Smart Supply Chain Management via Data Driven Optimization

点击翻译按钮获取中文摘要

With the advances of innovation technologies, such as internet of things, big data, cloud computing, AI, and blockchain, the real-time visibility and integration of supply chains are evolving to become more and more cost-effective, information-shared and environmental-aware. On another aspect, the different partners of supply chains face new challenges arising from the new manufacturing/business models, highly dynamic environments, and different risks from uncertainty to new techniques' application. Thus smart supply chains are to be studied that have the ability to connect the different partners, reconfigure and optimize the existing supply networks, and even have the intelligent capacity to plan, control and adjust the system to match the supply to demands in a real-time and effective way. In this proposed research, we will study the new challenges faced by supply chains under digital environments and new business models, develop a novel framework for smart supply chains via data driven hybrid optimization methods and other approaches. In details, we will work on the following: 1). Study the impacts and opportunities of new digital technologies (such as internet of things (IoT) and cloud service), and new business models (such as e-commerce and omnichannel) on modern supply chains. 2). Develop new concepts and methods for smart supply chain management: we will focus on some critical problems in the strategic, tactical and operational phases of supply chains and logistics management under a digital manufacturing/business environment, including strategic design of smarter supply networks under the IoT and uncertainty, tactical integrated decisions for production planning, procurement, distribution, and sales with digital technology, smart warehouse operation and management under IoT and omnichannel supply chains. 3). Develop data driven optimization models, methods and hybrid algorithms, i.e., studying how to combine data analysis/data driven methods with classical optimization methods to solve complex supply chain management problems. The integration of optimization method with machine learning will also be studied. 4). Work with our partners in automotive, medical, and food industries, solve the real-world supply chain problems under digital manufacturing/business environment, verify the proposed frame and new solution approaches, and make the effort for the transfer of the results from this research to the applicable industries.