To satisfy the high-load bearing and high-temperature resistance requirements put forward by the increased power density of the cast iron cylinder head, the cast iron/GH4169 bimetal was manufactured by Powder Bed Fusion (PBF) in forward design. The performance of bimetals is simultaneously affected by different properties in several regions. Thus, a more comprehensive approach to evaluating bimetallic performance is urgently needed. This paper uses the Multi-Attribute-Decision-Making (MADM) method to evaluate the bondability and thermal fatigue resistance of the cast iron/GH4169 bimetal under different process parameters. Meanwhile, the shear test was used to verify the evaluation results of the bimetallic bondability. Furthermore, the matching relationship between process parameters and performance evaluation scores was established by combining the BP neural network to achieve the prediction of bimetallic thermal fatigue resistance. The results show that the evaluation results using the combination weighting method based on Game Theory (GT) were more accurate than those of the Analytic hierarchy process (AHP), Entropy method (EM), and combination weighting method based on average. The evaluation results of the interfacial bondability had a relatively high degree of congruence with the shear test results. It is feasible to use MADM to comprehensively evaluate the performance of the cast iron/GH4169 bimetal. Finally, the prediction model based on the BP neural network demonstrates good prediction capability. This study can provide research methods for evaluating and predicting the performance of bimetals to meet engineering needs in forward design.

中文翻译：

---

基于正向设计要求的增材制造铸铁/GH4169双金属综合性能评估与预测

为了满足铸铁缸盖功率密度增加所提出的高承载和耐高温要求，采用粉末床熔合（PBF）正向设计制造铸铁/GH4169双金属。双金属的性能同时受到多个区域的不同特性的影响。因此，迫切需要一种更全面的方法来评估双金属性能。本文采用多属性决策（MADM）方法评估铸铁/GH4169双金属在不同工艺参数下的粘结性和抗热疲劳性能。同时，通过剪切试验验证了双金属键合性能的评价结果​​。进一步结合BP神经网络建立工艺参数与性能评价分数的匹配关系，实现双金属抗热疲劳性能的预测。结果表明，基于博弈论（GT）的组合赋权法的评价结果​​比层次分析法（AHP）、熵值法（EM）和平均组合赋权法的评价结果​​更准确。界面结合性评价结果与剪切试验结果具有较高的一致性。利用MADM综合评价铸铁/GH4169双金属的性能是可行的。最后，基于BP神经网络的预测模型表现出了良好的预测能力。本研究可为评估和预测双金属性能提供研究方法，以满足正向设计中的工程需求。