Prediction of Remaining Execution Time of Business Processes With Multiperson Collaboration in Assembly Line Production

The prediction of remaining execution time is a critical area of research in business process monitoring. However, limited data availability and deficiencies in existing models have hindered progress in this area. To address these challenges, we introduce two production log datasets, coarse-grained log for television (CGL-TV) and fine-grained log for television (FGL-TV), collected from a semiautomated assembly line for television manufacturing. These datasets aim to address the issue of data scarcity in monitoring, analyzing, and optimizing the manufacturing process. Then, we investigate the significance of role information in semiautomated production processes and propose a novel feature selection strategy. That strategy replaces the traditional activity attributes with role attributes as the basis for prediction, resulting in a significant improvement in prediction accuracy. Furthermore, existing recurrent neural network (RNN)-based prediction methods have two major drawbacks: limited ability to capture long-term dependencies and the inability to parallelize computations. To address these issues, we propose a novel transformer-based remaining time prediction (TRTP) model. This model utilizes the self-attention mechanism instead of hidden state passing, which effectively incorporates global contextual information and enables potential parallel computing. The experimental results across four datasets demonstrate that our proposed method achieves state-of-the-art performance, e.g., a 5.2% performance gain on FGL-TV.