论文部分内容阅读
建立组合遗传神经网络,并建立刮板机焊点疲劳寿命与各种影响因素之间的映射关系,通过该映射关系能大大降低对于类似研究刮板机焊点疲劳寿命的计算工作量。利用该网络模型对不同工艺参数下焊点的疲劳寿命进行预测,预测值和实验值比较表明,预测数据与实验数据吻合良好,验证了所提方法的优越性,为刮板机焊点的疲劳寿命研究提出一种新方法。
The combined genetic neural network is established and the relationship between the fatigue life of the scraper pad and various influencing factors is established. Through this mapping relationship, the computational workload on the fatigue life of the similar scraper welding machine can be greatly reduced. The network model was used to predict the fatigue life of solder joints under different process parameters. The comparison between predicted and experimental values shows that the predicted data are in good agreement with the experimental data, which verifies the superiority of the proposed method. Life-long research proposes a new method.