Discrete Workshop Production Bottleneck Prediction with CNN-LSTM Spatio-temporal Network Integrated with Dual Attention Mechanism

TY - JOUR

T1 - Discrete Workshop Production Bottleneck Prediction with CNN-LSTM Spatio-temporal Network Integrated with Dual Attention Mechanism

AU - Shi, Yihan

AU - Zhang, Xu

AU - Zhuang, Cunbo

AU - Liu, Jinshan

AU - Wang, Jiaxiu

AU - Sun, Liansheng

N1 - Publisher Copyright: © 2026, Chinese Mechanical Engineering Society. All rights reserved.

PY - 2026/3/5

Y1 - 2026/3/5

N2 - In the assembly pull production mode, the discrete manufacturing workshop, which is characterized by decentralized production tasks, flexible equipment layout, and complex processes, serves as the core carrier of the multi-factory(shop) production mode. However, the dynamic drift of bottleneck units in both temporal and spatial dimensions has become a critical challenge that limits the improvement of production efficiency and resource utilization. Thus, investigating the bottleneck prediction problem in discrete workshops is crucial for enhancing overall production efficiency in multi-factory settings. To address this, a spatiotemporal network prediction model integrating dual attention mechanisms, CNN-LSTM-DAM (Convolutional neural network-long short term memory-dual attention mechanism), is proposed. First, a composite definition-based bottleneck identification model is constructed, considering the multi-attribute coupling of bottleneck units. Second, the identified historical quasi-bottleneck data are input into the spatial feature perceiver integrated with CNN and spatial attention mechanism, as well as the temporal feature perceiver integrated with LSTM and state attention mechanism, as auxiliary data to further enhance the model's ability to capture spatial and temporal information in production sequence data. Finally, through ablation experiments, the proposed model is compared with other LSTM variants, such as gated recurrent unit (GRU) and bidirectional long short term memory (BiLSTM). The results verify the model's accuracy and effectiveness in predicting bottleneck units and their drift trends within a given time delay.

AB - In the assembly pull production mode, the discrete manufacturing workshop, which is characterized by decentralized production tasks, flexible equipment layout, and complex processes, serves as the core carrier of the multi-factory(shop) production mode. However, the dynamic drift of bottleneck units in both temporal and spatial dimensions has become a critical challenge that limits the improvement of production efficiency and resource utilization. Thus, investigating the bottleneck prediction problem in discrete workshops is crucial for enhancing overall production efficiency in multi-factory settings. To address this, a spatiotemporal network prediction model integrating dual attention mechanisms, CNN-LSTM-DAM (Convolutional neural network-long short term memory-dual attention mechanism), is proposed. First, a composite definition-based bottleneck identification model is constructed, considering the multi-attribute coupling of bottleneck units. Second, the identified historical quasi-bottleneck data are input into the spatial feature perceiver integrated with CNN and spatial attention mechanism, as well as the temporal feature perceiver integrated with LSTM and state attention mechanism, as auxiliary data to further enhance the model's ability to capture spatial and temporal information in production sequence data. Finally, through ablation experiments, the proposed model is compared with other LSTM variants, such as gated recurrent unit (GRU) and bidirectional long short term memory (BiLSTM). The results verify the model's accuracy and effectiveness in predicting bottleneck units and their drift trends within a given time delay.

KW - CNN-LSTM

KW - bottleneck prediction

KW - dual attention mechanism

KW - multi-attribute bottleneck

KW - multi-step time series forecasting

UR - https://www.scopus.com/pages/publications/105036639088

U2 - 10.3901/JME.260227

DO - 10.3901/JME.260227

M3 - Article

AN - SCOPUS:105036639088

SN - 0577-6686

VL - 62

JO - Jixie Gongcheng Xuebao/Chinese Journal of Mechanical Engineering

JF - Jixie Gongcheng Xuebao/Chinese Journal of Mechanical Engineering

IS - 5

ER -