Self-Supervised Long-Short Term Memory Network for Solving Complex Job Shop Scheduling Problem

doi:10.3837/tiis.2021.08.016

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where , , are the neural network parameters, with 0 indicating complete abandonment and 1 indicating complete retention, and finally by multiplying with the cell state , the result of which determines which information the cell state is to abandon (i.e. forget) [8].…”

Section: Long Short-term Memory Networkmentioning

confidence: 99%

See 1 more Smart Citation

On algorithms for JSSP based on hybrid graph neural network

Shi,

Chen

2023

Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023)

View full text Add to dashboard Cite

The Job-Shop Scheduling Problem (JSSP), one of the traditional scheduling issues in combinatorial optimization problems, has been the subject of much research for many years. In this study, to further take into account the influence of time sequence information on the operation between different processes, we develop a network architecture that combines graph neural networks and long short-term memory networks. We then train a policy network using proximal policy optimization to efficiently extract node features from JSSP disjunctive graphs and automate the learning of Priority Dispatch Rules (PDRs). The experimental results demonstrate that the proposed model for solving the JSSP problem has a high generalization performance and a global performance that is noticeably better than the current best PDRs, offering a useful approach for solving the JSSP problem.

show abstract

Section: Long Short-term Memory Networkmentioning

confidence: 99%

“…PPO is a DRL algorithm [8] for training an agent to learn and perform tasks in sophisticated environments. The central idea of the algorithm is to enable the training of intelligences by PPO so that the gap between the old and new strategies is smaller [9] .…”

Section: Proximal Policy Optimizationmentioning

confidence: 99%

On algorithms for JSSP based on hybrid graph neural network

Shi,

Chen

2023

Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023)

View full text Add to dashboard Cite

show abstract

“…Tian et al [24] use the long short-term memory network (LSTM) that can retain the features with time steps to predict the production information and use the improved GA to achieve the scheduling. Shao et al [25] also build a model based on LSTM named self-supervised long-short term memory (SS-LSTM), which can deal with dynamic events effectively, but the hyperparameters in SS-LSTM are difficult to determine. All the above-mentioned deep learning models either need one module to preprocess the input of the neural network or use other modules to process the output of the neural network to get the final scheduling plan, which may aggravate the errors between each module and lead to the suboptimal scheduling plan.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Deep Learning Method for Dynamic Job Shop Scheduling Problem

2022

View full text Add to dashboard Cite

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.

show abstract