Data-Driven Support Vector Machine with Optimization Techniques for Structural Health Monitoring and Damage Detection

Guoqing Gui,Hong Pan,Zhibin Lin,Yonghua Li,Zhijun Yuan 대한토목학회 2017 KSCE JOURNAL OF CIVIL ENGINEERING Vol.21 No.2

Rapid detecting damages/defeats in the large-scale civil engineering structures, assessing their conditions and timely decision making are crucial to ensure their health and ultimately enhance the level of public safety. Advanced sensor network techniques recently allow collecting large amounts of data for structural health monitoring and damage detection, while how to effectively interpret these complex sensor data to technical information posts many challenges. This paper presents three optimization-algorithm based support vector machines for damage detection. The optimization algorithms, including grid-search, partial swarm optimization and genetic algorithm, are used to optimize the penalty parameters and Gaussian kernel function parameters. Two types of feature extraction methods in terms of time-series data are selected to capture effective damage characteristics. A benchmark experimental data with the 17 different scenarios in the literature were used for verifying the proposed data-driven methods. Numerical results revealed that all three optimized machine learning methods exhibited significantly improvement in sensitivity, accuracy and effectiveness over conventional methods. The genetic algorithm based SVM had a better prediction than other methods. Two different feature methods used in this study also demonstrated the appropriate features are crucial to improve the sensitivity in detecting damage and assessing structural health conditions. The findings of this study are expected to help engineers to process big data and effectively detect the damage/defects, and thus enable them to make timely decision for supporting civil infrastructure management practices.

High-precision flux linkage observation of induction motor at low switching frequency

Pan, Yuedou,Cai, Guoqing,Zhang, Weifeng The Korean Institute of Power Electronics 2021 JOURNAL OF POWER ELECTRONICS Vol.21 No.2

The delay effect caused by the switching device is not considered in traditional methods of induction motor flux observation. However, ignoring the delay effect causes the mathematical model of the induction motor flux observation to be inaccurate. In actual work, this disadvantage will affect the flux observation of the induction motor. It will also influence the anti-load performance of the motor and even lead to system instability. Especially at low switching frequencies, switch delay causes input delay. Input delay will result in configuration poles deviating from their expected position in the closed-loop control, affecting the induction motor performance. In this study, the induction motor time-delay model is established to modify the model and solve the above problem. Spectral decomposition theory is used to establish the induction motor flux observer, which configures the unstable poles of the system. The poles that deviate from their expected position are also reconfigured to the desired position, which improves the motor performance and the observing accuracy of the flux chain. Finally, the process of proving the stability of the spectral decomposition flux observer (SDFO) is provided. The reliability of the SDFO is proven through specific simulations and experiments.

Deep BBN Learning for Health Assessment toward Decision-Making on Structures under Uncertainties

Hong Pan,Guoqing Gui,Zhibin Lin,Changhui Yan 대한토목학회 2018 KSCE Journal of Civil Engineering Vol.22 No.3

Structural systems are often exposed to harsh environment, while these environmental factors in turn could degrade the system over time. Their health state and structural conditions are key for structural safety control and decision-making management. Although great efforts have been paid on this field, the high level of variability due to noise and other interferences, and the uncertainties associated with data collection, structural performance and in-service operational environments post great challenges in finding information to assist decision making. The machine learning techniques in recent years have been gaining increasing attentions due to their merits capturing information from statistical representation of events and thus enabling making decision. In this study, the deep Bayesian Belief Network Learning (DBBN) was used to extract structural information and probabilistically determine structural conditions. Different to conventional shallow learning that highly relies on the quality of the hand-crafted features, the deep learning is an end-to-end method to encode the information and interpret vast amount of data with minimizing or no features. A case study was conducted to address the methods for structure under viabilities and uncertainties due to operation, damage and noise interferences. Numerical results revealed that the deep learning exhibits considerably enhanced accuracy for structural diagnostics, as compared to the supervised shallow learning. With predetermined training set, the DBBN could accurately determine the structural health state in terms of damage level, which could dramatically help decision making for further structural retrofit or not. Note that the noise interference could contaminate the data representation and in turn increase the difficulty of the data mining, though the deep learning could reduce the impacts, as compared to conventional shallow learning techniques.

Apolipoprotein H: a novel regulator of fat accumulation in duck myoblasts

Ziyi Pan,Guoqing Du,Guoyu Li,Dongsheng Wu,Xingyong Chen,Zhaoyu Geng 한국축산학회 2022 한국축산학회지 Vol.64 No.6

Apolipoprotein H (APOH) primarily engages in fat metabolism and inflammatory disease response. This study aimed to investigate the effects of APOH on fat synthesis in duck myoblasts (CS2s) by APOH overexpression and knockdown. CS2s overexpressing APOH showed enhanced triglyceride (TG) and cholesterol (CHOL) contents and elevated the mRNA and protein expression of AKT serine/threonine kinase 1 (AKT1), ELOVL fatty acid elongase 6 (ELOVL6), and acetyl-CoA carboxylase 1 (ACC1) while reducing the expression of protein kinase AMP-activated catalytic subunit alpha 1 (AMPK), peroxisome proliferator activated receptor gamma (PPARG), acyl-CoA synthetase long chain family member 1 (ACSL1), and lipoprotein lipase (LPL). The results showed that knockdown of APOH in CS2s reduced the content of TG and CHOL, reduced the expression of ACC1, ELOVL6, and AKT1, and increased the gene and protein expression of PPARG, LPL, ACSL1, and AMPK. Our results showed that APOH affected lipid deposition in myoblasts by inhibiting fatty acid beta-oxidation and promoting fatty acid biosynthesis by regulating the expression of the AKT/AMPK pathway. This study provides the necessary basic information for the role of APOH in fat accumulation in duck myoblasts for the first time and enables researchers to study the genes related to fat deposition in meat ducks in a new direction.

Immunomodulatory biomaterials for implant-associated infections: from conventional to advanced therapeutic strategies

Dong Jiale,Wang Wenzhi,Zhou Wei,Zhang Siming,Li Meng,Li Ning,Pan Guoqing,Zhang Xianzuo,Bai Jiaxiang,Zhu Chen 한국생체재료학회 2023 생체재료학회지 Vol.27 No.00

Implant-associated infection (IAI) is increasingly emerging as a serious threat with the massive application of biomaterials. Bacteria attached to the surface of implants are often difficult to remove and exhibit high resistance to bactericides. In the quest for novel antimicrobial strategies, conventional antimicrobial materials often fail to exert their function because they tend to focus on direct bactericidal activity while neglecting the modulation of immune systems. The inflammatory response induced by host immune cells was thought to be a detrimental force impeding wound healing. However, the immune system has recently received increasing attention as a vital player in the host’s defense against infection. Anti-infective strategies based on the modulation of host immune defenses are emerging as a field of interest. This review explains the importance of the immune system in combating infections and describes current advanced immune-enhanced anti-infection strategies. First, the characteristics of traditional/conventional implant biomaterials and the reasons for the difficulty of bacterial clearance in IAI were reviewed. Second, the importance of immune cells in the battle against bacteria is elucidated. Then, we discuss how to design biomaterials that activate the defense function of immune cells to enhance the antimicrobial potential. Based on the key premise of restoring proper host-protective immunity, varying advanced immune-enhanced antimicrobial strategies were discussed. Finally, current issues and perspectives in this field were offered. This review will provide scientific guidance to enhance the development of advanced anti-infective biomaterials.

Sequence Analysis of Mitochondrial Genome of Toxascaris leonina from a South China Tiger

Kangxin Li,Fang Yang,A. Y. Abdullahi,Meiran Song,Xianli Shi,Minwei Wang,Yeqi Fu,Weida Pan,Fang Shan,Wu Chen,Guoqing Li 대한기생충학열대의학회 2016 The Korean Journal of Parasitology Vol.54 No.6

Toxascaris leonina is a common parasitic nematode of wild mammals and has significant impacts on the protection of rare wild animals. To analyze population genetic characteristics of T. leonina from South China tiger, its mitochondrial (mt) genome was sequenced. Its complete circular mt genome was 14,277 bp in length, including 12 protein-coding genes, 22 tRNA genes, 2 rRNA genes, and 2 non-coding regions. The nucleotide composition was biased toward A and T. The most common start codon and stop codon were TTG and TAG, and 4 genes ended with an incomplete stop codon. There were 13 intergenic regions ranging 1 to 10 bp in size. Phylogenetically, T. leonina from a South China tiger was close to canine T. leonina. This study reports for the first time a complete mt genome sequence of T. leonina from the South China tiger, and provides a scientific basis for studying the genetic diversity of nematodes between different hosts.