進行波型測試測量的錯誤檢查是確保電子產品達到標準的關鍵步驟。然而，這是一個耗時的過程，特別是在大規模生產環境中。對於異常檢測，此實驗方法可以對圖像進行修正，將其通過模型進行運算，輸出去除異常的圖像，然後將其與原圖進行比較，根據差異的大小來判定原圖是否為異常訊號。
在此次實驗中，提出了一種深度學習方法。該方法通過設計一種名為轉換修正 U-net 的模型來進行波型測量的異常檢測，以加速檢查過程。實驗中開發的轉換模型將會操作相關訊號通過相互轉換來生成波型，從而克服了輸入訊號直接通過skip connect被複製的問題。修正模型則利用一種循環機制來精煉和修正生成的波型。
為了建立時間軸上相鄰像素之間的連接，此研究會將長短期記憶（LSTM）整合到 U-net 架構中，使得序列訊息能夠被納入生成模型。這種方法提高了波型圖測試測量的效率，還能夠大幅地降低參數量，做到輕量化的結果，通過自動化檢查程序並降低檢查時間。這種創新的方法將有助於提升電子產品的品質標準，並為未來的研究提供了新的方向。

This research introduces a deep learning method that expedites the inspection process by designing a model called “Conversion Correction U-Net” for waveform measurement anomaly detection. This method generates waveforms through mutual transformation, overcoming the issue of input signals being directly copied via skip connections. Long Short-Term Memory (LSTM) is incorporated into the U-net architecture, allowing sequence information to be included in the generative model. This approach not only enhances the efficiency of waveform testing measurements but also significantly reduces the number of parameters, achieving lightweight results, automating the inspection process, and cutting down inspection time. This innovative method will help elevate the quality standards of electronic products and provide new directions for future research.

[1] Kihyun Choi, Hyun Chul Sagong, Minjung Jin, Jiang Hai, Miji Lee, Taeyoung Jeong, Myung Soo Yeo, Hyewon Shim, Da Ahn, Wooyeon Kim, Yongjeung Kim, JuneKyun Park, Hwasung Rhee, Euncheol Lee, "Reliability on Evolutionary FinFET CMOS Technology and Beyond," in IEEE International Electron Devices Meeting (IEDM), 2020, pp. 9.3.1-9.3.4.
[2] Kyungmee O. Kim, Ming J. Zuo, Way Kuo, "On the relationship of semiconductor yield and reliability," IEEE Transactions on Semiconductor Manufacturing, vol. 18, no. 3, pp. 422-429, 2005.
[3] Ian Hill, Parvez Chanawala, Rohit Singh, S. Arash Sheikholeslam, André Ivanov, , "CMOS Reliability From Past to Future: A Survey of Requirements, Trends, and Prediction Methods," IEEE Transactions on Device and Materials Reliability, vol. 22, no. 1, pp. 1-18, 2022.
[4] M. Kang, M. Chang, Y. Park, C. Noh, S. H. Hong, B. Park, Y. H Park, Y.C Jung, W.S. Lim, G.H. Kim, Y. Lee, H. Yang, D. Shin, J. G. Yang, K. H. Cho, W. C. Jeong, H.-J Cho, W. H. Kwon, D.W. Kim, K. Rim, J. H. Song, "Device Design and Reliability of GAA MBCFET," in IEEE International Reliability Physics Symposium (IRPS), 2024, pp. 1-6.
[5] Zesheng Shen, Siyi Jing, Yiyuan Heng, Yifan Yao, K. N. Tu, Yingxia Liu, "Electromigration in three-dimensional integrated circuits," Applied Physics Reviews, vol. 10, no. 2, 2023.
[6] Huimei Zhou, Miaomiao Wang, Ernest Wu, "Challenges of Gate Stack TDDB in Gate-All-Around Nanosheet Towards Further Scaling," in IEEE International Reliability Physics Symposium (IRPS), 2024, pp. 2A.1-1-2A.1-6.
[7] T. Nigam, P. Paliwoda, X. Wang, A. Kerber, "Addressing reliability challenges in advance nodes for commercial and automotive application," in IEEE International Electron Devices Meeting (IEDM), 2019, pp. 21.1.1-21.1.4.
[8] Sudipta Khan, Pradyut Sarkar, "A Comprehensive Review of Machine Learning Applications in VLSI Testing: Unveiling the Future of Semiconductor Manufacturing," in International Conference on Electronics,Materials Engineering & Nano-Technology (IEMENTech), 2023, pp. 1-5.
[9] Lina Zhou, Shimei Pan, Jianwu Wang, Athanasios V. Vasilakos, "Machine learning on big data: Opportunities and challenges," Neurocomputing, vol. 237, pp. 350-361, 2017.
[10] Guansong Pang, Chunhua Shen, Longbing Cao, Anton Van Den Hengel, "Deep Learning for Anomaly Detection: A Review," ACM Comput. Surv., vol. 54, no. 2, p. Article 38, 2021.
[11] Xun Xu, Yuqian Lu, Birgit Vogel-Heuser, Lihui Wang, "Industry 4.0 and Industry 5.0—Inception, conception and perception," Journal of Manufacturing Systems, vol. 61, pp. 530-535, 2021.
[12] Héctor Cañas, Josefa Mula, Manuel Díaz-Madroñero, Francisco Campuzano-Bolarín, "Implementing Industry 4.0 principles," Computers & Industrial Engineering, vol. 158, p. 107379, 2021.
[13] Ricardo Silva Peres, Xiaodong Jia, Jay Lee, Keyi Sun, Armando Walter Colombo, Jose Barata, "Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook," IEEE Access, vol. 8, pp. 220121-220139, 2020.
[14] Imran Ahmed, Gwanggil Jeon, Francesco Piccialli, "From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where," IEEE Transactions on Industrial Informatics, vol. 18, no. 8, pp. 5031-5042, 2022.
[15] Xian Tao, Xinyi Gong, Xin Zhang, Shaohua Yan, Chandranath Adak, "Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-21, 2022.
[16] Yi Yan, Deming Wang, Guangliang Zhou, Qijun Chen, "Unsupervised Anomaly Segmentation Via Multilevel Image Reconstruction and Adaptive Attention-Level Transition," IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-12, 2021.
[17] Kaixuan Song, Jinchun Gao, George T. Flowers, Ziren Wang, Chaoyi Wang, Wei Yi, Zhongyang Cheng, "The Impact of the Connection Failure of Ground Solder Balls on Digital Signal Waveform," IEEE Transactions on Electromagnetic Compatibility, vol. 65, no. 1, pp. 312-322, 2023.
[18] R. Saravanan, Pothula Sujatha, "A State of Art Techniques on Machine Learning Algorithms: A Perspective of Supervised Learning Approaches in Data Classification," in International Conference on Intelligent Computing and Control Systems (ICICCS), 2018, pp. 945-949.
[19] Hao Guo, Xin Lin, Kunpeng Zhu, "Pyramid LSTM Network for Tool Condition Monitoring," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-11, 2022.
[20] Alex Sherstinsky, "Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network," Physica D: Nonlinear Phenomena, vol. 404, p. 132306, 2020.
[21] Tangqing Li, Zheng Wang, Siying Liu, Wen-Yan Lin, "Deep Unsupervised Anomaly Detection," in IEEE Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 3635-3644.
[22] Ming-Chang Lee, Jia-Chun Lin, Ernst Gunner Gan, "ReRe: A Lightweight Real-Time Ready-to-Go Anomaly Detection Approach for Time Series," presented at the IEEE Computers, Software, and Applications Conference (COMPSAC), 2020.
[23] Nina Tuluptceva, Bart Bakker, Irina Fedulova, Anton Konushin, "Perceptual Image Anomaly Detection," Cham, 2020: Springer International Publishing, in Pattern Recognition, pp. 164-178.
[24] Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Gang Wang, Jianfei Cai, Tsuhan Chen, "Recent advances in convolutional neural networks," Pattern Recognition, vol. 77, pp. 354-377, 2018.
[25] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin, "Attention is all you need," Advances in neural information processing systems, vol. 30, 2017.
[26] Olaf Ronneberger, Philipp Fischer, Thomas Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," Cham, 2015: Springer International Publishing, in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 234-241.
[27] Lin Zhang, Lei Zhang, Xuanqin Mou, David Zhang, "FSIM: A Feature Similarity Index for Image Quality Assessment," IEEE Transactions on Image Processing, vol. 20, no. 8, pp. 2378-2386, 2011.
[28] Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese, "Generalized intersection over union: A metric and a loss for bounding box regression," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 658-666.
[29] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[30] Zhou Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, 2004.