A5090268937- Ultrasonics and Acoustic Wave Propagation
- Non-Destructive Testing Techniques
- Structural Health Monitoring Techniques
- 2D Materials and Applications
- Optical measurement and interference techniques
- Thermography and Photoacoustic Techniques
- Machine Fault Diagnosis Techniques
- AI in cancer detection
- Gear and Bearing Dynamics Analysis
- Graphene research and applications
- Optical Systems and Laser Technology
- Diabetic Foot Ulcer Assessment and Management
- Flow Measurement and Analysis
- GNSS positioning and interference
- Engineering Diagnostics and Reliability
- Geophysical Methods and Applications
- Quantum Dots Synthesis And Properties
- MXene and MAX Phase Materials
- Image Processing Techniques and Applications
- Image Retrieval and Classification Techniques
- Digital Imaging for Blood Diseases
- Advanced Frequency and Time Standards
- Advanced Optical Sensing Technologies
- 3D Surveying and Cultural Heritage
- Advanced Computational Techniques and Applications
Shandong University
2019-2024
Shandong Academy of Sciences
2023
Qilu University of Technology
2023
Université Grenoble Alpes
2020
Centre Hospitalier Universitaire de Grenoble
2020
Qingdao Binhai University
2020
Chongqing University
2018-2019
Army Medical University
2019
Southwest Hospital
2019
The First Affiliated Hospital, Sun Yat-sen University
2019
A key issue in black-box testing is how to select adequate test cases from input domain on the basis of specification. However, for some kinds software, developing output more suitable than domain. In this paper, we present a novel approach automatically generate model created via neural network take as function substitute software under test, and then model, given outputs employ an improved genetic algorithm find corresponding inputs, so that automation generation completed. order...
Abstract Pipeline structures are widely used in industry, but the increase service life may lead to damage pipeline structure, bringing economic losses. Ultrasonic Guided Wave has been for accurate detection of structures. However, temperature variations can also changes guided wave signals. In order reduce influence brought by external environment, this paper proposes a dual-signal reconstruction method based on empirical modal decomposition. By simultaneously performing mode decomposition...
Ultrasonic guided wave (UGW) imaging technology has been extensively adopted to assess the structural performance of composite laminates for its high detection accuracy, quick speed, and real-time capability. However, algorithm design in structures is hindered by complexity anisotropy dispersion. It still challenging optimize localization range sparse sensing arrays though probabilistic diagnostic (PDI) method avoids precise signal analysis. In this study, a modified delay factor-based...
Ultrasonic guided wave detection technology is the one of most effective damage identification method in structural health monitoring, but external factors will cause errors during identifying damage. Based on ring probability distribution and path optimization, a Bayesian fusion localization proposed. Firstly, band healthy signal damaged collected by piezoelectric sensor array selected, solve correlation. The threshold obtained correlation coefficient screened, so obtain valid greatly...
Pipeline structures are widely used in construction, oil transportation and other industrial fields, but with increasing service life, pipeline can develop health problems such as perforations cracks, which cause fractures bring serious safety accidents economic losses if they aren't detected at an early stage. Ultrasonic guided wave detection technology has been applied precise damage of structures. To facilitate the grasp structural status, a imaging method combined time-of-flight (ToF)...
The hole-structural bearing crossbeam plays an important role in high-speed trains. In the service process, however, long-term fatigue load may lead to structural damage such as cracks, resulting performance degradation and failure. Ultrasonic guided wave (GW) technology is one of most effective localization methods health monitoring (SHM), with a high sensitivity wide range. To address crossbeams, modified reconstruction algorithm for probabilistic inspection (RAPID) based on corrected...
The in-situ observation is of great significance to the study growth mechanism and controllability two-dimensional transition metal dichalcogenides (TMDCs). Here, differential reflectance spectroscopy (DRS) was performed monitor molybdenum disulfide (MoS2) on a SiO2/Si substrate prepared by chemical vapor deposition (CVD). A home-built DRS setup applied MoS2 in-situ. formation evolution monolayer are revealed (DR) spectra. morphology, vibration mode, absorption characteristics thickness have...
Click-Through Rate (CTR) prediction is one of the core tasks in recommender systems (RS). It predicts a personalized click probability for each user-item pair. Recently, researchers have found that performance CTR model can be improved greatly by taking user behavior sequence into consideration, especially long-term sequence. The report on an e-commerce website shows 23\% users more than 1000 clicks during past 5 months. Though there are numerous works focus modeling sequential behaviors,...
State monitoring and fault diagnosis of an internal combustion engine are critical for complex machinery safety. In the present study, a high‐frequency vibration system was proposed based on Fiber Bragg Grating (FBG) cantilever sensor intelligent algorithm. Structural signal containing information valves oil nozzle identified by FBG sensors preprocessed using wavelet decomposition reconstruction. Moreover, energy taken as characteristics. Subsequently, identification model built multiclass υ...
The accurate and instant diagnosis of burn severity is always the key point optimal wound management clinical treatment. However, accuracy depth assessment low via visual inspection lacks a quantitative measurement. In this work, full-field detection system proposed using near-infrared hyperspectral imaging with ensemble regression. rotational feature subspace regression introduced to establish complex model between data depth. By in vivo measurement porcine model, method can get average...
Abstract The lack of labelled data presents a common challenge in many fault diagnosis and machine learning tasks. It requires the model to be able efficiently capture useful features from smaller amount data. In this paper, method train multiple convolutional auto‐encoders by self‐learning integrate them using ensemble learning, called self‐taught (STL‐CAEs), is proposed, which can effectively extract bearing vibration signals. First, an strategy proposed obtain two that satisfy optimizing...
Fringe projection profilometry (FPP) technology is an important method for 3D reconstruction. In this paper, we proposed a flexible calibration of FPP system based on the imaging principle and geometrical structure system. The target coordinates are only related to its pixel phase. First, fringe images projected onto plate, phase can be calculated through four-step phase-shifting method. Then, feature points located with binarized centroid Finally, parameters by nonlinear least-squares...