Research on Concrete Cracks Recognition based on Dual Convolutional Neural Network

Dong Liang,Xue-Feng Zhou,Song Wang,Chen-Jing Liu 대한토목학회 2019 KSCE JOURNAL OF CIVIL ENGINEERING Vol.23 No.7

Cracks are the most common and important diseases of concrete bridges. A dual convolutional neural network (DCN) model which is composed of one convolutional neural network (CNN) model and one fully convolutional network (FCN) model is proposed to recognize the cracks in image. Firstly, the CNN model is used to identify the crack area. The interfering factors such as spot, shadow, water stain, and graffiti in the non-crack area will be excluded by CNN model. Then, the CNN results will be segmented by the FCN model with the structure of merging layer-by-layer to extract crack features such as length and width. The DCN model is trained to recognize the actual concrete bridge cracks in this paper. The recognition results show that the DCN model has a good balance between high accuracy and low noise in the process of crack recognition compared with the current image recognition method. The reliability and accuracy of recognition are both greatly improved. The DCN model is helpful for automatic identification of cracks in concrete bridges.

Deviation Calculation and Analysis of Tooth Surfaces of Conjugate-Curve Gear Drive

Dong Liang,Bingkui Chen,Shuai Peng,Chengli Hua,Ruijin Liao 한국정밀공학회 2017 International Journal of Precision Engineering and Vol.18 No.5

Conjugate-curve gears are point contact gears and the locus curves of contact points are conjugate curves. For conjugate-curve gear drive, the application of rack cutters may result in geometrical deviation between the theoretical tooth profiles and the generated tooth profiles. To discuss the deviation conditions between two tooth surfaces, generation of theoretical tooth profiles is described and the tooth profiles generated by the rack cutters are derived. General calculation method for the deviation is provided and the analysis of tooth surfaces is also carried out. Numerical examples utilizing the circular-arc curve and parabolic curve are performed, respectively. The obtained results are discussed and the influences of design parameters including the design parameter, helix angle and the radius of pitch circle on the deviation are shown. The summarized contents of this paper are finally present.

Analysis of Differences in Fun, Flow, and Self-Directed Learning According to the Background Variables and Characteristics of the Senior Citizens Participating in the HEALTH QIGONG Program

Dong Liang,Jaebum Lee,Hyunwoo Kim J-INSTITUTE 2021 Protection Convergence Vol.6 No.3

Purpose: This study has analyzed the differences between fun, flow, and self-directed learning according to the background variables and the characteristics of senior citizens participating in the Health Qigong program with a view to use them as the basic data for the senior citizens’ health education. Method: Participants in this study were 241 elderly people participating in the Health Qigong program at sen-ior welfare centers, senior centers, and public health centers located in Seoul and Gyeonggi-do, Korea. As an anal-ysis method, MANOVA was conducted to examine the differences in fun, flow, and self-directed learning accord-ing to background characteristics such as age, education, training experience, number of training sessions, and residence type, which are background variables of the elderly. Results: As a result of study, the fun variable, flow variable, and the self-directed learning variable demon-strated differences each according to the demographic background variable. In particular, it was evident that the demographic characteristics of age, training experience, and number of training sessions demonstrated the statis-tically significant differences for fun, flow, and self-directed learning. Conclusion: The results of this study demonstrate the possibility that very active physical activities and related experiences for the senior citizens for health intervention would bring about the self-directed learning through the experiences of fun and flow, which in turn might impact the improvement of the quality of life for the old age. It confirmed that in terms of the operation of the Health Qigong program, it is necessary to accommodate the needs by age, experience, and number of training sessions, and also induce the senior citizens participating in the exer-cises to participate in the program positively through the development of the Health Qigong program towards that end.

A method for inductor design to improve efficiency in PFC boost converter

Dong Liang,Woong-Jae Kang,Hwi-Beom Shin 전력전자학회 2017 전력전자학술대회 논문집 Vol.2017 No.7

Research on diagnosis method of centrifugal pump rotor faults based on IPSO-VMD and RVM

Dong Liang,Chen Zeyu,Hua Runan,Hu Siyuan,Fan Chuanhan,Xiao xingxin 한국원자력학회 2023 Nuclear Engineering and Technology Vol.55 No.3

Centrifugal pump is a key part of nuclear power plant systems, and its health status is critical to the safety and reliability of nuclear power plants. Therefore, fault diagnosis is required for centrifugal pump. Traditional fault diagnosis methods have difficulty extracting fault features from nonlinear and nonstationary signals, resulting in low diagnostic accuracy. In this paper, a new fault diagnosis method is proposed based on the improved particle swarm optimization (IPSO) algorithm-based variational modal decomposition (VMD) and relevance vector machine (RVM). Firstly, a simulation test bench for rotor faults is built, in which vibration displacement signals of the rotor are also collected by eddy current sensors. Then, the improved particle swarm algorithm is used to optimize the VMD to achieve adaptive decomposition of vibration displacement signals. Meanwhile, a screening criterion based on the minimum Kullback-Leibler (K-L) divergence value is established to extract the primary intrinsic modal function (IMF) component. Eventually, the factors are obtained from the primary IMF component to form a fault feature vector, and fault patterns are recognized using the RVM model. The results show that the extraction of the fault information and fault diagnosis classification have been improved, and the average accuracy could reach 97.87%.

Effect of Phosphodiesterase-5 Inhibitors on the Treatment of Male Infertility: A Systematic Review and Meta-Analysis

Dong Liang,Zhang Xiaojin,Yan Xuhong,Shen Yifeng,Li Yulin,Yu Xujun 대한남성과학회 2021 The World Journal of Men's Health Vol.39 No.4

Purpose: Male infertility is a worldwide problem with limitations in the treatment. Phosphodiesterase-5 inhibitors (PDE5is) is the first choice for the treatment of erectile dysfunction, more and more studies show that it has a certain effect on male infertility in recent years. But there was currently no high quality of systematic review to evaluate the effects of PDE5is on semen quality. Materials and Methods: We retrieved the electronic databases of MEDLINE, PubMed, Web of Science, EMBASE, etc. Related randomized controlled trials (RCTs) were collected and selected up to May 20, 2020. We have searched literature with terms “male infertility”, “phosphodiesterase-5 inhibitors”, “PDE5i”, “Tadalafil”, “Sildenafil”, “Vardenafil”, “Udenafil”, “Avanafil”, “semen”, and “sperm”. Mean value and its standard deviation were used to perform quantitative analysis. All statistical analyses were conducted by RevMan 5.3 and Stata software. Results: There were a total of 1,121 participants in the nine included studies. There was a statistically significant improvement treated with PDE5is compared with sham therapy, which including sperm concentration (mean difference [MD]=1.96, 95% confidence interval [CI]=1.70–2.21, p<0.001; MD=3.22, 95% CI=1.96–4.48, p<0.001), straight progressive motility (%) Grade A (MD=3.71, 95% CI=2.21–5.20, p<0.001), sperm motility (MD=8.09, 95% CI=7.83–8.36, p<0.001), morphologically normal spermatozoa (%) (MD=0.67, 95% CI=0.20–1.15, p=0.005; MD=1.27, 95% CI=0.02–2.52, p=0.05), sperm abnormalities (%) (MD=-0.64, 95% CI=-0.81–-0.47, p<0.001), and progressive motile sperm (MD=5.34, 95% CI=3.87–6.81, p<0.001). Conclusions: In this meta-analysis of nine RCTs, treatment with PDE5is could improve some indicators of male sperm.

Inductor Design Minimizing Power Loss for Boost Converter

Dong Liang,Eun-Sung Seo(서은성),Hwi-Beom Shin(신휘범) 전력전자학회 2016 전력전자학술대회 논문집 Vol.2016 No.7

Mathematical model and meshing analysis of internal meshing gear transmission with curve element

Dong Liang,Weibin Li,Bingkui Chen 대한기계학회 2020 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.34 No.12

A new internal meshing gear transmission with curve element is put forward in this paper. The mathematical principle of tooth profile generation is described based on conjugate curves theory. For a given spatial curve, the meshing equation and its conjugated spatial curve under the motion law were derived. Considering the equidistant kinematic method, general internal tooth profiles models were established by the conjugate-curve pair. Numerical example of the internal gear pair was developed according to gear parameters and gear solid models were established by MATLAB and UG software. Motion simulation result shows that the gear pair satisfies point contact condition and design requirements. Meshing analysis of tooth profiles using FEA method was carried out. Stress analysis results of tooth profiles with single point contact and two points contact were, respectively, obtained. The conclusions lay the foundation for multi-point contact generation and tooth profile design. Also, further studies on transmission characteristics and manufacturing technology of the new gear drive will be carried out.

Hobbing Manufacturing of New Type of Involute-Helix Gears for Wind Turbine Gearbox

Dong Liang,Bingkui Chen,Yane Gao 한국정밀공학회 2019 International Journal of Precision Engineering and Vol.6 No.2

The involute gears are widely used in the gearbox for wind turbine. To satisfy the requirements of reduction of noise and increase of the endurance of the gear drive, the new type of involute-helix gears, which have the advantages of involute gears and circular arc gears, had been proposed. In this paper, the hobbing cutters of involute-helix gears are designed utilizing the normal section of convex and concave tooth profiles, respectively. Mathematical models of hobbing cutters are established and general products are also manufactured. Using the developed hobbing cutters, the proposed gear pair is manufactured based on the numerical control technology. Combining with the measure method of gear measuring center and the characteristic of the investigated gears, the method of error measurement of special tooth profiles is provided. The further development of special detection software for the gears will be carried out. The results will lay the foundations for the large-scale industrial practice and production applications of gear drive.

Research on a New Collaborative Filtering Recommendation Algorithm Based on Data Mining

Dong Liang 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.10

Under the conditions of different community formation, this paper proposed two different models of formation communities. Firstly, we put forward two kinds of similarity calculation models, and compare them with the traditional similarity model, Secondly, several similarity models are tested under different conditions of community formation. Finally it compares tow models of forming communities and finds that for non-strict division of community model has a higher accuracy and diversity of recommendation, compared with the strict division of community model. Thus, the experiments show that the non-strictly divided communities’ model is more suitable for recommendation system, especially for the personalized recommendation.