A5100366356- Bladed Disk Vibration Dynamics
- Machine Fault Diagnosis Techniques
- Turbomachinery Performance and Optimization
- Gear and Bearing Dynamics Analysis
- Adhesion, Friction, and Surface Interactions
- Brake Systems and Friction Analysis
- Structural Health Monitoring Techniques
- Industrial Vision Systems and Defect Detection
- Fault Detection and Control Systems
- Concrete and Cement Materials Research
- Advanced Algorithms and Applications
- Engineering Diagnostics and Reliability
- Heat Transfer Mechanisms
- Geotechnical Engineering and Underground Structures
- Fatigue and fracture mechanics
- Erosion and Abrasive Machining
- Transportation Safety and Impact Analysis
- Power System Reliability and Maintenance
- Smart Grid and Power Systems
- Material Properties and Failure Mechanisms
- Innovative concrete reinforcement materials
- Energy Load and Power Forecasting
- Cyclone Separators and Fluid Dynamics
- Advanced Aircraft Design and Technologies
- Model Reduction and Neural Networks
Xi'an Jiaotong University
2015-2025
China University of Mining and Technology
2024
Fuzhou University
2023
China Resources (China)
2023
Southwest Petroleum University
2020
Henan Normal University
2020
Beijing University of Technology
2020
Jiangsu University of Science and Technology
2018
China Datang Corporation (China)
2012
Universidad del Noreste
2011
(1) Background: Rolling bearings are important components in mechanical equipment, but they also with a high failure rate. Once malfunction occurs, it will cause equipment to and may even affect personnel safety. Therefore, studying the fault diagnosis methods for rolling is of great significance current research hotspot frontier. However, vibration signals usually exhibit nonlinear non-stationary characteristics, easily affected by industrial environmental noise, making difficult accurately...
This paper focuses on the steady vibration characteristics of bladed-disk subjected to dry friction damping under periodic excitation. The multi-harmonic method and continuation procedure are combined trace solution nonlinear forced problem. To obtain a stable fast solver, analytical formulation Jacobian matrix in frequency-domain is derived for elastic Coulomb model with variable normal force. Furthermore, generalized via different parameters, including not only commonly used excitation...
In recent years, machine learning techniques have been proven to be a promising tool for early fault detection of rolling bearings. many actual applications, however, bearing whole-life data are not easy historically accumulated, while insufficient may result in training model that is good enough. If utilizing the available under different working conditions facilitate training, distribution bearings usually quite different, which does meet precondition i n d e p t c l s r b u o ( . ) and...
Abstract In this paper, a method for predicting remaining useful life (RUL) of turbine blade under water droplet erosion (WDE) based on image recognition and machine learning is presented. Using the experimental rig testing WDE characteristics materials, morphology pictures specimen surface at different times in process are collected. According to data processing ASTM-G73 cumulative erosion-time curves, stages materials quantitatively divided coefficient (ζ) defined. The could be used...
In general, only in tangential direction, friction motion between blade dampers is concerned for vibration analysis of mistuned bladed disk. However, practical, excitation acting on blades inevitably causes normal movement at interface due to the existence angle force and contact surface. This fact leads a variation or even result separation, which determine maximum static frictional vibration. order assess realistic nonlinear forced disk assemblies subjected actual with contact, an...
Intelligent fault diagnosis using deep learning has achieved much success in recent years. Using method to diagnose bearing requires designing an appropriate neural network model and then train with a massive data. On the one hand, up now, variety of structures have been proposed for different diagnostic tasks, but there is lack research unified structure. other data training are collected from location point, which quite actual data, because sensor cannot be located at point accurately....
With increasing consumption of primary energy and deterioration the global environment, clean sources with large reserves, such as natural gas, have gradually gained a higher proportion structure. Monitoring predicting data play crucial role in reducing waste improving supply efficiency. However, owing to factors high monitoring device costs, safety risks associated installation, low efficiency manual meter reading, gas at household level is challenging. Moreover, there lack methods for...
Deep foundation pit settlement prediction based on machine learning is widely used for ensuring the safety of construction, but previous studies are limited to not fully considering spatial correlation between monitoring points. This paper proposes a transformer-based deep method that considers both and temporal correlations among excavation The proposed creates dataset collects all points into vector consider transformer, which can handle correlations. To verify model's accuracy, it was...
Abstract The wide application of transfer learning technology can effectively solve the problem difference between data collection and actual equipment traditional intelligent fault diagnosis methods in practical process. However, subdomain space serious imbalance samples process simultaneous restricts deep to engineering high-precision diagnosis. In order matching with different subspaces unbalanced samples, this paper we study adaptive method propose a scale (SASM) method. SASM divides...
Abstract This paper proposes a deep learning algorithm to diagnose ship faults in order improve the accuracy and diagnostic efficiency of fault diagnosis. 90% large number unlabeled operational data samples are selected for model training, remaining 10% is used testing. We optimize parameters diagnosis classification. Hidden layer functions extract multi-layer features perform feature fusion. Gain values define faults, primary secondary tertiary faults. Finally, we use soft-max classifier...
The requirement for frequent start-ups and shutdowns is prevalent in turbo-generator units to accommodate fluctuating loads during flexible operations. These cause drastic changes temperature stress, leading instantaneous structural deformations. Hence, research on intelligent start-up control essential ensuring safety. In this work, a rotor stress field reconstruction model based deep convolutional neural network was first designed. This enabled rapid prediction of the foundation...