Reliability Of Vehicles Research Articles

Motor Fault Diagnosis Based on Convolutional Block Attention Module-Xception Lightweight Neural Network.

Electric motors play a crucial role in self-driving vehicles. Therefore, fault diagnosis in motors is important for ensuring the safety and reliability of vehicles. In order to improve fault detection performance, this paper proposes a motor fault diagnosis method based on vibration signals. Firstly, the vibration signals of each operating state of the motor at different frequencies are measured with vibration sensors. Secondly, the characteristic of Gram image coding is used to realize the coding of time domain information, and the one-dimensional vibration signals are transformed into grayscale diagrams to highlight their features. Finally, the lightweight neural network Xception is chosen as the main tool, and the attention mechanism Convolutional Block Attention Module (CBAM) is introduced into the model to enforce the importance of the characteristic information of the motor faults and realize their accurate identification. Xception is a type of convolutional neural network; its lightweight design maintains excellent performance while significantly reducing the model's order of magnitude. Without affecting the computational complexity and accuracy of the network, the CBAM attention mechanism is added, and Gram's corner field is combined with the improved lightweight neural network. The experimental results show that this model achieves a better recognition effect and faster iteration speed compared with the traditional Convolutional Neural Network (CNN), ResNet, and Xception networks.

The novel stereoscopic cooling plate designs and performance analysis for battery thermal management systems

This study explores the design and performance of liquid cooling plate-based battery thermal management system for lithium-ion battery packs through numerical simulation. We first assess traditional straight-channel cooling plates with three different placement strategies. The conventional design with bottom-mounted cooling plates demonstrates the most effective thermal management at the same total coolant mass flow rate. This suggests that the influence of reducing coolant flow velocity on the cooling performance outweighs the influence of increasing the heat exchange area under our simulated conditions. Advanced stereoscopic cooling plate structures, referred to as 3DCP-A and 3DCP-B, are then introduced, significantly enhancing battery thermal management performance. To achieve a maximum temperature difference ≤ 5.0 K for the most discharge process, the required mass flow rate of the 3DCP-B decreases by 30.0 g∙s−1 and 10.0 g∙s−1 compared to the conventional bottom-mounted cooling plate and 3DCP-A, respectively, and the pressure drop reduces by 75.9 % and 44.3 %, respectively. The power consumption for the 3DCP-B design is only 6.0 % of that for the traditional design. Finally, the effects of key operating temperatures on the cooling performance of the optimal 3DCP-B design are discussed. The insights obtained in this study provide valuable guidance for developing more efficient and effective pack-level liquid cooling plate-based battery thermal management system, essential for improving the reliability and performance of electric vehicles.

Internal Short Circuit and Dynamic Response of Large-Format Prismatic Lithium-Ion Battery Under Mechanical Abuse

Abstract Prismatic lithium-ion batteries (LIBs) are becoming the most prevalent battery type in electric vehicles, and their mechanical safety is garnering increased attention. Understanding the mechanical response and internal short circuit (ISC) of prismatic LIBs during dynamic impact is important for enhancing the safety and reliability of electric vehicles. Thanks to the pioneer's works on the cylindrical and pouch LIB, prismatic LIB can draw on relevant experimental and numerical modeling methods. However, there is still a lack of research on the dynamic effects of prismatic LIB in various loading directions. To address this disparity, the current research utilizes quasi-static and dynamic impact experiments on prismatic LIBs as a foundation. First, the mechanical response of a sizable prismatic LIB under quasi-static conditions and the dynamic effects are examined when subjected to mechanical abuse from various loading directions. Second, an anisotropic finite element model that considers dynamic strain rates are developed, enabling it to accurately represent the mechanical response to both quasi-static and dynamic impact loads. At last, we performed an analysis of ISC occurring under dynamic loading conditions combining the experimental and simulated results. The experimental results as well as the established model can provide reference for the safe design, application, and analysis of prismatic LIBs.

Whale Optimization Algorithm BP Neural Network with Chaotic Mapping Improving for SOC Estimation of LMFP Battery

The state of charge (SOC) is a core parameter in the battery management system for LMFP batteries. Accurate SOC estimation is crucial for ensuring the safety and reliability of energy storage applications and new energy vehicles. In order to achieve better SOC estimation accuracy, this article proposes an adaptive whale optimization algorithm (WOA) with chaotic mapping to improve the BP neural network (BPNN) model. The SOC estimation accuracy of the BPNN model was improved by utilizing WOA to find the optimal target weight values and thresholds. Comparative simulation experiments (including constant current and working condition discharge experiments) were conducted in Matlab/Simulink R2018a to verify the proposed algorithm and the other four algorithms. The experimental results show that the proposed algorithm had higher SOC estimation accuracy than the other four algorithms, and its prediction errors were less than 1%. This indicates that the proposed SOC estimation method has better prediction accuracy and stability, and has certain theoretical research significance.

A comprehensive review of BMS fault analysis in pure electric vehicles

Pure electric vehicle technology faces numerous technical challenges during the process of independent research and development, with the safety and endurance of power batteries being particularly critical. The Battery Management System (BMS) is a core factor affecting the performance and safety of electric vehicles. The normal operation of the BMS is essential for ensuring the reliability of electric vehicles. However, in practical applications, the BMS may encounter faults that can lead to a decline in battery performance, a reduction in lifespan, and even trigger safety incidents. Therefore, the development of an efficient and accurate fault analysis and diagnostic system is particularly important. This paper systematically explores the fault issues of electric vehicle BMS, including the composition, working principles, and main functions of the BMS, as well as the classification, level definition, case analysis, and resolution measures of faults. The article also provides a detailed introduction to fault analysis methods, including qualitative and quantitative analyses. Finally, based on recent hot topics and the latest research progress, it is concluded that model-based fault diagnosis will become increasingly important. This paper aims to provide a reference for the development of the field of electric vehicle battery management fault diagnosis technology.

Comparison of lidar semantic segmentation performance on the structured SemanticKITTI and off-road RELLIS-3D datasets

Existing lidar-based semantic segmentation algorithms and datasets focus on autonomous vehicles operating in urban environments. This has greatly improved the safety and reliability of these autonomous vehicles in predictable scenery. A new dataset provides lidar data focusing on off-road environments as seen by autonomous ground vehicles, ushering in a new era of off-road exploration capabilities. To the best of our knowledge, no new algorithms have been developed specifically for this unstructured environment. To gain an understanding of how existing algorithms perform in an off-road environment, we assess the baseline performance of four algorithms, KPConv, SalsaNext, Cylinder3D, and SphereFormer, on a commonly used on-road dataset, SemanticKITTI. We then compare the results with an off-road dataset, RELLIS-3D. We discuss the degradation of each algorithm on the off-road dataset and investigate potential causes such as class imbalance, inconsistencies in the labeled data, and the inherent difficulty of segmenting off-road environments. We present the strengths and weaknesses of each algorithm’s segmentation abilities and provide a comparison of the runtime of each algorithm for real-time capabilities. This is crucial for identifying what network architecture features are potentially the most beneficial for unstructured scenes. A robust, open-source software implementation via docker containers and bash scripts provides simple, repeatable execution of all algorithm training and evaluations. All code is publicly available at https://github.com/UA-Lidar-Segmentation-Research.

A label-free battery state of health estimation method based on adversarial multi-domain adaptation network and relaxation voltage

The state of health (SOH) estimation of lithium-ion batteries is crucial for the operational reliability and safety of electric vehicles. However, traditional data-driven methods face problems of label shortage and domain discrepancy caused by diverse battery types and operating conditions. This paper proposes a label-free SOH estimation method based on adversarial multi-domain adaptation technique and relaxation voltage (RV). Firstly, the raw RV and integral voltage are proposed to construct the two-dimensional input sequence to ensure high adaptability across various target domains. Secondly, a two-dimensional convolutional neural network integrated with fully connected layers is developed to establish the feature extractor and SOH estimator, which paves the way for effective knowledge transfer. Furthermore, an adversarial multi-domain adaptation method with a domain discriminator is developed to optimize the extraction of domain-invariant features and enable accurate SOH estimation without SOH labels. Datasets of 50 batteries with different temperatures and materials are used for the validation. The proposed method shows outstanding performance, achieving the average RMSE and MAE of 0.0274 and 0.0240 across various working temperatures, and 0.0177 and 0.0148 across different battery types. It suggests that the proposed method can achieve robust adaptive battery SOH estimation across multiple target domains without using SOH labels.

Multi-Source Image Matching Algorithms for UAV Positioning: Benchmarking, Innovation, and Combined Strategies

The accuracy and reliability of unmanned aerial vehicle (UAV) visual positioning systems are dependent on the performance of multi-source image matching algorithms. Despite many advancements, targeted performance evaluation frameworks and datasets for UAV positioning are still lacking. Moreover, existing consistency verification methods such as Random Sample Consensus (RANSAC) often fail to entirely eliminate mismatches, affecting the precision and stability of the matching process. The contributions of this research include the following: (1) the development of a benchmarking framework accompanied by a large evaluation dataset for assessing the efficacy of multi-source image matching algorithms; (2) the results of this benchmarking framework indicate that combinations of multiple algorithms significantly enhance the Match Success Rate (MSR); (3) the introduction of a novel Geographic Geometric Consistency (GGC) method that effectively identifies mismatches within RANSAC results and accommodates rotational and scale variations; and (4) the implementation of a distance threshold iteration (DTI) method that, according to experimental results, achieves an 87.29% MSR with a Root Mean Square Error (RMSE) of 1.11 m (2.22 pixels) while maintaining runtime at only 1.52 times that of a single execution, thus optimizing the trade-off between MSR, accuracy, and efficiency. Furthermore, when compared with existing studies on UAV positioning, the multi-source image matching algorithms demonstrated a sub-meter positioning error, significantly outperforming the comparative method. These advancements are poised to enhance the application of advanced multi-source image matching technologies in UAV visual positioning.

A novel strengthened road roughness estimation framework based on the adaptive unbiased minimum variance with unknown input

The accurate acquisition of the strengthened road roughness is significant to vehicle reliability and durability. However, the existing road roughness estimation methods are inapplicable due to the non-Gaussian characteristic of the strengthened road roughness. To fulfil this gap, this work proposes a novel strengthened road roughness estimation framework based on the adaptive unbiased minimum variance with unknown input (AUMV-UI) to accurately estimate the roughness of strengthened roads. The proposed AUMV-UI framework consists of four sub-models, i.e. the quarter suspension model, the vehicle parameter identification model, the road roughness estimation model, and the estimation error correction model. In the road roughness estimation model, the unbiased minimum variance with unknown input (UMV-UI) method is proposed for the first to estimate the strengthened road roughness, and thus the first three sub-models are also integrated as the UMV-UI framework. In the estimation error correction model, the Sage–Husa method is introduced to further correct the potential errors of the UMV-UI method. The AUMV-UI framework is validated and compared to the UMV-UI framework by simulations and experiments. The results show that the AUMV-UI framework can significantly improve the estimation accuracy, which can serve as an elegant tool to accurately acquire the strengthened road roughness.

Analisis Perawatan dan Pemeliharaan Kendaraan PKP-PK Terhadap Operasi Pemadaman

Airport Rescue and Fire Fighting (ARFF) is a unit at the airport that is responsible for handling aviation and fire emergencies. This study discusses the maintenance and care of ARFF vehicles at the airport. Maintenance is interpreted as an activity carried out systematically to ensure that facilities function effectively and efficiently. Maintenance includes preventive and corrective actions to maintain the operational readiness of ARFF vehicles. The purpose of this study is to analyze the effect of vehicle maintenance and care on firefighting operations. This study also aims to determine the maintenance and care of vehicles that affect readiness in carrying out firefighting operations and their impacts. The method used in this study is a literature review (library research), which involves collecting and analyzing data from various relevant literature sources. This study focuses on previous studies on the maintenance and care of ARFF vehicles and their influence on the effectiveness of firefighting operations. The results of the study show that good maintenance and care have a positive effect on firefighting operations. Regular maintenance and systematic maintenance increase the reliability of ARFF vehicles, so that responses to emergency situations can be carried out quickly and effectively. Therefore, better personnel training and more detailed maintenance planning are needed to improve operational performance.

A transfer learning-based ensemble learning model for electric vehicles lithium-ion battery capacity estimation using electrochemical impedance spectroscopy

Lithium-ion battery capacity estimation is crucial to ensure the operational reliability and safety of electric vehicles. Electrochemical Impedance Spectroscopy (EIS) can provide rich physical degradation information of the battery, which makes the EIS-based data-driven method a promising solution for accurate battery capacity estimation. However, batteries tend to present diverse degradation patterns due to the diverse operating conditions and manufacturing, resulting in large capacity estimation errors in practical applications. Therefore, this paper proposes a transfer learning (TL) based ensemble learning (EL) method based on multi-layer perception for the battery capacity estimation. First, the influential impedance features are identified from the EIS using Spearman rank coefficient analysis. Second, three TL models are developed based on distinct TL strategies to enable sufficient knowledge transfer considering the different degradation pattern. Further, an EL method with Gaussian kernel-based weighted assignment technique is proposed to integrate the developed TL models and improve the estimation robustness. The performance of the developed model has been successfully validated only using the first 1/3 cycles of the historical data from target battery obtained under different operating conditions and batteries. The results reveal that the proposed method can largely suppress estimation errors, presenting more accurate capacity estimation compared to other methods with an RMSE lower than 1%.

Enhanced Object Detection in Autonomous Vehicles through LiDAR—Camera Sensor Fusion

To realize accurate environment perception, which is the technological key to enabling autonomous vehicles to interact with their external environments, it is primarily necessary to solve the issues of object detection and tracking in the vehicle-movement process. Multi-sensor fusion has become an essential process in efforts to overcome the shortcomings of individual sensor types and improve the efficiency and reliability of autonomous vehicles. This paper puts forward moving object detection and tracking methods based on LiDAR—camera fusion. Operating based on the calibration of the camera and LiDAR technology, this paper uses YOLO and PointPillars network models to perform object detection based on image and point cloud data. Then, a target box intersection-over-union (IoU) matching strategy, based on center-point distance probability and the improved Dempster–Shafer (D–S) theory, is used to perform class confidence fusion to obtain the final fusion detection result. In the process of moving object tracking, the DeepSORT algorithm is improved to address the issue of identity switching resulting from dynamic objects re-emerging after occlusion. An unscented Kalman filter is utilized to accurately predict the motion state of nonlinear objects, and object motion information is added to the IoU matching module to improve the matching accuracy in the data association process. Through self-collected data verification, the performances of fusion detection and tracking are judged to be significantly better than those of a single sensor. The evaluation indexes of the improved DeepSORT algorithm are 66% for MOTA and 79% for MOTP, which are, respectively, 10% and 5% higher than those of the original DeepSORT algorithm. The improved DeepSORT algorithm effectively solves the problem of tracking instability caused by the occlusion of moving objects.

Human factors influencing the reliability and safety of vehicles, Kenya case study

This paper investigates how human decisions and actions in maintenance practices influence the reliability and safety of vehicles in the Kenyan transportation sector. It specifically addresses several human factors that play a crucial role in influencing the reliability and safety of vehicles. Neglecting the manufacturer's recommended maintenance schedule, employing inadequately skilled maintenance personnel, utilizing substandard replacement parts, and exhibiting poor driving habits emerge as key contributors to the compromised reliability and safety within the country's road transportation sector. The research underscores the substantial implications of these human factors, shedding light on their profound influence on the overall condition and security of vehicles in the Kenyan transportation landscape. This paper aims to contribute valuable insights for improving maintenance practices and fostering a safer and more reliable environment within the country's transportation sector, ultimately promoting enhanced safety standards and operational efficiency.

REMOTE VEHICLE DIAGNOSTIC SYSTEM DEVELOPMENT BASED ON THE INTERNET OF THINGS TECHNOLOGY

Background. Advanced artificial intelligence and IoT gateways are working together in the automotive industry to predict potential vehicle problems by analysing sensor data and optimizing quality control processes. Manufacturers can detect anomalies, improve product reliability, and eliminate manufacturing defects or malfunctions in advance. Predictive analytics also lead to improved fuel efficiency, performance and overall vehicle reliability. Objective. The purpose of this work is to develop a model for remote diagnosis of vehicle faults using a Raspberry Pi model B microcomputer and a SIM7600G-H GSM module. Configure data modules, install the necessary software and configure it, demonstrate step-by-step actions, and perform diagnostics and testing of this module for data transmission. Methods. A prototype was created on the basis of Raspberry Pi 4. and provides monitoring of machine operation in remote mode using the SIM7600E-H LTE Cat-4 4G/3G module. The design has small dimensions, easy installation, requires only initial adjustment and has a wide range of improvements. Results. This prototype uses a diagnostic OBD-II car scanner ELM327 with Bluetooth connection support, a Raspberry PI 4 model B microcomputer with 8 GB of RAM, 4 USB connectors (2 ports type USB3 and 2 ports type USB2), a Gigabit Ethernet port, a USB-C power supply port, and two micro HDMI 4K display connectors. On top of the module there are 48 pins (contacts) with which you can connect modules of different types and directions. The SIM7600G-H communication module is connected to these pins. The last element of the prototype is the SIM card of one of the telephone service providers and the micro SD card, which will act as the main memory element on which the operating system will be written and data will be stored. Conclusions. The article proposes the development of a device model using Internet of Things technologies, which is capable of providing remote diagnosis of car malfunctions. This model is based on the use of the SIM7600G-H module, which provides data transmission through the mobile network. The developed model allows you to read data from various car sensors, as well as transfer this data to a remote device for further analysis. This makes it possible to quickly detect malfunctions and make timely decisions on their correction.

Vision-Based UAV Detection and Localization to Indoor Positioning System.

In recent years, the technological landscape has undergone a profound metamorphosis catalyzed by the widespread integration of drones across diverse sectors. Essential to the drone manufacturing process is comprehensive testing, typically conducted in controlled laboratory settings to uphold safety and privacy standards. However, a formidable challenge emerges due to the inherent limitations of GPS signals within indoor environments, posing a threat to the accuracy of drone positioning. This limitation not only jeopardizes testing validity but also introduces instability and inaccuracies, compromising the assessment of drone performance. Given the pivotal role of precise GPS-derived data in drone autopilots, addressing this indoor-based GPS constraint is imperative to ensure the reliability and resilience of unmanned aerial vehicles (UAVs). This paper delves into the implementation of an Indoor Positioning System (IPS) leveraging computer vision. The proposed system endeavors to detect and localize UAVs within indoor environments through an enhanced vision-based triangulation approach. A comparative analysis with alternative positioning methodologies is undertaken to ascertain the efficacy of the proposed system. The results obtained showcase the efficiency and precision of the designed system in detecting and localizing various types of UAVs, underscoring its potential to advance the field of indoor drone navigation and testing.

AUVs Under Ice: A Four-Decade Retrospective on Strategy and Risk Through the Autosub Looking Glass

Abstract Autonomous underwater vehicles (AUVs) have been used in the polar regions for decades. The technical challenges are well understood, and since the mid 1990s, missions of several hundred kilometers under sea ice have been possible. However, there remains a large gap between the endurance achieved in practice and the 1000+ km needed for large-scale sea ice studies; multiple, parallel sections under West Antarctic ice shelves; or sections under the Filchner-Ronne Ice Shelf. This retrospective examines how the U.K. Autosub program's requirements for under ice observations were determined and how those requirements helped build a strategy for a decade of technical progression and scientific achievement. At times progress was faltering, vehicle reliability was inadequate and the approach to risk management was reactive rather than proactive. New analytical tools, some controversial, were developed to assess and manage risk and to drive improvements. While new satellite techniques arguably reduced the need for deployments under sea ice, they remain the only effective solution to fill data-gaps in bathymetry and ocean/ice interactions under ice shelves. The challenge for international collaboration is to accelerate the development of robust and reliable vehicles. The first task remains to survey the basic geometry of the key Antarctic ice shelf cavities. Taking a decadal view, AUV capability should expand to be capable of yearlong deployments under critical ice shelves.

PROCESS MONITORING IN HYBRID ELECTRIC VEHICLES BASED ON DYNAMIC NONLINEAR METHOD

Highway third-level faults can significantly deteriorate the reliability and performance of hybrid electric vehicle (HEV) powertrains. This study presents a novel process monitoring method aimed at addressing this issue. We propose a multivariate statistical method based on dynamic nonlinear improvement, namely dynamic neural component analysis (DNCA). This method does not require the establishment of precise analytical models; instead, it only necessitates acquiring data from HEV powertrains. Through numerical simulation and real HEV experiments, we demonstrate the effectiveness of this approach in monitoring highway third-level faults. The testing outcomes demonstrate that DNCA outperforms traditional dynamic methods like dynamic principal component analysis (DPCA), conventional nonlinear methods such as kernel PCA (KPCA) and NCA, as well as traditional dynamic nonlinear methods like DKPCA.

Smart EV Charging Station Monitoring and User Feedback System

The efficiency and reliability of electric vehicle (EV) charging stations are pivotal for user satisfaction and broader EV adoption. This research introduces a system that monitors essential parameters of EV charging stations, such as temperature, voltage, and current, using advanced sensors and the ESP32 microcontroller. The collected data is transmitted through the Bylnk platform, for real-time monitoring and analysis. To enhance the user experience, a mobile application has been developed, allowing users to review these critical details and receive notifications. The app provides a detailed overview of each charging station's performance, helping users identify the best stations based on historical data and user reviews. By offering insights into the operational status and efficiency of charging stations, the system aids users in making informed decisions about where to charge their vehicles. This integration of real-time monitoring with user-friendly mobile access improves user convenience and optimizes the EV charging infrastructure management.

Fault Diagnosis Model for Bearings under Multiple Operating Conditions Based on Feature Parameterization Weighting

As a core component of automobile transmission, rolling bearings play a main role in the safety and reliability of vehicles. Existing diagnostic models often treat all features equally after feature extraction, without effectively distinguishing the importance of fault features, resulting in low accuracy and poor robustness in bearing fault diagnosis. To address this issue, a fault diagnosis model for bearings under multiple operating conditions based on feature parameterization weighting is proposed. The model utilizes a feature parameterization weighting module to categorize faults into two classes based on differences in means and implements different feature processing methods. The experimental results validate that the proposed feature parameterization weighting module effectively improves the diagnostic accuracy of the model by 8.95%. In terms of noise resistance, on two multi-condition datasets, the proposed diagnostic model achieves diagnostic accuracy of 98.79% and 98.36%. The diagnostic accuracy is improved by 15.7% and 22.48%, which indicates that the model has strong anti-noise ability.

GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction

Predicting pedestrian behavior is the key to ensure safety and reliability of autonomous vehicles. While deep learning methods have been promising by learning from annotated video frame sequences, they often fail to fully grasp the dynamic interactions between pedestrians and traffic, crucial for accurate predictions. These models also lack nuanced common sense reasoning. Moreover, the manual annotation of datasets for these models is expensive and challenging to adapt to new situations. The advent of Vision Language Models (VLMs) introduces promising alternatives to these issues, thanks to their advanced visual and causal reasoning skills. To our knowledge, this research is the first to conduct both quantitative and qualitative evaluations of VLMs in the context of pedestrian behavior prediction for autonomous driving. We evaluate GPT-4V(ision) on publicly available pedestrian datasets: JAAD and WiDEVIEW. Our quantitative analysis focuses on GPT-4V's ability to predict pedestrian behavior in current and future frames. The model achieves a 57% accuracy in a zero-shot manner, which, while impressive, is still behind the state-of-the-art domain-specific models (70%) in predicting pedestrian crossing actions. Qualitatively, GPT-4V shows an impressive ability to process and interpret complex traffic scenarios, differentiate between various pedestrian behaviors, and detect and analyze groups. However, it faces challenges, such as difficulty in detecting smaller pedestrians and assessing the relative motion between pedestrians and the ego vehicle.