A5100395630- Drilling and Well Engineering
- Tunneling and Rock Mechanics
- Rock Mechanics and Modeling
- Interactive and Immersive Displays
- Tactile and Sensory Interactions
- Water Systems and Optimization
- Teleoperation and Haptic Systems
- Ergonomics and Musculoskeletal Disorders
- Educational and Technological Research
- Dam Engineering and Safety
- Advanced Numerical Analysis Techniques
- Advanced Neural Network Applications
- Geotechnical Engineering and Soil Stabilization
- Fire Detection and Safety Systems
- Photonic Crystal and Fiber Optics
- Geophysical Methods and Applications
- Fault Detection and Control Systems
- Human Pose and Action Recognition
- Ultrasonics and Acoustic Wave Propagation
- Advanced Fiber Optic Sensors
- Geotechnical Engineering and Analysis
- Mineral Processing and Grinding
- Advanced Optical Sensing Technologies
- Human Motion and Animation
- Video Analysis and Summarization
Northeast Petroleum University
2023-2024
China Railway Group (China)
2023
Institute for Forecasting of the Slovak Academy of Sciences
2023
Cytoskeleton (United States)
2023
Harbin Foresty Machinery Institute
2022
Fuzhou University
2022
University of Chicago
2021
Beihang University
2020
China Railway Construction Machinery Research & Design Institute
2019
This review summarizes the research outcomes and findings documented in 45 journal papers using a shared tunnel boring machine (TBM) dataset for performance prediction efficiency optimization learning methods. The big was collected during Yinsong water diversion project construction China, covering excavation of 20 km-section with 199 items monitoring metrics taken an interval one second. were result call contributions TBM contest 2019 covered variety topics related to intelligent TBM....
This review discusses the application scenarios of machine learning-supported performance prediction and optimization efficiency tunnel boring machines (TBMs). The rock mass quality ratings, which are based on Chinese code for geological survey, were used to provide "labels" suitable supervised learning. As a result, generation grades reasonably agreed with ground truth documented in maps. In contrast, main operational parameters, i.e., thrust torque, can be predicted historical data....
The variation in Tunnelling boring machine (TBM) equipment and geological information of tunnels result substantial differences real-time TBM tunnelling data. This makes it difficult to apply learning models trained by historical engineering data on new projects. To overcome this challenge, a novel conversion approach from mechanical analysis perspective has been proposed normalise data, such as cutterhead torque thrust, which help unify different projects under the same framework....
The reliability of autonomous driving sensing systems impacts the overall safety system. However, perception system fault diagnosis is currently a weak area research, with limited attention and solutions. In this paper, we present an information-fusion-based fault-diagnosis method for systems. To begin, built simulation scenario using PreScan software, which collects information from single millimeter wave (MMW) radar camera sensor. photos are then identified labeled via convolutional neural...
Skeleton tracking based on multiple Kinects data fusion has been proved to have better accuracy and robustness than single Kinect. However, previous works did not consider the inconsistency of in field Kinect self-occlusion human body assembly operation, which are vital importance performance task simulation. In this work, we developed a multi-Kinect algorithm achieve robust full-body virtual reality (VR)-aided Two reliability functions first applied evaluate confidences reflecting impacts...
This study presents a novel sensor that combines air pressure and temperature measurement using dual-interference microfiber resonators. The leverages intermode interference the resonant ring resonance effects within loop structure, enabling simultaneous demodulation of pressure. We have developed mathematical model is closely monitored alongside reflectance spectral structure. exhibits two distinct linear sensitivities for different temperature, as revealed by our testing results....
摘要: 基于TBM施工数据进行围岩感知对保障TBM施工安全、提高施工效率至关重要,其中TBM掘进参数预测的准确率是检验围岩感知效果的重要依据.为此,以吉林引松工程TBM四标段为研究对象,选取TBM上升段破岩数据为输入特征X1,选择两个施工控制参数(刀盘转速和推进速度)为输入特征X2,构建卷积神经网络机器学习模型,对TBM掘进响应参数Y(刀盘扭矩和总推力)进行预测.按照学习对象的不同,分别构建了只学习稳定段掘进响应行为的点预测模型和同时学习上升段和稳定段掘进响应行为的线预测模型,结果表明:点预测模型无法描述控制参数对掘进响应参数的影响;线预测模型虽然可以描述控制参数对掘进响应参数的影响,但是对稳定段的掘进响应预测数值偏低.考虑到上述局限性的原因是稳定段行为样本数量只占总样本数量的9%,提出了一种通过调节损失函数的方法来提高稳定段行为样本的权重,显著提高了线预测模型的预测精度.改进后的结果表明:在TBM掘进参数预测中,应对整个掘进段的行为进行学习,并提高稳定段行为的权重,以便获得高精度的掘进响应参数预测模型.获得的模型能够为进一步的围岩感知和控制参数优化提供基础. 关键词:...
Most analytical methods used to analyze the stability of pile-supported embankments are based on shear and bending failure piles. However, centrifuge test practical engineering show that rigid have a mode soil sliding around Therefore, analysis method embankment under piles upper bound theorem is given in this study. First, mechanism assumed be body slide along two logarithmic spiral surfaces soft soil. The rate external work internal energy dissipation further obtained, wherein obtained...
Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading models remain closed-source, resulting a notable performance gap between industry capabilities those available to public. In this report, we introduce HunyuanVideo, an innovative open-source foundation model that demonstrates comparable to, or even surpassing, of closed-source models. HunyuanVideo encompasses comprehensive framework integrates several key...
We propose a nail-mounted foldable haptic device that provides tactile feedback to mixed reality (MR) environments by pressing against the user's fingerpad when user touches virtual object. What is novel in our it quickly tucks away interacts with real-world objects. Its design allows fold back on top of nail not use, keeping free to, for instance, manipulate handheld tools and other objects while MR. To achieve this, we engineered wireless self-contained device, which measures 24×24×41 mm...
We propose a nail-mounted foldable haptic device that provides tactile feedback to mixed reality (MR) environments by pressing against the user's fingerpad when user touches virtual object. What is novel in our it quickly tucks away interacts with real-world objects. Its design allows fold back on top of nail not use, keeping free to, for instance, manipulate handheld tools and other objects while MR. To achieve this, we engineered wireless self-contained device, which measures 24×24×41 mm...
Civil aero-engine gas-path fault diagnosis is challenging due to its complicated parametric variation mechanism and the nonlinear relationship between performance parameter variation. There still lacks effective approaches provide reliable detection results with massive Quick Access Recorder(QAR) data which has been used monitor condition by expert experience. In this paper, we propose a novel methodology using Convolutional Neural Network(CNN). We use C-MAPSS train neural network. Using...
AdaBoost regression predicts the ranking of college students using super star learning APP
The performance of abnormal sound source localization technology for substation equipment based on acoustic sensor array is not only related to the processing algorithm, but also depends model sensor. Increasing number sensors improve estimation will often lead an increase in cost. This paper proposed a non-redundant fourth-order cumulant virtual expansion method uniform planar (UPA), which could without changing hardware design. Compared with low-order cumulant, high-order increases through...