Wheel fault diagnosis model based on multichannel attention and supervised contrastive learning

As wheels are important components of train operation, diagnosing and predicting wheel faults are essential to ensure the reliability of rail transit. Currently, the existing studies always separately deal with two main types of wheel faults, namely wheel radius difference and wheel flat, even though they are both reflected by wheel radius changes. Moreover, traditional diagnostic methods, such as mechanical methods or a combination of data analysis methods, have limited abilities to efficiently extract data features. Deep learning models have become useful tools to automatically learn features from raw vibration signals. However, research on improving the feature-learning capabilities of models under noise interference to yield higher wheel diagnostic accuracies has not yet been conducted. In this paper, a unified training framework with the same model architecture and loss function is established for two homologous wheel faults. After selecting deep residual networks (ResNets) as the backbone network to build the model, we add the squeeze and excitation (SE) module based on a multichannel attention mechanism to the backbone network to learn the global relationships among feature channels. Then the influence of noise interference features is reduced while the extraction of useful information features is enhanced, leading to the improved feature-learning ability of ResNet. To further obtain effective feature representation using the model, we introduce supervised contrastive loss (SCL) on the basis of ResNet + SE to enlarge the feature distances of different fault classes through a comparison between positive and negative examples under label supervision to obtain a better class differentiation and higher diagnostic accuracy. We also complete a regression task to predict the fault degrees of wheel radius difference and wheel flat without changing the network architecture. The extensive experimental results show that the proposed model has a high accuracy in diagnosing and predicting two types of wheel faults.

Kinematics and dynamics of an incomplete circular wheel drive of an agricultural tractor

The disadvantage of wheeled tractors is soil compaction, slipping due to limited traction, low tangential force. Experimental studies of a tractor with incomplete circular wheel mover on stubble, sand and virgin snow showed an increase in cross-country ability, a decrease in skidding, an increase in traction, and an increase in productivity. The purpose of the study is to develop a methodology for kinematic and dynamic analysis of incompletely rounded wheel propellers with a built-in differential. The equation of motion of the wheel is obtained on the basis of two-stage overcoming by the wheel of a single threshold obstacle taking into account the longitudinal and radial stiffness of the tire, its deformation, air resistance in the tire. The main influence is provided by translational speed, wheel radius and radial stiffness, the moment of inertia of the wheel and the shoulder of the application of mass. Planetary gearbox proposed in which the shaft of the driving satellite is a bearing, while the radius of the gear is an order of magnitude smaller than the radius of the wheel. The direction of improvement of wheel mover, increasing their traction properties is justified.

Flexible-Rigid Wheelset Introduced Dynamic Effects due to Wheel Tread Flat

The widespread faults that occur in railway wheels and can cause a massive dynamic impact are the wheel tread flat. The current work considered changes in vehicle speed or wheel radius deviation and studied the dynamic impact load. The modal technique for the impact evaluation induced by the wheel flat was proposed via the finite element analysis (FEA) software package ANSYS, integrated into a multibody dynamics model of the high-speed train CRH2A (EMU) through SIMPACK. The irregularity track line has developed and depends on the selected simulation data points. Additionally, a statistical approach is designed to analyze the dynamic impact load response and effect and consider different wheel flat lengths and vehicle speeds. The train speed influence on the flat size of the vertical wheel-rail impact response and the statistical approach are discussed based on flexible, rigid wheelsets. The results show that the rigid wheel flat has the highest vertical wheel impact load and is more significant than the flexible wheel flat force. The consequences suggest that the wheelset flexibility can significantly improve vertical acceleration comparably to the rigid wheel flats. In addition, the rendering of the statistical approach shows that the hazard rate, PDF, and CDF influence increase when the flat wheel length increases.

The Concept of a Wind Car with a Front Propeller

This is a concept of a wind car with a front side propeller. We all know that wind car can accelerate more than wind velocity. This concept has produced less friction hypothetically. This is a hypothetical concept. The ratio between the size of the propeller and the wheel radius will play a crucial role in the acceleration procedure.

An Investigation on the Effects of Input Parameters on the Dynamic and Electric Consumption of Electric Motorcycles

The purpose of this paper is to study how input parameters affect the dynamic characteristics and electric consumption characteristics of an electric motorcycle. To achieve this goal, a simulation model of the electric motorcycle, including dynamic models and battery models were established based on mathematical models and using the MATLAB SIMULINK software (Parnas Tower 14th Floor521 Teheran-street Gangnam-district Seoul 06164 Korea). The simulation model was used to determine the velocity, propulsion torque, electric consumption characteristics with variable electric motorcycle mass, driver mass, wheel radius, frontal area, and transmission ratio. Through the simulation study, the paper found that when the electric motorcycle mass was increased from 60 kg to 100 kg, the maximum velocity decreased by 5.45%, the moving distance was reduced by 5.89%, and electric consumption increased by 0.11%. Following increased driver mass from 48 kg to 88 kg, the velocity and moving distance decreased by 5.45% and 5.89%, respectively, while also increasing electric consumption by 0.11%. When the wheel radius was changed from 0.205 m to 0.245 m, the maximum velocity increased by 11%, the moving distance increased by 11.2%, and electric consumption increased by 0.11%. When the frontal area was increased from 0.52 m2 to 0.92 m2, the velocity and moving distance decreased by 2.43% and 2.06%, respectively, while electric consumption increased by 0.04%. When the transmission ratio was increased from 2.66 to 4.94, the velocity and moving distance increased from 30.74 km/h to 70.7 km/h and from 303.12 m to 710.44 m, respectively, while electric consumption increased by 0.16%. Finally, an experimental study is conducted to examine the dynamics of the electric motorcycle. The experimental results have the same trend with simulation in the same initial condition. Through combination simulation and experiment, the researcher can optimize the dynamic and electric consumption of an electric motorcycle.

DIMENSIONAREA SISTEMULUI DE PROPULSIE AL UNUI VEHICUL ELECTRIC. STUDIU DE CAZ

This paper aims to present to readers concrete mathematical models, transposed into simulation schemes, to calculate the forces acting on a car at its interaction with the road and the atmosphere, to properly size the electric motor and batteries of an electric car. For the calculation of these forces, a table with predefined values ​​such as vehicle mass, rolling resistance coefficient, gear ratio, wheel radius, was used throughout the work. In the second section of the paper, the values ​​of the resistance forces that oppose the movement of the vehicle and the traction force necessary to overcome these resistive forces were determined. The mathematical calculation model was compiled in Matlab and the graphs in figures 3-9 were obtained.

The permissible wheel load, wheel radius, and speed on a railroad

The paper aims to determine the permissible wheel load, wheel radius, and speed on a railroad considering fatigue shear stress in the rail head. In the literature, there are permissible wheel load and wheel radius formulae which consider shear fatigue limit as permissible shear stress; and hence do not offer acceptable wheel load, radius and speed. The deficiency lies in the permissible shear fatigue stress value. The permissible shear fatigue stress is suggested to be 24.4% of the tensile strength of rail steel with an assumed reliability of 99%. Addressing the deficiency, formulae are suggested for permissible wheel load, wheel radius and speed under three approaches. The formulae are generalised too considering the coefficient of friction at the wheel tread/rail interface. The permissible speed is suggested to be the minimum of two speeds based on the permissible shear fatigue stress at the wheel tread/rail interface and bending fatigue stress at the rail foot. A bending fatigue stress corresponding to a reliability of 95% is suggested for heavy haul because it makes a close balance between the two aforementioned speeds.

Adaptive Frame of Universal Vehicle Course

Background: Motor vehicles play an important role in the economies of many countries, providing efficient means of transporting goods and people. These vehicles can also have significant impacts on safety, infrastructure and the environment. Methods: The design of the suspension affects the vehicle's performance, in terms of the drive, damage to infrastructure, the working space of the suspension, power, and stability against overturning, stability against yaw, braking, and traction. Results: The article considers the types and methods of application of adaptive suspensions of modern vehicles, justifies the feasibility of their use for various vehicles, such as modern cars, tractors, etc., which allows the usage of these vehicles for traffic in different road conditions - mountainous terrains with a slope of more than 35o, steppe off-road conditions with frontal obstacles up to half the length of the wheel radius. Conclusion: The existing control schemes and prospects for their further development can be improved and intelligent transport systems could be introduced.

Scene wheels: Measuring perception and memory of real-world scenes with a continuous stimulus space

Precisely characterizing mental representations of visual experiences requires careful control of experimental stimuli. Recent work leveraging such stimulus control in continuous report paradigms have led to important insights; however, these findings are constrained to simple visual properties like colour and line orientation. There remains a critical methodological barrier to characterizing perceptual and mnemonic representations of realistic visual experiences. Here, we introduce a novel method to systematically control visual properties of natural scene stimuli. Using generative adversarial networks (GAN), a state-of-art deep learning technique for creating highly realistic synthetic images, we generated scene wheels in which continuously changing visual properties smoothly transition between meaningful realistic scenes. To validate the efficacy of scene wheels, we conducted a memory experiment in which participants reconstructed to-be-remembered scenes from the scene wheels. Reconstruction errors for these scenes resemble error distributions observed in prior studies using simple stimulus properties. Importantly, memory precision varied systematically with scene wheel radius. These findings suggest our novel approach offers a window into the mental representations of naturalistic visual experiences.

Wheel shape optimization approaches to reduce railway rolling noise

A wheel shape optimization of a railway wheel cross section by means of Genetic Algorithms (GAs) is presented with the aim of minimizing rolling noise radiation. Two different approaches have been implemented with this purpose, one centred on direct Sound poWer Level (SWL) minimization, calculated using TWINS methodology, and another one emphasizing computational efficiency, focused on natural frequencies maximization. Numerical simulations are carried out with a Finite Element Method (FEM) model using general axisymmetric elements. The design space is defined by a geometric parametrization of the wheel cross section with four parameters: wheel radius, a web thickness factor, fillet radius and web offset. For all wheel candidates, a high-cycle fatigue analysis has been performed according to actual standards, in order to assure structural feasibility. Rolling noise reductions have been achieved, with a decrease of up to 5 dB(A) when considering the wheel component. Response surfaces have been also computed to study the dependency of the objective functions on the geometric parameters and to test the adequacy of the optimization algorithm applied.