Two-step machine learning-assisted label-free surface-enhanced Raman spectroscopy for reliable prediction of dissolved furfural in transformer oil

被引:0
作者
Wan, Fu [1 ,2 ]
Li, Shufan [1 ]
Lei, Yu [1 ]
Wang, Mingliang [1 ]
Liu, Ruiqi [1 ]
Hu, Kaida [1 ]
Xia, Yaoyang [1 ]
Chen, Weigen [1 ,2 ]
机构
[1] Chongqing Univ, Sch Elect Engn, State Key Lab Power Transmiss Equipment Technol, Chongqing 400044, Peoples R China
[2] Chongqing Univ, Natl Innovat Ctr Ind Educ Integrat Energy Storage, Sch Elect Engn, Chongqing 400044, Peoples R China
基金
中国国家自然科学基金;
关键词
Surface-enhanced Raman spectroscopy; Furfural; Design of experiments; Optimization algorithm; Machine learning; SERS; OPTIMIZATION; ALGORITHM;
D O I
10.1016/j.saa.2024.124571
中图分类号
O433 [光谱学];
学科分类号
0703 ; 070302 ;
摘要
Accurate detection of dissolved furfural in transformer oil is crucial for real-time monitoring of the aging state of transformer oil -paper insulation. While label -free surface -enhanced Raman spectroscopy (SERS) has demonstrated high sensitivity for dissolved furfural in transformer oil, challenges persist due to poor substrate consistency and low quantitative reliability. Herein, machine learning (ML) algorithms were employed in both substrate fabrication and spectral analysis of label -free SERS. Initially, a high -consistency Ag@Au substrate was prepared through a combination of experiments, particle swarm optimization -neural network (PSO-NN), and a hybrid strategy of particle swarm optimization and genetic algorithm (Hybrid PSO-GA). Notably, a two-step ML framework was proposed, whose operational mechanism is classification followed by quantification. The framework adopts a hierarchical modeling strategy, incorporating simple algorithms such as kernel support vector machine (Kernel-SVM), k -nearest neighbors (KNN), etc., to independently establish lightweight regression models on each cluster, which allows each model to focus more effectively on fitting the data within its cluster. The classification model achieved an accuracy of 100%, while the regression models exhibited an average correlation coefficient (R 2 ) of 0.9953 and the root mean square errors (RMSE) consistently below 10 -2 . Thus, this ML framework emerges as a rapid and reliable method for detecting dissolved furfural in transformer oil, even in the presence of different interfering substances, which may also have potentiality for other complex mixture monitoring systems.
引用
收藏
页数:9
相关论文
共 50 条
[21]   Label-free surface-enhanced Raman spectroscopy coupled with machine learning algorithms in pathogenic microbial identification: Current trends, challenges, and perspectives [J].
Tang, Jia-Wei ;
Yuan, Quan ;
Wen, Xin-Ru ;
Usman, Muhammad ;
Tay, Alfred Chin Yen ;
Wang, Liang .
INTERDISCIPLINARY MEDICINE, 2024, 2 (03)
[22]   Label-free detection of trace level zearalenone in corn oil by surface-enhanced Raman spectroscopy (SERS) coupled with deep learning models [J].
Zhu, Jiaji ;
Jiang, Xin ;
Rong, Yawen ;
Wei, Wenya ;
Wu, Shengde ;
Jiao, Tianhui ;
Chen, Quansheng .
FOOD CHEMISTRY, 2023, 414
[23]   Deep learning-assisted surface-enhanced Raman spectroscopy detection of intracellular reactive oxygen species [J].
Chen, Hua-Ying ;
He, Yue ;
Wang, Xiao-Yuan ;
Ye, Ming-Jie ;
Chen, Chao ;
Qian, Ruo-Can ;
Li, Da-Wei .
TALANTA, 2025, 284
[24]   Machine learning (ML)-assisted surface-enhanced raman spectroscopy (SERS) technologies for sustainable health [J].
Khondakar, Kamil Reza ;
Mazumdar, Hirak ;
Das, Suparna ;
Kaushik, Ajeet .
ADVANCES IN COLLOID AND INTERFACE SCIENCE, 2025, 344
[25]   Label-free detection of ssDNA base insertion and deletion mutations by surface-enhanced Raman spectroscopy [J].
Yufeng Zhang ;
Jiayu Zeng ;
Chao Huang ;
Bixue Zhu ;
Qianjun Zhang ;
Dongmei Chen .
Analytical and Bioanalytical Chemistry, 2022, 414 :1461-1468
[26]   Label-free detection of ssDNA base insertion and deletion mutations by surface-enhanced Raman spectroscopy [J].
Zhang, Yufeng ;
Zeng, Jiayu ;
Huang, Chao ;
Zhu, Bixue ;
Zhang, Qianjun ;
Chen, Dongmei .
ANALYTICAL AND BIOANALYTICAL CHEMISTRY, 2022, 414 (04) :1461-1468
[27]   Nanoparticle surface-enhanced Raman spectroscopy as a noninvasive, label-free tool to monitor hematological malignancy [J].
Grieve, Stacy ;
Puvvada, Nagaprasad ;
Phinyomark, Angkoon ;
Russell, Kevin ;
Murugesan, Alli ;
Zed, Elizabeth ;
Hassan, Ansar ;
Legare, Jean-Francois ;
Kienesberger, Petra C. ;
Pulinilkunnil, Thomas ;
Reiman, Tony ;
Scheme, Erik ;
Brunt, Keith R. .
NANOMEDICINE, 2021, 16 (24) :2175-2188
[28]   Silver Nano-bulks Surface-Enhanced Raman Spectroscopy Used as Rapid In-Situ Method for Detection of Furfural Concentration in Transformer Oil [J].
Gu, Zhaoliang ;
Chen, Weigen ;
Yung, Yuxin ;
Shi, Haiyang ;
Du, Lingling ;
Wan, Fu .
IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION, 2018, 25 (02) :457-463
[29]   Label-Free Detection of Single-Base Mismatches in DNA by Surface-Enhanced Raman Spectroscopy [J].
Papadopoulou, Evanthia ;
Bell, Steven E. J. .
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION, 2011, 50 (39) :9058-9061
[30]   Rapid and label-free screening of echinococcosis serum profiles through surface-enhanced Raman spectroscopy [J].
Yue, Xiaxia ;
Li, Hongmei ;
Tang, Jun ;
Liu, Jie ;
Jiao, Juan .
ANALYTICAL AND BIOANALYTICAL CHEMISTRY, 2020, 412 (02) :279-288