Pub Date : 2023-06-01DOI: 10.1109/IS3C57901.2023.00086
C. Tseng, Su-Ling Lee
Polynomial graph filter (PGF) is an important tool for processing the irregular data captured from various complex networks, so the design of PGF is studied in this paper. First, Legendre polynomials are briefly reviewed and the basics of graph signal processing (GSP) are described. Second, the PGF design using Legendre polynomials is presented. The closed-form solution of filter coefficients is derived for lowpass, bandpass and highpass filters. Third, an efficient implementation structure of PGF based on recurrence relation of Legendre polynomials is investigated. Finally, the signal denoising application of sensor network data is demonstrated to show that the PGF method has better performance than the conventional smoothness-based method in term of the improvement of signal to noise ratio.
{"title":"Polynomial Graph Filter Design Using Legendre Polynomials","authors":"C. Tseng, Su-Ling Lee","doi":"10.1109/IS3C57901.2023.00086","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00086","url":null,"abstract":"Polynomial graph filter (PGF) is an important tool for processing the irregular data captured from various complex networks, so the design of PGF is studied in this paper. First, Legendre polynomials are briefly reviewed and the basics of graph signal processing (GSP) are described. Second, the PGF design using Legendre polynomials is presented. The closed-form solution of filter coefficients is derived for lowpass, bandpass and highpass filters. Third, an efficient implementation structure of PGF based on recurrence relation of Legendre polynomials is investigated. Finally, the signal denoising application of sensor network data is demonstrated to show that the PGF method has better performance than the conventional smoothness-based method in term of the improvement of signal to noise ratio.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130572549","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}
Modern grids contain new components, such as renewable power resources, HVDC transmissions, energy storage systems and others. These new components will affect the frequency-response characteristics in power systems. That is, some power electronics-based elements with according control schemes will replace a part of traditional thermal or hydro generators with governor droop control. Thus, novel frequency control technologies for energy storages, HVDC or energy storage systems should be studied. This paper summarized frequency control technologies for the abovementioned components, and discussed about the hybrid energy systems with control schemes. Additionally, some significant trends, including the optimal design of capacity size, adaptive droop or inertia gains of controllers, detailed models for small-signal analyses or grid forming controls, and simplified frequency-response models, were also investigated in this paper.
{"title":"Overview of Coordinated Frequency Control Technologies for Wind Turbines, HVDC and Energy Storage Systems","authors":"Yuan-Kang Wu, Tung Trinh Duc, Baolong Phung Nguyen","doi":"10.1109/IS3C57901.2023.00077","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00077","url":null,"abstract":"Modern grids contain new components, such as renewable power resources, HVDC transmissions, energy storage systems and others. These new components will affect the frequency-response characteristics in power systems. That is, some power electronics-based elements with according control schemes will replace a part of traditional thermal or hydro generators with governor droop control. Thus, novel frequency control technologies for energy storages, HVDC or energy storage systems should be studied. This paper summarized frequency control technologies for the abovementioned components, and discussed about the hybrid energy systems with control schemes. Additionally, some significant trends, including the optimal design of capacity size, adaptive droop or inertia gains of controllers, detailed models for small-signal analyses or grid forming controls, and simplified frequency-response models, were also investigated in this paper.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114152269","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 : 2023-06-01DOI: 10.1109/is3c57901.2023.00029
Ling-Shen Tseng, Chih-Hung Wu, Yi Han Chen, Chuing-Hui Tsai
Artificial Intelligence-based Automated Optical Inspection (AI-AOI) using Convolutional Neural Networks (CNNs) is commonly used for defect detection, including metal defect detection, in modern manufacturing. However, in most AOI applications, the occurrence of defects is much less than the normal ones. CNN-based defection models perform poorly due to the imbalanced and less divergent training data. This study presents the performance of CNN-based AOI for metal defect detection with the techniques of generative AI for data augmentation. The Wasserstein Generative Adversarial Network (WGAN) is employed for generating negative training data and increasing the divergence when training AOI models. The similarity of data generated by WGAN to the original ones is evaluated by the Structural Similarity Index Measure (SSIM). The performance of ten CNN models trained with data before and after being augmented by WGAN are compared. Three metal defect datasets are used for evaluating the performance of CNN-based AOI with WGAN. The experimental results show that the performance of defect classification can be improved by 1%-12% with data augmented by WGAN.
{"title":"GAN-based Data Augmentation for Metal Surface Defect Detection Using Convolutional Neural Networks","authors":"Ling-Shen Tseng, Chih-Hung Wu, Yi Han Chen, Chuing-Hui Tsai","doi":"10.1109/is3c57901.2023.00029","DOIUrl":"https://doi.org/10.1109/is3c57901.2023.00029","url":null,"abstract":"Artificial Intelligence-based Automated Optical Inspection (AI-AOI) using Convolutional Neural Networks (CNNs) is commonly used for defect detection, including metal defect detection, in modern manufacturing. However, in most AOI applications, the occurrence of defects is much less than the normal ones. CNN-based defection models perform poorly due to the imbalanced and less divergent training data. This study presents the performance of CNN-based AOI for metal defect detection with the techniques of generative AI for data augmentation. The Wasserstein Generative Adversarial Network (WGAN) is employed for generating negative training data and increasing the divergence when training AOI models. The similarity of data generated by WGAN to the original ones is evaluated by the Structural Similarity Index Measure (SSIM). The performance of ten CNN models trained with data before and after being augmented by WGAN are compared. Three metal defect datasets are used for evaluating the performance of CNN-based AOI with WGAN. The experimental results show that the performance of defect classification can be improved by 1%-12% with data augmented by WGAN.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121265444","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}
Evaluation of power system reliability is significant for power system planning and operation, especially for a power system that include many renewable power resources. Appropriate methods to estimate the reliability of generation, transmission or distribution systems can help investigate the performance of smart grid developments. Several international standards such as IEEE 1366 or IEEE 762 have been released to recommend system operators or generator owners to follow the rules. In addition, North American Electric Reliability Corporation (NERC) also defined new reliability indices, such as adequate level of reliability (ALR) metrics and others. These new reliability indices consider power system resilience. This paper will summarize the existing reliability indices for power system operation, and investigate possible resilience indices for considering severity risk. Additionally, this paper provides a future trend for resilience indices.
{"title":"Review of Power System Reliability Indices for Renewable Energy Environments","authors":"Yuan-Kang Wu, Quoc-Thang Phan, Baolong Phung Nguyen","doi":"10.1109/IS3C57901.2023.00075","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00075","url":null,"abstract":"Evaluation of power system reliability is significant for power system planning and operation, especially for a power system that include many renewable power resources. Appropriate methods to estimate the reliability of generation, transmission or distribution systems can help investigate the performance of smart grid developments. Several international standards such as IEEE 1366 or IEEE 762 have been released to recommend system operators or generator owners to follow the rules. In addition, North American Electric Reliability Corporation (NERC) also defined new reliability indices, such as adequate level of reliability (ALR) metrics and others. These new reliability indices consider power system resilience. This paper will summarize the existing reliability indices for power system operation, and investigate possible resilience indices for considering severity risk. Additionally, this paper provides a future trend for resilience indices.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125982669","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00062
Guoping Wang
The Internet of Things (IoT) refers to a network of physical devices embedded with sensors, actuators, software, and other technologies that can connect and exchange data with other devices via the Internet. These devices range from everyday household items to advanced industrial tools.This paper outlines a power monitoring system across multiple manufacturing plants using LabVIEW. Unlike other IoT platforms that use Raspberry Pi, Arduino, or bare-metal MCU systems and require an edge device, middle-ware broker, and client applications, the LabVIEW system is sufficient and efficient for this power monitoring system. The power usage, including voltage and current amplitudes, from multiple plants is sampled and recorded on a single PC workstation with LabVIEW installed. LabVIEW enables real-time data collection and generation of daily/monthly reports. The LabVIEW-based power monitoring system has proven to be efficient and reliable in industrial IoT applications.
{"title":"LabVIEW-Based Power Monitor IoT System","authors":"Guoping Wang","doi":"10.1109/IS3C57901.2023.00062","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00062","url":null,"abstract":"The Internet of Things (IoT) refers to a network of physical devices embedded with sensors, actuators, software, and other technologies that can connect and exchange data with other devices via the Internet. These devices range from everyday household items to advanced industrial tools.This paper outlines a power monitoring system across multiple manufacturing plants using LabVIEW. Unlike other IoT platforms that use Raspberry Pi, Arduino, or bare-metal MCU systems and require an edge device, middle-ware broker, and client applications, the LabVIEW system is sufficient and efficient for this power monitoring system. The power usage, including voltage and current amplitudes, from multiple plants is sampled and recorded on a single PC workstation with LabVIEW installed. LabVIEW enables real-time data collection and generation of daily/monthly reports. The LabVIEW-based power monitoring system has proven to be efficient and reliable in industrial IoT applications.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132939486","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00027
Hung-Chung Li, Chun-Hsun Huang, P. Sun
The research aims to conduct a psychophysical experiment to explore the subjective emotion perception of the observers under white light sources with different illuminance, correlated color temperature (CCT), and distance to the black-body locus (Duv). Based on the experimental results, appropriate lighting conditions will be derived, and an evaluation model is established for beauty and aromatherapy to assess emotion perception under different white light sources based on the large amount of data obtained from the experiment.
{"title":"Establishing Suitable White Light Source and Perception Models for Beauty Aromatherapy Application","authors":"Hung-Chung Li, Chun-Hsun Huang, P. Sun","doi":"10.1109/IS3C57901.2023.00027","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00027","url":null,"abstract":"The research aims to conduct a psychophysical experiment to explore the subjective emotion perception of the observers under white light sources with different illuminance, correlated color temperature (CCT), and distance to the black-body locus (Duv). Based on the experimental results, appropriate lighting conditions will be derived, and an evaluation model is established for beauty and aromatherapy to assess emotion perception under different white light sources based on the large amount of data obtained from the experiment.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132565126","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00084
Chun-Hsi Su, Yian-Ting Chen
This study attempts to develop a remote-controllable variable frequency drive (VFD). The control signal unit is separated from the power transfer unit of an inverter. After the control signal of sinusoidal pulse width modulation (SPWM) is generated at a remote site, a set of wireless communication units performs the function of transmitting and receiving signals, and the power unit at the local site follows the received signals to work on driving a motor. An alternative current (AC) single phase induction motor is then driven and operates at 179 radians per minute (rpm.)
{"title":"A Remote-Controllable Variable Frequency Drive","authors":"Chun-Hsi Su, Yian-Ting Chen","doi":"10.1109/IS3C57901.2023.00084","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00084","url":null,"abstract":"This study attempts to develop a remote-controllable variable frequency drive (VFD). The control signal unit is separated from the power transfer unit of an inverter. After the control signal of sinusoidal pulse width modulation (SPWM) is generated at a remote site, a set of wireless communication units performs the function of transmitting and receiving signals, and the power unit at the local site follows the received signals to work on driving a motor. An alternative current (AC) single phase induction motor is then driven and operates at 179 radians per minute (rpm.)","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134198961","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00056
Jesús Eduardo Ochoa Astorga, Weiwei Du, Yahui Peng, Linni Wang
Fundus image registration is essential for clinical eye disease examination, in which diseases such as diabetic retinopathy or macular degeneration may require a meticulous monitoring. Multiple retinal images may be registered to analyze the evolution of patients over time, to widen the field of view or to enhance the resolution for a detailed examination. At present, feature-based fundus registration methods prevail, nonetheless, some methods have a great feature points density, which may complicate the matching process for some feature descriptors due to the similarity among the points. Furthermore, several methods for vessel structure segmentation have been developed, occasionally employing Hessian matrix features. However, the use of these features, has not been extensively employed for registration purposes. This paper proposes a fundus image registration with binary morphology extraction of feature points that involves the frangi filter for demarcating a region of interest, prioritizing the points distribution over the abundance. Later, medial axis transform and pattern detection are made for obtaining feature points that are characterized by the Fast Retina Keypoint (FREAK) descriptor and matched for computing the transformation matrix. The proposed method is assessed with the Fundus Image Registration Dataset (FIRE). Results suggest that the proposed method can compete to certain extent with some of the former similar approaches in regard to registration error, achieving a 0.5084 for area under the curve.
{"title":"Fundus Image Registration with Binary Morphology Extraction of Feature Points","authors":"Jesús Eduardo Ochoa Astorga, Weiwei Du, Yahui Peng, Linni Wang","doi":"10.1109/IS3C57901.2023.00056","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00056","url":null,"abstract":"Fundus image registration is essential for clinical eye disease examination, in which diseases such as diabetic retinopathy or macular degeneration may require a meticulous monitoring. Multiple retinal images may be registered to analyze the evolution of patients over time, to widen the field of view or to enhance the resolution for a detailed examination. At present, feature-based fundus registration methods prevail, nonetheless, some methods have a great feature points density, which may complicate the matching process for some feature descriptors due to the similarity among the points. Furthermore, several methods for vessel structure segmentation have been developed, occasionally employing Hessian matrix features. However, the use of these features, has not been extensively employed for registration purposes. This paper proposes a fundus image registration with binary morphology extraction of feature points that involves the frangi filter for demarcating a region of interest, prioritizing the points distribution over the abundance. Later, medial axis transform and pattern detection are made for obtaining feature points that are characterized by the Fast Retina Keypoint (FREAK) descriptor and matched for computing the transformation matrix. The proposed method is assessed with the Fundus Image Registration Dataset (FIRE). Results suggest that the proposed method can compete to certain extent with some of the former similar approaches in regard to registration error, achieving a 0.5084 for area under the curve.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129975644","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00019
Shou-Kai Yin, Jenhui Chen
Recently, transformer-based models have achieved significant success in various computer vision tasks, with the attention-based token mixer module commonly believed to be the key factor. However, further research has shown that the attention-based token mixer module in transformers can be replaced by other methods, such as spatial multilayer perceptrons (MLPs) or Fourier transforms, to mix information between different tokens without sacrificing performance. Therefore, some have raised whether the success of transformers and its variants is not solely due to the attention-based token mixer module but rather to other factors. In a recent paper titled “PoolFormer” the authors demonstrated that using a simple spatial pooling operation instead of the attention module in transformers can achieve competitive performance in object detection vision tasks. Based on this finding, we propose a low-computation model for image denoising based on the PoolFormer and an MLP + CNN Transformer decoder for image restoration. By reducing the computational complexity brought by the token mixer, the model still achieves a good peak signal-to-noise ratio (PSNR) in grayscale as well as in color image denoising. This suggests that, in low-level vision tasks such as denoising, simple attention modules can also achieve good results, particularly in grayscale image denoising.
{"title":"IDP: Image Denoising Using PoolFormer","authors":"Shou-Kai Yin, Jenhui Chen","doi":"10.1109/IS3C57901.2023.00019","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00019","url":null,"abstract":"Recently, transformer-based models have achieved significant success in various computer vision tasks, with the attention-based token mixer module commonly believed to be the key factor. However, further research has shown that the attention-based token mixer module in transformers can be replaced by other methods, such as spatial multilayer perceptrons (MLPs) or Fourier transforms, to mix information between different tokens without sacrificing performance. Therefore, some have raised whether the success of transformers and its variants is not solely due to the attention-based token mixer module but rather to other factors. In a recent paper titled “PoolFormer” the authors demonstrated that using a simple spatial pooling operation instead of the attention module in transformers can achieve competitive performance in object detection vision tasks. Based on this finding, we propose a low-computation model for image denoising based on the PoolFormer and an MLP + CNN Transformer decoder for image restoration. By reducing the computational complexity brought by the token mixer, the model still achieves a good peak signal-to-noise ratio (PSNR) in grayscale as well as in color image denoising. This suggests that, in low-level vision tasks such as denoising, simple attention modules can also achieve good results, particularly in grayscale image denoising.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133495532","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 : 2023-06-01DOI: 10.1109/IS3C57901.2023.00010
Hsieh Tung-Hsien, Jywe Wen-Yuh, Lai Hsin-Yu, Yi-Hao Chou, Wu Tsai-Hsu
The thermal error of machine tools is a key factor which affects machining accuracy. Currently, most inspection methods build a set of 3-axis or 5-axis non-contact measurement system using capacitance probes. However, since the equipment is expensive and not easy to set up, most thermal error model of machine tools can only be modeled beforehand. Therefore, once the AI model fails, it is often impossible to repair, or the equipment may be required to be brought to the manufacturing site again for installation, set-up, data collection and model building. In view of this, the study uses an optical non-contact spindle temperature measurement system previously developed by the team, which includes a 3D position sensing module, a standard glass ball (mounted on a standard tool holder interface), a PT100 temperature sensing module, an edge computer, and a human-machine interface. During the verification process, the system can effectively collect machine tool thermal data, including XYZ displacements, spindle speed, temperature, etc. By designing a quick tool holder jig, the center of the standard glass ball can be placed at the center of the 3D position sensor, significantly reducing the setup time. As for model building, this study uses XGBoost to establish correlation between temperature parameters and displacement in order to perform preliminary sensor selection. The RMSE and MSE of remaining sensors were then compared. After sensor selection, this study reduces the number of sensors used to 5, 7, 10, and 14. Then, LSTM and TCN is applied to build the thermal error model, with data from Day-1 (2022/07/15) as the training dataset. Using software and hardware modules mentioned in the study, thermal error for the test datasets Day-2 (2022/07/17) and Day-3 (2022/08/15) were decreased by more than 70%, which is also applicable to other dates.
{"title":"Development of LSTM and TCN Spindle Thermal Compensation Model by Using the Laser R-Test System","authors":"Hsieh Tung-Hsien, Jywe Wen-Yuh, Lai Hsin-Yu, Yi-Hao Chou, Wu Tsai-Hsu","doi":"10.1109/IS3C57901.2023.00010","DOIUrl":"https://doi.org/10.1109/IS3C57901.2023.00010","url":null,"abstract":"The thermal error of machine tools is a key factor which affects machining accuracy. Currently, most inspection methods build a set of 3-axis or 5-axis non-contact measurement system using capacitance probes. However, since the equipment is expensive and not easy to set up, most thermal error model of machine tools can only be modeled beforehand. Therefore, once the AI model fails, it is often impossible to repair, or the equipment may be required to be brought to the manufacturing site again for installation, set-up, data collection and model building. In view of this, the study uses an optical non-contact spindle temperature measurement system previously developed by the team, which includes a 3D position sensing module, a standard glass ball (mounted on a standard tool holder interface), a PT100 temperature sensing module, an edge computer, and a human-machine interface. During the verification process, the system can effectively collect machine tool thermal data, including XYZ displacements, spindle speed, temperature, etc. By designing a quick tool holder jig, the center of the standard glass ball can be placed at the center of the 3D position sensor, significantly reducing the setup time. As for model building, this study uses XGBoost to establish correlation between temperature parameters and displacement in order to perform preliminary sensor selection. The RMSE and MSE of remaining sensors were then compared. After sensor selection, this study reduces the number of sensors used to 5, 7, 10, and 14. Then, LSTM and TCN is applied to build the thermal error model, with data from Day-1 (2022/07/15) as the training dataset. Using software and hardware modules mentioned in the study, thermal error for the test datasets Day-2 (2022/07/17) and Day-3 (2022/08/15) were decreased by more than 70%, which is also applicable to other dates.","PeriodicalId":142483,"journal":{"name":"2023 Sixth International Symposium on Computer, Consumer and Control (IS3C)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125219834","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：