The present work proposes a fuzzy decision-making approach for the optimisation of the Laser Powder Bed Fusion (L-PBF) processing of AlSi10Mg alloy. First, a systematic approach based on Design of Experiment was adopted in order to identify and explain the effect of each operational parameter, i.e. volumetric energy density and building orientation, on the response variables, i.e. ultimate tensile strength, hardness and roughness. Then, a combined fuzzy-multi-objective genetic algorithm model was developed and tested in order to find the best input parameters’ combination able to satisfy the requirement of the highest mechanical performances. The use of a multi-objective optimisation based on genetic algorithm concerned the computation of optimal fuzzy numbers in order to take into account a precise percentage of experimental data for a given degree of membership, in combination with the smallest uncertainty level. Moreover, from the technological point of view, the proposed experimental results showed a similar and even improved mechanical properties of the alloy, if compared with the die casted one, except for the roughness. Finally, the fuzzy process maps generated allow to select the operational parameters in order to obtain the desired process output, in combination with the lowest uncertainty level, providing, as additional information, how much the accuracy of the model and the process varies by changing those operational parameters.

本工作提出了一种模糊决策方法，用于优化AlSi10Mg合金的激光粉末床熔合（L-PBF）工艺。首先，采用基于实验设计的系统方法来识别和解释每个操作参数（即体积能量密度和建筑物方向）对响应变量（即极限抗拉强度，硬度和粗糙度）的影响。然后，开发并测试了组合的模糊多目标遗传算法模型，以找到能够满足最高机械性能要求的最佳输入参数组合。基于遗传算法的多目标优化的使用涉及到最佳模糊数的计算，以便考虑给定隶属度的实验数据的精确百分比，并结合最小的不确定性级别。此外，从技术角度来看，所提议的实验结果表明，与压铸件相比，合金的机械性能与粗糙度相似，甚至更高。最后，生成的模糊过程图允许选择操作参数，以便获得所需的过程输出，同时结合最低的不确定性级别，作为附加信息，通过更改模型和过程的精度来改变模型和过程的精度。操作参数。结合最小的不确定性水平。此外，从技术角度来看，所提议的实验结果表明，与压铸件相比，合金的机械性能与粗糙度相似，甚至更高。最后，生成的模糊过程图允许选择操作参数，以便获得所需的过程输出，同时结合最低的不确定性级别，作为附加信息，通过更改模型和过程的精度来改变模型和过程的精度。操作参数。结合最小的不确定性水平。此外，从技术角度来看，所提议的实验结果表明，与压铸件相比，合金的机械性能与粗糙度相似，甚至更高。最后，生成的模糊过程图允许选择操作参数，以便获得所需的过程输出，同时结合最低的不确定性级别，作为附加信息，通过更改模型和过程的精度来改变模型和过程的精度。操作参数。