controller at a normal condition; and

determining the predetermined threshold based on the health model.

10. The method of claim 9, wherein generating the health model includes generating the health model based on a self-organizing map (SOM), a restricted Boltzmann machine (RBM), a deep neural network (DNN), an autoencoder, a convolutional RBM, a convolutional DNN, a Hotelling'"'"'s T-squared statistic, a Q-statistic, a one-class classifier, one-class support vector machine, a support vector data description (SVDD), a fuzzy c-means, a Gaussian mixture model (GMM) model, a k nearest neighbors (kNN), or a sliding window error rate.

11. The method of claim 1, wherein the manufacturing apparatus includes a plurality of controllers and at least one valve associated with the plurality of controllers,

the method further including:

generating health indices each indicating health of a different one of the plurality of controllers; and

identifying, when two or more of the health indices exceed corresponding predetermined thresholds, a responsible controller based on spatial-temporal relations among the plurality of controllers and the at least one valve.

12. The method of claim 11, wherein identifying the responsible controller based on the spatial-temporal relations includes identifying the responsible controller based on relative positions of the plurality of controllers and the at least one valve in a network of connected pipes with respect to flow directions of materials inside the network and closing/opening time of the at least one valve.

13. The method of claim 11, wherein identifying the responsible controller includes identifying one of the plurality of controllers that causes at least one other controller to have at least one health index exceeding the corresponding predetermined threshold.

14. The method of claim 11, wherein identifying the responsible controller includes identifying the responsible controller further based on a multivariable analysis.

15. The method of claim 2, wherein generating the warning signal includes generating the warning signal to include:

a first health index indicating health of the controller at a past time,

a second health index indicating health of the controller at a current time,

the control signal and the sensing signal of the controller, and

the offset value.

16. The method of claim 5, wherein generating the warning signal includes generating the warning signal to include:

a first health index indicating health of the controller at a past time,

a second health index indicating health of the controller at a current time,

the control signal and the sensing signal of the controller, and

the offset values.

17. The method of claim 11, wherein generating the warning signal includes generating the warning signal to include:

a first health index indicating health of the responsible controller at a past time,

a second health index indicating health of the responsible controller at a current time,

the control signal and the sensing signal of the responsible controller, and

a temporal and spatial event analysis result among the plurality of controllers including the responsible controller and the at least one valve.

18. The method of claim 1, further comprising:

displaying a warning message on a display interface of the manufacturing apparatus based on the warning signal.

19. The method of claim 1, further comprising:

transmitting the warning signal to a monitoring apparatus; and

displaying a warning message based on the warning signal on a user interface of the monitoring apparatus.

20. A manufacturing system, comprising:

a manufacturing apparatus including a controller; and

a monitoring apparatus including;

a processor; and

a memory storing instructions that, when executed by the processor, cause the processor to;

collect a control signal of the controller, and a corresponding sensing signal, over a predetermined period of time;

segment the control signal and the corresponding sensing signal by categorizing change of the control signal and the corresponding sensing signal in time, to obtain at least one control step;

calculate a character of the controller based on at least one of the control signal, the sensing signal, the at least one control step, or information from a user manual;

generate, based on the character, a health index indicating health of the controller; and

generate a warning signal when the health index exceeds a predetermined threshold.

21. The system of claim 20, wherein:

the manufacturing apparatus includes a plurality of controllers and at least one valve associated with the plurality of controllers, and

the instructions further cause the processor to;

generate health indices each indicating health of a different one of the plurality of controllers; and

identify, when two or more of the health indices exceed corresponding predetermined thresholds, a responsible controller based on spatial-temporal relations among the plurality of controllers and the at least one valve.

22. An apparatus for monitoring a manufacturing apparatus, comprising:

a processor; and

a memory storing instructions that, when executed by the processor, cause the processor to;

collect a control signal of a controller, and a corresponding sensing signal, of the manufacturing apparatus over a predetermined period of time;

segment the control signal and the corresponding sensing signal by categorizing change of the control signal and the corresponding sensing signal in time, to obtain at least one control step;

calculate a character of the controller based on at least one of the control signal, the sensing signal, the at least one control step, or information from a user manual;

generate, based on the character, a health index indicating health of the controller; and

generate a warning signal when the health index exceeds a predetermined threshold.

23. The apparatus of claim 22, wherein:

the manufacturing apparatus includes a plurality of controllers and at least one valve associated with the plurality of controllers, and

the instructions further cause the processor to;

generate health indices each indicating health of a different one of the plurality of controllers; and

identify, when two or more of the health indices exceed corresponding predetermined thresholds, a responsible controller based on spatial-temporal relations among the plurality of controllers and the at least one valve.

24. A non-transitory computer-readable storage medium embodying a computer program product, the computer program product comprising instructions configured to cause a computing device to perform a method comprising:

collecting a control signal of a controller, and a corresponding sensing signal, of a manufacturing apparatus over a predetermined period of time;

segmenting the control signal and the corresponding sensing signal by categorizing change of the control signal and the corresponding sensing signal in time, to obtain at least one control step;

calculating a character of the controller based on at least one of the control signal, the sensing signal, the at least one control step, or information from a user manual;

generating, based on the character, a health index indicating health of the controller; and

generating a warning signal when the health index exceeds a predetermined threshold.

25. The non-transitory computer-readable storage medium of claim 24, wherein:

the manufacturing apparatus includes a plurality of controllers and at least one valve associated with the plurality of controllers, and

the instructions are configured to cause the computing device to perform a method further comprising;

generating health indices each indicating health of a different one of the plurality of controllers; and

identifying, when two or more of the health indices exceed corresponding predetermined thresholds, a responsible controller based on spatial-temporal relations among the plurality of controllers and the at least one valve.