融合点阵拓扑优化法和熵权法的铲运机外观设计

Appearance design of LHDs based on lattice topology optimization method and EWM

为更好地指导矿山开采大型机械设备的创新设计,归纳铲运机外观特点,提出点阵拓扑优化法和熵权法(EWM)设计、评估铲运机外观。首先,通过点阵拓扑优化法设计铲运机外观,使用层次分析法-熵权法(AHP-EWM)对评价指标赋权,搭建层次准则模型;其次,通过调研归纳出创造性指标、美学指标、功能性指标、经济性指标、技术性指标5个指标并建立评价体系;然后,运用层次分析法(AHP)对一级指标主观赋权,通过EWM分析二级指标的客观权重,依据python计算灰色关联度、多属性决策分析权重(CRITIC)、独立性权重、模糊综合评价法和逼近理想解排序法、理想点法(TOPSIS法)5种方法的权重,通过对比分析并验证AHP-EWM的可行性;最后,基于指标权重与方案得分优化备选方案设计,并使用最小支持向量机(LSSVM)来验证模型。结果表明:使用LSSVM模型进行回归分析,其决定系数达到0.93以上,均方误差在0.01以内,明显优于传统模型且精度较高,验证点阵拓扑优化法和EWM相结合的优化决策模型。

To facilitate the innovative design of large-scale mining machinery,the external characteristics of LHDs were summarized.Additionally,a lattice topology optimization method and EWM were proposed for designing and evaluating the appearance of LHDs.The lattice topology optimization method was used to refine the appearance of the LHD.Subsequently,the analytic hierarchy process-EWM(AHP-EWM)was employed to assign weights to the evaluation indicators and construct the hierarchical criterion model.Five indicators,namely creativity,aesthetics,functionality,economic viability,and technical ability,were identified to constitute the evaluation system.The AHP was used to assign subjective weights to first-level indicators,and the objective weights of second-level indicators were analyzed by EWM.According to python,the weights of five methods,namely grey relational degree,multi-attribute decision analysis weight(CRITIC),independence weight,fuzzy comprehensive evaluation method,approximate ideal solution sorting method,and ideal point method(TOPSIS),were calculated.The feasibility of the AHP-EWM method was demonstrated.Finally,alternative designs were optimized based on the indicator weights and their corresponding scores,and the least squares support vector machine(LSSVM)was used to validate the model.The results show that the LSSVM model achieves a coefficient of determination above 0.93 and a mean square error below 0.01 in regression analysis.It outperforms traditional models with higher accuracy,confirming the effectiveness of the optimization decision model combining the lattice topology optimization method and EWM.