22 December 2023 in IEEE Transactions on Computational Social Systems
As an emerging technology, the knowledge graph (KG) has been successfully applied in various industries. Though some potential benefits of the KG have been identified, there is still little work on implementing the KG in supply chain risk management (SCRM). This study develops a KG-based risk management framework to improve the resilience of Supply Chains (SCs). Specifically, the construction of the SC knowledge graph (SC-KG) framework, including the implementation steps, is presented in detail for the purpose of SC knowledge retrieval, data visualization analysis, risk monitoring, early warning, and decision support. Furthermore, the SC-KG is well constructed to build a scenario-based SCRM framework under consideration of the severity of disruptions. Especially during long-term disruptions, the continuity of SCs is maintained through the employment of a product change strategy and a structurally scalable and dynamically adapted network design method. The findings of the study are instructive for SC managers in adopting digital technologies for SC mitigation and recovery under disruptions. Finally, a practical SC-KG containing over 2.5 million entities and 11 types of relationships has been developed and its basic functions have been implemented, which contributes to improving the quality of SC management.
9 August 2023 in IEEE Transactions on Industrial Informatics
The product and its supply chain (SC) are two key parts of corporate competitiveness under mass production or customization. Nevertheless, they are frequently isolated in manufacturing field evolution. At the operational decision level, this article studies uncertainty processing in the coevolution of products and SCs using a measure-to-control supported approach. A decision system framework that can incorporate macrochange interactions between products and SCs is presented. From the systematic view on coevolution, an interface for measure and control of uncertainty propagation is provided, which has two potential benefits: 1) facilitating concurrent measures of risks with multiple causes and consequences; and 2) allowing control theory to tackle multiple dynamics and identify their interrelations. Specifically, via effective value and entropy rate measures of bullwhip effect and ripple effect, cost-guaranteed control methods are proposed for attenuating risks of the product-SC uncertainty system. Finally, a mask SC application verifies the robustness and resilience of the proposed approach.
28 January 2025 in International Journal of Production Economics
10 January 2025 in IEEE Transactions on Fuzzy Systems
Based on Petri nets (PNs), this paper tackles the problem of hybrid modeling and fuzzy control of supply chain networks (SCNs) under disruptions. First, a new fuzzy-based SCN operational model using delivery rate regulation experience is developed, which can be regarded as a fuzzy interconnected large-scale system. Then, a PN-based formal system approximation for continuous operational activities is performed, while visualizing discrete disruption events. As a result, the unified model of SCN hybrid dynamics is achieved via PNs, which has the potential advantage on facilitating the monitor of SCN changes in a general graphical and mathematical language. Furthermore, PN-based fuzzy control design criteria are derived via Lagrange and Lyapunov stability analysis on the hybrid markings. Finally, a hydrogen SCN case in the IEEE PJM 5-bus power system is provided to substantiate the effectiveness and benefits of the proposed methods.
16 December 2025 in International Journal of Production Economics
12 March 2025 in IEEE Transactions on Computational Social Systems
The bullwhip effect, driven by uncertain customer demands, often causes the supply chain network operation to deviate from the stationary level, i.e., the instability nonlinear operational dynamics. This article proposes a fuzzy-based bull-whip effect mitigation strategy to stabilize supply chain network operations, thereby assisting risk decision-making. First, a new fuzzy control model of the bullwhip effect is proposed. Compared with the existing benchmark models, the proposed model has two potential advantages. 1) It is more general to quantify operational and behavioral causes simultaneously rather than only one. 2) Proactively incorporating operational experience into the feedback has the potential to enhance control performance against bullwhip effect. Then, the studied system can be deemed as a closed-loop control system. Furthermore, a series of criteria are provided for the existence of fuzzy control strategies to stabilize the closed-loop system with the bullwhip effect reduction. Finally, simulations verify the advantages and effectiveness of proposed strategies.