论文部分内容阅读
硬岩掘进机优化设计过程中设计变量较多的问题,采用应力分布为设计变量,再通过反问题计算得到截割头来间接对截割头进行参数化;针对评价函数计算量太大的问题,根据试验设计理论安排训练样本,采用神经网络建立设计变量与目标函数间的复杂的响应关系,并且详细研究了径向基函数网络在对评价函数进行预测过程中的应用,建立了一种新的截割头优化设计方法。与传统的优化方法相比,其设计变量数目较少,利用此方法对硬岩掘进机截割头的能耗和效率进行优化,所得截割头破碎性能良好,从而验证了此方法的有效性。
Hard rock tunneling machine optimization design process more design variables, the use of stress distribution as a design variable, and then through the inverse problem to calculate the cutting head to indirectly parameterize the cutting head; for the evaluation function is too large , The training samples are arranged according to the experimental design theory, the neural network is used to establish the complex response relationship between the design variables and the objective function, and the application of the radial basis function network in the prediction process of the evaluation function is studied in detail. Cutting head optimization design method. Compared with the traditional optimization methods, the number of design variables is small. By using this method, the energy consumption and efficiency of the cutting head of the TBM are optimized. The obtained cutting head has good crushing performance, which verifies the effectiveness of this method .