在环境资源问题日益严峻的背景下，面向可持续制造的调度研究迫切而有意义。以多维目标寻优和多元任务组合优化为特征的可持续制造调度是对传统生产调度研究的拓展。本项目拟发挥多种智能算法的各自优势，并借助于工业大数据资源和技术，研究可持续制造调度中多维目标下的多元协同优化策略与方法。. 研究内容包括：构建基于经济-环境-社会三维目标协同的可持续优化目标和评测体系；提出级联式和并行式可持续调度任务的协同模式，并分别针对级联式资源配置-生产调度协同、并行式生产运行-设备运维协同，建立相应的协同优化策略方法；结合问题需求设计多种智能算法（如，机器学习、进化算法、人工智能等）的混合机制，形成数据驱动的混合智能调度优化算法，并进一步增强算法在复杂动态生产环境下的更新能力，提出数据驱动的适应性混合智能算法。从而为促进可持续制造调度的有效实施提供技术和方法支持。

Scheduling for sustainable manufacturing is an increasingly urgent and significant research issue due to environmental concerns, limited energy, diminishing non-renewable resources, etc. As an extension of the traditional production scheduling problem, sustainable manufacturing scheduling studies the multi-task collaborative optimization problem under multi-dimensional optimization objectives. This project intends to explore the collaborative optimization strategies and methods for sustainable manufacturing scheduling problems, by taking the advantages of hybrid intelligent algorithms, and supported by industrial big data as well as the big data analysis technologies.. The following aspects are the main contents of this research proposal. Firstly, to construct the system of sustainable optimization objectives and assessment criteria based on an economic-environmental-social three-dimensional collaborative framework. Secondly, to propose two kinds of general collaborative patterns, the cascaded collaborative pattern (CCP) and paralleled collaborative pattern (PCP), for sustainable scheduling. Then, to study collaborative optimization strategies and methods for two representative sustainable scheduling problems: the resource allocation - manufacturing scheduling collaborative optimization with CCP, and the production scheduling - equipment maintenance collaborative optimization with PCP. Thirdly, to design novel hybrid intelligent algorithms by merging various intelligent algorithms for these collaborative optimization problems. Furthermore, to propose big-data-based adaptive hybrid intelligent algorithms by enhancing the updating ability in complex dynamic manufacturing environments. The research results of this project are expected to provide technical and methodological support for the effective implementation of sustainable manufacturing scheduling.