The Setting Approach for R eflow Soldering Parameter Based on the Improved ANN-GA
-
摘要: 针对回流焊工艺过程中输入参数难以设定的问题,对多重质量特征值间非线性映射关系进行分析,提出一种基于改进遗传算法的输入参数设定方法。采用实数编码形式,直接表达了各基因表示的意义。应用改进的遗传算子和染色体重启机制,提高了搜索准确程度,避免了早熟现象和陷入局部最优的可能。再结合神经网络预测方案建立完整的参数设置与生产预测模型。以某公司实际生产数据为例,MAPE评估显示预设参数满足企业生产误差精度要求,因此所提出的设定方法可以有效地进行回流焊生产,为企业回流焊生产工艺规划提供指导。Abstract: Currently, experiment plays the prime method in soldering reflow profile forecasting. The prime difficul-ty in reflow processing is input parameters setting. According to the nonlinear relationship between the multi input and output, an improved genetic algorithm (GA)-based input parameters setting method is proposed. R eal-coding form expressed each gene's significances directly. Usage of improved genetic operators and chromosome restart mechanism avoids the premature phenomenon and possibility of fell into a local optimum, and improves search ac-curacy as well. The genetic operation combined with neural network prediction program built the complete parame-ter settings and production forecasting model. MAPE(mean absolute percentage error) assessment is carried to compare GA prediction and the production data of a company. R esult shows that predicted error meets the required precision. In conclusion, BP neural network is effective and efficient in reflow profile prediction.
-
Key words:
- backpropaogation /
- chromosomes /
- genes /
- efficiency /
- errors
-
[1] Sarvar F，Conway P P．Effective modeling of the reflow soldering process: basis，construction，and operation of a process model [A]. IEEE Transactions in Components，Packaging，and Manufacturing Technology-part C[C]，1998，21(2) [2] Amir D．Establishing control of the solder reflow process[J]．Electronic Packaging and Production，1998，38(7):84～90 [3] Tsung-nan Tsai．Development of an integrated reflow soldering control system using increment-tal hybrid process knowledge[J]．Expert Systems with Applications，2005，(28):681～692 [4] 郭瑜，孙志礼，潘尔顺，杨强．基于改进神经网络的 SMT 回流 焊温度曲线预测[J]. 东北大学学报(自然科学版)，2011，32 (12):1749～1752 [5] 杜轩，李宗斌，贾晓晨．基于遗传算法的复合式贴片机贴装过 程优化[J]. 西安交通大学学报，2009，43(5): 80～84 [6] Cang T，Pan Er-shun，Zhang M X．Optimization study of reflow soldering profile for surface mount technology[A]．Proceedings of 2011 International Conference on Computer Science and Network Technology[C]，ICCSNT 2011，2011，(3):1772～1775 [7] 张超群，郑建国，钱洁．遗传算法编码方案比较[J]. 计算机应 用研究，2011，28(3):819～822 [8] 杨成文，张铁．基于遗传算法的串联机械手驱动系统减速比 优化[J]．机械科学与技术，2012，31(5):842～846(850) [9] 韩旭炤，黄玉美，陈纯，张永贵，杨新刚．基于遗传算法的平面 运动并联机构尺度综合[J]. 机械科学与技术，2010，29(1): 54～58 [10] 周俊虎，沈彬彬，陈寅彪等．基于遗传算法的动力配煤方案的 Boltzmann 优化模型的研究[J]. 动力工程，2003，23(4):2598～2602 -
点击查看大图
计量
- 文章访问数: 305
- HTML全文浏览量: 36
- PDF下载量: 6
- 被引次数: 0
下载:
