Vehicle Fuel Optimization Under Real-World Driving Conditions: An Explainable Artificial Intelligence Approach

Barbado, Alberto; Corcho, Óscar

doi:10.48550/arxiv.2107.06031

Cited by 3 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The significant advantages of EPS are also highlighted by environmental regulations. 19 The prospects for developing electronic control technology can be further explored in the direction of dynamic modelling of the steering system and the vehicle as a whole. Important factors include the rationality and precision of road comfort planning, the accuracy of stability control, and the effect of fail-safe steering strongly depends on the accuracy of model setting, degree, and precision.…”

Section: Discussionmentioning

confidence: 99%

“…The model used the dynamic characteristics of the steering resistance of the hydraulic steering system and the steering gear ratio. Barbado and Corcho, 19 specific trends in vehicle dynamics research were presented while underlining the need for an appropriate experimental research tool, a measurement, and a simulation platform. A platform concept was presented with a list of requirements concerning, among other things, the domain of virtual channels for online analysis and simulation, along with online validation of measurement methods and measuring devices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design and analysis of electric power-assisted steering in vehicles for mountain forests

Kalyashov

Михеев

Kunickaya

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

This study investigates the problem of vehicle exploitation in the mountainous and wooded regions of the Russian Federation. Considering how critical rollover accidents are in the logging industry, it is vital to ensure safe and stable driving. This study aims to develop a model of electric power steering (EPS) control using a quasi-continuous sliding-mode controller in MATLAB/Simulink. Experiments were carried out under the following conditions: maximum slope angle, 30°; maximum steering angle, 30°; maximum driving speed, 7 m/s. The dynamic characteristics of the suspension and EPS systems were optimized using the receding horizon optimization technique. The theoretical and experimental results suggest that the model reaches its critical state of stability (−0.2) at a speed range of 0–7 m/s with a steering angle of 25°. After optimization, critical stability (0.3) occurs at the driving speed of 7 m/s when the steering angle is 30°. The paper discussed the possibility of installing the EPS control system into vehicles that operate in mountainous wooded areas.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Design and analysis of electric power-assisted steering in vehicles for mountain forests

Kalyashov

Михеев

Kunickaya

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

show abstract

“…Some of them fall under many categories, including those relating to drivers, weather, traffic, travel, and vehicles, among others. Barbado and Corcho (2021) evaluated the literature on a number of factors that might affect a vehicle's fuel consumption. Considering the effects related to travel factors, the authors identified eco-routing as a crucial element in reducing fuel consumption.…”

Section: Literature Reviewmentioning

confidence: 99%

Truck Fuel Consumption Prediction Using Logistic Regression and Artificial Neural Networks

Shamuyarira,

Tawanda,

Munapo

2023

International Journal of Operations Research and Information Systems

View full text Add to dashboard Cite

Rising international oil costs and the transport industry's recovery from the effects of Covid-19 resulted in the efficient management of fuel by logistics companies becoming a significant concern. One way of managing this is by analyzing the fuel consumption of trucks so as to better utilize the costly resource. Twenty-three driving data variables were gathered from 210 freight trucks and analyzed this data. Relevant variables that impact truck fuel consumption were extracted from the initial 23 variables gathered using stepwise regression, and then a prediction model was built from the identified relevant variables utilizing a binary logistic regression model. In addition, a back propagation neural network was employed in this study to create a second model of truck fuel use, and comparisons between the two models were made. The outcomes showed that the binary logistic regression model and the back-propagated neural network model prediction accuracy were 68.4% and 77.2%, respectively.

show abstract

“…However, the "black box" nature of ML makes it difficult to explain the relationship between input and output variables [12]. To address this issue, some propose the Explainable Boosting Machine (EBM) [13] and the Shapley Additive Explanations (SHAP) [14] algorithm to quantify the contribution of each input parameter to the output parameter, thus achieving the goal of explaining predictive models. Researchers have explored this problem; for example, Mangalathu et al [15] used the SHAP method to quantitatively analyze the impact of various parameters on the failure mode of shear walls based on existing models.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Failure Modes of Steel Tube-Reinforced Concrete Shear Walls Using Blending Fusion Model Based on Generative Adversarial Networks Data Augmentation

Yang,

Zhang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The steel tube-reinforced concrete (STRC) shear wall plays an important role in the seismic design of high-rise building structures. Due to the synergistic collaboration between steel tubes and concrete, they effectively enhance the ductility and energy dissipation capacity of conventional shear walls. To identify vulnerable areas prone to brittle failure and optimize the design, it is essential to develop a rapid method for identifying the failure mode of STRC shear walls. In this study, a fast identification method of STCR shear wall failure modes based on a Blending fusion model with Generative Adversarial Network (GAN) augmented data is proposed. The GAN is employed to address the issue of inadequate experimental data by generating new samples. This method combines classification boosting (Catboost), Random Forest (RF), K-Nearest Neighbors (KNN), and Least Absolute Shrinkage and Selection Operator (LASSO) to establish the Blending-CRKL fusion model to improve the prediction accuracy of the failure mode of STRC shear walls. The results reveal a significant improvement in the prediction performance of KNN, Backpropagation Neural Network (BPNN), RF, Light Gradient Boosting Machine (LightGBM), Catboost, and Blending-CRKL models after augmenting the training set with GAN. On average, the accuracy increased by 13%, precision increased by 81%, recall increased by 48%, and F1 score increased by 67%. The proposed Blending-CRKL fusion model outperforms the tested KNN, BPNN, RF, LightGBM, and Catboost models, achieving an accuracy rate of 97% in predicting the failure mode of STRC shear walls. Additionally, the stability and robustness of the Blending-CRKL model were validated, while the important features and value ranges of different failure modes were analyzed. This study provides a reference for the rapid identification of the failure mode of STRC shear walls.

show abstract

Vehicle Fuel Optimization Under Real-World Driving Conditions: An Explainable Artificial Intelligence Approach

Cited by 3 publications

References 16 publications

Design and analysis of electric power-assisted steering in vehicles for mountain forests

Design and analysis of electric power-assisted steering in vehicles for mountain forests

Truck Fuel Consumption Prediction Using Logistic Regression and Artificial Neural Networks

Prediction of Failure Modes of Steel Tube-Reinforced Concrete Shear Walls Using Blending Fusion Model Based on Generative Adversarial Networks Data Augmentation

Contact Info

Product

Resources

About