A Dynamic Joint Production-Service Scheduling Approach by a Model-and-Data Driven Algorithm

Dynamic production and service scheduling are critical in manufacturing servitization. Unlike previous research assuming unrealistic specific mappings between products and services, this paper studies a more general and complex setting with a two-product-two-service mapping in a product service system, formulating it as a Markov Decision Process model. To solve this model with large-scale cases, designing a data-driven prediction algorithm is a common approach to overcome the curse of dimensionality. However, there might exist inconsistencies in the statistical distribution between the training and testing sets, as the training samples generated by the exact algorithm may not cover the entire state space. To tackle this problem, we propose a novel model-and-data-driven framework. We extract a service priority rule from the model as prior knowledge and embed it into the machine learning algorithm through tailored feature engineering. This strengthens prediction capabilities in unexplored state space regions compared to a purely data-driven approach. Numerical experiments validate our contributions, displaying the potential for embracing industrial automation and exploring the synergy effects for further exploration of the optimal structure as more effective prior knowledge. Note to Practitioners—Dynamic joint scheduling of production and service plays an important role in industrial automation. In this context, a wide range of studies are dedicated to developing efficient algorithms to meet the quick response requirement to tackle large-scale cases beyond the capability of exact algorithms. However, these studies often rely on unrealistic assumptions or have unsatisfactory computational performance, limiting potential cost reduction. To overcome this challenge, we relax unnecessary hypotheses and generalize the problem by allowing for a more generalized production-service mapping, which better reflects the reality. Apart from that, we integrate the prior knowledge into existing data to construct a more powerful approximation algorithm and enrich the prediction capability to accommodate the dynamic environment. With greater computation resources and data samples, the proposed algorithm achieves superior solutions. Furthermore, our research uncovers some key properties of the product service system, which could be leveraged to customize more effective automated scheduling rules.