The current popular methods for decision making and project optimisation in mine ventilation contain a number of deficiencies as they are solely based on either subjective knowledge or objective information.This paper...The current popular methods for decision making and project optimisation in mine ventilation contain a number of deficiencies as they are solely based on either subjective knowledge or objective information.This paper presents a new approach to rank the alternatives by G1-coefficient of variation method.The focus of this approach is the use of the combination weighing,which is able to compensate for the deficiencies in the method of evaluation index single weighing.In the case study,an appropriate evaluation index system was established to determine the evaluation value of each ventilation mode.Then the proposed approach was used to select the best development face ventilation mode.The result shows that the proposed approach is able to rank the alternative development face ventilation mode reasonably,the combination weighing method had the advantages of both subjective and objective weighing methods in that it took into consideration of both the experience and wisdom of experts,and the new changes in objective conditions.This approach provides a more reasonable and reliable procedure to analyse and evaluate different ventilation modes.展开更多
随着功率模块集成化程度的提高,其散热结构优化已成为研发中的关键。拓扑优化可通过变换散热器形貌、结构来最大化地提升散热效果,因此受到了广泛关注。但在拓扑优化过程中,每步迭代均需要计算模块与散热器温度分布,占用较庞大的计算资...随着功率模块集成化程度的提高,其散热结构优化已成为研发中的关键。拓扑优化可通过变换散热器形貌、结构来最大化地提升散热效果,因此受到了广泛关注。但在拓扑优化过程中,每步迭代均需要计算模块与散热器温度分布,占用较庞大的计算资源和计算时间。为加速传统散热器拓扑优化进程,在基于传统固体各向同性材料惩罚SIMP(solid isotropic material with penalization)散热器拓扑优化方法的基础上,提出一种嵌套神经网络NN(neural network)同步学习的快速迭代方法。首先,构建散热器基于编码器-解码器结构的NN预测模型,即基于散热器形貌迭代进化过程实现优化结构的快速预测;其次,将NN模型与散热器SIMP拓扑优化流程相嵌套,利用迭代过程中的中间形貌同步训练NN;最后,针对单芯片、两芯片模块结构,对比所提方法与传统迭代方法的拓扑优化结果,验证了所提NN同步学习方法的准确性和快速性。展开更多
基金Projects(51504286,51374242)supported by the National Natural Science Foundation of ChinaProject(2015M572270)supported by China Postdoctoral Science FoundationProject(2015RS4004)supported by the Science and Technology Plan of Hunan Province,China
文摘The current popular methods for decision making and project optimisation in mine ventilation contain a number of deficiencies as they are solely based on either subjective knowledge or objective information.This paper presents a new approach to rank the alternatives by G1-coefficient of variation method.The focus of this approach is the use of the combination weighing,which is able to compensate for the deficiencies in the method of evaluation index single weighing.In the case study,an appropriate evaluation index system was established to determine the evaluation value of each ventilation mode.Then the proposed approach was used to select the best development face ventilation mode.The result shows that the proposed approach is able to rank the alternative development face ventilation mode reasonably,the combination weighing method had the advantages of both subjective and objective weighing methods in that it took into consideration of both the experience and wisdom of experts,and the new changes in objective conditions.This approach provides a more reasonable and reliable procedure to analyse and evaluate different ventilation modes.
文摘随着功率模块集成化程度的提高,其散热结构优化已成为研发中的关键。拓扑优化可通过变换散热器形貌、结构来最大化地提升散热效果,因此受到了广泛关注。但在拓扑优化过程中,每步迭代均需要计算模块与散热器温度分布,占用较庞大的计算资源和计算时间。为加速传统散热器拓扑优化进程,在基于传统固体各向同性材料惩罚SIMP(solid isotropic material with penalization)散热器拓扑优化方法的基础上,提出一种嵌套神经网络NN(neural network)同步学习的快速迭代方法。首先,构建散热器基于编码器-解码器结构的NN预测模型,即基于散热器形貌迭代进化过程实现优化结构的快速预测;其次,将NN模型与散热器SIMP拓扑优化流程相嵌套,利用迭代过程中的中间形貌同步训练NN;最后,针对单芯片、两芯片模块结构,对比所提方法与传统迭代方法的拓扑优化结果,验证了所提NN同步学习方法的准确性和快速性。
