期刊文献+

基于改进BiLSTM的多工序产品质量预测研究

Research on Multi-process Product Quality Prediction Based on Improved BiLSTM
下载PDF
导出
摘要 针对多工序产品制造过程的复杂性,为了解决多工序产品生产过程中影响产品质量问题的不确定因素,同时提高生产工序的生产能力,保证生产的稳定性,提出了一种基于核主成分分析和改进麻雀搜索算法优化BILSTM的多工序产品质量预测模型。利用KPCA对数据预处理,主成分分析的基础上结合核方法建立核函数,降维去除冗余特征,引入改进的高斯变异和均匀变异算子η改进麻雀搜索算法;将改进的麻雀搜索算法引入双向长短期记忆网络中,将降维处理后的数据导入ISSA-BiLSTM模型中实现多工序产品的质量预测;以TFT-LCD制造过程为例进行案例分析,并与现有方法比较分析。实验结果表明:该预测模型具有较好的预测精度,且均方根误差值小于10%,有效地提高了多工序产品质量的预测精度。 In response to the complex manufacturing process of multi-process products,a multi-process product quality prediction model based on the kernel principal component analysis(KPCA)-and improved sparrow search algorithm(ISSA)optimized bi-directional long short-term memory(BiLSTM)was proposed to address the uncertain factors that affect product quality,while improving the capacity for each process and ensuring the stability,in multi-process production.Firstly,KPCA was used for data preprocessing,and a kernel function was established on the basis of principal component analysis together with kernel methods.As redundant features were removed through dimension reduction,an improved Gaussian mutation and the uniform mutation operatorηwere introduced to improve the sparrow search algorithm.Secondly,the ISSA was introduced into the BiLSTM,and the dimensionality reduced data were imported into the ISSA-BiLSTM model to achieve the quality prediction of multi-process products.Finally,the TFT-LCD manufacturing process was analyzed as an example and compared with the existing methods.The experimental results show that the prediction model has a high prediction accuracy,with the root mean square error less than 10%,effectively improving the accuracy of multi-process product quality prediction.
作者 张天瑞 刘玉亭 王译可 Zhang Tianrui;Liu Yuting;Wang Yike(School of Mechanical Engineering,Shenyang University,Shenyang 110044,China)
出处 《系统仿真学报》 CAS CSCD 北大核心 2023年第11期2321-2332,共12页 Journal of System Simulation
基金 国家自然科学基金面上项目(52075088) 辽宁省研究生教育教学改革研究资助项目(LNYJG2022490)。
关键词 多工序产品 质量预测 KPCA ISSA BILSTM multi-process production quality prediction kernel principal component analysis(KPCA) improved sparrow search algorithm(ISSA) bi-directional long short-term memory(BiLSTM)
  • 相关文献

参考文献5

二级参考文献48

  • 1董春曦,饶鲜,杨绍全,徐松涛.支持向量机参数选择方法研究[J].系统工程与电子技术,2004,26(8):1117-1120. 被引量:65
  • 2邵信光,杨慧中,陈刚.基于粒子群优化算法的支持向量机参数选择及其应用[J].控制理论与应用,2006,23(5):740-743. 被引量:128
  • 3吕志军,杨建国,项前,王晓玲.基于支持向量机的纺纱质量预测模型研究[J].控制与决策,2007,22(6):693-696. 被引量:17
  • 4SCHNELLE K D, MAH R S H. Product quality management using a real-time expert system[J]. ISIJ International, 1994, 34(10): 815-821.
  • 5ZHOU S M. Combining dynamic neural networks and image sequences in a dynamic model for complex industrial production processes[J]. Expert Systems with Applications, 1999, 16(1): 13-19.
  • 6LU N, GAO F. Stage-based online quality control for batch processes[J]. Industrial & Engineering Chemistry Research, 2006, 45(7): 2272-2280.
  • 7WIDODO A, YANG B S. Support vector machine in machine condition monitoring and fault diagnosis[J]. Mechanical Systems and Signal Processing, 2007, 21 (6): 2560-2574.
  • 8WU Q, LAW R. The complex fuzzy system forecasting model based on fuzzy SVM with triangular fuzzy number input and output[J]. Expert Systems with Applications, 2011, 38(10): 12085-12093.
  • 9LI J, FREIHEIT T, HU S J, et al. A quality prediction framework for multistage machining processes driven by an engineering model and variation propagation model[J]. Journal of Manufacturing Science and Engineering, 2007, 129(6): 1088-1100.
  • 10ZHAO C, WANG F, MAO Z, et al. Quality prediction based on phase-specific average trajectory for batch processes[J]. AIChE Journal, 2008, 54(3): 693-705.

共引文献42

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部