Multi-objective multi-mode resource-constrained project scheduling with fuzzy activity durations in prefabricated building construction

Different from traditional project management, the prefabricated building (PB) construction project has a complex distributed supply chain model, and the overall project is completed by multi-stage cooperation. Therefore, the implementation process will be restricted by many constraints, and various uncertain factors will also interfere with the smooth implementation of the project. In order to improve the stability and reliability of the PB construction project implementation process, it is very important to study an effective robust project scheduling method considering resource constraints in an uncertain environment. In this paper, we formulate a PB construction resource-constrained project scheduling with multi-objective multi-mode, focus on the uncertainty of the execution time of the execution activity, and constructs the interval value of the execution time to express it through fuzzy theory; also considers the multiple objectives of PB construction project, including time-based profit, and cost-based profit. Secondly, we propose a hybrid cooperative co-evolution algorithm (HCOEA) to obtain the highly robust project scheduling, reduce the impact of the uncertainty of the execution time of the activity on the overall project. Resource-constrained project scheduling problem (RCPSP) is an NP-hard combinatorial optimization problem. This paper also needs to consider the complex combination of time-resource and/or time-cost constraints. At the same time, it is necessary to consider the impact of time changes in different mode combinations. Therefore, how to design an effective multi-objective optimization algorithm is very difficult. This paper design a Hybrid Cooperative Co-evolution Algorithm (HCOEA) with multi-stage representation for the activity sequencing and the resource allocation, further improve the search efficiency. We improve the cooperative co-evolution framework with a self-adaptive mechanism and a self-adaptive selection process. Finally, benchmarks and extended datasets with fuzzy processing time are adopted to test our HCOEA. Computational results show that the HCOEA performs better than the existing state-of-the-art methods.