Search Results

Abstract This article introduces an innovative method for predicting tire–road interaction forces by exclusively utilizing longitudinal and lateral acceleration measurements. Given that sensors directly measuring these forces are either expensive or challenging to implement in a vehicle, this approach fills a crucial gap by leveraging readily available sensor data. Through the application of a multi-output neural network architecture, the study focuses on simultaneously predicting the longitudinal, lateral, and vertical interaction forces exerted by the rear wheels, specifically those involved in traction. Experimental validation demonstrates the efficacy of the methodology in accurately forecasting tire–road interaction forces. Additionally, a thorough analysis of the input–output relationships elucidates the intricate dynamics characterizing tire–road interactions.

Abstract In this article, we investigated the effects of material parameters on the clinching joint geometry using finite element model (FEM) simulation and machine learning-based metamodels. The FEM described in this study was first developed to reproduce the shape of clinching joints between two AA5052 aluminum alloy sheets. Neural network metamodels were then used to investigate the relation between material parameters and joint geometry as predicted by FEM. By interpreting the data-driven metamodels using explainable machine learning techniques, the effects of the hard-to-measure material parameters during the clinching are studied. It is demonstrated that the friction between the two metal sheets and the flow stress of the material at high (up to 100%) plastic strain are the most influential factors on the interlock and the neck thickness of the clinching joints. However, their dependence on the material parameters is found to be opposite.

Abstract Reinforcement learning (RL) is a computational approach to understanding and automating goal-directed learning and decision-making. The difference from other computational approaches is the emphasis on learning by an agent from direct interaction with its environment to achieve long-term goals [1]. In this work, the RL algorithm was implemented using Python. This then enables the RL algorithm to make decisions to optimize the output from the system and provide real-time adaptation to changes and their retention for future usage. A diesel engine is a complex system where a RL algorithm can address the NOx–soot emissions trade-off by controlling fuel injection quantity and timing. This study used RL to optimize the fuel injection timing to get a better NO–soot trade-off for a common rail diesel engine. The diesel engine utilizes a pilot–main and a pilot–main–post-fuel injection strategy.

Abstract This article presents the design and the analysis of a control logic capable of optimizing vehicle’s energy consumption during a braking maneuver. The idea arose with the purpose of enhancing regeneration and health management in electric vehicles with electro-actuated brakes. Regenerative braking improves energy efficiency and allows a considerable reduction in secondary emissions, but its efficiency is strongly dependent on the state of charge (SoC) of the battery. In the analyzed case, a vehicle equipped with four in-wheel motors (one for each wheel), four electro-actuated brakes, and a battery was considered. The proposed control system can manage and optimize electrical and energy exchanges between the driveline’s components according to the working conditions, monitoring parameters such as SoC of the battery, brake temperature, battery temperature, motor temperature, and acts to optimize the total energy consumption.

Abstract Various feedstocks can be employed for biodiesel production, leading to considerable variation in composition and engine fuel characteristics. Using biodiesels originating from diverse feedstocks introduces notable variations in engine characteristics. Therefore, it is imperative to scrutinize the composition and properties of biodiesel before deployment in engines, a task facilitated by predictive models. Additionally, the international commercialization of biodiesel fuel is contingent upon stringent regulations. The traditional experimental measurement of biodiesel properties is laborious and expensive, necessitating skilled personnel. Predictive models offer an alternative approach by estimating biodiesel properties without depending on experimental measurements. This research is centered on building models that correlate mid-infrared spectra of biodiesel and critical fuel properties, encompassing kinematic viscosity, cetane number, and calorific value.

Abstract In 2018, the state explicitly proposed to “promote the cancellation of expressway toll stations at provincial boundaries.” Electronic toll collection has become the main toll collection method on expressways. With the construction of ETC toll lanes, the proportion of ETC vehicles in the expressway traffic flow is increasing, and the rapid processing of vehicle special situations is facing challenges. At present, various provinces have adopted various methods to improve the traffic efficiency and transaction success rate of ETC from the issuance link, customer service link, and lane transaction link. According to statistical data, the average transaction success rate of ETC lane is not higher than 99% at present. As of October 2021, the number of ETC users nationwide has reached 256 million, and there are an average of 40 million ETC transactions per day across the network, that is, about 400,000 special cases need to be processed.

Abstract Due to the presence of uncertain disturbances in the actual steering system, disturbances in the system may affect the handling stability of the vehicle. Therefore, this article proposes an integrated steering system control strategy with stronger anti-disturbance performance. When disturbances exist in the system, the proposed control strategy effectively reduces the attitude changes during the vehicle steering process. In the upper-level control strategy, a variable transmission ratio curve is designed to coordinate the high-speed handling stability and low-speed steering sensitivity of the vehicle. On this basis, a sideslip angle observer is proposed based on the extended state observation theory, which does not depend on an accurate system model, thus determining the intervention timing of the active front wheel steering system. In the lower-level control strategy, DR-PI/DR-PID controllers are designed for the integrated steering system.

Abstract A time domain analysis method of ride comfort and energy dissipation characteristics is proposed for automotive vibration proportional–integral–derivative (PID) control. A two-degrees-of-freedom single wheel model for automotive vibration control is established, and the conventional vibration response variables for ride comfort evaluation and the energy consumption vibration response variables for energy dissipation characteristics evaluation are determined, and the Routh stability criterion method was introduced to assess the impact of PID control on vehicle stability. The PID control parameters are tuned using the differential evolution algorithm, and to improve the algorithm’s adaptive ability, an adaptive operator is introduced, so that the mutation factor of differential evolution algorithm can change with the number of iterations.

Abstract This article presents a novel approach to optimize the placement of light detection and ranging (LiDAR) sensors in autonomous driving vehicles using machine learning. As autonomous driving technology advances, LiDAR sensors play a crucial role in providing accurate collision data for environmental perception. The proposed method employs the deep deterministic policy gradient (DDPG) algorithm, which takes the vehicle’s surface geometry as input and generates optimized 3D sensor positions with predicted high visibility. Through extensive experiments on various vehicle shapes and a rectangular cuboid, the effectiveness and adaptability of the proposed method are demonstrated. Importantly, the trained network can efficiently evaluate new vehicle shapes without the need for re-optimization, representing a significant improvement over classical methods such as genetic algorithms.

Abstract In the process of injection molding, the vacuum pump rear housing is prone to warping deformation and volume shrinkage, which affects its sealing performance. The main reason is the improper control of the injection process and the large flat structure of the vacuum pump rear housing, which does not meet its production and assembly requirements (the warpage deformation should be controlled within 1.1 mm and the volume shrinkage within 10%). To address this issue, this study initially utilized orthogonal experiments to obtain training samples and conducted a preliminary analysis using gray relational analysis. Subsequently, a predictive model was established based on a one-dimensional convolutional neural network (1D CNN).

Abstract An automatic collision avoidance control method integrating optimal four-wheel steering (4WS) and direct yaw-moment control (DYC) for autonomous vehicles on curved road is proposed in this study. Optimal four-wheel steering is used to track a predetermined trajectory, and DYC is adopted for vehicle stability. Two single lane change collision avoidance scenarios, i.e., a stationary obstacle in front and a moving obstacle at a lower speed in the same lane, are constructed to verify the proposed control method. The main contributions of this article include (1) a quintic polynomial lane change trajectory for collision avoidance on curved road is proposed and (2) four different kinds of control method for autonomous collision avoidance, namely 2WS, 2WS+DYC, 4WS, and 4WS+DYC, are compared. In the design of DYC controller, two different feedback control methods are adopted for comparison, i.e., sideslip angle feedback and yaw rate feedback.

Abstract In order to enhance the path-tracking accuracy and adaptability of the electric flatbed vehicle (EFV) in the soft-target vehicle test system, an improved controller is designed based on the linear quadratic regulator (LQR) algorithm. First, the LQR feedback controller is designed based on the EFV dynamics tracking error model, and the genetic algorithm is utilized to obtain the optimal weight coefficient matrix for different speeds. Second, a weight coefficient matrix compensation strategy is proposed to address the changes in the relationship between the vehicle–road position and attitude caused by external disturbances and the state of EFV. An offline parameter table is created to reduce the computational load on the microcontroller of EFV and enhance real-time path-tracking performance. Furthermore, an adaptive preview time control strategy is added to reduce the overshooting caused by control delay. This strategy is based on road curvature and traveling speed.

Abstract Reactivity-controlled compression ignition (RCCI) engine is an innovative dual-fuel strategy, which uses two fuels with different reactivity and physical properties to achieve low-temperature combustion, resulting in reduced emissions of oxides of nitrogen (NOx), particulate matter, and improved fuel efficiency at part-load engine operating conditions compared to conventional diesel engines. However, RCCI operation at high loads poses challenges due to the premixed nature of RCCI combustion. Furthermore, precise controls of indicated mean effective pressure (IMEP) and CA50 combustion phasing (crank angle corresponding to 50% of cumulative heat release) are crucial for drivability, fuel conversion efficiency, and combustion stability of an RCCI engine.

Abstract This scientific publication presents the application of artificial intelligence (AI) techniques as a virtual sensor for tailpipe emissions of CO, NOx, and HC in a high-performance vehicle. The study aims to address critical challenges faced in real industrial applications, including signal alignment and signal dynamics management. A comprehensive pre-processing pipeline is proposed to tackle these issues, and a light gradient-boosting machine (LightGBM) model is employed to estimate emissions during real driving cycles. The research compares two modeling approaches: one involving a unique “direct model” and another using a “two-stage model” which leverages distinct models for the engine and the aftertreatment. The findings suggest that the direct model strikes the best balance between simplicity and accuracy.

Abstract Accurate estimation of traction force is essential for the development of advanced control systems, particularly in the domain of autonomous driving. This study presents an innovative approach to enhance the estimation of tire–road interaction forces under combined slip conditions, employing a combination of empirical models and neural networks. Initially, the well-known Pacejka formula, or magic formula, was adopted to estimate tire–road interaction forces under pure longitudinal slip conditions. However, it was observed that this formula yielded unsatisfactory results under non-pure slip conditions, such as during curves. To address this challenge, a neural network architecture was developed to predict the estimation error associated with the Pacejka formula. Two distinct neural networks were developed. The first neural network employed, as inputs, both longitudinal slip ratios of the driving wheels and the slip angles of the driving wheels.

Abstract The swift progress of electric vehicles (EVs) and hybrid electric vehicles (HEVs) has driven advancements in battery management systems (BMS). However, optimizing the algorithms that drive these systems remains a challenge. Recent breakthroughs in data science, particularly in deep learning networks, have introduced the long–short-term memory (LSTM) network as a solution for sequence problems. While graphics processing units (GPUs) and application-specific integrated circuits (ASICs) have been used to improve performance in AI-based applications, field-programmable gate arrays (FPGAs) have gained popularity due to their low power consumption and high-speed acceleration, making them ideal for artificial intelligence (AI) implementation. One of the critical components of EVs and HEVs is the BMS, which performs operations to optimize the use of energy stored in lithium-ion batteries (LiBs).

Abstract This study proposes a machine learning tabulation (MLT) method that employs deep neural networks (DNNs) to predict ignition delay and knock propensity in spark ignition (SI) engines. The commonly used Arrhenius model and Livengood–Wu integral for fast knock prediction are not accurate enough to account for residual gas species and may require adjustments or modifications to account for specific engine characteristics. Detailed kinetics modeling is computationally expensive, so the MLT approach is introduced to solve these issues. The MLT method uses precalculated thermochemical states of the mixture that are clustered based on a combustion progress variable. Hundreds of DNNs are trained with the stochastic Levenberg–Marquardt (SLM) optimization algorithm, reducing training time and memory requirements for large-scale problems. MLT has high interpolation accuracy, eliminates the need for table storage, and reduces memory requirements by three orders of magnitude.

Abstract Sealed electronic components are the basic components of aerospace equipment, but the issue of internal loose particles greatly increases the risk of aerospace equipment. Traditional material recognition technology has a low recognition rate and is difficult to be applied in practice. To address this issue, this article proposes transforming the problem of acquiring material information into the multi-category recognition problem. First, constructing an experimental platform for material recognition. Features for material identification are selected and extracted from the signals, forming a feature vector, and ultimately establishing material datasets. Then, the problem of material data imbalance is addressed through a newly designed direct artificial sample generation method. Finally, various identification algorithms are compared, and the optimal material identification model is integrated into the system for practical testing.

Abstract Connected fuel cell vehicles (C-FCVs) have gained increasing attention for solving traffic congestion and environmental pollution issues. To reduce operational costs, increase driving range, and improve driver comfort, simultaneously optimizing C-FCV speed trajectories and powertrain operation is a promising approach. Nevertheless, this remains difficult due to heavy computational demands and the complexity of real-time traffic scenarios. To resolve these issues, this article proposes a two-level eco-driving strategy consisting of speed planning and energy management layers. In the top layer, the speed planning predictor first predicts dynamic traffic constraints using the long short-term memory (LSTM) model. Second, a model predictive control (MPC) framework optimizes speed trajectories under dynamic traffic constraints, considering hydrogen consumption, ride comfort, and traffic flow efficiency.

Abstract Vehicle-to-infrastructure (V2I) connectivity technology presents the opportunity for vehicles to perform autonomous longitudinal control to navigate safely and efficiently through sequences of V2I-enabled intersections, known as connected corridors. Existing research has proposed several control systems to navigate these corridors while minimizing energy consumption and travel time. This article analyzes and compares the simulated performance of three different autonomous navigation systems in connected corridors: a V2I-informed constant acceleration kinematic controller (V2I-K), a V2I-informed model predictive controller (V2I-MPC), and a V2I-informed reinforcement learning (V2I-RL) agent. A rules-based controller that does not use V2I information is implemented to simulate a human driver and is used as a baseline. The performance metrics analyzed are net energy consumption, travel time, and root-mean-square (RMS) acceleration.