Product quality prediction model based on generative adversarial network and hard case mining
李剑锋 1柏雪 1赵春财 2钱朋超 2王洪涛 1徐伟风3
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 中国计量大学经济与管理学院,浙江 杭州 310018
2. 新凤鸣集团研究院质量管理部,浙江 桐乡 314513
3. 杭州古珀医疗科技有限公司研发中心,浙江 杭州 311200
折叠
摘要
针对连续性工业生产特点,重点关注类别不平衡造成的不合格样本召回率低问题.为了从高维数据提取有效特征,结合one class F-score和最小冗余最大相关性在特征提取方面的优势,有效降低特征维度并提取有价值特征;利用Wasserstein生成对抗网络(WGAN)方法扩增不合格样本数量;通过类别权重优化Focal Loss函数以提高困难样本识别率;通过轻量级梯度提升机算法结合阈值移动策略,构建基于WGAN数据增强和难例挖掘技术的质量预测模型(WGAN_Focal Loss_LGB(TM)).将所提模型应用于开源SECOM数据集,验证了所提方法的有效性.
Abstract
According to the characteristics of process industries,the issue of low recall in identifying defective prod-ucts caused by imbalanced class was addressed.To extract effective features from high-dimensional data,the advan-tages of one class F-score and mRMR in feature extraction were combined to effectively reduce the feature dimension and extract valuable features.Then,the Wasserstein Generative Adversarial Network(WGAN)algorithm was em-ployed to augment the quantity of defective product.Subsequently,the focal loss function was optimized with class weights to enhance the recognition rate of hard case.Furthermore,leveraging the LightGBM algorithm in conjunction with a threshold movement strategy,a quality prediction model was constructed based on WGAN and hard case mining techniques.Finally,the proposed model was applied to the open-source SECOM dataset,and the result indicated that the presented approach effectively enhanced the recall rate of defective products while maintai-ning overall accuracy,which provided a scientific and practical method for in-depth exploration of the intricate map-ping relationship between critical production factors and product quality,as well as facilitating intelligent quality prediction efforts.
维普
万方数据