Aero engine is impacted by foreign objects frequently during daily use, including runway gravel, birds, fuselage components and so on, so the fan and compressor may damage, resulting in serious the air crash.It needs to simulate the impact of blades and establish the numerical analysis model of dynamic response.The damp-ing coefficient is one of the most important physical parameters of the blade structure and cannot be directly meas-ured.The damping ratio of the flat blade was obtained by BP neural network inversion method.Firstly, simulate twenty groups models with different damping ratio and obtain their amplitudes and decay time.Secondly, obtain the mapping relations of amplitudes, decay time with damping ratio by training a BP neural network.Thirdly, substi-tute the experimental amplitudes, decay time into the mapping relations and then calculate the damping ratio by in-version.Finally, the damping ratio is substituted into the other blade impact simulation with different parameters, and the results are consistent with the experimental data, which indicates that the damping ratio obtained by inver-sion are reasonable and reliable.%航空发动机在工作中容易受到外物撞击,包括跑道砂石、鸟体、机身零件等,对风扇和压气机造成损伤,导致机毁人亡的严重事故;故需要模拟外物撞击转子叶片,建立动态响应数值分析模型;其中阻尼系数是叶片振动分析最重要的物理参数之一;但其无法直接测量.研究采用BP神经网络反演的方法得到平板叶片阻尼比.先取二十组阻尼比的叶片撞击仿真模型中的振幅和衰减时间,通过训练BP神经网络理论得到振幅、衰减时间与阻尼比的映射关系,再将实验得到的真实振幅和衰减时间输入映射关系,反演出真实结构的阻尼比.最后将阻尼比代入另一组参数的叶片撞击仿真,与试验结果进行对比,两者一致性较高,表明反演得到的阻尼参数是合理可靠的.
展开▼
