Exposed Aggregate Detection of Stilling Basin Slabs Using Attention U-Net Network

Yonglong Li,Xiaoxia Li,Haoran Wang,Shuang Wang,Shuhao Gu,Hua Zhang 대한토목학회 2020 KSCE Journal of Civil Engineering Vol.24 No.6

Exposed aggregate is a typical feature of the abrasion erosion in stilling basin slabs concrete surface. Although a variety of underwater robots are designed for inspection, the exposed aggregate detection for identifying abrasion is often done by manual work. The scarcity of image samples, large differences in aggregate size, color and shape are the main difficulties in automatic detection. To address this problem, an improved Attention U-Net deep fully convolutional network-based detection method was proposed. To realize this method, underwater images in site were captured via a self-developed operated underwater robot. Through randomly separating and the cropping of the 128 underwater images, the 512×512 pixels images dataset was built according to the ratio of 8:1:1, including 408 training images, 52 validation images and 52 test images. After the data augmentation, loss function and the optimizer were carefully designed and selected, the proposed Attention U-Net architecture was evaluated on this dataset. For comparative research, the full convolution network (FCN) and U-Net network were trained with the same training and validation dataset. The performance comparison on the test dataset showed that the Attention U-Net architecture has better detection accuracy.

Preview Repetitive Control for Linear Continuous-time System

Li Li,Xiaohua Meng,Yonglong Liao 제어·로봇·시스템학회 2023 International Journal of Control, Automation, and Vol.21 No.2

This paper presents a preview repetitive control for linear continuous-time systems when a periodic reference signal is previewed. First, an augmented two-dimensional (2D) system is constructed by state augmentation technique and a 2D model approach. Then, the preview repetitive control laws are proposed for the augmented 2D system, which transforms the preview repetitive control problem into a stabilization problem. Using Lyapunov functions, sufficient conditions for asymptotic stability of the 2D continuous-discrete system are derived in the form of linear matrix inequalities (LMIs). The design of a preview repetitive controller is proposed through the LMI approach. Finally, the developed design techniques are applied to two examples. The simulation results demonstrate the validity of the proposed method.

Fabrication of Superior Au–Ag Composites Surface-Enhanced Raman Scattering Active Substrates Based on One-Step Method of Chemical Etching

Li Zhang,Jinghuai Fang,Chaonan Wang,Tian Xu,Yonglong Jin 성균관대학교(자연과학캠퍼스) 성균나노과학기술원 2016 NANO Vol.11 No.7

Bimetallic silver–gold composites are currently among the most studied substrates for detection based on surface-enhanced Raman scattering (SERS). Here, we developed Au–Ag composite films as high sensitivity, large-scale, chemically stable and reproducible SERS substrates. Au–Ag composite films were fabricated by chemical etching of Ag–Au alloy leaves with HAuCl4 aqueous solutions. Along with galvanic replacement reaction and dealloying, films with distinct microstructural features exhibit dramatic improvement in the SERS intensity. Especially, the Au–Ag composite films with legible nano-ridges fabricated by alloy leaves of 9 carat present the strongest SERS enhancement. The superior SERS enhancement is attributed to the confluence effect of enhanced local surface plasmon fields and electromagnetic coupling within nanogaps, sharp edges and corners. In addition, results showed that features of the films mightily depend on the initial proportions of Ag–Au alloys.

Condition Assessment for Wind Turbines with Doubly Fed Induction Generators Based on SCADA Data

Sun, Peng,Li, Jian,Wang, Caisheng,Yan, Yonglong The Korean Institute of Electrical Engineers 2017 Journal of Electrical Engineering & Technology Vol.12 No.2

This paper presents an effective approach for wind turbine (WT) condition assessment based on the data collected from wind farm supervisory control and data acquisition (SCADA) system. Three types of assessment indices are determined based on the monitoring parameters obtained from the SCADA system. Neural Networks (NNs) are used to establish prediction models for the assessment indices that are dependent on environmental conditions such as ambient temperature and wind speed. An abnormal level index (ALI) is defined to quantify the abnormal level of the proposed indices. Prediction errors of the prediction models follow a normal distribution. Thus, the ALIs can be calculated based on the probability density function of normal distribution. For other assessment indices, the ALIs are calculated by the nonparametric estimation based cumulative probability density function. A Back-Propagation NN (BPNN) algorithm is used for the overall WT condition assessment. The inputs to the BPNN are the ALIs of the proposed indices. The network structure and the number of nodes in the hidden layer are carefully chosen when the BPNN model is being trained. The condition assessment method has been used for real 1.5 MW WTs with doubly fed induction generators. Results show that the proposed assessment method could effectively predict the change of operating conditions prior to fault occurrences and provide early alarming of the developing faults of WTs.

Condition Assessment for Wind Turbines with Doubly Fed Induction Generators Based on SCADA Data

Peng Sun,Jian Li,Caisheng Wang,Yonglong Yan 대한전기학회 2017 Journal of Electrical Engineering & Technology Vol.12 No.2

This paper presents an effective approach for wind turbine (WT) condition assessment based on the data collected from wind farm supervisory control and data acquisition (SCADA) system. Three types of assessment indices are determined based on the monitoring parameters obtained from the SCADA system. Neural Networks (NNs) are used to establish prediction models for the assessment indices that are dependent on environmental conditions such as ambient temperature and wind speed. An abnormal level index (ALI) is defined to quantify the abnormal level of the proposed indices. Prediction errors of the prediction models follow a normal distribution. Thus, the ALIs can be calculated based on the probability density function of normal distribution. For other assessment indices, the ALIs are calculated by the nonparametric estimation based cumulative probability density function. A Back-Propagation NN (BPNN) algorithm is used for the overall WT condition assessment. The inputs to the BPNN are the ALIs of the proposed indices. The network structure and the number of nodes in the hidden layer are carefully chosen when the BPNN model is being trained. The condition assessment method has been used for real 1.5 MW WTs with doubly fed induction generators. Results show that the proposed assessment method could effectively predict the change of operating conditions prior to fault occurrences and provide early alarming of the developing faults of WTs.

Structural Damage Detection using Deep Convolutional Neural Network and Transfer Learning

Chuncheng Feng,Hua Zhang,Shuang Wang,Yonglong Li,Haoran Wang,Fei Yan 대한토목학회 2019 KSCE JOURNAL OF CIVIL ENGINEERING Vol.23 No.10

During the long-term operation of hydro-junction infrastructure, water flow erosion causes concrete surfaces to crack, resulting in seepage, spalling, and rebar exposure. To ensure infrastructure safety, detecting such damage is critical. We propose a highly accurate damage detection method using a deep convolutional neural network with transfer learning. First, we collectedimages from hydro-junction infrastructure using a high-definition camera. Second, we preprocessed the images using an imageexpansion method. Finally, we modified the structure of Inception-v3 and trained the network using transfer learning to detectdamage. The experiments show that the accuracy of the proposed damage detection method is 96.8%, considerably higher thanthe accuracy of a support vector machine. The results demonstrate that our damage detection method achieves better damagedetection performance.