Jaw Functional Orthopedics and Cranoficial Growth
Not a member yet
968 research outputs found
Sort by
Research on bearing equipment fault diagnoses via SAWOA-LSTM
Get PDFTo address the current low fault diagnosis accuracy problem for bearing equipment, and improve the detection methods, in this paper a sine-adapted whale optimization algorithm (SAWOA)-based optimization of a long short-term memory (LSTM) network is proposed as the equipment fault diagnosis method (SAWOA-LSTM). First, an optimization strategy based on sinusoidal population initialization and adaptive optimization is proposed for the whale optimization algorithm, which has the two drawbacks of slow convergence and easily falling into a local optimum. Second, to improve the accuracy and efficiency of fault diagnoses, the SAWOA is used to optimize the number of hidden units and the learning rate parameter of the LSTM. Compared with ACO-, PSO-, and WOA-based LSTM models, the proposed method improves diagnostic accuracy by 14.17 %, 15.03 %, and 4.32 %, respectively. In tests on 50 bearing samples, SAWOA-LSTM further improves accuracy for RBD, IRA, and ORD by 1.08 %, 1.62 %, and 1.10 %, respectively. Our algorithm provides an innovative solution for the health management of complex industrial bearing equipment
Self-supervised CNN for user behavior analysis on smart meter data
Get PDFSmart meters generate extensive data on individual consumer electricity usage, providing valuable insights that can aid in identifying demographic information and advancing the development of smart grids. Current research has primarily focused on traditional machine learning approaches for this task, with relatively few studies exploring deep learning methods, despite their potential for more accurate and efficient analysis. To address this gap, this paper proposes a self-supervised deep learning approach based on Convolutional Neural Network (CNN) to identify demographic information from smart meter data. The model leverages the Fast Fourier Transform (FFT) to detect frequency cycles within the dataset, which are then used to optimize the sizes of convolutional kernels. This design enhances periodic stability during shallow feature extraction, improving the model’s ability to capture meaningful patterns in the data. Furthermore, the model incorporates a self-supervised pre-training strategy to predict temporal and spatial interactions in load signals, effectively enhancing representation learning without relying on extensive labeled data. This approach ensures the model’s robustness and adaptability to different datasets. Comprehensive experiments were conducted on a publicly available Irish dataset to evaluate the model’s performance. Results demonstrate that the proposed model surpasses a series of state-of-the-art (SOTA) methods, achieving superior performance in demographic information identification. These findings highlight the effectiveness of integrating FFT-based kernel design and self-supervised learning in improving feature extraction and representation learning for smart meter data
Numerical simulation of chloride ion transport in concrete based on a random aggregate model
Get PDFA three-dimensional stochastic aggregate model of concrete was established using the Monte Carlo method, and a numerical simulation of chloride ion diffusion at the microscopic level was conducted. The study investigated the migration behaviour of chloride ions in concrete regarding mixing proportions and temperature. The results showed that compared to the simulation results at an ambient temperature of 20 ℃, the chloride ion diffusion coefficient increased by 31 % and 70.5 % for concrete at 25 ℃ and 30 ℃ at 28 days, respectively. The chloride ion penetration depth increased by 17.3 % and 34.9 % for concrete at 25 ℃ and 30 ℃, respectively. With a slag content of 10.4 %, 20.8 %, and 27.1 %, the chloride ion diffusion coefficient at 28 days decreased by 1.4 %, 2.7 %, and 4.1 %, respectively. With a fly ash content of 8.3 %, 16.7 %, and 25 %, the chloride ion diffusion coefficient at 28 days decreased by 2.1 %, 5.4 %, and 9.2 %, respectively. Both slag and fly ash can reduce the chloride ion diffusion coefficient in concrete, with fly ash showing better effectiveness than slag. A water-to-binder ratio of 0.4, combined with 27.1 % slag and 25 % fly ash as cement replacements, can effectively improve the resistance of concrete to chloride ion attack. The micro-scale finite element model of concrete, developed through Monte Carlo simulation, offers enhanced visualization of chloride ion penetration processes under varying mix proportions and temperature conditions
Complex fault diagnosis in wind turbine bearings: a hybrid approach combining the improved feature mode decomposition and convolutional neural networks
Get PDFThe complex noise interference and diverse fault-induced signals in vibration data from wind turbine equipment pose significant challenges for bearing fault diagnosis, including cumbersome methodologies, prolonged processing times, and compromised accuracy. To address these limitations, this study proposes a novel composite fault diagnosis framework that integrates Feature Mode Decomposition (FMD), Fast Spectral Kurtosis (FSK), and Convolutional Neural Network (CNN). While conventional Empirical Mode Decomposition (EMD) exhibits limited noise robustness and struggles to extract subtle fault signatures in composite failure scenarios, our approach employs FMD to decompose fault-related intrinsic mode functions (IMFs)and further filters the IMF components using fast spectral cliffs with enhanced feature separability. Subsequently, the Short-Time Fourier Transform (STFT) is applied to derive time-frequency representations, followed by Fast Spectral Kurtosis analysis to identify optimal demodulation bands for non-stationary signals. The energy spectrum of denoised signals is converted into grayscale images, serving as input to a tailored CNN architecture for hierarchical feature learning. Experimental validation demonstrates that this hybrid methodology achieves a fault recognition accuracy of 98 % under compound fault conditions, outperforming conventional EMD-based approaches in terms of noise immunity and diagnostic precision. Comparative analysis reveals an 8 % improvement in detection reliability over standalone deep learning models, particularly in low signal-to-noise ratio (SNR) environments. The proposed framework offers a robust solution for multi-fault identification in industrial Bearing machinery, demonstrating superior generalization capability across varying operational conditions
Design peculiarities and kinematic analysis of a shaking conveyor with multiple transporting and screening trays
Get PDFThe paper focuses on the design peculiarities and kinematic analysis of a novel shaking conveyor equipped with three interconnected transporting and screening trays. The goal is to develop a comprehensive mathematical model to describe the system’s motion and analyze the interplay between the trays, providing a basis for improved design and optimization. The scientific novelty lies in the detailed kinematic study of this specific multi-tray configuration, particularly the interaction of the dual beam systems actuating the intermediate tray, leading to complex coupled motion profiles. The practical value of the research is substantial for designing and optimizing such multi-functional vibratory equipment, as the kinematic data (displacements, velocities, accelerations) provide critical insights into material-tray interaction, aiding in predicting and enhancing material processing efficiency, estimating inertial loads for robust structural design, and informing vibration isolation strategies. The methods employed include the development of a kinematic diagram and corresponding motion equations for the multi-loop linkage mechanism, followed by numerical modeling of the system’s motion using Wolfram Mathematica software. The main results characterize the complex motion profiles for a steady-state operational frequency of 10 Hz, revealing distinct amplitudes and near-linear inclined trajectories for key hinges representing each tray. Notably, the upper tray exhibited the most significant displacements and accelerations, with horizontal accelerations reaching approximately 3 g and vertical accelerations around 1.3 g, indicating a motion profile conducive to effective material lifting, “throwing”, and bed stratification. Scopes of further research include a complete dynamic analysis incorporating mass properties and driving forces, experimental validation of the models, optimization of geometric and operational parameters, integration with Discrete Element Method (DEM) simulations for detailed material flow analysis, and investigations into wear, fatigue life, and advanced control strategies
Analysis of the natural characteristics of fiber-reinforced cantilever beams using 8-node solid elements
No full textA combined theoretical and experimental approach is employed to investigate the dynamic characteristics of fiber-reinforced cantilever beams. An 8-node element method establishes the theoretical model of the cantilever beam, allowing for the determination of its dynamic properties. A relevant experimental platform is constructed to test the fiber-reinforced cantilever beams, thereby validating the accuracy of the theoretical model. The results indicate that the theoretical model accurately predicts the dynamic characteristics of fiber-reinforced cantilever beams. Finally, based on the established theoretical model, the effects of cantilever beam length, width, and elastic modulus on the dynamic characteristics of the cantilever beam are discussed
Multi-parameter inversion of concrete face rockfill dam using wild horse optimizer and optimal polynomial chaos kriging
No full textStructural parameter inversion is essential for monitoring and assessing the risks of concrete face rockfill dams. Current parameter inversion techniques are, however, often overly complex, computationally demanding, and inefficient, especially when the dam is simulated with a 3D nonlinear finite element method. This study proposes a novel approach combining the Wild Horse Optimizer with Optimal Polynomial Chaos Kriging (WHO_OPCK) to tackle these issues. The method benefits from the low computational cost of optimal polynomial chaos kriging and the fast convergence of the wild horse optimizer. By incorporating statistical uncertainty in input parameters, the method successfully inverts four key constitutive parameters φ, Kb, K, and Rf based on displacement data from a complex dam. The approach proves practical and cost-effective in real engineering applications and has culminated in the development of specialized software that streamlines this structural parameter inversion process. Sensitivity analysis using Sobol’ indices further highlights the importance of each parameter at a low computational cost. The study highlights two key advantages of WHO_OPCK: (i) Unlike traditional methods that struggle with complex dams, WHO_OPCK significantly reduces computational costs and handles parameter determination efficiently. (ii) Compared to other surrogate model combinations with WHO, the proposed WHO_OPCK method offers superior accuracy and efficiency. This method establishes a solid foundation for multi-parameter inversion in concrete face rockfill dams
Experimental diagnostics of the condition and behavior of an excavation machine: a review of the most important methods
No full textThe paper presents an integral procedure for conducting experimental measurements on excavation machines. Excavators have a complex structure with pronounced dynamic behavior. The identification of exploitation behavior is observed through experimental measurement of stress and acceleration, drive load, and vibrations. Electro-resistive measuring tapes were used to observe the steel structure, devices for measuring current, i.e. engaged power on the drives, as well as devices for measuring vibrations at characteristic points of the drive. The results obtained realistically reflect the condition and behavior of the structure and drive equipment. The goal is to introduce systematic research to monitor the condition and behavior of the equipment on the excavator. This approach forms the backbone of predictive observation, influencing the proper management of the excavator. Experimental measurements are performed to prove the correctness of the numerical model and to diagnose the condition and behavior of the structure and power units. By monitoring the condition and behavior of the equipment, we can optimally influence the process of maintenance of the equipment as well as the lifespan of the mining machine. This work includes the most important experimental measurements to carry out reconstructions, revitalizations, and modernizations on mining machines
Research on the temperature system of an evaporator based on Smith-VUF PID
No full textTemperature serves as a critical process parameter in industrial systems, directly influencing reaction kinetics, product quality, and operational efficiency. The variation of temperature can affect reaction rate, product quality, and impurity generation, directly impacting production efficiency and product performance. However, due to the nonlinearity of temperature control systems, traditional controllers cannot meet design requirements, particularly in scenarios demanding high - temperature control accuracy, it is difficult for them to achieve a small deviation range. Therefore, this study focuses on the evaporator as the controlled object and conducts modeling, simulation analysis, and control strategy research on the evaporator temperature control system. It establishes the Smith-variable universe fuzzy PID(Smith-VUF-PID) temperature control system and deploys control strategies, solving issues such as large overshoot and inadequate control accuracy often encountered with traditional methods
Study on stability of shaft surrounding rock under adjacent shafts mining disturbance in underground mine
No full textThe stability of mine shafts is crucial for safe production in underground mining. To elucidate the impact of adjacent shaft mining disturbance on shaft structural stability in underground mines, this study takes a Manganese Mine in Guizhou, China as a case study. A refined three-dimensional model at engineering scale was established by using the Rhino-FLAC3D coupled modeling method. This model can numerically simulate the mining of ore bodies at different stages of mining. The displacement, stress distribution, and plastic zone in both strata and shaft surrounding rock were systematically analyzed to reveal the response laws of shaft surrounding rock under mining disturbance. The results showed that during the first and second mining phases, no measurable deformation occurred in the surrounding rock of the main shaft, auxiliary shaft, or ventilation shaft. During the third mining phase, the maximum displacement observed in these shafts’ surrounding rock reached 0.048 m, which remains within the stability threshold of rock masses according to evaluation criteria. Regression analysis was conducted on the monitoring displacement of three mining stages, and power function fitting curves were obtained. Plastic zones (20-30 m range) developed along the periphery of goaf areas, maintaining a safe distance of 45-55 m from adjacent shafts. A stress gradient formed around goaf areas, with tension stresses up to 1.33 MPa exceeding the ultimate tension strength of roof strata. There was potential tension failure in the roof strata of the goaf. Although mining disturbance effects on main and auxiliary shafts intensified with depth progression, no substantial structural impacts were observed. This confirms that all shaft structures can maintain stability during operational phases. The findings provide theoretical guidance for shaft stability control in deep mining operations