A task allocation optimization model in mechanical product development was proposed. First, Bayesian network was introduced and used to describe quality characteristic (QC) relations of mechanical products. The quality characteristic importance was then analyzed based on the Bayesian network. Weights were assigned to QCs according to the QCs importance. QCs are generally manufactured by different types of manufacturing resources, such as machine tools, cutting tools, measuring tools, and fixtures. For convenience, these manufacturing resources were encapsulated as manufacturing cells. QCs were considered as tasks to be completed by manufacturing cells. Numerous tasks and manufacturing cells were involved in mechanical product development; therefore, the core problem was to allocate these tasks to manufacturing cells in an optimal way to achieve better product quality. Time and cost were considered as the main constraints. The ant colony algorithm was used to solve the task allocation optimization problem. A numerical case study was also presented to indicate the effectiveness of the proposed model.

提出了机械产品开发中的任务分配优化模型。首先，贝叶斯网络被引入并用于描述机械产品的质量特性（QC）关系。然后基于贝叶斯网络分析了质量特征的重要性。根据质量控制的重要性将权重分配给质量控制。质量控制通常由不同类型的制造资源制造，例如机床，切削工具，测量工具和固定装置。为了方便起见，将这些制造资源封装为制造单元。质量控制被认为是制造单元要完成的任务。机械产品开发涉及许多任务和制造部门。所以，核心问题是以最佳方式将这些任务分配给制造单元，以实现更好的产品质量。时间和成本被认为是主要的制约因素。蚁群算法用于解决任务分配优化问题。还进行了数值案例研究，以表明所提出模型的有效性。