JVE International
Not a member yet
1200 research outputs found
Sort by
Gabor wavelet transform combined with area CNN in appearance intelligent detection of stayed cables
Get PDFThe major structure for transmitting forces in a cable-stayed bridge is the stay cable. If the stay cable system fails, the whole bridge will collapse. At present, there is no very mature technical means for the detection of bridge cables. The most common method is for workers to perform regular manual inspection and replacement of cables. Although the defect condition of the cable can be detected to a certain extent, the real-time monitoring of its health cannot be realized. Therefore, the research used the median filter, mean standardization method and Retinex algorithm to preprocess the image data. And after extracting the stay cable picture’s macroscopic characteristics using the Gabor wavelet transform, it implemented image segmentation using the OTSU approach. The obtained feature images were applied to the Faster Regional Convolution Neural Network (RCNN) recognition model to detect microscopic defects. During the research, the training efficiency of traditional Convolution Neural Network (CNN) was not high. Therefore, Faster RCNN built a cable defect recognition model. Based on this, the research built an intelligent detection model for apparent defects of stay cables based on Gabor wavelet transform and improved RCNN. Through the experimental analysis, the model built for the study has a recognition accuracy rate of 94.14 %, which can achieve dynamic bridge health monitoring and instantly identify the condition of the stay cables, and maintain the safety of the bridge
Application of machine learning techniques for obesity prediction: a comparative study
Get PDFObesity, characterized by excess adipose tissue, is becoming a major public health problem. This condition, caused primarily by unbalanced energy intake (overconsumption) and exacerbated by modern lifestyles such as physical inactivity and suboptimal dietary habits, is the harbinger of a variety of health disorders such as diabetes, cardiovascular disease, and certain cancers. Therefore, there is an urgent need to accurately diagnose and assess the extent of obesity in order to formulate and apply appropriate preventive measures and therapeutic interventions. However, the heterogeneous results of existing diagnostic techniques have triggered a fierce debate on the optimal approach to identifying and assessing obesity, thus complicating the search for a standard diagnostic and treatment method. This research primarily aims to use machine learning techniques to build a robust predictive model for identifying overweight or obese individuals. The proposed model, derived from a person's physical characteristics and dietary habits, was evaluated using a number of machine learning algorithms, including Multilayer Perceptron (MLP), Support Vector Machine (SVM), Fuzzy K-Nearest Neighbors (FuzzyNN), Fuzzy Unordered Rule Induction Algorithm (FURIA), Rough Sets (RS), Random Tree (RT), Random Forest (RF), Naive Bayes (NB), Logistic Regression (LR), and Decision Table (DT). Subsequently, the developed models were evaluated using a number of evaluation measures such as correlation coefficient, accuracy, kappa statistic, mean absolute error, and mean square error. The hyperparameters of the model were properly calibrated to improve accuracy. The study revealed that the random forest model (RF) had the highest accuracy of 95.78 %, closely followed by the logistic regression model (LR) with 95.22 %. Other algorithms also produced satisfactory accuracy results but could not compete with the RF and LR models. This study suggests that the pragmatic application of the model could help physicians identify overweight or obese individuals and thus accelerate the early detection, prevention, and treatment of obesity-related diseases
Dynamic analysis of gear pairs with the effects of stick-slip
Get PDFThe instantaneous dynamic contact state analysis is carried out to reveal the process of scuffing failure of the gear tooth pair. A stick-slip dynamic model of a two-gear set is proposed and the coupling effects of time-varying mesh stiffness, tooth separations, friction between the gear teeth surfaces, and potential stick-slip are considered. Dynamic analysis shows that stick contact is an important source of tooth scuffing failure. Additionally, stick contact dramatically increases the vibration amplitudes and causes chaos. Parametric studies show that heavy load and rough tooth surfaces increase the probability of sticking and increase the time of stick state over a single mesh period. This study provides a design guard for avoiding scuffing failure and improving the reliability of gear transmission
Field test of blasting vibration and adjacent slope stability under the influence of blasting vibration in mining
Get PDFBlasting mining in open-pit has a significant impact on the adjacent slope, which often causes the rock mass cracking and spalling of the slope to form a landslide disaster. In order to explore the impact of blasting vibration on the adjacent slope, field tests were carried out with professional testing equipment, and several blasting vibration data were measured. Sadovsky formula was used for fitting analysis, and the influence coefficient of blasting vibration was obtained. The slope stability analysis was carried out by using the limit equilibrium SLIDE analysis software, and the slope safety factor under the influence of blasting vibration was obtained. The results show that: The maximum blasting vibration speed monitored in this blasting is 2.1987 cm/s, and the main vibration frequency is 14.6484 Hz. Therefore, according to the standards in the regulations, the impact of this blasting on the slope meets the corresponding requirements. In this slope stability analysis, the blasting vibration influence coefficient Kc= 0.032, when 40 m away from the final slope is used. Morgen Prince method and Spencer method generally have higher safety factors than Bishop method. The safety factor of the analysis section at the 45° slope angle is 1.217. The slope can maintain stability under the influence of blasting vibration
A review on different regulation for the measurement of transport noise and vibration
Get PDFTransport noise and vibration have a negative influence on the environment, human health, and quality of life. The measurement and analysis of transport noise and vibration are required by the regulations and guidelines that various countries have set in order to manage and mitigate these effects. This review paper provides an overview of the requirements for the measurement and analysis of vibration and noise in transportation in different countries. The paper examines the measurement and analysis parameters, methods, and standards used in the United States, Europe, Australia and Japan. The review finds that although the requirements for measurement and analysis vary between countries, there are common parameters and methods used worldwide, such as sound pressure level and frequency spectrum measurements, noise and vibration impact assessment, prediction, and control measures. A comprehensive understanding of the measurement and analysis requirements for transport noise and vibration in different countries is essential for ensuring compliance with regulations, mitigating adverse impacts, and promoting sustainable transport development
Experimental study on bulge deformation of geotextile under ring-restrained conditions
Get PDFGeotextile layers are arranged on and below the geomembrane to prevent the geomembrane from being punctured and damaged. The geotextile not only plays a role in physical protection, like anti-puncture but also makes a great difference to the mechanical properties of the geomembrane’s air expansion deformation. In this paper, the bulging deformation of geotextile is simplified as spherical bulging deformation under ring-restrained conditions. Using the special bulging deformation test equipment, the bulging deformation experiment of geotextile is realized, the main factors affecting the bulging deformation are analyzed, the law of bulging deformation and failure of geotextile is summarized, the failure mechanism of geotextile and the Influence of geotextile on the properties of geomembrane are discussed, and the following conclusions are drawn. The failure of bulging deformation of geotextiles belongs to tensile failure, which is characterized by fast speed and high strength. The typical failure mode is spindle-shaped cracks distributed along the crown, whose failure mechanism belongs to tensile failure produced in weak areas. The bulging deformation of the geotextile shows nonuniformity, with the largest deformation at the crown top and the smallest deformation at the ring constraint. When the geotextile is covered on the geomembrane, bulging pressure is shared by both the geomembrane and the geotextile. At the initial deformation stage, the geomembrane replaces it, and then the geotextile bears more internal pressure and plays a decisive role till destruction
Temperature and humidity sensor monitoring of directly buried cable based on temperature field distribution simulation of power cable
Get PDFPower cable is a piece of major transmission equipment, and its operating temperature as a major factor determines whether the cable system can operate safely and reliably and the current-carrying capacity. Therefore, it is of great significance to master the real-time temperature and the distribution of the power cable core. During the aging of cable insulation, temperature, as a major factor, directly determines the aging rate. One of the basic parameters on the power cable is the ampacity. If the ampacity is high, the cable will be overloaded. In this paper, the thermal circuit method is used to construct and calculate the cable, and the whale algorithm is used to estimate the temperature of the cable conductor. The conductor is estimated accurately within the allowable error range. The results are compared with the results of finite element simulation to verify the effectiveness of the finite element method. Through the experimental analysis, the model is established according to the cable trench on the spot. The steady-state temperature field is calculated through parameter setting. The average packet loss rate is 0.066 %, and the relative error is 0.32 %, which proves that this study can optimize the communication mode of the network and achieve a better monitoring effect. The method realizes the real-time temperature rise prediction of the cable core conductor by using the temperature rise of the outer skin. It can provide a certain theoretical basis for the online monitoring and engineering practical application of the cable core temperature and has practical significance
Design and analysis of experimental adaptive feedback system for active noise control (ANC) in a duct
Get PDFThe limitations of passive noise control methods impose a need for new technical solutions to solve the problem of reducing low-frequency noise, which is considered to be a dominant component of noise disturbance. In recent years, the subject of intensive research are the active noise control systems, which have aroused considerable interest and represent a promising solution to the problem of low-frequency noise control. This paper proposes a robust methodology for simplified design and analysis of an experimental active noise control system for real-time control of acoustic environment in a duct. The proposed feedback control model is based on using the LMS algorithm, combined with FxLMS algorithm for estimation and neutralization of the secondary path in the electro-acoustic system. The study shows the potential of the FPGA module and the Real-time module of cRIO from National Instruments, combined with the LabView software environment when applied in adaptive system for active noise control. The reliability and validity of the developed active noise control system is tested for a frequency range of 100 to 1000 [Hz], by measuring the amplitude-time domain in [V] and sound level in [dB]. The comparison of the experimental results shows great efficiency of the system at lower frequency range from 200 to 400 [Hz], where a maximum reduction in sound level achieved at a frequency of 200 [Hz] is 14 [dB] or 17 [%]. A significant sound level reduction is also achieved at both 300 [Hz] and 400 [Hz] which is 12 % or 10 [dB] in both cases. Given the analysis of the challenges and opportunities of the developed active noise control system, recommendations for advancements and future work are proposed
Wave propagation in different theories of fractional thermoelasticity
Get PDFIn the present paper, the theories of fractional thermoelasticity with derivative and integral fractional orders are employed to study the homogeneous plane waves and the Rayleigh surface waves. The governing equations of homogeneous and isotropic generalized fractional thermoelasticity are solved for plane wave solutions and a dispersive velocity equation is obtained. There exists one transverse and two coupled longitudinal waves in a two-dimensional model of fractional thermoelastic medium where the speeds of coupled longitudinal waves are found to be dependent on the derivative and integral fractional orders. The Rayleigh waves is also studied along the traction-free surface of a half-space of a generalized fractional thermoelastic solid. The governing equations are solved for the general surface wave solutions which follow the decaying conditions in the half-space. A Rayleigh wave secular equation is obtained for thermally insulated surface. For a particular example of the present model, the numerical values of the speeds of coupled longitudinal waves and the Rayleigh wave are computed and graphically illustrated to visualize the effects of derivative and integral fractional orders and the circular frequency on the wave speeds
Research on deformation of valve slice of automobile shock absorber
Get PDFBased on the bending deformation theory of cantilever beam, the mathematical model of bending deformation of single valve slice under uniform load is proposed and deduced by using the microbeam element method (MEM). The accuracy and reliability of the mathematical model established by the MEM and the small deflection method (SDM) are verified through the finite element simulation comparison. The results show that the valve slice deformation mathematical model under uniform load established by using the deformation theory of the MEM is suitable not only for the small deflection deformation (SDD) but also for the large deflection deformation (LDD) of the valve slice, and can reflect the dynamic deformation characteristics of the valve slice more truly than the SDM, which provides a certain theoretical basis for the deformation study of single valve slice. At the same time, the mathematical model is used to simulate the deformation law of the valve slice when the thickness, inner radius and outer radius change. The conclusion provides technical support for the design and performance prediction of the shock absorber