System and method for cycle time analysis and bottleneck detection in smart factory assembly lines

Patent metadata

Field	Value
Publication number	US-12585250-B2
Application number	US-202318368433-A
Country	US
Kind code	B2
Filing date	Sep 14, 2023
Priority date	Sep 14, 2023
Publication date	Mar 24, 2026
Grant date	Mar 24, 2026

Abstract

In some implementations, the device may receive, for a plurality of stations, processing times indicating a time required for a part to be processed by each station, and waiting times indicating how long the part waited before moving to a subsequent one of the plurality of stations. In addition, the device may determine, cycle times for a predetermined window of time, where the cycle times indicates an average number of parts processed by the plurality of stations during the predetermined window of time. The device may determine one of the stations as a potential bottleneck station. Moreover, the device may display, to a user, the potential bottleneck station as a visualization which includes the processing time, the waiting time, and the cycle time of the potential bottleneck station. Also, the device may receive, from the user, a user feedback related to the potential bottleneck station.

First claim

What is claimed is:

1 . A method for improving productivity in an industrial setting, the method comprising:
receiving, for a plurality of stations, processing times indicating a time required for a part to be processed by each station, and waiting times indicating how long the part waited before moving to a subsequent one of the plurality of stations; determining, for the plurality of stations, cycle times for a predetermined window of time, where the cycle times indicates an average number of parts processed by the plurality of stations during the predetermined window of time; determining one of the stations as a potential bottleneck station based on the processing times, the waiting times, and the cycle times; displaying, to a user, the potential bottleneck station as a visualization which includes the processing times, the waiting times, and the cycle times of the potential bottleneck station; receiving, from the user, a user feedback related to the potential bottleneck station wherein the user feedback indicates that the potential bottleneck station is not a bottleneck; and updating the visualization to indicate that the potential bottleneck station is not the bottleneck, wherein the determining of the one or more stations as the potential bottleneck station is further based on a comparison between an average cycle time of each station and a user-defined average cycle time threshold.

2 . The method of claim 1 , wherein the determining of the one or more stations as the potential bottleneck station is performed by a pre-trained machine learning model.

3 . The method of claim 2 , further comprising: determining, by the pre-trained machine learning model, the potential bottleneck based on a set of heuristic rules; and updating the set of heuristic rules, based on the user feedback indicating the potential bottleneck station is not the bottleneck, to output a result that is consistent with the user feedback.

4 . The method of claim 2 , further comprising: training the pre-trained machine learning model based on the processing time, the waiting time, the cycle time of the potential bottleneck station, and the user feedback.

5 . The method of claim 1 , wherein the user feedback indicates that the potential bottleneck station is one of: an expected bottleneck and an unexpected bottleneck.

6 . The method of claim 1 , wherein the visualization further includes at least one of a bar chart, histogram, area chart, pie chart, scatter plot, line chart, box plot, and heat map.

7 . A device for improving productivity in an industrial setting comprising:
one or more processors configured to:
receive, for a plurality of stations, processing times indicating a time required for a part to be processed by each station, and waiting times indicating how long the part waited before moving to a subsequent one of the plurality of stations;
determine, for the plurality of stations, cycle times for a predetermined window of time, where the cycle times indicates an average number of parts processed by the plurality of stations during the predetermined window of time;
determine one of the stations as a potential bottleneck station by a pre-trained machine learning model based on the processing times, the waiting times, the cycle times, and a set of heuristic rules;
display, to a user, the potential bottleneck station as a visualization which includes the processing times, the waiting times, and the cycle times of the potential bottleneck station;
receive, from the user, a user feedback related to the potential bottleneck station; and
update the set of heuristic rules, based on the user feedback indicating the potential bottleneck station is not a bottleneck, to output a result that is consistent with the user feedback,
wherein determining of the one or more stations as the potential bottleneck station is further based on a comparison between an average cycle time of each station and a user-defined average cycle time threshold.

8 . The device of claim 7 , wherein the visualization further includes at least one of a bar chart, histogram, area chart, pie chart, scatter plot, line chart, box plot, and heat map.

9 . The device of claim 7 , wherein the predetermined window of time is determined based on input received from the user.

10 . The device of claim 8 , wherein the one or more processors are further configured to: train the pre-trained machine learning model based on the processing time, the waiting time, the cycle time of the potential bottleneck station, and the user feedback.

11 . The device of claim 7 , wherein the user feedback indicates that the potential bottleneck station is one of: an expected bottleneck and an unexpected bottleneck.

12 . The device of claim 7 , wherein the user feedback indicates that the potential bottleneck station is not the bottleneck, the one or more processors is further configured to: update the visualization to indicate that the potential bottleneck station is not a bottleneck.

13 . A device for improving productivity in an industrial setting comprising: one or more processors configured to:
receive, for a plurality of stations, processing times indicating a time required for a part to be processed by each station, and waiting times indicating how long the part waited before moving to a subsequent one of the plurality of stations; determine, for the plurality of stations, cycle times for a predetermined window of time, where the cycle times indicates an average number of parts processed by the plurality of stations during the predetermined window of time; determine one of the stations as a potential bottleneck station based on the processing times, the waiting times, and the cycle times; display, to a user, the potential bottleneck station as a visualization which includes the processing times, the waiting times, and the cycle times of the potential bottleneck station; and receive, from the user, a user feedback related to the potential bottleneck station wherein the user feedback indicates that the potential bottleneck station is not a bottleneck, wherein the determining of the one or more stations as the potential bottleneck station is further based on a comparison between an average cycle time of each station and a user-defined average cycle time threshold.

14 . The device of claim 13 , wherein the determining of the one or more stations as the potential bottleneck station is performed by a pre-trained machine learning model.

15 . The device of claim 14 , wherein the one or more processors are further configured to: determine, by the pre-trained machine learning model, the potential bottleneck based on a set of heuristic rules; and update the set of heuristic rules, based on the user feedback indicating the potential bottleneck station is not the bottleneck, to output a result that is consistent with the user feedback.

16 . The device of claim 14 , wherein the one or more processors are further configured to: train the pre-trained machine learning model based on the processing time, the waiting time, the cycle time of the potential bottleneck station, and the user feedback.

17 . The device of claim 13 , wherein the user feedback indicates that the potential bottleneck station is one of: an expected bottleneck and an unexpected bottleneck.

Assignees

• Bosch Gmbh Robert

Inventors

• Guo Jiajing
• Gou liang
• Kimport Samuel
• Ren Liu

Classifications

• G05B19/4183 Primary

  characterised by data acquisition, e.g. workpiece identification · CPC title