论文部分内容阅读
采用一个神经网络估测器进行焊点力学性能无损在线分析。在此估测器中，经训练的神经元网络将用于描述动态电阻曲线与焊点力学性能的映射关系。试验结果证实了神经元网络用于这类应用场合的可行性和有效性。
Adopting a neural network estimator to perform non-destructive on-line analysis of mechanical properties of solder joints. In this estimator, a trained neural network will be used to describe the mapping of the dynamic resistance curve to the mechanical properties of the weld. The experimental results confirm the feasibility and effectiveness of neural networks for such applications.