Pub Date : 2020-10-18DOI: 10.1109/IECON43393.2020.9255382
Zhuolin Jiang, N. Beniwal, S. Ceballos, J. Pou, H. D. Tafti, G. Farivar
The neutral-point-clamped (NPC) converter employed in applications like bipolar dc-bus, back-to-back converters, power compensator, etc., requires a nonzero average neutral-point (NP) current injection under certain operating conditions. In order to better implement the average NP current injection, this paper studies the maximum and minimum average NP current that can be injected with an NPC converter. For this study, a three-level modulation technique is employed in which one of the three phases is selected to switch between the positive dc-rail and the negative dc-rail while the other two phases switch in two consecutive voltage levels. The maximum and minimum average NP current injection limits are analyzed under different loading conditions. The presented study also evaluates the effects of modulation index and operating power factor on the limits.
{"title":"Analysis of the Average Neutral-Point Current Limits of the Neutral-Point-Clamped Converter Under Three-Level Modulation","authors":"Zhuolin Jiang, N. Beniwal, S. Ceballos, J. Pou, H. D. Tafti, G. Farivar","doi":"10.1109/IECON43393.2020.9255382","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9255382","url":null,"abstract":"The neutral-point-clamped (NPC) converter employed in applications like bipolar dc-bus, back-to-back converters, power compensator, etc., requires a nonzero average neutral-point (NP) current injection under certain operating conditions. In order to better implement the average NP current injection, this paper studies the maximum and minimum average NP current that can be injected with an NPC converter. For this study, a three-level modulation technique is employed in which one of the three phases is selected to switch between the positive dc-rail and the negative dc-rail while the other two phases switch in two consecutive voltage levels. The maximum and minimum average NP current injection limits are analyzed under different loading conditions. The presented study also evaluates the effects of modulation index and operating power factor on the limits.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"50 2 1","pages":"4079-4084"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91061918","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254389
Simon Göltz, O. Sawodny
In this paper an overall, simplified modeling approach describing the dependency between applied brake pressure and brake torque is presented. Therefore the internal amplification of a disc brake, the so-called brake-factor, is modeled in dependency of the vehicle velocity, the brake pressure and the brake temperature. As the application of this model requires the brake temperature, which is commonly not measured, a new lumped-mass-based brake temperature model, that describes the thermal behavior of a typical disc brake is stated and validated.
{"title":"Simplified Disc Brake Modeling, Identification, and Validation focusing on Temperature Influences","authors":"Simon Göltz, O. Sawodny","doi":"10.1109/IECON43393.2020.9254389","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254389","url":null,"abstract":"In this paper an overall, simplified modeling approach describing the dependency between applied brake pressure and brake torque is presented. Therefore the internal amplification of a disc brake, the so-called brake-factor, is modeled in dependency of the vehicle velocity, the brake pressure and the brake temperature. As the application of this model requires the brake temperature, which is commonly not measured, a new lumped-mass-based brake temperature model, that describes the thermal behavior of a typical disc brake is stated and validated.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"54 1","pages":"2063-2068"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91096896","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254334
Ludek Buchta, M. Kozovský, Lukáš Otava
In this paper, a new compensation strategy design of the dead-time effects and other VSI non-linearities is presented for a dual three-phase PMSM. The strategy is based on an estimation of compensation voltages for each motor sub-system by the proposed disturbance observer. This observer is based on the Kalman filter algorithm and the knowledge of the motor model structure and its parameters. The proposed approach is verified by experiments on the test bench which consists of the experimental dual three-phase PMSM and set of three-phase power stages controlled by one Tricore AURIX TC275 microcontroller. The achieved results are compared with the results of the standard compensation strategy.
{"title":"Voltage disturbance observer for dual three-phase PMSM system","authors":"Ludek Buchta, M. Kozovský, Lukáš Otava","doi":"10.1109/IECON43393.2020.9254334","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254334","url":null,"abstract":"In this paper, a new compensation strategy design of the dead-time effects and other VSI non-linearities is presented for a dual three-phase PMSM. The strategy is based on an estimation of compensation voltages for each motor sub-system by the proposed disturbance observer. This observer is based on the Kalman filter algorithm and the knowledge of the motor model structure and its parameters. The proposed approach is verified by experiments on the test bench which consists of the experimental dual three-phase PMSM and set of three-phase power stages controlled by one Tricore AURIX TC275 microcontroller. The achieved results are compared with the results of the standard compensation strategy.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"64 1","pages":"1108-1113"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91121757","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}
According to the different directions of carrier disposing, carrier-based PWM (CBPWM) can be classified into in-phase disposition PWM (IPDPWM) and phase opposition disposition PWM (PODPWM). To design a synchronized modulation strategy for three-level neutral point clamped (3-L NPC) inverter, which is convenient to implement and satisfies waveform symmetry, the harmonic characteristics of IPD PWM and PODPWM are analyzed by using double Fourier series in this paper firstly. On this basis, the carrier ratio that can make the phase voltage of IPDPWM and PODPWM meet three-phase symmetry (TPS) and half-wave symmetry (HWS) are deduced. By mixing IPDPWM and PODPWM, a synchronized CBPWM (SCBPWM) that makes the phase voltage waveform satisfies TPS and HWS at the carrier ratio is an integer multiple of 3 is further proposed. Finally, a full frequency range modulation strategy based on SCBPWM is designed, which is easy to implement and ensures the maximum switching frequency is not more than 450Hz. The simulation results verify the validity of the SCBPWM.
{"title":"Research on the Synchronized Carrier-Based PWM Strategy Under Low Switching Frequency for Three-Level Neutral Point Clamped Inverter","authors":"Zhan Gao, Yao-hua Li, Qiongxuan Ge, Ke Wang, Mutian Zhao, Jinquan Zhu","doi":"10.1109/IECON43393.2020.9254800","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254800","url":null,"abstract":"According to the different directions of carrier disposing, carrier-based PWM (CBPWM) can be classified into in-phase disposition PWM (IPDPWM) and phase opposition disposition PWM (PODPWM). To design a synchronized modulation strategy for three-level neutral point clamped (3-L NPC) inverter, which is convenient to implement and satisfies waveform symmetry, the harmonic characteristics of IPD PWM and PODPWM are analyzed by using double Fourier series in this paper firstly. On this basis, the carrier ratio that can make the phase voltage of IPDPWM and PODPWM meet three-phase symmetry (TPS) and half-wave symmetry (HWS) are deduced. By mixing IPDPWM and PODPWM, a synchronized CBPWM (SCBPWM) that makes the phase voltage waveform satisfies TPS and HWS at the carrier ratio is an integer multiple of 3 is further proposed. Finally, a full frequency range modulation strategy based on SCBPWM is designed, which is easy to implement and ensures the maximum switching frequency is not more than 450Hz. The simulation results verify the validity of the SCBPWM.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"27 1","pages":"4121-4126"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91177559","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254607
Zhan Li, Yuan Gao, Hao Ma, Xin Zhang
This paper presents a new diagnosis method for open-switch faults in power converters based on Artificial Neural Network (ANN). The ANN inputs comprise both sampled signals and control signals. Only the signals of one switching period are used in the method. The combination of control signals and output signals enables the trained ANN to represent the internal characteristics of converter behaviors, which is crucial for fault diagnosis. Compared with other data-driven methods, the ANN approach is simpler, making it easier to be applied in microcontrollers. Besides, the ANN responds quickly to the fault due to the training with instant signals. Therefore, easy operation and fast diagnosis can be both achieved. Finally, the open-switch fault diagnosis in a two-level three-phase converter is studied for method validation. In this case, an ANN is trained with 9 input elements, 7 output elements, and 10 neurons in the hidden layer. Simulation results are given to demonstrate the good performance of the ANN method.
{"title":"A Simple ANN-Based Diagnosis Method for Open-Switch Faults in Power Converters","authors":"Zhan Li, Yuan Gao, Hao Ma, Xin Zhang","doi":"10.1109/IECON43393.2020.9254607","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254607","url":null,"abstract":"This paper presents a new diagnosis method for open-switch faults in power converters based on Artificial Neural Network (ANN). The ANN inputs comprise both sampled signals and control signals. Only the signals of one switching period are used in the method. The combination of control signals and output signals enables the trained ANN to represent the internal characteristics of converter behaviors, which is crucial for fault diagnosis. Compared with other data-driven methods, the ANN approach is simpler, making it easier to be applied in microcontrollers. Besides, the ANN responds quickly to the fault due to the training with instant signals. Therefore, easy operation and fast diagnosis can be both achieved. Finally, the open-switch fault diagnosis in a two-level three-phase converter is studied for method validation. In this case, an ANN is trained with 9 input elements, 7 output elements, and 10 neurons in the hidden layer. Simulation results are given to demonstrate the good performance of the ANN method.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"57 1","pages":"2835-2839"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91217844","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254657
Miodrag Basić, A. Schwery, D. Dujić
As fossil-fuel- and nuclear-based generating facilities are being phased-out in favor of intermittent renewable energy sources, the need for large scale, highly flexible balancing storage is imminent. By the generating capacity of readily available units, enormous potential lays in retrofitting of large pumped hydro storage plants to variable speed operation, increasing their flexibility to meet future power system demands. Indirect Modular Multilevel Converter is a highly scalable and inherently redundant topology that meets the power and voltage ratings of large pumped hydro generating units. Variable DC link converter operation, offering common-mode-free machine-side operation has been evaluated, considering constraints in retrofit of old machines, not designed for converter-fed operation. Performance evaluation over the entire operating range of the plant is performed. Grid support dynamics has been assessed. Finally, application-specific challenges in the design stage are pointed out.
{"title":"Highly Flexible Indirect Modular Multilevel Converter for High Power Pumped Hydro Storage Plants","authors":"Miodrag Basić, A. Schwery, D. Dujić","doi":"10.1109/IECON43393.2020.9254657","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254657","url":null,"abstract":"As fossil-fuel- and nuclear-based generating facilities are being phased-out in favor of intermittent renewable energy sources, the need for large scale, highly flexible balancing storage is imminent. By the generating capacity of readily available units, enormous potential lays in retrofitting of large pumped hydro storage plants to variable speed operation, increasing their flexibility to meet future power system demands. Indirect Modular Multilevel Converter is a highly scalable and inherently redundant topology that meets the power and voltage ratings of large pumped hydro generating units. Variable DC link converter operation, offering common-mode-free machine-side operation has been evaluated, considering constraints in retrofit of old machines, not designed for converter-fed operation. Performance evaluation over the entire operating range of the plant is performed. Grid support dynamics has been assessed. Finally, application-specific challenges in the design stage are pointed out.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"3 1","pages":"5290-5295"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89804976","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254711
E. Carfagna, G. Migliazza, F. Immovilli, C. M. Verrelli, E. Lorenzani
Extended Kalman Filters (EKFs), Phase Locked Loops (PLLs), and Stator Flux Observers (SFOs) are widely used for sensorless control of Permanent Magnet Synchronous Motors (PMSMs) drives. Their use (in their most advanced version) is here extended, on the basis of model analogies and suitably-guaranteed closed loop stability properties, to the sensorless speed regulation control of Hybrid Stepper Motors (HSMs), in which position and speed sensors are not employed to reduce costs and increase robustness with respect to high temperature and high-vibration environments. Both realistic simulations and experimental results demonstrate the feasibility of the proposed methods in terms of closed-loop performance and robustness to parameters mismatch.
{"title":"PMSM-Model-Based Sensorless Control of Hybrid Stepper Motors: Performance and Robustness to Parameters Dispersion","authors":"E. Carfagna, G. Migliazza, F. Immovilli, C. M. Verrelli, E. Lorenzani","doi":"10.1109/IECON43393.2020.9254711","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254711","url":null,"abstract":"Extended Kalman Filters (EKFs), Phase Locked Loops (PLLs), and Stator Flux Observers (SFOs) are widely used for sensorless control of Permanent Magnet Synchronous Motors (PMSMs) drives. Their use (in their most advanced version) is here extended, on the basis of model analogies and suitably-guaranteed closed loop stability properties, to the sensorless speed regulation control of Hybrid Stepper Motors (HSMs), in which position and speed sensors are not employed to reduce costs and increase robustness with respect to high temperature and high-vibration environments. Both realistic simulations and experimental results demonstrate the feasibility of the proposed methods in terms of closed-loop performance and robustness to parameters mismatch.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"1 1","pages":"1063-1068"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89981775","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254659
Runze Ding, C. Ding, Yunlang Xu, Weike Liu, Xiaofeng Yang
This paper develops an optimal actuator placement method for direct-drive stages. Control bandwidth of rigid body motion, which is limited by flexible modes, is maximized. According to a reduced-order state-space model of stage dynamics, a dual-loop optimization method is proposed to optimize actuator locations. In the inner loop, a specific control scheme is employed to obtain the maximum control bandwidth, which is used to formulate a cost function. This control scheme is only for optimization, which does not limit the choices of control methods for an optimized stage. In the outer loop, Genetic Algorithm (GA) is employed to minimize the cost function such that the actuator locations are optimized. Compared with existing over-actuation methods, this method has low cost and complexity. Numerical simulations verify the effectiveness of the proposed method.
{"title":"An Optimal Actuator Placement Method for Direct-drive Stages to Maximize Control Bandwidth","authors":"Runze Ding, C. Ding, Yunlang Xu, Weike Liu, Xiaofeng Yang","doi":"10.1109/IECON43393.2020.9254659","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254659","url":null,"abstract":"This paper develops an optimal actuator placement method for direct-drive stages. Control bandwidth of rigid body motion, which is limited by flexible modes, is maximized. According to a reduced-order state-space model of stage dynamics, a dual-loop optimization method is proposed to optimize actuator locations. In the inner loop, a specific control scheme is employed to obtain the maximum control bandwidth, which is used to formulate a cost function. This control scheme is only for optimization, which does not limit the choices of control methods for an optimized stage. In the outer loop, Genetic Algorithm (GA) is employed to minimize the cost function such that the actuator locations are optimized. Compared with existing over-actuation methods, this method has low cost and complexity. Numerical simulations verify the effectiveness of the proposed method.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"2 1","pages":"556-561"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89623182","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254844
Zhan Gao, Yao-hua Li, Ke Wang, Qiongxuan Ge, Lu Zhao, Bo Zhang
In this paper, the principle of the synchronized 3 integer multiples SVPWM (S3MSVM) which can make the phase voltage pulse number be an integer multiple of 3 is introduced. Then the equivalent relationship between carrier-based PWM (CBPWM) and S3MSVM in different modulation index regions is derived. On this basis, a carrier-based S3MSVM (CBS3MSVM) is proposed by comparing the carrier with the single modulation wave or double modulation wave at each sampling point. CBS3MSVM can make the voltage waveform satisfies three-phase symmetry (TPS), half-wave symmetry (HWS), and quarter waveform symmetry (QWS), it optimizes the harmonic performance of the voltage and its calculation is simpler than S3MSVM. The correctness of the theoretical analysis is verified by simulation results.
{"title":"A Carrier-Based Synchronized 3 Integer Multiples SVPWM Algorithm for Three-level Inverter with Symmetrical Waveforms","authors":"Zhan Gao, Yao-hua Li, Ke Wang, Qiongxuan Ge, Lu Zhao, Bo Zhang","doi":"10.1109/IECON43393.2020.9254844","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254844","url":null,"abstract":"In this paper, the principle of the synchronized 3 integer multiples SVPWM (S3MSVM) which can make the phase voltage pulse number be an integer multiple of 3 is introduced. Then the equivalent relationship between carrier-based PWM (CBPWM) and S3MSVM in different modulation index regions is derived. On this basis, a carrier-based S3MSVM (CBS3MSVM) is proposed by comparing the carrier with the single modulation wave or double modulation wave at each sampling point. CBS3MSVM can make the voltage waveform satisfies three-phase symmetry (TPS), half-wave symmetry (HWS), and quarter waveform symmetry (QWS), it optimizes the harmonic performance of the voltage and its calculation is simpler than S3MSVM. The correctness of the theoretical analysis is verified by simulation results.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"26 1","pages":"1142-1147"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89643260","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 : 2020-10-18DOI: 10.1109/IECON43393.2020.9254858
Duy-Linh Nguyen, M. D. Putro, K. Jo
The drowsiness is the leading cause of many accidents on the road. These causes can be reduced by using the drowsiness alarm or drowsiness detection system. These systems monitor drivers while driving and alarm when they don’t focus or have some abnormal signs in the driver’s body. Currently, most methodologies use the analysis of human behaviors, vehicle behaviors, and human physiological conditions. This paper regards eyes status analysis based on deep learning method using proposed Convolutional Neural Networks (CNN) with two stages are face detection and eyes classification. The face detector employs a single detector module and shallow layer, then the eyes classifier using simple CNN without ignoring the accuracy. As a result, the average speed was tested in real-time by 50.03 fps (frames per second) on Intel Core I7-4770 CPU @ 3.40 GHz.
困倦是道路上许多事故的主要原因。这些原因可以通过使用困倦警报或困倦检测系统来减少。这些系统在驾驶时监测驾驶员，并在驾驶员注意力不集中或身体出现异常迹象时发出警报。目前，大多数方法都是分析人的行为、车辆的行为和人的生理状况。本文采用提出的卷积神经网络(CNN)进行基于深度学习的眼睛状态分析，分为人脸检测和眼睛分类两个阶段。人脸检测器采用单个检测器模块和浅层，然后眼睛分类器使用简单的CNN而不忽略准确率。因此，在英特尔酷睿I7-4770 CPU @ 3.40 GHz上实时测试了平均速度为50.03 fps(每秒帧数)。
{"title":"Eyes Status Detector Based on Light-weight Convolutional Neural Networks supporting for Drowsiness Detection System","authors":"Duy-Linh Nguyen, M. D. Putro, K. Jo","doi":"10.1109/IECON43393.2020.9254858","DOIUrl":"https://doi.org/10.1109/IECON43393.2020.9254858","url":null,"abstract":"The drowsiness is the leading cause of many accidents on the road. These causes can be reduced by using the drowsiness alarm or drowsiness detection system. These systems monitor drivers while driving and alarm when they don’t focus or have some abnormal signs in the driver’s body. Currently, most methodologies use the analysis of human behaviors, vehicle behaviors, and human physiological conditions. This paper regards eyes status analysis based on deep learning method using proposed Convolutional Neural Networks (CNN) with two stages are face detection and eyes classification. The face detector employs a single detector module and shallow layer, then the eyes classifier using simple CNN without ignoring the accuracy. As a result, the average speed was tested in real-time by 50.03 fps (frames per second) on Intel Core I7-4770 CPU @ 3.40 GHz.","PeriodicalId":13045,"journal":{"name":"IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society","volume":"1 1","pages":"477-482"},"PeriodicalIF":0.0,"publicationDate":"2020-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89647573","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：