Nicolas Lampe, Zygimantas Ziaukas, C. Westerkamp, Hans-Georg Jacob
Knowledge of vehicle dynamics and in particular the maximum friction coefficient is required for the optimization of advanced driver assistance systems and the implementation of autonomous driving. Since the maximum friction coefficient cannot be measured directly, estimating this coefficient based on available sensors is a field of interest. In particular, model-based approaches based on Kalman filter derivates are used. However, their accuracy is limited by the accuracy of the physical model. Due to the real-time capability required, more detailed modeling is not possible. In addition, system identification and a robust filter design are needed. As a result, data-based approaches are gaining popularity in vehicle dynamics, which are also suitable for estimating the maximum friction coefficient. In this paper, maximum friction coefficient estimation is presented using recurrent artificial neural networks (RANN) based on vehicle sensors. In order to avoid incorrect estimations during low vehicle excitation, an excitation monitoring approach is introduced. Typical longitudinal and lateral driving maneuvers on different road surfaces simulated in IPG CarMaker with a Dacia Duster are used for training, validation and testing of the RANN. Finally, the data-based approach shows improved results compared to the model-based approach of a sensitivity-based unscented Kalman filter (sUKF) from previous works.
{"title":"Estimation of Maximum Friction Coefficient Using Recurrent Artificial Neural Networks","authors":"Nicolas Lampe, Zygimantas Ziaukas, C. Westerkamp, Hans-Georg Jacob","doi":"10.1145/3560453.3560459","DOIUrl":"https://doi.org/10.1145/3560453.3560459","url":null,"abstract":"Knowledge of vehicle dynamics and in particular the maximum friction coefficient is required for the optimization of advanced driver assistance systems and the implementation of autonomous driving. Since the maximum friction coefficient cannot be measured directly, estimating this coefficient based on available sensors is a field of interest. In particular, model-based approaches based on Kalman filter derivates are used. However, their accuracy is limited by the accuracy of the physical model. Due to the real-time capability required, more detailed modeling is not possible. In addition, system identification and a robust filter design are needed. As a result, data-based approaches are gaining popularity in vehicle dynamics, which are also suitable for estimating the maximum friction coefficient. In this paper, maximum friction coefficient estimation is presented using recurrent artificial neural networks (RANN) based on vehicle sensors. In order to avoid incorrect estimations during low vehicle excitation, an excitation monitoring approach is introduced. Typical longitudinal and lateral driving maneuvers on different road surfaces simulated in IPG CarMaker with a Dacia Duster are used for training, validation and testing of the RANN. Finally, the data-based approach shows improved results compared to the model-based approach of a sensitivity-based unscented Kalman filter (sUKF) from previous works.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126948697","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}
This study established the dynamic math model and the physical simulation model of a hybrid transmission system, and investigated the abuse torque load characteristics of the Differential Mechanism. It is found that, when the transmission system contains a large moment of inertia of components, the abuse torque load of the Differential Mechanism is 23% greater than that of traditional vehicles, which may lead to Differential Mechanism failure. By monitoring the change of wheel angular acceleration and controlling the output torque of the driving motor, the peak abuse torque load can be reduced by 35%. At the same time, the spline interface design of the Differential Mechanism and Half Shafts were improved to increase the impact resistance from the source. At last, the Differential Mechanism was subjected to an impact fatigue test with positive results.
{"title":"Abuse Torque Load Simulation and Design of Differential Mechanism in Hybrid Electric Vehicle","authors":"Guogeng Zhang, Pengcheng Huang, Xiaowen Song","doi":"10.1145/3560453.3560458","DOIUrl":"https://doi.org/10.1145/3560453.3560458","url":null,"abstract":"This study established the dynamic math model and the physical simulation model of a hybrid transmission system, and investigated the abuse torque load characteristics of the Differential Mechanism. It is found that, when the transmission system contains a large moment of inertia of components, the abuse torque load of the Differential Mechanism is 23% greater than that of traditional vehicles, which may lead to Differential Mechanism failure. By monitoring the change of wheel angular acceleration and controlling the output torque of the driving motor, the peak abuse torque load can be reduced by 35%. At the same time, the spline interface design of the Differential Mechanism and Half Shafts were improved to increase the impact resistance from the source. At last, the Differential Mechanism was subjected to an impact fatigue test with positive results.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127825070","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}
The aim of this paper is to present the development of a vortex suction robot for cleaning the surface of the bridges or the dams. Based on the principle of vortex suction, the suction mechanism is designed in order that the underwater cleaning robot can stably adhere to the wall surface in the underwater environment. This paper mainly elaborates the design and suction performance of vortex suction mechanism. The required suction force of the vortex suction cup is obtained by designing and analyzing the underwater cleaning robot. Simulation analysis and experimental verification of the proposed underwater robot and the vortex suction cup installed on the robot are carried out. The results show that the vortex suction cup designed in this paper can make the underwater cleaning robot obtain stable and reliable suction performance.
{"title":"Development of an Underwater Cleaning Robot with Vortex Suction Mechanism","authors":"Yibing Zhao, Canjun Yang","doi":"10.1145/3560453.3560455","DOIUrl":"https://doi.org/10.1145/3560453.3560455","url":null,"abstract":"The aim of this paper is to present the development of a vortex suction robot for cleaning the surface of the bridges or the dams. Based on the principle of vortex suction, the suction mechanism is designed in order that the underwater cleaning robot can stably adhere to the wall surface in the underwater environment. This paper mainly elaborates the design and suction performance of vortex suction mechanism. The required suction force of the vortex suction cup is obtained by designing and analyzing the underwater cleaning robot. Simulation analysis and experimental verification of the proposed underwater robot and the vortex suction cup installed on the robot are carried out. The results show that the vortex suction cup designed in this paper can make the underwater cleaning robot obtain stable and reliable suction performance.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127488236","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}
Ruijun Dou, Tianji Feng, M. Zhou, Qin Xu, Liang Kou
In order to realize the purpose of early braking vibration and noise verification and assist in model selection, data screening and kinematic segment division of the collected vehicle brake Huangshan braking load spectrum were carried out, and the Markov working condition was used to construct the theory, and the state transition probability matrix was carried out. build, and apply the stochastic case construction method for candidate case construction.Cluster analysis is performed on the constructed candidate working conditions, the final transformation working condition is selected, and the transformation working condition is formulated as the inertia test bench working condition.Finally, the same samples were subjected to inertia bench test and vehicle road test respectively, and the test results of the two were compared and analyzed. It can be seen from the analysis results that the converted bench conditions can reproduce the problems found in the vehicle test to a certain extent.Through the conversion conditions of this study, it can realize the preliminary verification for the main engine factory in the early stage of brake system selection, find and solve most of the vibration and noise problems of the selected samples, shorten the development cycle and save the development cost.
{"title":"Research on working condition transformation of Huangshan test bench based on Markov braking vibration noise","authors":"Ruijun Dou, Tianji Feng, M. Zhou, Qin Xu, Liang Kou","doi":"10.1145/3560453.3560462","DOIUrl":"https://doi.org/10.1145/3560453.3560462","url":null,"abstract":"In order to realize the purpose of early braking vibration and noise verification and assist in model selection, data screening and kinematic segment division of the collected vehicle brake Huangshan braking load spectrum were carried out, and the Markov working condition was used to construct the theory, and the state transition probability matrix was carried out. build, and apply the stochastic case construction method for candidate case construction.Cluster analysis is performed on the constructed candidate working conditions, the final transformation working condition is selected, and the transformation working condition is formulated as the inertia test bench working condition.Finally, the same samples were subjected to inertia bench test and vehicle road test respectively, and the test results of the two were compared and analyzed. It can be seen from the analysis results that the converted bench conditions can reproduce the problems found in the vehicle test to a certain extent.Through the conversion conditions of this study, it can realize the preliminary verification for the main engine factory in the early stage of brake system selection, find and solve most of the vibration and noise problems of the selected samples, shorten the development cycle and save the development cost.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126589626","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}
Wei Zhang, Shunxing Xu, Zhihang Wang, Fang Yu, Zishu He
Automotive radar has been emerging as a key technology enabling intelligent and autonomous features in modern vehicles. However, its great weakness is the poor angular resolution compared with its competitors, such as LiDAR or camera. Thus, one of the most challenging problems automotive radars faced is how to achieve high angular resolution, especially with the restriction of limited array aperture and in high dynamic environment. In this paper, a novel approach for high angular resolution DOA is proposed to separate two targets in the same range and Doppler cell by introducing one completely new concept of virtual sparse extension array. Based on the radar returns from the physical array, an extremely large virtual sparse aperture can be formed in a unique way. The simulation results demonstrate that, for a typical time division modulation (TDM) multiple-input multiple-output (MIMO) automotive radar with 3 transmitters and 4 receivers, the angular resolution can reach 0.01°, which is far better than other algorithms. In addition, the proposed method only needs single snapshot, and this is especially valuable to deal with the practical high dynamic environment.
{"title":"Super Resolution DOA Based on Virtual Sparse Extension Array for FMCW Automotive Radar","authors":"Wei Zhang, Shunxing Xu, Zhihang Wang, Fang Yu, Zishu He","doi":"10.1145/3560453.3560461","DOIUrl":"https://doi.org/10.1145/3560453.3560461","url":null,"abstract":"Automotive radar has been emerging as a key technology enabling intelligent and autonomous features in modern vehicles. However, its great weakness is the poor angular resolution compared with its competitors, such as LiDAR or camera. Thus, one of the most challenging problems automotive radars faced is how to achieve high angular resolution, especially with the restriction of limited array aperture and in high dynamic environment. In this paper, a novel approach for high angular resolution DOA is proposed to separate two targets in the same range and Doppler cell by introducing one completely new concept of virtual sparse extension array. Based on the radar returns from the physical array, an extremely large virtual sparse aperture can be formed in a unique way. The simulation results demonstrate that, for a typical time division modulation (TDM) multiple-input multiple-output (MIMO) automotive radar with 3 transmitters and 4 receivers, the angular resolution can reach 0.01°, which is far better than other algorithms. In addition, the proposed method only needs single snapshot, and this is especially valuable to deal with the practical high dynamic environment.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115017417","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}
The braided corrugated hose is widely used in aerospace, marine, chemical and other fields due to its good displacement compensation and vibration damping. This paper uses finite element method to explore the effect of braiding angle on the axial mechanical properties of the braided corrugated hose. The numerical results show that the axial stiffness of the braided corrugated hose is nonlinear, which can be explained in three stages. The first stage is a linear stage, and the stiffness of the bellows plays a major role. The second stage is the non-linear stage called the ‘soft characteristic’ stage and the third stage is the linear stage. The braiding angle mainly affects the ‘the soft characteristic’ stage. As the braiding angle increases, the faster the ‘soft characteristic’ changes, the greater the axial stiffness of the braided corrugated hose increases. The conclusion can provide a theoretical basis for the design of braided corrugated hoses.
{"title":"Numerical study of the axial mechanical properties of braided corrugated hose with different braiding angles","authors":"Dacheng Huang, Jianrun Zhang","doi":"10.1145/3560453.3560464","DOIUrl":"https://doi.org/10.1145/3560453.3560464","url":null,"abstract":"The braided corrugated hose is widely used in aerospace, marine, chemical and other fields due to its good displacement compensation and vibration damping. This paper uses finite element method to explore the effect of braiding angle on the axial mechanical properties of the braided corrugated hose. The numerical results show that the axial stiffness of the braided corrugated hose is nonlinear, which can be explained in three stages. The first stage is a linear stage, and the stiffness of the bellows plays a major role. The second stage is the non-linear stage called the ‘soft characteristic’ stage and the third stage is the linear stage. The braiding angle mainly affects the ‘the soft characteristic’ stage. As the braiding angle increases, the faster the ‘soft characteristic’ changes, the greater the axial stiffness of the braided corrugated hose increases. The conclusion can provide a theoretical basis for the design of braided corrugated hoses.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128800958","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}
Maamar Al Tobi, Ramachandran K p, Saleh Al-Araimi, Rene Pacturan, Amuthakkannan Rajakannu, Geetha Achuthan
This work presents an investigation for a number of mechanical conditions (healthy, imbalance, misalignment, gear fault, bearing fault). The vibration conditions are simulated and based on real-time vibration data that are acquired from a Machinery Fault Simulator (MFS). The diagnosis process passes through two main stages after the data acquisition, where then the Continuous Wavelet Transform (CWT) method is applied to preprocess the obtained datasets (signals), and extract the features based on five statistical parameters namely: RMS, Kurtosis, Peak, Impulse Factor and Shape Factor. Then Artificial Intelligence (AI) based classification is applied using the Multilayer Feed-Forward Perceptron Neural Network (MLP) using different cases, where different number of neurons for the hidden layer and two different datasets of the input features with 250 features for each condition and also 2000 features for each condition once with normalized and also with non-normalized features to investigate the best cases for the performance classification in terms of neurons and features number, and also the impact of features normalization. The obtained results based on the classification performance using MLP-NN with the different cases are comparable, where the normalized features with less number of features and moderate neurons have shown better classification performance. Moreover, the results have shown the advantage of integrating CWT with the MLP-NN by providing significant classification rates for the different mechanical conditions.
{"title":"Machinery Fault Diagnosis using Continuous Wavelet Transform and Artificial Intelligence based classification","authors":"Maamar Al Tobi, Ramachandran K p, Saleh Al-Araimi, Rene Pacturan, Amuthakkannan Rajakannu, Geetha Achuthan","doi":"10.1145/3560453.3560463","DOIUrl":"https://doi.org/10.1145/3560453.3560463","url":null,"abstract":"This work presents an investigation for a number of mechanical conditions (healthy, imbalance, misalignment, gear fault, bearing fault). The vibration conditions are simulated and based on real-time vibration data that are acquired from a Machinery Fault Simulator (MFS). The diagnosis process passes through two main stages after the data acquisition, where then the Continuous Wavelet Transform (CWT) method is applied to preprocess the obtained datasets (signals), and extract the features based on five statistical parameters namely: RMS, Kurtosis, Peak, Impulse Factor and Shape Factor. Then Artificial Intelligence (AI) based classification is applied using the Multilayer Feed-Forward Perceptron Neural Network (MLP) using different cases, where different number of neurons for the hidden layer and two different datasets of the input features with 250 features for each condition and also 2000 features for each condition once with normalized and also with non-normalized features to investigate the best cases for the performance classification in terms of neurons and features number, and also the impact of features normalization. The obtained results based on the classification performance using MLP-NN with the different cases are comparable, where the normalized features with less number of features and moderate neurons have shown better classification performance. Moreover, the results have shown the advantage of integrating CWT with the MLP-NN by providing significant classification rates for the different mechanical conditions.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132588133","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}
The unauthorized drones in restricted areas are being observed more frequently these days. This poses a serious threat to the highly confidential operations of a country. The swarm intelligence and ornithopter robots can play a crucial role in dealing with these threats. In this paper, we analyze the necessity and propose an architecture of the swarm ornithopter. We call the resulting robots as the swarm ornithopter robirds. The proposed architecture has key features such as a wireless jamming gun, high-resolution camera, pattern formation, identifying, detecting and tracking unauthorized drones. Additionally, the limitations and future work of swarm ornithopter robirds have been discussed. This architecture has made several significant contributions to the military and defense sectors.
{"title":"Swarm Ornithopter Robirds: An Architecture to Protect Aerospace for Aerial Defense","authors":"Yash Patel, Parag Rughani","doi":"10.1145/3560453.3560456","DOIUrl":"https://doi.org/10.1145/3560453.3560456","url":null,"abstract":"The unauthorized drones in restricted areas are being observed more frequently these days. This poses a serious threat to the highly confidential operations of a country. The swarm intelligence and ornithopter robots can play a crucial role in dealing with these threats. In this paper, we analyze the necessity and propose an architecture of the swarm ornithopter. We call the resulting robots as the swarm ornithopter robirds. The proposed architecture has key features such as a wireless jamming gun, high-resolution camera, pattern formation, identifying, detecting and tracking unauthorized drones. Additionally, the limitations and future work of swarm ornithopter robirds have been discussed. This architecture has made several significant contributions to the military and defense sectors.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125834376","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}
The correctness and safety of the substation switching operation is related to the safe and stable operation of the power grid. In recent years, the frequent occurrence of misoperation incidents in substations has revealed that there are still many problems in the reliability of the anti-misoperation locking system. Therefore, a comprehensive and objective evaluation is of great significance for grasping the reliability level of the anti-misoperation locking system. Considering that the reliability of the system is closely related to its components, on the basis of analyzing the factors affecting the reliability of each component, this paper established a comprehensive reliability evaluation index system, the entropy weighting method is used to calculate the weight of each index, and the TOPSIS method is used to achieve comprehensive evaluation and ranking. Finally, the effectiveness of the proposed method is verified by taking the anti-misoperation locking system of 9 substations in 3 regions as an example.
{"title":"Research on Reliability Evaluation of the Substation Anti-misoperation Locking System","authors":"Junjie Zhang, Li Zhang, Xin-zhu Li","doi":"10.1145/3560453.3560466","DOIUrl":"https://doi.org/10.1145/3560453.3560466","url":null,"abstract":"The correctness and safety of the substation switching operation is related to the safe and stable operation of the power grid. In recent years, the frequent occurrence of misoperation incidents in substations has revealed that there are still many problems in the reliability of the anti-misoperation locking system. Therefore, a comprehensive and objective evaluation is of great significance for grasping the reliability level of the anti-misoperation locking system. Considering that the reliability of the system is closely related to its components, on the basis of analyzing the factors affecting the reliability of each component, this paper established a comprehensive reliability evaluation index system, the entropy weighting method is used to calculate the weight of each index, and the TOPSIS method is used to achieve comprehensive evaluation and ranking. Finally, the effectiveness of the proposed method is verified by taking the anti-misoperation locking system of 9 substations in 3 regions as an example.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124691482","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}
Iker Arandia, Iñaki Cejudo, E. Irigoyen, Itziar Urbieta, Harbil Arregui, E. Loyo
In electric vehicles context, battery consumption and "range anxiety" are the biggest worries. Different studies have shown that electric vehicle battery consumption depends on many factors and parameters that can be related with the vehicle, the driver or the route. In this paper we will show the impact of those parameters in the energy consumption based on a real life dataset. This dataset contains information about different real life routes completed by an electric vehicle (Volkswagen e-Golf). To see if a parameter affects the energy consumption, we will use different graphics and the statistical ANOVA-test and Welch's test. When parameters are categorical variables, we will see how the energy consumption changes between categories, showing that different values of that parameter imply different value of energy consumption. Continuous variables are going to be analyzed using the pairplot. The results show that using auxiliaries, an aggressive driving style and winter tires increase the consumption. Also, it is an important conclusion how in long routes the energy consumption is more stable than in shorter routes.
{"title":"Analyzing the Influence of Driver, Route and Vehicle-Related Factors in Electric Vehicle Energy Consumption, Based on Real Life Data","authors":"Iker Arandia, Iñaki Cejudo, E. Irigoyen, Itziar Urbieta, Harbil Arregui, E. Loyo","doi":"10.1145/3560453.3560467","DOIUrl":"https://doi.org/10.1145/3560453.3560467","url":null,"abstract":"In electric vehicles context, battery consumption and \"range anxiety\" are the biggest worries. Different studies have shown that electric vehicle battery consumption depends on many factors and parameters that can be related with the vehicle, the driver or the route. In this paper we will show the impact of those parameters in the energy consumption based on a real life dataset. This dataset contains information about different real life routes completed by an electric vehicle (Volkswagen e-Golf). To see if a parameter affects the energy consumption, we will use different graphics and the statistical ANOVA-test and Welch's test. When parameters are categorical variables, we will see how the energy consumption changes between categories, showing that different values of that parameter imply different value of energy consumption. Continuous variables are going to be analyzed using the pairplot. The results show that using auxiliaries, an aggressive driving style and winter tires increase the consumption. Also, it is an important conclusion how in long routes the energy consumption is more stable than in shorter routes.","PeriodicalId":345436,"journal":{"name":"Proceedings of the 2022 3rd International Conference on Robotics Systems and Vehicle Technology","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128173097","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：