An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem
Job shop scheduling problem (JSSP) is essential in the production, which can significantly improve production efficiency. Dynamic events such as machine breakdown and job rework frequently occur in smart manufacturing, making the dynamic job shop scheduling problem (DJSSP) methods urgently needed. E...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/10/7/573 |
| _version_ | 1827618868755955712 |
|---|---|
| author | Shifan Chen Zuyi Huang Hongfei Guo |
| author_facet | Shifan Chen Zuyi Huang Hongfei Guo |
| author_sort | Shifan Chen |
| collection | DOAJ |
| description | Job shop scheduling problem (JSSP) is essential in the production, which can significantly improve production efficiency. Dynamic events such as machine breakdown and job rework frequently occur in smart manufacturing, making the dynamic job shop scheduling problem (DJSSP) methods urgently needed. Existing rule-based and meta-heuristic methods cannot cope with dynamic events in DJSSPs of different sizes in real time. This paper proposes an end-to-end transformer-based deep learning method named spatial pyramid pooling-based transformer (SPP-Transformer), which shows strong generalizability and can be applied to different-sized DJSSPs. The feature extraction module extracts the production environment features that are further compressed into fixed-length vectors by the feature compression module. Then, the action selection module selects the simple priority rule in real time. The experimental results show that the makespan of SPP-Transformer is 11.67% smaller than the average makespan of dispatching rules, meta-heuristic methods, and RL methods, proving that SPP-Transformer realizes effective dynamic scheduling without training different models for different DJSSPs. To the best of our knowledge, SPP-Transformer is the first application of an end-to-end transformer in DJSSP, which not only improves the productivity of industrial scheduling but also provides a paradigm for future research on deep learning in DJSSP. |
| first_indexed | 2024-03-09T10:15:27Z |
| format | Article |
| id | doaj.art-6f079465a37344b9b621020a7747566c |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-09T10:15:27Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-6f079465a37344b9b621020a7747566c2023-12-01T22:23:33ZengMDPI AGMachines2075-17022022-07-0110757310.3390/machines10070573An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling ProblemShifan Chen0Zuyi Huang1Hongfei Guo2School of Intelligent Systems Science and Engineering, Jinan University, Zhuhai 519070, ChinaSchool of Intelligent Systems Science and Engineering, Jinan University, Zhuhai 519070, ChinaSchool of Intelligent Systems Science and Engineering, Jinan University, Zhuhai 519070, ChinaJob shop scheduling problem (JSSP) is essential in the production, which can significantly improve production efficiency. Dynamic events such as machine breakdown and job rework frequently occur in smart manufacturing, making the dynamic job shop scheduling problem (DJSSP) methods urgently needed. Existing rule-based and meta-heuristic methods cannot cope with dynamic events in DJSSPs of different sizes in real time. This paper proposes an end-to-end transformer-based deep learning method named spatial pyramid pooling-based transformer (SPP-Transformer), which shows strong generalizability and can be applied to different-sized DJSSPs. The feature extraction module extracts the production environment features that are further compressed into fixed-length vectors by the feature compression module. Then, the action selection module selects the simple priority rule in real time. The experimental results show that the makespan of SPP-Transformer is 11.67% smaller than the average makespan of dispatching rules, meta-heuristic methods, and RL methods, proving that SPP-Transformer realizes effective dynamic scheduling without training different models for different DJSSPs. To the best of our knowledge, SPP-Transformer is the first application of an end-to-end transformer in DJSSP, which not only improves the productivity of industrial scheduling but also provides a paradigm for future research on deep learning in DJSSP.https://www.mdpi.com/2075-1702/10/7/573smart manufacturingdynamic job shop scheduling problemdeep learningtransformerspatial pyramid poolinggeneralization |
| spellingShingle | Shifan Chen Zuyi Huang Hongfei Guo An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem Machines smart manufacturing dynamic job shop scheduling problem deep learning transformer spatial pyramid pooling generalization |
| title | An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem |
| title_full | An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem |
| title_fullStr | An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem |
| title_full_unstemmed | An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem |
| title_short | An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem |
| title_sort | end to end deep learning method for dynamic job shop scheduling problem |
| topic | smart manufacturing dynamic job shop scheduling problem deep learning transformer spatial pyramid pooling generalization |
| url | https://www.mdpi.com/2075-1702/10/7/573 |
| work_keys_str_mv | AT shifanchen anendtoenddeeplearningmethodfordynamicjobshopschedulingproblem AT zuyihuang anendtoenddeeplearningmethodfordynamicjobshopschedulingproblem AT hongfeiguo anendtoenddeeplearningmethodfordynamicjobshopschedulingproblem AT shifanchen endtoenddeeplearningmethodfordynamicjobshopschedulingproblem AT zuyihuang endtoenddeeplearningmethodfordynamicjobshopschedulingproblem AT hongfeiguo endtoenddeeplearningmethodfordynamicjobshopschedulingproblem |