{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T06:13:49Z","timestamp":1778393629244,"version":"3.51.4"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":87,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100024990","name":"National Yang Ming Chiao Tung University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100024990","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mobile Netw Appl"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Diamond multi-wire sawing machines are essential in semiconductor manufacturing, especially for slicing hard and brittle third-generation materials such as silicon carbide (SiC) and gallium nitride (GaN). The increased difficulty in processing these materials has highlighted the urgent need for reliable machine health monitoring and anomaly detection systems. While Predictive Maintenance and Prognostics and Health Management (PHM) frameworks have been widely applied across various industries, little research has specifically addressed semiconductor cutting equipment, where operational dynamics and data confidentiality present unique challenges. This study, in collaboration with an industry partner, develops two anomaly detection models tailored for diamond multi-wire sawing machines. The first model is a rule-based approach that utilizes sliding window techniques to extract statistical features and establish dynamic thresholds for anomaly detection. The second model employs a data-driven Univariate Autoencoder (UAE) to perform unsupervised anomaly detection by learning reconstruction errors from normal operating data. Both models are trained and validated using confidential industrial sensor datasets. Experimental results demonstrate that the UAE-based model achieves high detection accuracy with no observed false positives, providing an effective solution for enhancing operational reliability and production efficiency in semiconductor wafer slicing processes.<\/jats:p>","DOI":"10.1007\/s11036-025-02477-2","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:33:20Z","timestamp":1761525200000},"page":"528-546","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Anomaly Detection for Semiconductor Wafer Multi-wire Sawing Machines Using Statistical and Deep Learning Methods"],"prefix":"10.1007","volume":"30","author":[{"given":"Zhen-Yin Annie","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Cheng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Cheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Chieh","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cherng-Yow","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"2477_CR1","doi-asserted-by":"crossref","unstructured":"Kimoto T, Cooper JA (2014) Fundamentals of silicon carbide technology: Growth, Characterization, Devices, and applications. Wiley-IEEE","DOI":"10.1002\/9781118313534"},{"key":"2477_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.precisioneng.2015.08.008","volume":"43","author":"H Wu","year":"2016","unstructured":"Wu H (2016) Wire sawing technology: a state-of-the-art review. Precis Eng 43:1\u20139","journal-title":"Precis Eng"},{"issue":"3","key":"2477_CR3","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1109\/TR.2015.2417153","volume":"64","author":"K He","year":"2015","unstructured":"He K, Maillart LM, Prokopyev OA (2015) Scheduling preventive maintenance as a function of an imperfect inspection interval. IEEE Trans Reliab 64(3):983\u2013997","journal-title":"IEEE Trans Reliab"},{"key":"2477_CR4","unstructured":"Ran Y, Zhou X, Lin P, Wen Y, Deng R (2019) A survey of predictive maintenance: Systems, purposes and approaches. ArXiv Preprint ArXiv: 1912.07383"},{"key":"2477_CR5","doi-asserted-by":"crossref","unstructured":"Kebande VR, Awad AI (2024) Industrial Internet of Things ecosystems security and digital forensics: Achievements, open challenges, and future directions. ACM Computing Surveys 56(5):1\u201337, 2024","DOI":"10.1145\/3635030"},{"issue":"11","key":"2477_CR6","doi-asserted-by":"publisher","first-page":"20271","DOI":"10.1109\/JIOT.2024.3372375","volume":"11","author":"M Alabadi","year":"2024","unstructured":"Alabadi M, Habbal A, Guizani M (2024) An innovative decentralized and distributed deep learning framework for predictive maintenance in the industrial internet of things. IEEE Internet Things J 11(11):20271\u201320286","journal-title":"IEEE Internet Things J"},{"key":"2477_CR7","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/s11036-023-02094-x","volume":"28","author":"X Ding","year":"2023","unstructured":"Ding X, Wang Y, Zheng H, Xu J, Zhai H (2023) A novel variable convolution kernel design according to time-frequency resolution altering in bearing fault diagnosis. Mob Netw Appl 28:406\u2013420","journal-title":"Mob Netw Appl"},{"key":"2477_CR8","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s11036-022-02017-2","volume":"28","author":"L Magad\u00e1n","year":"2023","unstructured":"Magad\u00e1n L, Su\u00e1rez F, Granda JC, Garc\u00eda DF (2023) Low-cost industrial Iot system for wireless monitoring of electric motors condition. Mob Netw Appl 28:97\u2013106","journal-title":"Mob Netw Appl"},{"key":"2477_CR9","volume":"74","author":"Z Liu","year":"2025","unstructured":"Liu Z, Liu Y, Zhu G, Pan S (2025) Incipient fault detection for medium voltage cables: considering the impact of solid insulation degradation on fault transient behavior. IEEE Trans Instrum Meas 74:Art3527211","journal-title":"IEEE Trans Instrum Meas"},{"issue":"14","key":"2477_CR10","doi-asserted-by":"publisher","first-page":"21813","DOI":"10.1016\/j.ceramint.2020.05.207","volume":"46","author":"W Ming","year":"2020","unstructured":"Ming W et al (2020) A comprehensive review of electric discharge machining of advanced ceramics. Ceram Int 46(14):21813\u201321838","journal-title":"Ceram Int"},{"key":"2477_CR11","doi-asserted-by":"crossref","unstructured":"Li H, Gao Y, Cheng D, Yang C (2025) Modeling and experimental investigation on sawing force in ultrasonic vibration\u2013assisted diamond wire sawing mono-Si considering material removal mode. The International Journal of Advanced Manufacturing Technology","DOI":"10.1007\/s00170-025-15542-7"},{"key":"2477_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.mssp.2023.107481","volume":"161","author":"Z Li","year":"2023","unstructured":"Li Z, Liu X, Jia H, Yu J, Cai Y, Li G (2023) Study on the temperature field in the cutting zone for machining monocrystalline silicon wafer using free abrasive multi-wire saw. Mater Sci Semicond Process 161:107481","journal-title":"Mater Sci Semicond Process"},{"issue":"Supplement","key":"2477_CR13","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.mfglet.2024.09.082","volume":"41","author":"EM Sefene","year":"2024","unstructured":"Sefene EM, Wang SHM, Chen CCA (2024) Analysis of contact length and temperature effect in rocking mode diamond wire sawing of monocrystalline silicon carbide wafer. Manuf Lett 41(Supplement):641\u2013652","journal-title":"Manuf Lett"},{"key":"2477_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmatprotec.2019.116267","volume":"273","author":"H Xiao","year":"2019","unstructured":"Xiao H, Wang H, Yu N, Liang R, Tong Z, Chen Z, Wang J (2019) Evaluation of fixed abrasive diamond wire sawing induced subsurface damage of solar silicon wafers. J Mater Process Technol 273:116267","journal-title":"J Mater Process Technol"},{"issue":"12","key":"2477_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.mssp.2020.105252","volume":"120","author":"T Liu","year":"2020","unstructured":"Liu T, Ge P, Bi W, Gao Y (2020) A new method of determining the slicing parameters for fixed diamond wire saw. Mater Sci Semicond Process 120(12):105252","journal-title":"Mater Sci Semicond Process"},{"issue":"5","key":"2477_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.mssp.2019.104779","volume":"106","author":"Y Yin","year":"2020","unstructured":"Yin Y, Gao Y, Li X, Pu T, Wang L (2020) Experimental study on slicing photovoltaic polycrystalline silicon with diamond wire saw. Mater Sci Semicond Process 106(5):104779","journal-title":"Mater Sci Semicond Process"},{"key":"2477_CR17","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1016\/j.solener.2020.07.018","volume":"207","author":"EC Costa","year":"2020","unstructured":"Costa EC, Xavier FA, Knoblauch R, Binder C, Weingaertner WL (2020) Effect of cutting parameters on surface integrity of monocrystalline silicon sawn with an endless diamond wire saw. Solar Energy 207:640\u2013650","journal-title":"Solar Energy"},{"issue":"4","key":"2477_CR18","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.precisioneng.2020.07.011","volume":"66","author":"B Wang","year":"2020","unstructured":"Wang B, Melkote SN, Wang P, Saraogi S (2020) Effect of speed on material removal behavior in scribing of monocrystalline silicon. Precis Eng 66(4):315\u2013323","journal-title":"Precis Eng"},{"key":"2477_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.mssp.2022.106838","volume":"148","author":"M Ge","year":"2022","unstructured":"Ge M, Chen Z, Wang P, Ge P (2022) Crack damage control for diamond wire sawing of silicon: the selection of processing parameters. Mater Sci Semicond Process 148:106838","journal-title":"Mater Sci Semicond Process"},{"key":"2477_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.mssp.2024.108938","volume":"185","author":"EC Costa","year":"2025","unstructured":"Costa EC, van Bellen B, Werner MO, de Sousa PC, Xavier FA (2025) Optimizing the diamond wire sawing of polycrystalline silicon: an experimental approach. Mater Sci Semicond Process 185:108938","journal-title":"Mater Sci Semicond Process"},{"key":"2477_CR21","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.wear.2016.07.009","volume":"364","author":"A Kumar","year":"2016","unstructured":"Kumar A, Kaminski S, Melkote SN, Arcona C (2016) Effect of wear of diamond wire on surface morphology, roughness and subsurface damage of silicon wafers. Wear 364:163\u2013168","journal-title":"Wear"},{"issue":"2","key":"2477_CR22","first-page":"52","volume":"1","author":"R Mikaeil","year":"2017","unstructured":"Mikaeil R, Haghshenas SS, Ozcelik Y, Haghshenas SS (2017) Development of intelligent systems to predict diamond wire saw performance. J Soft Comput Civil Eng 1(2):52\u201369","journal-title":"J Soft Comput Civil Eng"},{"key":"2477_CR23","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.jmapro.2023.01.003","volume":"87","author":"M Ge","year":"2023","unstructured":"Ge M, Zhang C, Wang P, Li Z, Ge P (2023) Modeling of electroplated diamond wire and its application towards precision slicing of semiconductors. J Manuf Process 87:141\u2013149","journal-title":"J Manuf Process"},{"issue":"11\u201312","key":"2477_CR24","doi-asserted-by":"publisher","first-page":"7923","DOI":"10.1007\/s00170-022-09901-x","volume":"121","author":"Y Zhao","year":"2022","unstructured":"Zhao Y, Ge P, Bi W, Zheng J, Lan J (2022) Machine vision online detection for abrasive protrusion height on the surface of electroplated diamond wire saw. Int J Adv Manuf Technol 121(11\u201312):7923\u20137932","journal-title":"Int J Adv Manuf Technol"},{"key":"2477_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112486","volume":"208","author":"Y Zhao","year":"2023","unstructured":"Zhao Y, Ge P, Bi W, Zheng J, Liu N (2023) MRF based image stitching of electroplated diamond wire saw: for improving visual inspection accuracy of manufacturing quality. Measurement 208:112486","journal-title":"Measurement"},{"key":"2477_CR26","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.precisioneng.2022.12.004","volume":"80","author":"J Zheng","year":"2023","unstructured":"Zheng J, Zhao Y, Ge M, Bi W, Ge P (2023) Machine vision-based transverse vibration measurement of diamond wire. Precis Eng 80:115\u2013126","journal-title":"Precis Eng"},{"issue":"5","key":"2477_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40393-y","volume":"19","author":"J Ouyang","year":"2025","unstructured":"Ouyang J, Huang S, Zhang L, Zhao X (2025) Model-based diagnosis with low-cost fault identification. Front Comput Sci 19(5):195333","journal-title":"Front Comput Sci"},{"key":"2477_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2025.120472","volume":"321","author":"J Mai","year":"2025","unstructured":"Mai J, Huang H, Wei F, Yang C, He W (2025) Autonomous underwater vehicle fault diagnosis model based on a deep belief rule with attribute reliability. Ocean Eng 321:120472","journal-title":"Ocean Eng"},{"key":"2477_CR29","unstructured":"Montgomery DC (2020) Introduction to statistical quality control. John Wiley & Sons"},{"key":"2477_CR30","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3136260","volume":"71","author":"J Dong","year":"2022","unstructured":"Dong J, Wang Y, Peng K (2022) A novel fault detection method based on the extraction of slow features for dynamic nonstationary processes. IEEE Trans Instrum Meas 71:3500611","journal-title":"IEEE Trans Instrum Meas"},{"key":"2477_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108507","volume":"118","author":"Y Cheng","year":"2022","unstructured":"Cheng Y, Wang C, Wu J, Zhu H, Lee CKM (2022) Multi-dimensional recurrent neural network for remaining useful life prediction under variable operating conditions and multiple fault modes. Appl Soft Comput 118:108507","journal-title":"Appl Soft Comput"},{"key":"2477_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2025.111108","volume":"261","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Wang S, Zhang C, Dui H, Chen R (2025) Application of physics-informed machine learning in performance degradation and RUL prediction of hydraulic piston pumps. Reliab Eng Syst Saf 261:111108","journal-title":"Reliab Eng Syst Saf"},{"key":"2477_CR33","doi-asserted-by":"crossref","unstructured":"Liu P, Zhao S, Kang L, Yin Y (2025) CNN Intelligent diagnosis method for bearing incipient faint faults based on adaptive stochastic resonance-wave peak cross correlation sliding sampling. Digital Signal Processing 156(B): 2025, 104871","DOI":"10.1016\/j.dsp.2024.104871"},{"issue":"10","key":"2477_CR34","doi-asserted-by":"publisher","first-page":"10423","DOI":"10.1109\/TKDE.2023.3266755","volume":"35","author":"F Zhou","year":"2023","unstructured":"Zhou F, Wang G, Zhang K, Liu S, Zhong T (2023) Semi-supervised anomaly detection via neural process. IEEE Trans Knowl Data Eng 35(10):10423\u201310435","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"2477_CR35","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1016\/j.measurement.2012.10.026","volume":"46","author":"G Cheng","year":"2013","unstructured":"Cheng G, Cheng YL, Shen LH, Qiu JB, Zhang S (2013) Gear fault identification based on Hilbert\u2013Huang transform and SOM neural network. Measurement 46(3):1137\u20131146","journal-title":"Measurement"},{"issue":"9","key":"2477_CR36","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1016\/S0098-1354(02)00093-5","volume":"26","author":"M Misra","year":"2002","unstructured":"Misra M, Yue HH, Qin SJ, Ling C (2002) Multivariate process monitoring and fault diagnosis by multi-scale PCA. Comput Chem Eng 26(9):1281\u20131293","journal-title":"Comput Chem Eng"},{"key":"2477_CR37","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.ymssp.2017.03.034","volume":"95","author":"H Shao","year":"2017","unstructured":"Shao H, Jiang H, Zhao H, Wang F (2017) A novel deep autoencoder feature learning method for rotating machinery fault diagnosis. Mech Syst Signal Process 95:187\u2013204","journal-title":"Mech Syst Signal Process"},{"issue":"6","key":"2477_CR38","doi-asserted-by":"publisher","first-page":"2508","DOI":"10.1109\/TNNLS.2021.3105827","volume":"33","author":"A Garg","year":"2021","unstructured":"Garg A, Zhang W, Samaran J, Savitha R, Foo CS (2021) An evaluation of anomaly detection and diagnosis in multivariate time series. IEEE Trans Neural Networks Learn Syst 33(6):2508\u20132517","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"issue":"2","key":"2477_CR39","doi-asserted-by":"publisher","first-page":"344","DOI":"10.3758\/BRM.38.2.344","volume":"38","author":"GL Thompson","year":"2006","unstructured":"Thompson GL (2006) An SPSS implementation of the nonrecursive outlier deletion procedure with shifting Z score criterion (Van Selst & Jolicoeur, 1994). Behav Res Methods 38(2):344\u2013352","journal-title":"Behav Res Methods"},{"key":"2477_CR40","unstructured":"Hochenbaum J, Vallis OS, Kejariwal A (2017) Automatic anomaly detection in the cloud via statistical learning. arXiv preprint arXiv:1704.07706"}],"container-title":["Mobile Networks and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-025-02477-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11036-025-02477-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-025-02477-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T09:54:24Z","timestamp":1773309264000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11036-025-02477-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":40,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2477"],"URL":"https:\/\/doi.org\/10.1007\/s11036-025-02477-2","relation":{},"ISSN":["1383-469X","1572-8153"],"issn-type":[{"value":"1383-469X","type":"print"},{"value":"1572-8153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"14 October 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}