A Two-Layer Long Short-Term Memory Network for Bottleneck Prediction in Multi-Job Manufacturing Systems

Throughput bottlenecks define and constrain the productivity of a production line. Prediction of future bottlenecks provides a great support for decision-making on the factory floor, which can help to foresee and formulate appropriate actions before production to improve the system throughput in a cost-effective manner. Bottleneck prediction remains a challenging task in literature. The difficulty lies in the complex dynamics of manufacturing systems. There are multiple factors collaboratively affecting bottleneck conditions, such as machine performance, machine degradation, line structure, operator skill level, and product release schedules. These factors impact on one another in a nonlinear manner and exhibit long-term temporal dependencies. State-of-the-art research utilizes various assumptions to simplify the modeling by reducing the input dimensionality. As a result, those models cannot accurately reflect complex dynamics of the bottleneck in a manufacturing system. To tackle this problem, this paper will propose a systematic framework to design a two-layer Long Short-Term Memory (LSTM) network tailored to the dynamic bottleneck prediction problem in multi-job manufacturing systems. This neural network based approach takes advantage of historical high dimensional factory floor data to predict system bottlenecks dynamically considering the future production planning inputs. The model is demonstrated with data from an automotive underbody assembly line. The result shows that the proposed method can achieve higher prediction accuracy compared with current state-of-the-art approaches.