Pub Date : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219125
Marianne Silva, Thaís Medeiros, Mariana Azevedo, Morsinaldo Medeiros, Mikael P. B. Themoteo, Tatiane Gois, I. Silva, Dan Costa
The Internet of Things (IoT) has significantly impacted various industries, particularly the automotive sector, due to the growing integration of IoT technologies in vehicles. As a result, the volume of data generated by vehicular sensors has increased, leading to a surge in studies focusing on driver behavior to enhance road safety and optimize transportation networks. However, traditional approaches to analyzing driver behavior have relied on supervised offline learning models, which are unsuitable for handling data streams in online learning environments. This study introduces an unsupervised online k-fix AutoCloud algorithm for detecting driver behavior patterns, leveraging the concepts of typicity and eccentricity while considering the historical-temporal relationships between samples. Furthermore, the algorithm autonomously and adaptively evolves without requiring a supervised training phase, making it compatible with the TinyML concept, encompassing Artificial Intelligence algorithms designed for low-power IoT devices. To validate the proposed method, a real case study was conducted over four days using a vehicle to compare the quantity and quality of clusters generated by the algorithm. The findings demonstrate the potential of the proposed approach for optimizing data processing with minimal computational power.
{"title":"An Adaptive TinyML Unsupervised Online Learning Algorithm for Driver Behavior Analysis","authors":"Marianne Silva, Thaís Medeiros, Mariana Azevedo, Morsinaldo Medeiros, Mikael P. B. Themoteo, Tatiane Gois, I. Silva, Dan Costa","doi":"10.1109/MetroAutomotive57488.2023.10219125","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219125","url":null,"abstract":"The Internet of Things (IoT) has significantly impacted various industries, particularly the automotive sector, due to the growing integration of IoT technologies in vehicles. As a result, the volume of data generated by vehicular sensors has increased, leading to a surge in studies focusing on driver behavior to enhance road safety and optimize transportation networks. However, traditional approaches to analyzing driver behavior have relied on supervised offline learning models, which are unsuitable for handling data streams in online learning environments. This study introduces an unsupervised online k-fix AutoCloud algorithm for detecting driver behavior patterns, leveraging the concepts of typicity and eccentricity while considering the historical-temporal relationships between samples. Furthermore, the algorithm autonomously and adaptively evolves without requiring a supervised training phase, making it compatible with the TinyML concept, encompassing Artificial Intelligence algorithms designed for low-power IoT devices. To validate the proposed method, a real case study was conducted over four days using a vehicle to compare the quantity and quality of clusters generated by the algorithm. The findings demonstrate the potential of the proposed approach for optimizing data processing with minimal computational power.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114436745","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219123
L. Cucchi, C. Gioia, Tommaso Senni, M. Paonni
The Galileo High Accuracy Service (HAS) is currently operational providing free-of-charge, Precise Point Positioning (PPP) corrections worldwide both through the Galileo signal in space and via the internet. The service increases the positioning accuracy up to few centimeters in nominal conditions. This is a key enabler for several applications including surveying, agriculture and automotive. In order to assess the positioning performance obtainable using HAS corrections an automotive test, carried out by the Joint Research Centre (JRC), has been performed. The test setup includes the HAS User Terminal (HAS UT) and different grade Global Navigation Satellite Systems (GNSSs) receivers. The performance of the HAS UT is compared with respect to PPP solutions obtained with and without HAS corrections. The performance is assessed in terms of solution availability and position accuracy for both horizontal and vertical channels. From the analysed test, it emerged that HAS UT performance is close to the PPP solutions using final precise products.
{"title":"Galileo High Accuracy Service: an automotive test","authors":"L. Cucchi, C. Gioia, Tommaso Senni, M. Paonni","doi":"10.1109/MetroAutomotive57488.2023.10219123","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219123","url":null,"abstract":"The Galileo High Accuracy Service (HAS) is currently operational providing free-of-charge, Precise Point Positioning (PPP) corrections worldwide both through the Galileo signal in space and via the internet. The service increases the positioning accuracy up to few centimeters in nominal conditions. This is a key enabler for several applications including surveying, agriculture and automotive. In order to assess the positioning performance obtainable using HAS corrections an automotive test, carried out by the Joint Research Centre (JRC), has been performed. The test setup includes the HAS User Terminal (HAS UT) and different grade Global Navigation Satellite Systems (GNSSs) receivers. The performance of the HAS UT is compared with respect to PPP solutions obtained with and without HAS corrections. The performance is assessed in terms of solution availability and position accuracy for both horizontal and vertical channels. From the analysed test, it emerged that HAS UT performance is close to the PPP solutions using final precise products.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131666323","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219129
Andrea Altomonte, E. Frasci, G. D. Ilio, I. Arsie, E. Jannelli
The kinetic energy recovery during braking is an essential feature of hybrid-electric vehicles, which significantly contributes to improve their fuel economy. In this work, an exhaustive performance analysis is conducted on the heavy-duty Diesel engine of a yard tractor used in port logistics, in order to estimate the potential of regenerative braking, which could be exploited in an electrified vehicle configuration.To this aim, experimental measurements are carried out at the dynamic test bench with reference to peculiar duty cycles, retrieved from an on-field measurement campaign. The on-field data are collected by means of a custom instrumentation, designed to gather real-time data from the CAN bus system of a yard tractor, equipped with the same engine, operating in the port of Salerno, Italy.First, a series of tests are carried out at the engine test bench in different steady-state and transient operating conditions, to experimentally characterize the engine performance in terms of torque, power output, and specific fuel consumption vs. engine speed and load request. Based on the engine characterization, the evaluation of engine efficiency and fuel consumption during the real duty cycles acquired on-field is performed. Furthermore, a comparison between the torque estimated by the engine control unit and the corresponding measurement by the test bench torsiometer is presented. Finally, the estimation of the kinetic energy recovery achievable by regenerative braking along the duty cycles under study is carried out, by analyzing the measured power and torque profiles. The results show that the energy recovery can significantly reduce the propulsion energy requested for performing the duty cycle.
{"title":"Experimental testing of a heavy-duty Diesel engine at the dynamic test bench to assess the potential of regenerative braking","authors":"Andrea Altomonte, E. Frasci, G. D. Ilio, I. Arsie, E. Jannelli","doi":"10.1109/MetroAutomotive57488.2023.10219129","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219129","url":null,"abstract":"The kinetic energy recovery during braking is an essential feature of hybrid-electric vehicles, which significantly contributes to improve their fuel economy. In this work, an exhaustive performance analysis is conducted on the heavy-duty Diesel engine of a yard tractor used in port logistics, in order to estimate the potential of regenerative braking, which could be exploited in an electrified vehicle configuration.To this aim, experimental measurements are carried out at the dynamic test bench with reference to peculiar duty cycles, retrieved from an on-field measurement campaign. The on-field data are collected by means of a custom instrumentation, designed to gather real-time data from the CAN bus system of a yard tractor, equipped with the same engine, operating in the port of Salerno, Italy.First, a series of tests are carried out at the engine test bench in different steady-state and transient operating conditions, to experimentally characterize the engine performance in terms of torque, power output, and specific fuel consumption vs. engine speed and load request. Based on the engine characterization, the evaluation of engine efficiency and fuel consumption during the real duty cycles acquired on-field is performed. Furthermore, a comparison between the torque estimated by the engine control unit and the corresponding measurement by the test bench torsiometer is presented. Finally, the estimation of the kinetic energy recovery achievable by regenerative braking along the duty cycles under study is carried out, by analyzing the measured power and torque profiles. The results show that the energy recovery can significantly reduce the propulsion energy requested for performing the duty cycle.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128697402","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219122
Emanuele Giovannardi, A. Brusa, Boris Petrone, N. Cavina, E. Corti, Massimo Barichello
The present study introduces a novel methodology that utilizes Light Gradient Boosting Regressors to predict engine-out emissions of NOx, HC, and CO. The accuracy of the proposed models is evaluated on different types of homologation cycles. The dataset used in this study is derived from a set of 47 experimental driving cycles, including RDE, WLTC, NEDC, ECE, US06, and HWFET. The experimental driving cycles are performed on a roll bench using a spark-ignited, naturally aspirated, V12 engine-equipped vehicle. A three-second sliding window is incorporated in the models to capture the dynamic behavior of pollutant emissions. The performance of the LightGBR models is assessed using the mean absolute percentage error (MAPE) on the total pollutant mass, which is found to be 5.2% for CO, 5.7% for HC, and 6.8% for NOx. The results demonstrate the efficacy of the proposed methodology, which can be used to estimate the impact of powertrain calibration changes on pollutant emissions in a virtual environment, thereby reducing the number and the cost of the experimental tests.
{"title":"An Enhanced Light Gradient Boosting Regressor for Virtual Sensing of CO, HC and NOx","authors":"Emanuele Giovannardi, A. Brusa, Boris Petrone, N. Cavina, E. Corti, Massimo Barichello","doi":"10.1109/MetroAutomotive57488.2023.10219122","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219122","url":null,"abstract":"The present study introduces a novel methodology that utilizes Light Gradient Boosting Regressors to predict engine-out emissions of NOx, HC, and CO. The accuracy of the proposed models is evaluated on different types of homologation cycles. The dataset used in this study is derived from a set of 47 experimental driving cycles, including RDE, WLTC, NEDC, ECE, US06, and HWFET. The experimental driving cycles are performed on a roll bench using a spark-ignited, naturally aspirated, V12 engine-equipped vehicle. A three-second sliding window is incorporated in the models to capture the dynamic behavior of pollutant emissions. The performance of the LightGBR models is assessed using the mean absolute percentage error (MAPE) on the total pollutant mass, which is found to be 5.2% for CO, 5.7% for HC, and 6.8% for NOx. The results demonstrate the efficacy of the proposed methodology, which can be used to estimate the impact of powertrain calibration changes on pollutant emissions in a virtual environment, thereby reducing the number and the cost of the experimental tests.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124465292","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219100
C. Guarnaccia, Alessandro Ruggiero, D. Russo, M. Ferro, S. D. Iacono, P. Valášek
The interest in the use of new green materials with considerable sound-absorbing power is no longer limited to the building sector but increasingly involves the automotive sector with attention focused on the possibility of improving the acoustic comfort of land vehicles (cars, buses) ensuring at the same time full ecological sustainability. The present work describes the expected soundproofing properties of a plant material and the measurement set-up used for its characterization and comparison with other types of material typically used to limit the impacts of the main acoustic sources in the passenger compartment of land vehicles. Finally, the experimental results of the characterization measurement are discussed in terms of the future automotive applications.
{"title":"Characterization of green materials for automotive acoustic comfort","authors":"C. Guarnaccia, Alessandro Ruggiero, D. Russo, M. Ferro, S. D. Iacono, P. Valášek","doi":"10.1109/MetroAutomotive57488.2023.10219100","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219100","url":null,"abstract":"The interest in the use of new green materials with considerable sound-absorbing power is no longer limited to the building sector but increasingly involves the automotive sector with attention focused on the possibility of improving the acoustic comfort of land vehicles (cars, buses) ensuring at the same time full ecological sustainability. The present work describes the expected soundproofing properties of a plant material and the measurement set-up used for its characterization and comparison with other types of material typically used to limit the impacts of the main acoustic sources in the passenger compartment of land vehicles. Finally, the experimental results of the characterization measurement are discussed in terms of the future automotive applications.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"46 22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133730821","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219128
F. Pisoni, N. Palella, Domenico Di Grazia, Leonardo Colombo, Giovanni Gogliettino
Loosely Coupled architectures based on Micro Electromechanical Systems (MEMS) Inertial Navigation Systems (INS), and multi-band GNSS are widely adopted to improve the availability of the integrated solution under difficult conditions, characterized by frequent obscurations of the GNSS signal. Typical scenarios include automotive urban tracks or open sky under dynamics, in presence of bridges and short tunnels. Low Earth Orbit (LEO) satellites also fall in this scope, as their lower altitude results in a Doppler curve with stronger rate variations, which sum up to receiver dynamics and are more challenging to track than traditional GNSS. In this paper, a hybrid solution is presented, where a classic loosely coupled scheme is complemented by deep integration. The INS-aided solution combines with GNSS satellites velocities and accelerations to derive code, Doppler, and Doppler rate observables predictions. Validation and performance assessment are conducted on a compact two-chip hardware platform, based on the state-of-the-art multi-band GNSS receiver STA8135 (TeseoV) and the MEMS IMU ASM330LHH from STMicroelectronics. Deep aiding has the potential to broaden the applicability of loosely coupled INS integration to the cases where signal weakness and the combined user to satellites dynamics exceed the tracking loops capability. Partially obscured automotive scenarios, reception of attenuated signals under high dynamics and assisted LEO satellites acquisition and tracking are among the applications that can benefit from the proposed scheme.
{"title":"A Loosely Coupled Architecture for INS/GNSS Integration with Tracking Loops Aiding","authors":"F. Pisoni, N. Palella, Domenico Di Grazia, Leonardo Colombo, Giovanni Gogliettino","doi":"10.1109/MetroAutomotive57488.2023.10219128","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219128","url":null,"abstract":"Loosely Coupled architectures based on Micro Electromechanical Systems (MEMS) Inertial Navigation Systems (INS), and multi-band GNSS are widely adopted to improve the availability of the integrated solution under difficult conditions, characterized by frequent obscurations of the GNSS signal. Typical scenarios include automotive urban tracks or open sky under dynamics, in presence of bridges and short tunnels. Low Earth Orbit (LEO) satellites also fall in this scope, as their lower altitude results in a Doppler curve with stronger rate variations, which sum up to receiver dynamics and are more challenging to track than traditional GNSS. In this paper, a hybrid solution is presented, where a classic loosely coupled scheme is complemented by deep integration. The INS-aided solution combines with GNSS satellites velocities and accelerations to derive code, Doppler, and Doppler rate observables predictions. Validation and performance assessment are conducted on a compact two-chip hardware platform, based on the state-of-the-art multi-band GNSS receiver STA8135 (TeseoV) and the MEMS IMU ASM330LHH from STMicroelectronics. Deep aiding has the potential to broaden the applicability of loosely coupled INS integration to the cases where signal weakness and the combined user to satellites dynamics exceed the tracking loops capability. Partially obscured automotive scenarios, reception of attenuated signals under high dynamics and assisted LEO satellites acquisition and tracking are among the applications that can benefit from the proposed scheme.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129210208","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219136
Mariano Nerone, Igor Valic, Matteo Zauli, N. Matteazzi, L. Marchi
Temperature monitoring is a key aspect in the field of electric motors. In high performance applications the rotor of a motor can reach very high temperatures leading to an over-heating of the rotor magnets, which can consequently lead to a demagnetization or to stator windings deterioration. These kinds of issues can severely impact the lifetime of an electric motor, and it is for such matter that is really important to monitor rotor temperatures: this way the motor can always be operated in a safe state, minimizing unexpected faults. Since minor errors in the simulation phase can lead to severe faults it is important to trust the simulations implemented, and this can be done by monitoring real data on the field. Such data can also be used to improve the simulation tools used to validate the motor design phase.The measurement system proposed in this paper is meant to be installed inside the motor rotor and can measure up to 8 thermocouples (type K, J, T, N, S, E, B and R) with a sampling frequency of 8 samples per second and an accuracy of ±2°C for temperatures between 0°C and 250°C. The board placed inside the rotor is powered by means of NFC energy harvest. The NFC protocol is also used to transfer data to a board placed on the motor stator.
温度监测是电机领域的一个重要方面。在高性能应用中，电机的转子可以达到非常高的温度，导致转子磁体过热，从而导致退磁或定子绕组恶化。这些问题会严重影响电机的使用寿命，因此监测转子温度非常重要:这样电机就可以始终在安全状态下运行，最大限度地减少意外故障。由于模拟阶段的小错误可能导致严重的故障，因此信任所实现的模拟非常重要，这可以通过监测现场的真实数据来实现。这些数据也可用于改进用于验证电机设计阶段的仿真工具。本文提出的测量系统旨在安装在电机转子内部，可测量多达8个热电偶(K, J, T, N, S, E, B和R型)，采样频率为每秒8个样本，精度为±2°C，温度为0°C至250°C。放置在转子内部的电路板是通过近场通信能量收集的方式供电的。NFC协议还用于将数据传输到放置在电机定子上的电路板上。
{"title":"A low power NFC data over power acquisition system for high speed Electric Motor Rotors","authors":"Mariano Nerone, Igor Valic, Matteo Zauli, N. Matteazzi, L. Marchi","doi":"10.1109/MetroAutomotive57488.2023.10219136","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219136","url":null,"abstract":"Temperature monitoring is a key aspect in the field of electric motors. In high performance applications the rotor of a motor can reach very high temperatures leading to an over-heating of the rotor magnets, which can consequently lead to a demagnetization or to stator windings deterioration. These kinds of issues can severely impact the lifetime of an electric motor, and it is for such matter that is really important to monitor rotor temperatures: this way the motor can always be operated in a safe state, minimizing unexpected faults. Since minor errors in the simulation phase can lead to severe faults it is important to trust the simulations implemented, and this can be done by monitoring real data on the field. Such data can also be used to improve the simulation tools used to validate the motor design phase.The measurement system proposed in this paper is meant to be installed inside the motor rotor and can measure up to 8 thermocouples (type K, J, T, N, S, E, B and R) with a sampling frequency of 8 samples per second and an accuracy of ±2°C for temperatures between 0°C and 250°C. The board placed inside the rotor is powered by means of NFC energy harvest. The NFC protocol is also used to transfer data to a board placed on the motor stator.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116253837","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219121
Mattia Stighezza, R. Ferrero, V. Bianchi, I. D. Munari
The Lithium-ion batteries market is rapidly growing. Estimating the batteries State of Charge (SOC) and their State of Health (SOH) is a challenging but crucial task, which Artificial Intelligence (AI) techniques can manage when trained with appropriate data. Physical measurements such as current, voltage and temperature during battery discharge are conventionally used as inputs of AI algorithms to provide an estimation of SOC. In this work, the effect of the battery impedance measurement on the training of a Support Vector Machine (SVM) has been studied. Electrochemical Impedance Spectroscopy (EIS) has been employed for in-situ impedance measurements at different frequencies to consider the effects of each perturbation. The obtained complex impedance values along with the measured current, voltage and temperature data, have been evaluated as features of a training set for an SVM in its regression form (SVR). To allow for simultaneous data acquisition, a module composed of 16 battery cells connected in series has undergone a total of 15 discharge cycles. Several SVR models have been trained with a variety of feature combinations, to evaluate the effect of different impedance information on the resulting model. When using the same battery cell for training and testing, the addition of magnitude and phase of the 100 Hz impedance to the input vector decreased the Root Mean Square Error (RMSE) of the estimated SOC from 1.34% to 1.09%. On the other hand, the same SVR model showed an RMSE of 1.23% when using different (but nominally identical) cells for testing.
{"title":"Machine learning and impedance spectroscopy for battery state of charge evaluation","authors":"Mattia Stighezza, R. Ferrero, V. Bianchi, I. D. Munari","doi":"10.1109/MetroAutomotive57488.2023.10219121","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219121","url":null,"abstract":"The Lithium-ion batteries market is rapidly growing. Estimating the batteries State of Charge (SOC) and their State of Health (SOH) is a challenging but crucial task, which Artificial Intelligence (AI) techniques can manage when trained with appropriate data. Physical measurements such as current, voltage and temperature during battery discharge are conventionally used as inputs of AI algorithms to provide an estimation of SOC. In this work, the effect of the battery impedance measurement on the training of a Support Vector Machine (SVM) has been studied. Electrochemical Impedance Spectroscopy (EIS) has been employed for in-situ impedance measurements at different frequencies to consider the effects of each perturbation. The obtained complex impedance values along with the measured current, voltage and temperature data, have been evaluated as features of a training set for an SVM in its regression form (SVR). To allow for simultaneous data acquisition, a module composed of 16 battery cells connected in series has undergone a total of 15 discharge cycles. Several SVR models have been trained with a variety of feature combinations, to evaluate the effect of different impedance information on the resulting model. When using the same battery cell for training and testing, the addition of magnitude and phase of the 100 Hz impedance to the input vector decreased the Root Mean Square Error (RMSE) of the estimated SOC from 1.34% to 1.09%. On the other hand, the same SVR model showed an RMSE of 1.23% when using different (but nominally identical) cells for testing.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125331970","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219139
Raffaele Marotta, Valentin Ivanov, S. Strano, M. Terzo, C. Tordela
In a road vehicle, the interaction forces between tire and road are strongly influenced by the longitudinal slip ratio. This kinematic quantity, therefore, represents one of the most important in the study of vehicle dynamics. The real-time knowledge of this quantity can allow the estimation of the interaction forces and the development of control systems to improve safety and handling. In particular, Anti-lock Braking Systems (ABS) and Traction Control Systems (TCS). Direct measurements of this quantity would require the insertion of sensors inside the tire, with consequent manufacturing complexity and increased costs. This paper proposes an estimate of the longitudinal slip ratio based on other easily measurable or estimable quantities. This estimator makes use of Neural Networks and is based on preliminary physical considerations.
{"title":"Deep Learning for the Estimation of the Longitudinal Slip Ratio","authors":"Raffaele Marotta, Valentin Ivanov, S. Strano, M. Terzo, C. Tordela","doi":"10.1109/MetroAutomotive57488.2023.10219139","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219139","url":null,"abstract":"In a road vehicle, the interaction forces between tire and road are strongly influenced by the longitudinal slip ratio. This kinematic quantity, therefore, represents one of the most important in the study of vehicle dynamics. The real-time knowledge of this quantity can allow the estimation of the interaction forces and the development of control systems to improve safety and handling. In particular, Anti-lock Braking Systems (ABS) and Traction Control Systems (TCS). Direct measurements of this quantity would require the insertion of sensors inside the tire, with consequent manufacturing complexity and increased costs. This paper proposes an estimate of the longitudinal slip ratio based on other easily measurable or estimable quantities. This estimator makes use of Neural Networks and is based on preliminary physical considerations.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128178428","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 : 2023-06-28DOI: 10.1109/MetroAutomotive57488.2023.10219111
Jin Dai, Shuo Sha, Yao Yao
Environment-aware millimeter wave radar (EMWR) is one of the most important sensors in autonomous driving system of car. With the number of cars installed EMWR increased rapidly in recent year, the problem of interference between EMWRs on different cars becomes a mounting crisis, which can seriously affect the safety of drivers on that car, especially driving on the highway. In order to solve the above problem, this paper conducts an anti-interference algorithm for 77G EMWR by dividing the interference among EWMRs into two types: the same frequency interference (SFI) and different frequency interference (DFI). In the SFI, the random initial frequency and random starting time are used to reduce the probability of signal collision to inhibit the interference. In DFI, the Hilbert transformation is used to extract the envelope and gets the location of the interference signal. Furthermore, Lagrange interpolation is used to improve the accuracy of the location in DFI to reduce the effective of different frequency interference on EMWRs.
{"title":"Anti-Interference Algorithm of Environment-Aware Millimeter Wave Radar","authors":"Jin Dai, Shuo Sha, Yao Yao","doi":"10.1109/MetroAutomotive57488.2023.10219111","DOIUrl":"https://doi.org/10.1109/MetroAutomotive57488.2023.10219111","url":null,"abstract":"Environment-aware millimeter wave radar (EMWR) is one of the most important sensors in autonomous driving system of car. With the number of cars installed EMWR increased rapidly in recent year, the problem of interference between EMWRs on different cars becomes a mounting crisis, which can seriously affect the safety of drivers on that car, especially driving on the highway. In order to solve the above problem, this paper conducts an anti-interference algorithm for 77G EMWR by dividing the interference among EWMRs into two types: the same frequency interference (SFI) and different frequency interference (DFI). In the SFI, the random initial frequency and random starting time are used to reduce the probability of signal collision to inhibit the interference. In DFI, the Hilbert transformation is used to extract the envelope and gets the location of the interference signal. Furthermore, Lagrange interpolation is used to improve the accuracy of the location in DFI to reduce the effective of different frequency interference on EMWRs.","PeriodicalId":115847,"journal":{"name":"2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114167354","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：