عنوان انگلیسی مقاله:
A deep autoencoder feature learning method for process pattern recognition
ترجمه فارسی عنوان مقاله:
یک روش یادگیری خودکار ویژگی برجسته برای تشخیص الگوی فرایند
Sciencedirect - Elsevier - Journal of Process Control , 79 (2019) 1-15: doi:10:1016/j:jprocont:2019:05:002
Jianbo Yua,∗, Xiaoyun Zhenga, Shijin Wangb
tRecognition of various defect patterns exhibited in discrete manufacturing processes can significantlyreduce the diagnostic processes, and increase manufacturing process stability and quality. Thus the effec-tive recognizers are in great demand to improve the performance of process pattern recognition (PPR).Deep learning has been widely applied in image and visual analysis with great successes. However, theapplication of deep learning in feature learning for process control is still few. This paper presents aneffective and reliable deep learning method known as stacked denoising autoencoder (SDAE) for PPR inmanufacturing processes. This paper will concentrate on developing an SDAE model to learn effectivefeatures from the process signals and then implementing an effective PPR through a deep network archi-tecture. Feature visualization is also performed to explicitly present the feature representation of theproposed SDAE model. The effectiveness of the proposed PPR method is verified through a big simulationdataset and Tennessee Eastman process. The result shows that the proposed method obtains good featurelearning and PPR performance.
Keywords:Manufacturing processProcess | pattern recognition | Deep learning | Stacked denoising autoencoder | Feature learning