An integrated spatial-temporal neural network for proactive throughput bottleneck prediction in high-variety shops with complex job routings

Throughput bottlenecks remain a main concern for managers in practice since they affect production output and throughput times. A large literature on bottleneck detection and prediction consequently emerged. Bottleneck prediction is specifically important in context where bottlenecks shift since it allows for counteracting the potential impact. The literature on throughput bottleneck prediction largely focusses on temporal aspects. Although this reflects the relation among stations if the routing of jobs is fairly directed, the relative station position constantly changes for more complex routings. A station maybe upstream, downstream or have no relation to another station dependent on the mix of jobs currently on the shop floor. In these high-variety contexts, both temporal and spatial features should be considered when predicting bottlenecks. In response, this study proposes a new neural network model that systematically connects multiple independent workstations into a system by extracting the spatial features between workstations. The new approach is different from traditional stacking mechanisms applied in the literature, and it allows for a better integration of spatial and temporal neural networks. Experimental results show that the proposed model outperforms alternative models and provides good prediction performance. Findings have important implications for research and practice.