Article
Engineering, Multidisciplinary
Zhenhua Nie, Zhaofeng Shen, Jun Li, Hong Hao, Yizhou Lin, Hongwei Ma, Hui Jiang
Summary: This article introduces a novel data-driven structural damage detection method called moving embedded principal component analysis to monitor bridge conditions and detect damage occurrence. By utilizing a fixed moving window and embedding state space, a novel damage index is proposed to accurately identify structural damage and abnormal behavior.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Automation & Control Systems
Atefeh Daemi, Bhushan Gopaluni, Biao Huang
Summary: In this article, we propose a novel transfer learning approach, called domain adversarial probabilistic principal component analysis (DAPPCA), to monitor processes with data from multiple distributions. DAPPCA automatically learns feature representations that are relevant across different operational modes and improves fault detection accuracy by transferring knowledge from previously known modes.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Shigeyoshi Yoshida, Masahiro Kozako, Masayuki Hikita
Summary: This study investigates the effect of white trace on partial discharge inception voltage (PDIV) of the composite insulation system using high-speed optical observation and electrical measurements. It reveals the impact of the white trace on discharge propagation and discusses the mechanism of discharge progression.
IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION
(2021)
Article
Engineering, Multidisciplinary
Zhijiang Lou, Zedong Li, Youqing Wang, Shan Lu
Summary: This paper introduces an improved neural component analysis (INCA) method, which addresses the issue of NCA's inability to handle non-Gaussian features by proposing a new cost function based on kurtosis. It also improves the extraction of key information from process data by selecting principal components (PCs) in the original data space. Experimental results show that INCA outperforms other methods in fault detection.
Article
Biochemical Research Methods
Kuangnan Fang, Rui Ren, Qingzhao Zhang, Shuangge Ma
Summary: Dimension reduction techniques like PCA, PLS, and CCA are extensively used in the analysis of high-dimensional omics data. Integrative analysis, which outperforms meta-analysis and individual-data analysis, has been developed for multiple datasets with compatible designs. We developed the R package iSFun to facilitate integrative dimension reduction analysis, offering comprehensive analysis options under different models and penalties.
Article
Engineering, Electrical & Electronic
Osvaldo Munoz, Roger Schurch, Jorge Alfredo Ardila-Rey
Summary: This study proposes a new methodology for identifying the aging stage of electrical trees using the discrete wavelet transform (DWT) and principal component analysis (PCA) to analyze each partial discharge pulse waveform. The results show that electrical trees can be characterized into three stages: initial, valley, and postcrossing, with different behaviors in terms of discharge and tree structure. The study also demonstrates the potential of this method for real power equipment insulation assessment, such as power cables.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Hardware & Architecture
Anfeng Zhu, Qiancheng Zhao, Tianlong Yang, Ling Zhou, Bing Zeng
Summary: This study proposes a new approach for condition monitoring of wind turbines (WTs) using a cascading convolutional neural network (CNN) and long- and short-term memory network (LSTM) with kernel principal component analysis (KPCA). The DBSCAN method is used to filter data from supervisory control and data acquisition (SCADA) for improved effectiveness. The KPCA-CNN-LSTM model is then established for performance monitoring and fault prediction of WT. Experimental results show that the proposed model can effectively monitor the state of the WT and predict abnormal operation at an early stage.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Forestry
Shuang Wu, Xiaohua Yao, Kailiang Wang, Shuiping Yang, Huadong Ren, Mei Huang, Jun Chang
Summary: A comprehensive method for evaluating pecan kernel quality was established by analyzing and testing multiple indicators of the kernels of different cultivars. The study found that the fatty acids in pecan kernels were dominated by unsaturated fats, with oleic acid having the highest content. Medicinal amino acids were found to be dominant in the amino acid composition, while potassium, magnesium, and calcium were the predominant mineral elements. Cluster analysis classified the pecan cultivars into three categories based on kernel quality, and 21 indicators were identified to differentiate among the cultivars. A reliable evaluation model was established and verified, and six cultivars with potential for excellent quality were preliminarily identified.
Article
Spectroscopy
Zozan Guleken, Huri Bulut, Berk Bulut, Wieslaw Paja, Magdalena Parlinska-Wojtan, Joanna Depciuch
Summary: Endometriosis refers to the formation of the uterus lining outside the uterus. Raman spectroscopy analysis of serum showed that it is possible to distinguish between healthy women and those with endometriosis using specific Raman ranges. Lipid vibrations may serve as spectral markers of the disease.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2022)
Article
Food Science & Technology
Mengyu Zhao, Junbo Gou, Kaixuan Zhang, Jingjun Ruan
Summary: In this study, the content of trace metal elements in buckwheat flour was determined using ICP-MS and ICP-AES. The results showed that Cu, Mg, Mo, and Cd are the characteristic elements of buckwheat flour. Cluster analysis divided the buckwheat samples into two groups, reflecting the genuineness of buckwheat flour to some extent. Buckwheat flour is rich in essential trace metal elements and can be a dietary source of Mg and Mo.
Article
Engineering, Electrical & Electronic
Gian Carlo Montanari, Riddhi Ghosh, Leonardo Cirioni, Giuseppe Galvagno, Salvatore Mastroeni
Summary: This paper presents a new approach to automatic, self-assessment of switchgear reliability based on partial discharge (PD) acquisition and processing, as well as a new type of PD sensor solution. The sensor, based on the capacitive divider in most bushings, indicates the presence or absence of voltage, and the innovative automatic software provides functions such as automatic noise and PD separation, noise rejection, and identification of the type of PD source. The results of the tests show that the sensor, coupled with the automatic software, has good sensitivity and capability to locate the cabinet and identify the type of source generating partial discharges.
IEEE TRANSACTIONS ON POWER DELIVERY
(2022)
Article
Engineering, Electrical & Electronic
S. Didouche, A. Nacer, A. Ziani, H. Moulai, K. Mazighi
Summary: In this paper, a new method for detection and localization of partial discharges in a power transformer is proposed. By using only two acoustic sensors, the method achieves efficient and accurate detection and localization. The spatio-temporal distribution of acoustic pressure is obtained through finite element method and an iterative approach. The method's performance is compared with a direct resolution method.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Engineering, Multidisciplinary
Ana Fernandez-Navamuel, Filipe Magalhaes, Diego Zamora-Sanchez, Angel J. Omella, David Garcia-Sanchez, David Pardo
Summary: This paper proposes a Deep Learning Enhanced Principal Component Analysis (PCA) approach for outlier detection to assess the structural condition of bridges. By adding residual connections, the outlier detection ability of the network is enhanced, allowing for the detection of lighter damages.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Pei Li, Wenlin Zhang, Chengjun Lu, Rui Zhang, Xuelong Li
Summary: A novel robust kernel principal component analysis method with optimal mean (RKPCA-OM) is proposed to enhance the robustness of KPCA by automatically eliminating the optimal mean. The theoretical proof guarantees the convergence of the algorithm and the obtained optimal subspaces and means. Exhaustive experimental results validate the superiority of the proposed method.
Article
Engineering, Industrial
Joaquim A. P. Braga, Antonio R. Andrade
Summary: Monitoring and assessing wear evolutions of railway wheelsets is crucial for effective maintenance, but can be complex and costly. This study analyzed real degradation data using multivariate statistical techniques to reduce complexity and identify different wear trajectories. Results show a strong correlation between certain wear characteristics, such as flange thickness and slope, and significant differences in wear trajectories between motor and trailer wheelsets.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)