Reliability Of Vehicles Research Articles

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.

Machine-Learning and Physics-Based Tool for Anomaly Identification in Propulsion Systems

Launch anomalies occur frequently during the early phase of a program, with many of the anomalies attributed to propulsion systems. Approaches for identifying and mitigating potential propulsion failures can aid development programs and accelerate the resolution of root cause investigations. In reusable systems, anomaly detection methods can be employed to detect latent system health issues that could become problematic as the system ages. Modern launch support relies on human judgement for redline limit generation and visual family data comparison for many operational aspects, which makes it challenging to identify failure modes and to diagnose an anomaly. Additionally, family data comparison is unavailable for the first few launches of a new vehicle. Automated tools to quickly identify system failures of new and reusable systems can bridge these gaps. Physics-based modeling and machine learning (PBMML) offers methods that can improve the reliability of new or reusable launch vehicles by identifying propulsion anomalies or issues before they jeopardize future space missions. PBMML can then be used to inform corrective actions. This paper describes an anomaly data generation module which automates the process of simulating anomalous scenarios in launch vehicle and fluid networks, while a long-term short-term memory network is used to provide real-time anomaly classification on a simplified stage test case.

An in-depth evaluation of deep learning-enabled adaptive approaches for detecting obstacles using sensor-fused data in autonomous vehicles

This paper delivers an exhaustive analysis of the fusion of multi-sensor technologies, including traditional sensors such as cameras, Light Detection and Ranging(LiDAR), Radio Detection and Ranging(RADAR), and ultrasonic sensors, with Artificial Intelligence(AI) powered methodologies in obstacle detection for Autonomous Vehicles(AVs). With the growing momentum in AVs adoption, a heightened need exists for versatile and resilient obstacle detection systems. Our research delves into study of literatures, where proposed approaches assimilate data from this diverse sensor suite, integrated through Deep Learning(DL) techniques, to refine AV performance. Recent advancements and prevailing challenges within the domain are thoroughly examined, with particular focus on the integration of sensor fusion techniques, the facilitation of real-time processing via edge and fog computing, and the implementation of advanced artificial intelligence architectures, including Convolutional Neural Networks(CNNs), Recurrent Neural Networks(RNNs), and Generative Adversarial Networks(GANs), to enhance data interpretation efficacy. In conclusion, the paper underscores the critical contribution of multi-sensor arrays and deep learning in enhancing the safety and reliability of autonomous vehicles, offering significant perspectives for future research and technological progress.

Visualization and Visual Analytics in Autonomous Driving.

Autonomous driving is no longer a topic of science fiction. Advancements of autonomous driving technologies are now reliable. Effectively harnessing the information is essential for enhancing the safety, reliability, and efficiency of autonomous vehicles. In this article, we explore the pivotal role of visualization and visual analytics (VA) techniques used in autonomous driving. By employing sophisticated data visualization methods, VA, researchers, and practitioners transform intricate datasets into intuitive visual representations, providing valuable insights for decision-making processes. This article delves into various visualization approaches, including spatial-temporal mapping, interactive dashboards, and machine learning-driven analytics, tailored specifically for autonomous driving scenarios. Furthermore, it investigates the integration of real-time sensor data, sensor coordination with VA, and machine learning algorithms to create comprehensive visualizations. This research advocates for the pivotal role of visualization and VA in shaping the future of autonomous driving systems, fostering innovation, and ensuring the safe integration of self-driving vehicles.

Development of a sensitivity analysis tool for the trajectory of multistage launch vehicles

The primary objective of this work is to create a highly accurate sensitivity analysis tool for multi-stage launch vehicle trajectories. This tool is designed to assess the impact of various parameters on the trajectory and performance of multi-stage launch vehicles. To achieve this, we have developed high-fidelity simulation software that considers all translational and angular movements by modelling the six-degrees-of-freedom (6DOF) equations of motion. The validation of this software is based on experimental data. An essential aspect of this work is the utilization of the developed sensitivity analysis tool to determine how different parameters affect the trajectory of multi-stage launch vehicles. Through the sensitivity analysis conducted using the developed tool, it is possible to identify which parameters are of critical importance during the design phase. We apply a generic mission profile for the Minotaur-I launcher to obtain parametric dependencies of the flight path. Through a comprehensive parametric study, we evaluate a range of critical parameters, including gross lift-off weight, a specific impulse of each stage, pitch-over manoeuvre initial time and angle, and ignition impulse of each stage. These parameters significantly influence the trajectory, performance, and reliability of the launch vehicle for mission design and success. The results of the sensitivity analysis underscore that even minor variations in these parameters can result in substantial deviations from the nominal insertion altitude. The acceptability of errors in specific impulse changes varies across stages, with maximum changes of 6.07%, and the fourth stage showing less sensitivity at 0.13%. However, it's important to note that variations in the parameters of the first stage tend to be challenging to rectify once they occur, with maximum changes in specific impulses reaching 75.57%. Another noteworthy discovery is that the acceptability of changes in pitch-over manoeuvre initiation times depends on the rate of change; they can be deemed either acceptable or unacceptable based on this factor, with changes ranging between 17.90% and 98.38%.

Performance Evaluation of YOLOv5-based Custom Object Detection Model for Campus-Specific Scenario

This study evaluates the performance of a custom object detection model based on the YOLOv5 architecture, specifically tailored for autonomous electric vehicles. The model undergoes pre-processing using the Roboflow computer vision platform, which offers a wide range of tools for data pre-processing and model training. The experiments were conducted on a diverse dataset comprising various objects encountered in campus-specific driving scenarios, such as pedestrians, vehicles, buildings, and obstacles. The performance of the custom object detection model is assessed using standard metrics, including precision, recall, mean average precision (mAP), and intersection-over-union (IoU) at different thresholds. The training process was conducted in a controlled environment, resulting in a Precision of 0.851, a Recall of 0.831, and a mAP of 0.843. These metrics were analyzed to evaluate the YOLOv5-based custom object detection model's ability to detect and categorize objects accurately, its precision in predicting bounding boxes, and its capability to handle various object categories. We also examined the effects of different hyperparameters and data augmentation techniques on the model's performance, including variations in learning rate, batch size, and optimizer algorithms to determine their impact on accuracy and convergence. This analysis provided valuable insights into the model's strengths and weaknesses, highlighting areas for improvement and optimization. These findings are instrumental in developing and deploying advanced object detection systems to enhance the safety and reliability of autonomous electric vehicles.

Intelligent Systems for Vehicle Reliability and Safety: Exploring AI in Predictive Failure Analysis

Intelligent Systems for Vehicle Reliability and Safety: Exploring AI in Predictive Failure Analysis

Increasing schedule reliability in the multiple depot vehicle scheduling problem with stochastic travel time

The multiple depot vehicle scheduling problem (MDVSP) is one of the most studied problems in public transport service planning. It consists of assigning buses to each timetabled trip while respecting vehicle availability at each depot. Although service quality, and especially reliability, is the core of most transport agencies, the MDVSP is more often than not solved solely in a cost-efficient way. This work introduces a data-driven model to the reliable MDVSP with stochastic travel time (R-MDVSP-STT). The reliability of a schedule is assessed and accounted for by propagating delays using the probability mass function of the travel time of each timetabled trip. We propose a heuristic branch-and-price algorithm to solve this problem and a labeling algorithm with a stochastic dominance criterion for the associated subproblems. The solutions obtained are compared based on three metrics — under normal and extraordinary circumstances. Computational results on real-life instances show that our method can efficiently find good trade-offs between operational costs and reliability, improving the reliability of the solutions with little cost increase.

The capacity degradation path prediction for the prismatic lithium-ion batteries based on the multi-features extraction with SGPR

Accurate capacity degradation path estimation of lithium-ion batteries plays a crucial role in ensuring the safety and reliability of electric vehicles. In recent years, the evolution of the status of health (SOH) prediction with machine learning techniques has become a research hotspot because of its powerful computing power and robustness. Thus, this study employes the sparse gaussian process regression (SGPR) data-driven approach with multi-features extracted from the battery cycling processes to project the potential degradation patterns of the lithium-ion batteries. Firstly, a battery life test platform was built. The accelerated life aging tests of batteries at different temperatures (25 °C, or 60 °C) and different discharge rates (1C, or 2C) were conducted to establish the dataset for the multi-features extraction and training of the SGPR algorithm. Secondly, different battery characteristic features were extracted based on the battery cycle charge-discharge curves. Various order-reduction treatments, i.e., the filter-based, embedding-based, and fusion-based selection algorithms, were performed to suppress the over-fitting and improve the estimate's accuracy. Finally, using the extracted features as inputs, SGPR models are constructed to estimate the degradation path of the battery. With the 50 % training data, the SGPR has a higher estimation accuracy than the regular GPR, and the average maximum absolute errors for the batteries are 2.80 %, 1.22 %, 3.57 %, and 1.83 %, respectively.

Automotive intelligence: Unleashing the potential of AI beyond advance driver assisting system, a comprehensive review

Big data, AI, and machine learning have ushered in a transformative era in computer processing and application. AI's capacity to emulate human cognition spans a spectrum of industries, from rudimentary tasks to intricate decision-making processes. Projections indicate that within a short span, AI technology will bestow computers with human-like capabilities, rendering it indispensable. This advancement has substantially bolstered industry autonomy, fortifying security and safety through the integration of electronics, internet connectivity, advanced algorithms, and cutting-edge processing chips.In this context, Automated Guided Vehicles (AGVs) leverage AI-powered systems and sensors to optimize performance and proactively thwart potential failures. Going beyond Advanced Driver Assistance Systems (ADAS), this review scrutinizes the broader spectrum of AI applications. Specifically, it synthesizes pertinent studies encompassing AI's impact on car emissions, predictive maintenance, security, and the realm of connected vehicles.While AGVs can utilize AI algorithms to chart emission-efficient routes and engineer energy-conservative vehicles, AI, through diverse algorithms, proficiently anticipates component failures, substantially enhancing the cost-effectiveness of predictive maintenance and bolstering vehicle reliability. Moreover, AI integrated with sensor technology safeguards vehicles against a spectrum of threats. Neural networks and machine learning further automate security measures for both cargo and passengers. Concurrently, AI and machine learning fortify traffic control and enhance vehicle communication within connected vehicle frameworks, albeit necessitating fortifications in data security, encryption, and system efficiency.This survey paper comprehensively covers the expanse of automotive AI and machine learning applications, extending beyond ADAS. It underscores that the evolving mobility landscape necessitates a thorough evaluation of network architecture, connectivity, and performance metrics, encompassing AGV technology, networking protocols, and swarm dynamics. In this vein, the paper advocates for experts to address existing literature gaps and proactively enhance automotive systems.

ВЛИЯНИЕ НАДЕЖНОСТИ АВТОМОБИЛЕЙ НА ЗАТРАТЫ НА ПРИОБРЕТЕНИЕ ЗАПАСНЫХ ЧАСТЕЙ

The operation of road transport is associated with maintaining the serviceability of vehicles. Companies that operate vehicles have different approaches to ensuring their serviceability. Small ones, as a rule, carry out maintenance and repair of vehicles at service stations, while large and medium-sized companies provide conditions for carrying out technical service at their own base. In this case, they are faced with the need to stock with spare parts. It was found that the costs of spare parts account for up to 45 % of all operating costs, their reduction is possible with the correct approach to planning and organization of spare parts supply. This confirms the relevance of the research. As the main factor affecting the cost of spare parts purchasing, the authors proposed to consider the reliability of car units and assemblies. A regularity was established: the reliability of a vehicle decreases with the increase of its service life, while the need for spare parts and, consequently, the purchasing cost of spare parts increases. Spare parts stocks are planned in two groups – for maintenance and repairs. It is possible to plan the consumption of spare parts for maintenance based on the vehicle fleet and on the recommendations of the manufacturer, which regulates the frequency of replacement and the list of spare parts. It is advisable to plan the nomenclature of spare parts for current repairs based on vehicles reliability. Forecasting of spare parts stock based on reliability will allow to manage spare parts stock effectively, to minimize their shelf life and to avoid the purchase of unclaimed spare parts.

THEORETICAL FRAMEWORKS OF ECOPFM PREDICTIVE MAINTENANCE (ECOPFM) PREDICTIVE MAINTENANCE SYSTEM

The Frameworks of EcoPFM Predictive Maintenance (PM) System presents a novel approach to maintenance optimization within eco-friendly power facilities, addressing the critical need for sustainable, efficient asset management. This paper introduces an integrated framework leveraging advanced predictive analytics, machine learning algorithms, and Internet of Things (IoT) technology to enable proactive maintenance interventions based on real-time data insights. Focusing on the context of the United States it highlights the significance of implementing such a system in the realm of eco-friendly energy infrastructure. The automotive and heavy-duty truck industries in the United States grapple with the challenge of optimizing maintenance strategies to ensure vehicle reliability, safety, and environmental sustainability. Traditional maintenance approaches, primarily reactive or scheduled maintenance, fall short in addressing the complexities of modern vehicle operations. The U.S. Department of Transportation reports that heavy-duty trucks transport approximately 70% of the nation's freight by weight, underscoring the sector's critical role in the economy. However, inefficiencies in maintenance strategies contribute to significant economic and operational setbacks. According to the American Transportation Research Institute, unscheduled truck maintenance and repairs are leading operational costs for fleets, with an average expense of 16.7 cents per mile in 2020, highlighting the financial strain of current maintenance practices. In the United States, the demand for eco-friendly power solutions is rapidly increasing, driven by a growing awareness of environmental sustainability and the imperative to reduce carbon emissions. As the nation transitions towards renewable energy sources and eco-friendly power facilities, the effective management of these assets becomes paramount to ensuring reliability, performance, and longevity. The EcoPFM PM System integrates diverse data sets sourced from eco-friendly power facilities across the USA, encompassing historical operational data, sensor readings, and environmental parameters. Through predictive analytics, the system identifies patterns and trends within these data sets to forecast equipment failures and performance degradation accurately. By prioritizing maintenance tasks based on risk assessment models and condition monitoring, the system enables organizations to optimize resource allocation, minimize downtime, and extend asset lifespan. Embracing the Frameworks of EcoPFM Predictive Maintenance System holds immense promise for organizations operating eco-friendly power facilities in the United States. By harnessing data-driven insights and proactive maintenance strategies, this system offers a pathway towards enhanced operational efficiency, cost reduction, and sustainability, ultimately contributing to the advancement of eco-friendly energy infrastructure in the nation.
 Keywords: Predictive Maintenance, System, ECOPFM, Technology.

Justification of usability of the heat accumulator of phase transition in vehicles’ engines pre-start warming-up procedure

BACKGROUND: The trend of activity increase in exploration of transpolar areas has been observed for recent years. Negative temperatures, the key feature of the North, have a negative impact on state of piston engines of on-ground transport. In engine’s cylinders, the process of transition of liquid fuel in gaseous state goes before the mixture ignition. Negative temperatures affect the phase transition process and impede the working body homogenization. Therefore, engine pre-start warming-up procedure goes before successful engine start. Existing typical methods of pre-start warming-up demand fuel consumption and, generally, significant staff resources. Achievements of modern science offer new technologies for solving the issues of warming-up procedures based on accumulating, storage and deployment of heat energy produces by an engine during its operation. AIM: Justification of usability of the heat accumulator of phase transition in pre-start warming-up procedure for vehicles’ engines operating in conditions of negative temperatures of cold climate. METHODS: Numerical values of heat accumulator charging period depending on temperature of heat-accumulating material at various initial temperatures of coolant as well as values of the discharging period depending on temperature of heat-accumulating material at various coolant rates were defined experimentally. High-density polyethylene was used as a heat-accumulating material. RESULTS: As a result of the described experiment, curves of heat accumulator charging period depending on heat-accumulating material temperature at various initial temperatures of coolant and curves of heat accumulator discharging period depending on coolant temperature at various coolant rates were built. CONCLUSIONS: It is found that the heat accumulator of phase transition with high-density polyethylene as a heat-accumulating material can be used for improving the reliability of vehicles’ piston engine start in conditions of negative temperatures of cold climate.

An Exhaustive Examination of the Motor System’s Reliability in Electric Vehicles

Due to their unique zero carbon emission feature, electric vehicles (EVs) have garnered increasing interest in recent years. However, concerns persist regarding their reliability, particularly concerning critical components. Efforts have been made to assess the reliability of drive motors in EVs. Yet, given the integration of drive motors and motor controllers as a single system in EVs, a combined assessment is essential for a more accurate reliability prediction. Additionally, considering the multiple components within both drive motors and motor controllers, their structure, type, and characteristics may influence the overall reliability of the motor system, a factor overlooked in previous research. To bridge this knowledge gap, this study investigates the reliability of the entire motor system in pure electric vans, encompassing both drive motors and motor controllers. The research begins with predicting the theoretical failure rates of subassemblies and components within the drive motor and motor controller. Subsequently, based on these predictions, the reliability of the entire motor system is assessed. The findings highlight vulnerable subassemblies and components within the motor system, shedding light on potential shortcomings in existing reliability research. These new insights are deemed crucial for informing future reliability design and maintenance practices for pure electric vans. This study undertakes an exhaustive investigation into the reliability of the motor system in EVs. As EVs gain prominence for their environmental benefits and increasing market share, concerns regarding the reliability of critical components, such as the drive motor and associated control systems, become paramount. While prior research has addressed component-level reliability, this study takes a holistic approach by assessing the entire motor system. Through theoretical modeling and empirical analysis, the study predicts failure rates of subassemblies and components within the drive motor and control systems, culminating in an evaluation of the overall motor system reliability. By uncovering vulnerabilities and potential areas for improvement, this research offers valuable insights to advance the design, development, and maintenance of reliable electric vehicles.

Enhancing Electric Vehicle Reliability: Advanced Fault Detection for Demagnetization Faults in PMSM Motor Using Artificial Neural Network

Enhancing Electric Vehicle Reliability: Advanced Fault Detection for Demagnetization Faults in PMSM Motor Using Artificial Neural Network

Intrusion Detection System for Autonomous Vehicles Using Non-Tree Based Machine Learning Algorithms

This research work highlights significant achievements in the domain of intrusion detection systems (IDSs) for autonomous vehicles, which are crucial in enhancing their safety, reliability, and cybersecurity. This study introduces an approach that leverages non-tree-based machine learning algorithms, such as K-nearest neighbors and ensemble learning, to develop an IDS tailored for autonomous vehicles. These algorithms were employed because of their ability to process complex and large datasets with less likeliness for overfitting, their scalability, and their ability to adapt to changing conditions in real time. These algorithms effectively handle imbalanced data, enhancing the detection accuracy of both normal and intrusive instances. The IDS’s performance was validated through the utilization of three real-world datasets, CAN intrusion, CICIDS2017, and NSL-KDD, where the proposed non-tree-based IDS (NTB-MTH-IDS) was measured with the standard measurement metrics: accuracy, precision, F1-score, and recall, including specificity and sensitivity. Notably, the results indicate that K-nearest neighbors and stacking, as part of NTB-MTH-IDS, has an accuracy of 99.00%, 98.57%, and 97.57%, and F1-scores of 99.00%, 98.79%, and 97.54% in the CICIDS2017, NSL-KDD, and CAN datasets, respectively. The results of this research can lead to establishing a robust intrusion detection framework, thereby ensuring the safety and reliability of autonomous vehicles. Through this achievement, road users, passengers, and pedestrians are safeguarded against the consequences of potential cyber threats.