Estimation of current and future machine states

Patent metadata

Field	Value
Publication number	US-11836636-B2
Application number	US-201916443914-A
Country	US
Kind code	B2
Filing date	Jun 18, 2019
Priority date	Dec 21, 2016
Publication date	Dec 5, 2023
Grant date	Dec 5, 2023

Abstract

Disclosed is a computer-implemented method for generating a prediction model. The model can be for use in processing machine event data to predict behavior of a plurality of industrial machines under supervision. The prediction model can be configured to determine current and future states of the industrial machines. The method can include: extracting event features from event codes and structuring the event features into feature vectors; and generating the prediction model by clustering the feature vectors into a plurality of vector clusters, the vector clusters being assigned to respective machine states. The prediction model can be constructed based on event data from a first industrial machine and be applied to control an operating state of a second industrial machine.

First claim

We claim:

1. A computer-implemented method for generating a prediction model, the model being for use in processing machine event data generated by one or more of a plurality of industrial machines sharing common properties, the method comprising:
receiving an event log comprising a plurality of codes representing events that occurred during operation of at least one of the industrial machines during an observation time interval, the event representations comprising respective time stamps and event codes;
extracting event features from the event codes and structuring the event features into feature vectors, wherein a first dimension of a first feature vector of the feature vectors corresponds to a first event feature of the extracted event features, and a second dimension of the first feature vector corresponds to a second event feature of the extracted event features;
generating the prediction model by clustering the feature vectors into a plurality of vector clusters, the vector clusters being assigned to respective machine states; and
after the prediction model has been generated, assigning a semantic meaning to at least one of the respective machine states, wherein the semantic meanings describe a meaning of the machine state;
wherein the prediction model is configured to receive, as an input, one or more of the event codes and to provide, as an output, a control signal based on one or more probabilities of the at least one industrial machine transitioning between a first of the machine states to a second of the machine states, the control signal to influence the operation of the at least one of the industrial machines.

2. The method of claim 1 , wherein the event codes comprise character strings.

3. The method of claim 2 , wherein the extracted event features describe at least one of:
a frequency of a first event associated with a first of the event codes;
a frequency of the first event and a second event occurring within a predetermine time interval, the second event associated with a second of the event codes;
a frequency of the first event and the second event occurring within a predetermined number of intervening event codes.

4. The method of claim 1 , wherein combining the event features into feature vectors comprises one or more of the following processing techniques: a skip-gram technique, continuous bag of words processing technique, a topic modelling technique, and a pairwise co-occurrence technique.

5. The method of claim 1 , wherein clustering the feature vectors comprises one or more of the following processing techniques: k-means, fuzzy c-means, expectation-maximization clustering, affinity-propagation, density based DB Scan, and density-based maximum-margin clustering.

6. The method of claim 1 , wherein the prediction model comprises a state sequence model which determines:
a current machine state and a probability of the current machine state transitioning into one of at least three known states during a finite time period of interest in the future,
a probability of a first one of the at least three known states transitioning into a second one of the least three known states,
a probability of an intrastate transition, wherein a previous machine state to the one of the at least three known states is identical to a subsequent machine state to the one of the at least three known states, and

wherein the method further comprises:
after generating the state sequence model for providing the probability of the current machine state transitioning for each of the at least three known states, each known state is assigned a semantic output meaning; and
altering the operation of the at least one of the industrial machines by the control signal using the semantic output meaning.

7. The method of claim 1 , wherein the at least one industrial machine comprises a first industrial machine and the method comprises:
receiving event codes from a second industrial machine of the plurality of industrial machines;
inputting the event codes received from the second industrial machine into the prediction model and outputting, from the prediction model, one or more probabilities of the second industrial machine transitioning between the first and the second machine states.

8. The method of claim 7 , comprising controlling a motor of the second industrial machine based on the one or more probabilities of the second industrial machine transitioning between the first and second machine states.

9. The method of claim 7 , comprising controlling the second industrial machine based on the one or more probabilities of the second industrial machine transitioning between the first and second machine states.

10. The method of claim 1 , wherein assigning semantic meanings to the machine states is performed by interacting with an expert human user.

11. The method of claim 1 , wherein the prediction model is configured to identify state transition probabilities between the machine states.

12. The method of claim 1 , further comprising:
assigning semantic meanings to the first of the machine states and the second of the machine states; and
interacting, based on the semantic meanings assigned to the first of the machine states and the second of the machine states, with at least one of the industrial machines using the control signal.

13. The method of claim 1 , wherein extracting event features from the event codes further comprises:
determining the first event feature based on a relation between a first event code of the event codes and either a second event code of the event codes or a different element of the received event log.

14. A computer-implemented method for predicting behavior of a first industrial machine of a plurality of industrial machines, the plurality of industrial machines sharing common properties, the method comprising:
generating a prediction model by receiving historical event data comprising event codes from a second industrial machine of the plurality of industrial machines;
extracting event features from the event codes and structuring the event features into feature vectors, wherein a first dimension of a first feature vector of the feature vectors corresponds to a first event feature of the extracted event features, and a second dimension of the first feature vector corresponds to a second event feature of the extracted event features;
generating the prediction model by clustering the feature vectors into a plurality of vector clusters, the vector clusters being assigned to respective machine states;
after the prediction model has been generated, assigning a semantic meaning to at least one of the respective machine states with an interaction of a human user;
receiving, with the prediction model, one or more of the event input codes and outputting, with the prediction model, one or more probabilities of the first industrial machine transitioning between a first of the machine states to a second of the machine states; and
adjusting a state of the first industrial machine based on the one or more probabilities.

15. The method of claim 14 , wherein assigning semantic meanings to the machine states is performed by interacting with an expert human user.

16. The method of claim 14 , wherein the prediction model is configured to identify state transition probabilities between the machine states.

17. A non-transitory computer-readable medium comprising code configured to cause a computing system comprising one or more computer devices to perform the method of claim 1 .

18. A non-transitory computer-readable medium comprising

Assignees

• Abb Schweiz Ag

Inventors

• Cohen Andrew
• Dix Marcel

Classifications

• G05B23/0205

  by means of a monitoring system capable of detecting and responding to faults · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G05B19/4155

  characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program · CPC title