In order to improve the stability and performance of an autonomous vehicle, optimization needs to be explicitly performed in the controllers, which has an essential part in the tracking system. This work proposes a novel longitudinal control optimization scheme and a novel longitudinal controller consisting of a feed-forward and feedback term. The feed-forward term is inspired by the vehicle’s steady-state response, whereas the feedback term is a proportional-integral-derivative (PID) controller. Also, a model representing the longitudinal vehicle dynamics is designed based on physical phenomena affecting the vehicle. Besides, some nature-inspired optimization algorithms are used to determine the optimal model parameters and optimize the controller parameters, i.e., Particle Swarm Optimization (PSO), Accelerated PSO (APSO), Flower Pollination Algorithm (FPA), and Modified FPA (MFPA). The algorithms are compared in optimizing the longitudinal vehicle model and controller using the CARLA simulator, and stability tests are also done for each algorithm. In addition, the characteristics of several cost functions in controller optimization are inspected. The results show that the MFPA is the most stable algorithm, the proposed model represents the system satisfactorily, and optimizing the controller using a regularized cost function leads to better overall performance. Our code is available in https://github.com/fadamsyah/Particle-Based-Optimization-for-Longitudinal-Control.
{"title":"Particle-Based Optimization Algorithms for Longitudinal Control of Autonomous Vehicle: A Comparative Study","authors":"Fadillah Adam Maani, Alif Rizqullah Mahdi, Karina Ardellia Arfian, Yul Yunazwin Nazaruddin","doi":"10.15282/ijame.20.2.2023.14.0812","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.14.0812","url":null,"abstract":"In order to improve the stability and performance of an autonomous vehicle, optimization needs to be explicitly performed in the controllers, which has an essential part in the tracking system. This work proposes a novel longitudinal control optimization scheme and a novel longitudinal controller consisting of a feed-forward and feedback term. The feed-forward term is inspired by the vehicle’s steady-state response, whereas the feedback term is a proportional-integral-derivative (PID) controller. Also, a model representing the longitudinal vehicle dynamics is designed based on physical phenomena affecting the vehicle. Besides, some nature-inspired optimization algorithms are used to determine the optimal model parameters and optimize the controller parameters, i.e., Particle Swarm Optimization (PSO), Accelerated PSO (APSO), Flower Pollination Algorithm (FPA), and Modified FPA (MFPA). The algorithms are compared in optimizing the longitudinal vehicle model and controller using the CARLA simulator, and stability tests are also done for each algorithm. In addition, the characteristics of several cost functions in controller optimization are inspected. The results show that the MFPA is the most stable algorithm, the proposed model represents the system satisfactorily, and optimizing the controller using a regularized cost function leads to better overall performance. Our code is available in https://github.com/fadamsyah/Particle-Based-Optimization-for-Longitudinal-Control.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135066320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.15282/ijame.20.2.2023.13.0811
None Lei Tang, None Ningsu Luo Ren, Shawn Funkhouser
As the Linear Quadratic Regulator (LQR) approach is applied extensively in the system control of automobile suspension, the accuracy improvement of the weighting Q and R matrices is getting concern. The Particle Swarm Optimization (PSO) algorithm is being introduced to identify parameters and optimize matrix Q and R in order to fix the insufficiency of these experienced values because of the fast convergence and a more accurate solution. In this article, a quarter car model and a Bouc-Wen-based magnetorheological (MR) damper model are developed to combine the control of PSO identification and PSO-LQR controller in the semi-active suspension system. The MR damper was performed with an experimental test for running identification using experimental data as input into the Bouc-Wen model to obtain six unknown parameters, where the parameters were estimated with the PSO algorithm. Since the numerical model has been done with all parameters clear, the need for damping force from suspension is obtained by means of running the model using an input current. In the employment of PSO for damper model and vehicle control, the dual applications succeeded in verifying the feasibility of parameter identification in the MR damper and successfully tuned the LQR controller in the semi-active suspension, which decreases the vehicle body acceleration and displacement so that the improvement of ride comfort and drive stability achieved.
{"title":"Semi-active Suspension Control with PSO Tuned LQR Controller Based on MR Damper","authors":"None Lei Tang, None Ningsu Luo Ren, Shawn Funkhouser","doi":"10.15282/ijame.20.2.2023.13.0811","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.13.0811","url":null,"abstract":"As the Linear Quadratic Regulator (LQR) approach is applied extensively in the system control of automobile suspension, the accuracy improvement of the weighting Q and R matrices is getting concern. The Particle Swarm Optimization (PSO) algorithm is being introduced to identify parameters and optimize matrix Q and R in order to fix the insufficiency of these experienced values because of the fast convergence and a more accurate solution. In this article, a quarter car model and a Bouc-Wen-based magnetorheological (MR) damper model are developed to combine the control of PSO identification and PSO-LQR controller in the semi-active suspension system. The MR damper was performed with an experimental test for running identification using experimental data as input into the Bouc-Wen model to obtain six unknown parameters, where the parameters were estimated with the PSO algorithm. Since the numerical model has been done with all parameters clear, the need for damping force from suspension is obtained by means of running the model using an input current. In the employment of PSO for damper model and vehicle control, the dual applications succeeded in verifying the feasibility of parameter identification in the MR damper and successfully tuned the LQR controller in the semi-active suspension, which decreases the vehicle body acceleration and displacement so that the improvement of ride comfort and drive stability achieved.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135052466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-31DOI: 10.15282/ijame.20.2.2023.12.0810
None M.Z.A. Kamaludin, Juffrizal Karjanto, None N. Muhammad, None N. Md. Yusof, None M.Z. Hassan, None A.F.H. Zulkifli, None Z.M. Jawi, None A.A. Ab Rashid
Along with the increasing application of a self-assessment questionnaire to recognize the driving style, questions have been raised about the possibility of reporting bias because of the driver’s misjudgment. A hazy reference point was the cause since drivers lack objective input directly tied to their driving behaviour when answering a self-assessment questionnaire. This study aims to validate the results of a driving style self-assessment questionnaire with road studies for Malaysian drivers. A total of 20 drivers’ driving styles were recorded and evaluated by the two designated observers. The driver completed the driving self-evaluation questionnaire (18 items) after finishing the two designated routes (familiarization and experiment route). In comparison, the observer evaluated the driver by using two forms: 1) a driver evaluation questionnaire (18 items) after the experiment and 2) an on-road driver observation form (25 items) during the experiment. Inference statistics analyzed the data using regression, Pearson correlation, Wilcoxon z-value, Analysis of Variance (ANOVA), and reliability test. For the reliability test, the questionnaire illustrates the consistency and reliability of the set questionnaire used in this study, ranging from acceptable to good. However, the result shows no significant correlations between driver and observer with on-road driver observation forms for error/violation during driving activities. Besides, there were significant differences between the driver and observer regarding driving style evaluation. The over-positive appraisal was higher among drivers with higher error/violation scores and with the ones that the observer evaluated. The theoretical and practical significance of the self-driving questionnaire is addressed.
{"title":"Validation of Malaysian Driving Style Self-Assessment with Observational Road Study","authors":"None M.Z.A. Kamaludin, Juffrizal Karjanto, None N. Muhammad, None N. Md. Yusof, None M.Z. Hassan, None A.F.H. Zulkifli, None Z.M. Jawi, None A.A. Ab Rashid","doi":"10.15282/ijame.20.2.2023.12.0810","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.12.0810","url":null,"abstract":"Along with the increasing application of a self-assessment questionnaire to recognize the driving style, questions have been raised about the possibility of reporting bias because of the driver’s misjudgment. A hazy reference point was the cause since drivers lack objective input directly tied to their driving behaviour when answering a self-assessment questionnaire. This study aims to validate the results of a driving style self-assessment questionnaire with road studies for Malaysian drivers. A total of 20 drivers’ driving styles were recorded and evaluated by the two designated observers. The driver completed the driving self-evaluation questionnaire (18 items) after finishing the two designated routes (familiarization and experiment route). In comparison, the observer evaluated the driver by using two forms: 1) a driver evaluation questionnaire (18 items) after the experiment and 2) an on-road driver observation form (25 items) during the experiment. Inference statistics analyzed the data using regression, Pearson correlation, Wilcoxon z-value, Analysis of Variance (ANOVA), and reliability test. For the reliability test, the questionnaire illustrates the consistency and reliability of the set questionnaire used in this study, ranging from acceptable to good. However, the result shows no significant correlations between driver and observer with on-road driver observation forms for error/violation during driving activities. Besides, there were significant differences between the driver and observer regarding driving style evaluation. The over-positive appraisal was higher among drivers with higher error/violation scores and with the ones that the observer evaluated. The theoretical and practical significance of the self-driving questionnaire is addressed.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135314852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-28DOI: 10.15282/ijame.20.2.2023.11.0809
Hamza Khatib, El Kebch Ali
This work aims to analyse the effect of the alternated multiaxial stress state on the relaxation mechanisms of residual stresses and the integrity of welded S355 steel, presenting a nonlinear and combined hardening behaviour. The first part of this work proposes a model to predict the residual stresses introduced by the thermal effect of the welding process. The stresses resulting from the thermal cycle were integrated into a second model in which the material was subjected to a cyclic load to analyse the relaxation process. To ensure a good accuracy of the relaxation results, the kinematic and isotropic hardening were combined in a nonlinear model. In the last part of this paper, a multiaxial fatigue strength analysis was carried out, taking into account the effect of residual stresses and the relaxation process. The results show a considerable relaxation of the residual stresses if they are subjected to low load levels applied under specific conditions. The relaxed residual stresses can have a considerable effect on fatigue strength. Also, the importance of the consideration of the relaxation process on the accuracy of the fatigue strength results is illustrated.
{"title":"Effect of Alternated Multiaxial Stress State on Fatigue Strength and Relaxation of Residual Stress in Welded S355 Steel with Nonlinear and Combined Hardening","authors":"Hamza Khatib, El Kebch Ali","doi":"10.15282/ijame.20.2.2023.11.0809","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.11.0809","url":null,"abstract":"This work aims to analyse the effect of the alternated multiaxial stress state on the relaxation mechanisms of residual stresses and the integrity of welded S355 steel, presenting a nonlinear and combined hardening behaviour. The first part of this work proposes a model to predict the residual stresses introduced by the thermal effect of the welding process. The stresses resulting from the thermal cycle were integrated into a second model in which the material was subjected to a cyclic load to analyse the relaxation process. To ensure a good accuracy of the relaxation results, the kinematic and isotropic hardening were combined in a nonlinear model. In the last part of this paper, a multiaxial fatigue strength analysis was carried out, taking into account the effect of residual stresses and the relaxation process. The results show a considerable relaxation of the residual stresses if they are subjected to low load levels applied under specific conditions. The relaxed residual stresses can have a considerable effect on fatigue strength. Also, the importance of the consideration of the relaxation process on the accuracy of the fatigue strength results is illustrated.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135608154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-28DOI: 10.15282/ijame.20.2.2023.10.0808
None SHITAL GUNJATE, None PROF.DR.SANJAY A KHOT
The increasing number of fatalities in nations across the world because of a deficiency of protective technology in automobiles has created a chaotic scene in recent years. However, the car driver’s Perception-Reaction Time (PRT) plays an important variable during such accidents and emergencies. The Anti-Lock Braking System (ABS) seems a viable technology, which today is used to prevent tires from sliding during quick brakes, whereas EBS is designed for braking assistance during tuning or emergency braking. Physical weight, rotational rigidity, diameter, and tire material strength of the vehicle are all used to simulate them. Advance Driver Assistance Systems (ADAS), which include Anti-lock brakes (ABS) and Emergency Braking Systems (EBS), are the foremost viable technique for minimizing the environmental impact and uncertainties of driving road transportation. The presented systematic review aims to deliver a ground-level analysis that can be used to enhance the safety of motor vehicle driving, reduce wheel slip to achieve the best possible stopping distance in commercial and specialized vehicles, and influence future transportation. In this study, the most widely utilized technologies for ADAS have been reviewed and discussed. Various sensors used to improve braking and vehicle performance have been systematically studied in the context of low power-consuming techniques like pulse width modulation. An analysis of emergency braking procedures performed by riders with varying degrees of braking expertise was conducted using previously collected experimental data, and the results were used to conclude potential loss of control situations.
{"title":"A Systematic Review of Emergency Braking Assistant System to Avoid Accidents Using Pulse Width Modulation and Fuzzy Logic Control Integrated with Antilock Braking","authors":"None SHITAL GUNJATE, None PROF.DR.SANJAY A KHOT","doi":"10.15282/ijame.20.2.2023.10.0808","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.10.0808","url":null,"abstract":"The increasing number of fatalities in nations across the world because of a deficiency of protective technology in automobiles has created a chaotic scene in recent years. However, the car driver’s Perception-Reaction Time (PRT) plays an important variable during such accidents and emergencies. The Anti-Lock Braking System (ABS) seems a viable technology, which today is used to prevent tires from sliding during quick brakes, whereas EBS is designed for braking assistance during tuning or emergency braking. Physical weight, rotational rigidity, diameter, and tire material strength of the vehicle are all used to simulate them. Advance Driver Assistance Systems (ADAS), which include Anti-lock brakes (ABS) and Emergency Braking Systems (EBS), are the foremost viable technique for minimizing the environmental impact and uncertainties of driving road transportation. The presented systematic review aims to deliver a ground-level analysis that can be used to enhance the safety of motor vehicle driving, reduce wheel slip to achieve the best possible stopping distance in commercial and specialized vehicles, and influence future transportation. In this study, the most widely utilized technologies for ADAS have been reviewed and discussed. Various sensors used to improve braking and vehicle performance have been systematically studied in the context of low power-consuming techniques like pulse width modulation. An analysis of emergency braking procedures performed by riders with varying degrees of braking expertise was conducted using previously collected experimental data, and the results were used to conclude potential loss of control situations.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135608152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-21DOI: 10.15282/ijame.20.2.2023.09.0807
Andrew G. Zebua, Sheila Tobing, Tajuddin Nur, M. A. Indianto
The study of the aerodynamics of flapping airfoils is crucial to understand the flight of natural flyers and its potential applications in developing micro air vehicles and wind/water turbine blades. There has been much research on the aerodynamics of flapping wings recently, but there is only a little research relating to the tandem airfoil. Therefore, this study is conducted to determine the aerodynamic characteristics of the tandem airfoil at Re = 100000, typical of insect flight. The tandem airfoil is plunging and pitching harmonically. This study numerically analyzes the effects of stagger, thickness, and curvature on tandem airfoil propulsion. The effects of stagger are studied using NACA 0012, while the effects of thickness are analyzed on NACA 0012, 0015, 0020 and 0030. The simulations to study the effects of curvature are conducted using NACA 0030. The optimum distance of the stagger is X/c = 2.5, but the propulsive efficiency of tandem NACA 0012 is still smaller than two single NACA 0012 airfoils. For the most optimum thickness at 30% of the chord length, the propulsive efficiency of tandem NACA 0030 is higher than two single NACA 0030 airfoils. Meanwhile, the most optimum curvature is 0% because the increase in curvature of the airfoil reduces propulsive efficiency.
{"title":"Numerical Analysis on The Effects of Stagger, Thickness, and Curvature on The Propulsion of Tandem Airfoil","authors":"Andrew G. Zebua, Sheila Tobing, Tajuddin Nur, M. A. Indianto","doi":"10.15282/ijame.20.2.2023.09.0807","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.09.0807","url":null,"abstract":"The study of the aerodynamics of flapping airfoils is crucial to understand the flight of natural flyers and its potential applications in developing micro air vehicles and wind/water turbine blades. There has been much research on the aerodynamics of flapping wings recently, but there is only a little research relating to the tandem airfoil. Therefore, this study is conducted to determine the aerodynamic characteristics of the tandem airfoil at Re = 100000, typical of insect flight. The tandem airfoil is plunging and pitching harmonically. This study numerically analyzes the effects of stagger, thickness, and curvature on tandem airfoil propulsion. The effects of stagger are studied using NACA 0012, while the effects of thickness are analyzed on NACA 0012, 0015, 0020 and 0030. The simulations to study the effects of curvature are conducted using NACA 0030. The optimum distance of the stagger is X/c = 2.5, but the propulsive efficiency of tandem NACA 0012 is still smaller than two single NACA 0012 airfoils. For the most optimum thickness at 30% of the chord length, the propulsive efficiency of tandem NACA 0030 is higher than two single NACA 0030 airfoils. Meanwhile, the most optimum curvature is 0% because the increase in curvature of the airfoil reduces propulsive efficiency.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139356950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-04DOI: 10.15282/ijame.20.2.2023.08.0806
N. Jain, Sangeeta Mittal
Driving is a complex task involving the perception of the driving event, planning response, and action. Safe driving ensures the vehicle’s and its passengers’ safety, whereas economical driving brings down fuel consumption. Eventually, eco-safe driving that ensures economical as well as safe driving is the best bet. This review paper provides a systematic comprehensive analysis across cross-cutting dimensions such as data collection mechanisms, features affecting eco-safe driving, computational models for driving behavior analysis, driver motivational approaches towards eco-safe driving, exploiting research gaps and opportunities for further research in this domain. Driving behavior along with environmental context, including weather information, road conditions, traffic flow and time of travel, represent the most effective factors for doing eco-safe driving analysis. 82% of reviewed papers recommended OBD as a reliable data collection source, along with supplementary information from body sensors and cameras. The K-Mean clustering is an effective driving profiling technique clubbed with dimensionality reduction techniques based on Random Forest regressor, PCA and autoencoders. Deep learning and ensemble learning-based safety approaches utilizing Recurrent Convolutional Networks (RCN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) and Decision Tree (DT) have achieved impressive accuracies surpassing 99%, followed by Neural Networks (NN), Support Vector Machines (SVM) and Random Forest (RF) with accuracy ranging from 91% to 96%. Long Short-Term Memory (LSTM) yielded superior Area Under Curve (AUC of 0.836) for fuel prediction, in comparison to Support Vector Machines (SVM) and Neural Networks (NN). Gated Recurrent Unit (GRU) represents fine-grained accurate fuel-prediction methods with accuracy comparable to Long Short-Term Memory (LSTM). Prominent research gaps identified during this study are the lack of a comprehensive approach covering all aspects related to safety, fuel economy, the scope of improvement in real-time driving risk assessment at appropriate granularity level, missing effective and engaging driving feedback, dealing with uncertain and incomplete driving events, driver’s personal traits affecting driving safety and fuel-economy. The review will help in establishing the readiness of automation of driving analysis for reinforcement of eco-safe driving for various kinds of vehicles plug-in hybrid vehicles, hybrid electric vehicles, electric vehicles, and self-driving cars.
{"title":"Review of Computational Techniques for Modelling Eco-Safe Driving Behavior","authors":"N. Jain, Sangeeta Mittal","doi":"10.15282/ijame.20.2.2023.08.0806","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.08.0806","url":null,"abstract":"Driving is a complex task involving the perception of the driving event, planning response, and action. Safe driving ensures the vehicle’s and its passengers’ safety, whereas economical driving brings down fuel consumption. Eventually, eco-safe driving that ensures economical as well as safe driving is the best bet. This review paper provides a systematic comprehensive analysis across cross-cutting dimensions such as data collection mechanisms, features affecting eco-safe driving, computational models for driving behavior analysis, driver motivational approaches towards eco-safe driving, exploiting research gaps and opportunities for further research in this domain. Driving behavior along with environmental context, including weather information, road conditions, traffic flow and time of travel, represent the most effective factors for doing eco-safe driving analysis. 82% of reviewed papers recommended OBD as a reliable data collection source, along with supplementary information from body sensors and cameras. The K-Mean clustering is an effective driving profiling technique clubbed with dimensionality reduction techniques based on Random Forest regressor, PCA and autoencoders. Deep learning and ensemble learning-based safety approaches utilizing Recurrent Convolutional Networks (RCN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) and Decision Tree (DT) have achieved impressive accuracies surpassing 99%, followed by Neural Networks (NN), Support Vector Machines (SVM) and Random Forest (RF) with accuracy ranging from 91% to 96%. Long Short-Term Memory (LSTM) yielded superior Area Under Curve (AUC of 0.836) for fuel prediction, in comparison to Support Vector Machines (SVM) and Neural Networks (NN). Gated Recurrent Unit (GRU) represents fine-grained accurate fuel-prediction methods with accuracy comparable to Long Short-Term Memory (LSTM). Prominent research gaps identified during this study are the lack of a comprehensive approach covering all aspects related to safety, fuel economy, the scope of improvement in real-time driving risk assessment at appropriate granularity level, missing effective and engaging driving feedback, dealing with uncertain and incomplete driving events, driver’s personal traits affecting driving safety and fuel-economy. The review will help in establishing the readiness of automation of driving analysis for reinforcement of eco-safe driving for various kinds of vehicles plug-in hybrid vehicles, hybrid electric vehicles, electric vehicles, and self-driving cars.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139363424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-30DOI: 10.15282/ijame.20.2.2023.02.0800
M. O. Görtan, Berkay Yüksel
Deep rolling (DR) is an effective mechanical surface treatment method to improve the fatigue properties of engineering components. In this method, the surface of the component was rolled using a roller with a predetermined force to obtain reduced roughness, hardness increases and compressive residual stresses in the surface region. These alterations allow for increasing the fatigue lives of the components in industrial applications. In the current study, DR was applied in tangential and longitudinal directions on specimens that were manufactured using EN-AW 6082-T6 aluminum. The resulting roughness, hardness and residual stresses were determined experimentally. Fatigue tests were carried out to determine the improvements in fatigue properties after DR. It was found that DR-induced compressive residual stresses depend on DR direction considerably. Due to this reason, fatigue strength improvements were found to be different for different DR direction applications. Longitudinal rolling resulted in a 23% fatigue strength increase compared to a 7% increase for tangential rolling. For both DR direction applications, fatigue cracks were shown to initiate at the sub-surface region, whereas the as-turned specimens exhibited surface crack initiation.
{"title":"Improvement of Fatigue Properties of EN AW 6082 Aluminum Alloy using Different Deep Rolling Directions","authors":"M. O. Görtan, Berkay Yüksel","doi":"10.15282/ijame.20.2.2023.02.0800","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.02.0800","url":null,"abstract":"Deep rolling (DR) is an effective mechanical surface treatment method to improve the fatigue properties of engineering components. In this method, the surface of the component was rolled using a roller with a predetermined force to obtain reduced roughness, hardness increases and compressive residual stresses in the surface region. These alterations allow for increasing the fatigue lives of the components in industrial applications. In the current study, DR was applied in tangential and longitudinal directions on specimens that were manufactured using EN-AW 6082-T6 aluminum. The resulting roughness, hardness and residual stresses were determined experimentally. Fatigue tests were carried out to determine the improvements in fatigue properties after DR. It was found that DR-induced compressive residual stresses depend on DR direction considerably. Due to this reason, fatigue strength improvements were found to be different for different DR direction applications. Longitudinal rolling resulted in a 23% fatigue strength increase compared to a 7% increase for tangential rolling. For both DR direction applications, fatigue cracks were shown to initiate at the sub-surface region, whereas the as-turned specimens exhibited surface crack initiation.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72962063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-30DOI: 10.15282/ijame.20.2.2023.03.0801
Jessica Gissella Maradey Lázaro, Helio Sneyder Esteban Villegas, Andres Felipe Aldana Afanador, Kevin Sebastián Cáceres Mojica
Automotive is one of the most important industries in the world, which lead to a need for continuous improvement of vehicles and their internal systems. Suspension systems have been improved for better vehicle performance and passenger comfort, keeping the tire in contact with the road surface. Active suspensions require optimal control to modulate the flow of energy and generate the control force by implementing active actuators able to provide negative damping and a wider range of forces and velocities. This article aims the design of an active suspension system based on LQG and LQR controller evaluating its performance in a distributed parameters simulation using COMSOL Multiphysics® and MATLAB®. The quarter car model is proposed and is linearized to design the optimal control (LQG and LQR) respectively. An early mathematical simulation is developed in MATLAB (R) software to verify and compare the open and closed loop results. Finally, the full system model is implemented in COMSOL Multiphysics (R) software considering rigid materials and the controller to analyze the distributed parameters simulation results.
{"title":"Optimal Control of an Active Suspension System Applying Distributed Parameter Simulation Test","authors":"Jessica Gissella Maradey Lázaro, Helio Sneyder Esteban Villegas, Andres Felipe Aldana Afanador, Kevin Sebastián Cáceres Mojica","doi":"10.15282/ijame.20.2.2023.03.0801","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.03.0801","url":null,"abstract":"Automotive is one of the most important industries in the world, which lead to a need for continuous improvement of vehicles and their internal systems. Suspension systems have been improved for better vehicle performance and passenger comfort, keeping the tire in contact with the road surface. Active suspensions require optimal control to modulate the flow of energy and generate the control force by implementing active actuators able to provide negative damping and a wider range of forces and velocities. This article aims the design of an active suspension system based on LQG and LQR controller evaluating its performance in a distributed parameters simulation using COMSOL Multiphysics® and MATLAB®. The quarter car model is proposed and is linearized to design the optimal control (LQG and LQR) respectively. An early mathematical simulation is developed in MATLAB (R) software to verify and compare the open and closed loop results. Finally, the full system model is implemented in COMSOL Multiphysics (R) software considering rigid materials and the controller to analyze the distributed parameters simulation results.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78971576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-30DOI: 10.15282/ijame.20.2.2023.01.0799
Ava A. K. Mohammed, G. I. Hassan, Younis K. Khdir
Hybrid fiber reinforced polymer with nanofiller composite was introduced into a lot of industries due to its extreme mechanical properties in comparison with non-hybrid material. In this investigation, cross and quasi-fiber laminated epoxy composites with and without nano Al2O3 were fabricated using Vacuum Assisted Resine Infusion Method and Ultrasonic Dual Mixing Method. In general, the results of mechanical properties indicated that the addition of 2% nano Al2O3 enhances the tensile and flexural properties. Cross number 2 with nano Al2O3 laminate had the maximum tensile strength 628 MPa and maximum tensile strain of 1.74%, while cross number 1 with nano Al2O3 laminate had the maximum tensile modulus of 37.756 GPa in the cross group. In the quasi group, quasi number 2 with nano Al2O3 had the maximum tensile strength, maximum tensile strain, and maximum tensile modulus, equal to 294 MPa, 1.98%, and 16.409 GPa, respectively. Regarding the flexural properties, cross number 1 with nano Al2O3 laminate had a maximum flexural strength of 708.2 MPa and maximum flexural strain of 2.027%, while cross number 2 with nano Al2O3 laminate had a maximum flexural modulus of 38.73 GPa in the cross group. On the other hand, quasi number 1 with nano Al2O3 laminate had the maximum flexural strength, maximum flexural strain, and maximum flexural modulus equal to 596 MPa, 2.424%, and 29.2 GPa, respectively in the quasi group. The internal structures of the failure laminated composites through scanning electronic microscopy confirm that the adhesion between fibers and matrix is good.
{"title":"Mechanical Behavior of Hybrid Laminated Nano Composite Containing Equal Numbers of Glass and Carbon Fiber Plies","authors":"Ava A. K. Mohammed, G. I. Hassan, Younis K. Khdir","doi":"10.15282/ijame.20.2.2023.01.0799","DOIUrl":"https://doi.org/10.15282/ijame.20.2.2023.01.0799","url":null,"abstract":"Hybrid fiber reinforced polymer with nanofiller composite was introduced into a lot of industries due to its extreme mechanical properties in comparison with non-hybrid material. In this investigation, cross and quasi-fiber laminated epoxy composites with and without nano Al2O3 were fabricated using Vacuum Assisted Resine Infusion Method and Ultrasonic Dual Mixing Method. In general, the results of mechanical properties indicated that the addition of 2% nano Al2O3 enhances the tensile and flexural properties. Cross number 2 with nano Al2O3 laminate had the maximum tensile strength 628 MPa and maximum tensile strain of 1.74%, while cross number 1 with nano Al2O3 laminate had the maximum tensile modulus of 37.756 GPa in the cross group. In the quasi group, quasi number 2 with nano Al2O3 had the maximum tensile strength, maximum tensile strain, and maximum tensile modulus, equal to 294 MPa, 1.98%, and 16.409 GPa, respectively. Regarding the flexural properties, cross number 1 with nano Al2O3 laminate had a maximum flexural strength of 708.2 MPa and maximum flexural strain of 2.027%, while cross number 2 with nano Al2O3 laminate had a maximum flexural modulus of 38.73 GPa in the cross group. On the other hand, quasi number 1 with nano Al2O3 laminate had the maximum flexural strength, maximum flexural strain, and maximum flexural modulus equal to 596 MPa, 2.424%, and 29.2 GPa, respectively in the quasi group. The internal structures of the failure laminated composites through scanning electronic microscopy confirm that the adhesion between fibers and matrix is good.","PeriodicalId":13935,"journal":{"name":"International Journal of Automotive and Mechanical Engineering","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85038915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：