The train horn sound is an active audible warning signal used for warning commuters and railway employees of the oncoming train(s), assuring a smooth operation and traffic safety, especially at barrier-free crossings. This work studies deep learning-based approaches to develop a system providing the early detection of train arrival based on the recognition of train horn sounds from the traffic soundscape. A custom dataset of train horn sounds, car horn sounds, and traffic noises is developed to conduct experiments and analysis. We propose a novel two-stream end-to-end CNN model (i.e., THD-RawNet), which combines two approaches of feature extraction from raw audio waveforms, for audio classification in train horn detection (THD). Besides a stream with a sequential one-dimensional CNN (1D-CNN) as in existing sound classification works, we propose to utilize multiple 1D-CNN branches to process raw waves in different temporal resolutions to extract an image-like representation for the 2D-CNN classification part. Our experiment results and comparative analysis have proved the effectiveness of the proposed two-stream network and the method of combining features extracted in multiple temporal resolutions. The THD-RawNet obtained better accuracies and robustness compared to those of baseline models trained on either raw audio or handcrafted features, in which at the input size of one second the network yielded an accuracy of 95.11% for testing data in normal traffic conditions and remained above a 93% accuracy for the considerable noisy condition of-10 dB SNR. The proposed THD system can be integrated into the smart railway crossing systems, private cars, and self-driving cars to improve railway transit safety.
The paper describes the developed curvilinear motion simulation model for a vehicle with two traction electric motors moving on a solid surface used to study the dynamic properties of a wheeled vehicle and to subject the developed methods to virtual testing. The simulation model of the electric all-wheel drive vehicle is carried out in the Simcenter Amesim environment to account for the dynamic characteristics and features of the vehicle. The simulation model was developed based on the drawn requirements while the assumptions were justified. Inertia characteristics, tire characteristics, suspension elements, grip characteristics, and surface and air resistance were considered, as these factors affect the vehicle longitudinal and transverse dynamics. The article presents the model implemented in the “Labcar” system and confirms its adequacy by comparing it with the data obtained during the full-scale prototype tests. The bench and range tests of a test vehicle with electric transmission equipped with a measuring complex confirmed the adequacy of the developed model. The results of comparative tests allow for the conclusion that the developed model complex is suitable for modeling purposes, including studying, debugging and initial calibrations of the algorithm of torque distribution on the driving axles of all-wheel drive electric vehicle.
The wheels of decelerating vehicles in braking mode roll with increased slip, up to complete lock-up, which is a negative phenomenon. This is effectively managed by the anti-lock braking system (ABS). However, in the course of braking, especially before the system activation, self-excited oscillatory processes with high amplitudes may occur, causing increased dynamic loads on the drive system. The paper studies the braking processes of a vehicle with an electromechanical individual traction drive in both electrodynamic regenerative and combined braking modes, utilizing the drive and the primary braking system. The theoretical framework is provided for identifying the self-excited oscillation onset conditions and developing a technique to detect wheel slips during braking to suppress these oscillations. To check the functionality of the wheel-slip observer in braking mode, the performance of the self-excited oscillation pulse suppression algorithm was studied in the MATLAB Simulink 2018b software package. The study results can be used to develop control systems equipped with the function of suppressing self-excited oscillations by vehicle motion.
The electric traction drive is increasingly being applied as a device providing traction force on driving wheels. This is due to its reliable torque transmission to the driving wheels, step-less regulation of the traction force on the driving wheels depending on the driving conditions, and increased design capabilities. In terms of power, the electric traction drive has maximum torque at low speeds, which internal combustion engines lack. This property of the electric drive is not applied in urban vehicles, as not all passengers are comfortable with intensive acceleration. In modern vehicles with an electric traction drive, the maximum acceleration can be limited by software, which is the focus of this study. This paper aims to develop an algorithm capable of recognizing when the permissible longitudinal acceleration exceeds the limit and generating an action to maintain the acceptable acceleration level. The electric traction drive of a large-class electric bus was used as a control object. An algorithm and a control law are hereby developed, which reduce longitudinal acceleration using PI control. Both simulation modeling and full-scale tests on the electric bus were carried out to evaluate the performance and efficiency of the algorithm. In this paper, the authors also introduce the cumulative velocity concept and prove the operability and efficiency of the developed method.
This paper presents an experimental study of the Automatic Emergency Braking (AEB) system, focusing on three essential testing phases: verifying the match between calculated and actual brake actuator operation time, validating the forecasted vs. real-time stabilized deceleration onset duration, and comparing the theoretically computed braking distance derived from mathematical models with its actual measurement. Standard instrumentation coupled with an original test procedure was utilized during the experiments. A full-scale experimental campaign was conducted on a specialized proving ground, thus substantiating the validity and robustness of the computational models used for assessing the AEB system parameters. The empirical outcomes confirmed that current-generation AEB systems offer dependable predictions regarding braking dynamics and exhibit prompt responsiveness to imminent collisions. However, it should be noted that variations in road conditions, driver behavior, and sensor precision may affect their performance. Consequently, additional efforts aimed at optimizing existing AEB solutions are required to minimize potential errors and enhance overall reliability. Finally, the significance of complying with design specifications and continuously upgrading AEB systems to meet evolving road safety standards is emphasized.
31 December 2024 in International Journal of Automotive Science And Technology
This research focuses on the development of a methodology for the analysis of nonlinear oscillations of a vehicle cab with a suspension system. When designing vehicles with cab suspension systems, it is important to align their operation with other vehicle modules and systems that collectively ensure the required comfort and dynamic parameters and prevent resonant oscillations in the cab. A vehicle cab is a dynamic system with 6 degrees of freedom, therefore its oscillations are spatially complex and feature energy direction switching. Thus, the problems of suspended cab dynamics should be solved in a non-linear spatial setting that can account for oscillation energy redistribution between various spatial direc-tions. The purpose of this work is to develop a mathematical model for the spatial oscillations of a suspended cab relative to the vehicle undercarriage that can help analyze the non-linear oscillations that occur in the cab to study their stability during vehicle movement. This study helped identify the adverse frequency ratios for the disturbing impact on the can suspension system that can reduce cab comfort and result in the instability of its oscillations. The authors developed methods to reduce the amplitudes of suspended cab sway when its spatial oscillations are unstable. The developed methods and mathematical model help identify and prevent resonant spatial phenomena in the cab at all stages of designing vehicle cab suspension systems. The authors proposed specific solutions to design cab suspension systems to improve cab comfort and reduce cab sway, including the usage of air bellows that can form progressive non-linear load characteristics and controllable hydraulic dampers that can increase the damping coefficient in the cab suspension system during cab sway.