Pub Date : 2022-02-01DOI: 10.1109/ICTech55460.2022.00061
Meng Chen, Fei Gao, Weiyou Ren
Aiming at the problem that the speed control accuracy of permanent magnet synchronous motors is easily affected by uncertain factors such as load moment of inertia, external disturbances, unmodeled dynamics, etc., a data-driven speed control method is proposed. This method firstly uses the least square method to identify the precise mathematical model of the system based on the input and output data of the controlled system in real time. Then, in order to reduce the difficulty of the controller parameter tuning, a method of numerically optimizing the controller parameters is proposed. We can use this method and the precise model of the system obtained in the previous step to tune the controller parameters. Through MATLAB simulation software and experimental platform, the speed control method proposed in this paper is compared with the PI control method. From the simulation and experimental results, it can be seen that the control method proposed in this paper can effectively adapt to the time-varying problem of the controlled model. After the load moment of inertia is increased by 20 times from initial value, the overshoot of the original PI control method increases at 14.8%, the adjustment time increases to 1 second. Using the control method in this paper, the overshoot can be controlled at 3% and the adjustment time can be controlled at 0.1 second.
{"title":"Speed Control of PMSM Based on Data-Driven Method","authors":"Meng Chen, Fei Gao, Weiyou Ren","doi":"10.1109/ICTech55460.2022.00061","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00061","url":null,"abstract":"Aiming at the problem that the speed control accuracy of permanent magnet synchronous motors is easily affected by uncertain factors such as load moment of inertia, external disturbances, unmodeled dynamics, etc., a data-driven speed control method is proposed. This method firstly uses the least square method to identify the precise mathematical model of the system based on the input and output data of the controlled system in real time. Then, in order to reduce the difficulty of the controller parameter tuning, a method of numerically optimizing the controller parameters is proposed. We can use this method and the precise model of the system obtained in the previous step to tune the controller parameters. Through MATLAB simulation software and experimental platform, the speed control method proposed in this paper is compared with the PI control method. From the simulation and experimental results, it can be seen that the control method proposed in this paper can effectively adapt to the time-varying problem of the controlled model. After the load moment of inertia is increased by 20 times from initial value, the overshoot of the original PI control method increases at 14.8%, the adjustment time increases to 1 second. Using the control method in this paper, the overshoot can be controlled at 3% and the adjustment time can be controlled at 0.1 second.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"2 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120918323","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00068
Zhixin Jing, Rui Fan, Wan-zhao Liu, Yan Shi, Fengjiu Yang
With the rapid development of China's data industry, power big data has gradually become the main object of national construction and innovation. Especially in the promotion of sensors and intelligent equipment and so on, more and more electric power data sources, the type characteristics shown more complex, the use of big data related to technology, the hidden data information, not only can improve the efficiency of the power system, can also provide effective basis for warehouse management. As the main management tool for power big data, power load prediction can guarantee the power system and power supply quality on the one hand, and can provide more effective information by warehouse management on the other hand, and the actual prediction results directly affect the accuracy of the whole system operation. Therefore, on the basis of understanding the development trend of power big data, this paper takes data mining technology as the core to improve and explore the power load prediction, so as to ensure the accuracy and effectiveness of online tools and data management of warehouse management.
{"title":"Evaluation of Online Tool Data Management for Warehouse Management for Power Big Data","authors":"Zhixin Jing, Rui Fan, Wan-zhao Liu, Yan Shi, Fengjiu Yang","doi":"10.1109/ICTech55460.2022.00068","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00068","url":null,"abstract":"With the rapid development of China's data industry, power big data has gradually become the main object of national construction and innovation. Especially in the promotion of sensors and intelligent equipment and so on, more and more electric power data sources, the type characteristics shown more complex, the use of big data related to technology, the hidden data information, not only can improve the efficiency of the power system, can also provide effective basis for warehouse management. As the main management tool for power big data, power load prediction can guarantee the power system and power supply quality on the one hand, and can provide more effective information by warehouse management on the other hand, and the actual prediction results directly affect the accuracy of the whole system operation. Therefore, on the basis of understanding the development trend of power big data, this paper takes data mining technology as the core to improve and explore the power load prediction, so as to ensure the accuracy and effectiveness of online tools and data management of warehouse management.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132319858","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00042
Ning Zhang, Fangjian Shang, Xin Li, Wenjun Zhu
At present, the application of artificial intelligence technology to test data generation has become one of the research hotspots. However, its research method is not suitable for the field of electric power Internet of Things. This paper analyzes the specific functions of the unified IOT management platform in the power IOT, and applies ant colony algorithm to realize the automatic generation of test data. so as to solve the problems of time-consuming and nonstandard manual data compilation by users and improve the test efficiency of the system.
{"title":"Research on Test Data Generation Method of IOT Management Platform Based on Ant Colony Algorithm","authors":"Ning Zhang, Fangjian Shang, Xin Li, Wenjun Zhu","doi":"10.1109/ICTech55460.2022.00042","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00042","url":null,"abstract":"At present, the application of artificial intelligence technology to test data generation has become one of the research hotspots. However, its research method is not suitable for the field of electric power Internet of Things. This paper analyzes the specific functions of the unified IOT management platform in the power IOT, and applies ant colony algorithm to realize the automatic generation of test data. so as to solve the problems of time-consuming and nonstandard manual data compilation by users and improve the test efficiency of the system.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132358154","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00082
Zhe Sun, H. Yang
In order to help beginners to quickly understand and participate in skiing, researchers put forward the design of skiing simulator during the design and research, which includes safety protection, sports training, virtual simulation of these three aspects. VR virtual simulation system can accurately simulate the scene of skiing training, so that the training personnel can feel the real charm of skiing in the participation. The sports training system contains a number of institutions, which can maximize the simulation of skiing posture, and the safety protection system can provide comprehensive protection to participants. The effective integration of Will technology and trainer can help people simulate multi-dimensional skiing posture in real skiing scene experience, and promote them to have a real experience during simulated training. In this paper, on the basis of understanding the design experience and composition of multi-sensor, the attitude training simulator of ski machine with multi-sensor as the core is deeply studied, so as to build a good simulation for skiing participants. The final results show that the attitude training simulator based on multi-sensor can show positive advantages in practical application.
{"title":"Development of a Multi-Sensor Based Ski Machine Attitude Training Simulator","authors":"Zhe Sun, H. Yang","doi":"10.1109/ICTech55460.2022.00082","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00082","url":null,"abstract":"In order to help beginners to quickly understand and participate in skiing, researchers put forward the design of skiing simulator during the design and research, which includes safety protection, sports training, virtual simulation of these three aspects. VR virtual simulation system can accurately simulate the scene of skiing training, so that the training personnel can feel the real charm of skiing in the participation. The sports training system contains a number of institutions, which can maximize the simulation of skiing posture, and the safety protection system can provide comprehensive protection to participants. The effective integration of Will technology and trainer can help people simulate multi-dimensional skiing posture in real skiing scene experience, and promote them to have a real experience during simulated training. In this paper, on the basis of understanding the design experience and composition of multi-sensor, the attitude training simulator of ski machine with multi-sensor as the core is deeply studied, so as to build a good simulation for skiing participants. The final results show that the attitude training simulator based on multi-sensor can show positive advantages in practical application.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133293248","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00070
Fan Zhou, Yang Wang
In the era of big data, with lower costs and higher efficiency, web crawlers access resources and information from the Internet, bringing a lot of convenience to businesses and individuals. Nevertheless, there are two sides to everything, as malicious crawlers bring incalculable threats and losses to websites. In order to prevent web crawlers from being abused or even developing into malicious crawlers, web sites usually perform anti-crawler based on techniques such as ip access frequency, browsing page speed, account login, input captcha, js encryption, ajax obfuscation, etc. Anti-crawlers cannot completely block crawlers with a particular technique, but only find ways to increase the cost of crawling for attackers, forcing the catching party to make the right choice after weighing the cost-benefit.
{"title":"Exploring The Role of Web Crawler and Anti-Crawler Technology in Big Data Era","authors":"Fan Zhou, Yang Wang","doi":"10.1109/ICTech55460.2022.00070","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00070","url":null,"abstract":"In the era of big data, with lower costs and higher efficiency, web crawlers access resources and information from the Internet, bringing a lot of convenience to businesses and individuals. Nevertheless, there are two sides to everything, as malicious crawlers bring incalculable threats and losses to websites. In order to prevent web crawlers from being abused or even developing into malicious crawlers, web sites usually perform anti-crawler based on techniques such as ip access frequency, browsing page speed, account login, input captcha, js encryption, ajax obfuscation, etc. Anti-crawlers cannot completely block crawlers with a particular technique, but only find ways to increase the cost of crawling for attackers, forcing the catching party to make the right choice after weighing the cost-benefit.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123587020","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00040
Conglei Lv, Xiwang Li, Wen Wang
With the development of network scale, network technology affects every aspect of people's life. It is of great significance to detect network intrusion. Traditional research is mostly based on open data sets, the open data sets lack timeliness, and the validity of the research results is unknown. Based on the previous research, this paper proposed a novel intrusion detection method based on convolutional neural network. Firstly, real abnormal data packets were obtained by building a network environment and using real network attack tools. Second, abnormal data packets were used to generate features. Furthermore those futures are transformed into gray images for visual analysis. In order to evaluate effectiveness and superiority of proposed method, several evaluating indicators were introduced. The experimental result shows that precision, recall and F1 value of the proposed method reached 0.99, 0.99 and 0.99 respectively, which were all superior to the traditional machine learning methods.
{"title":"Application of Convolution Neural Network in Network Abnormal Traffic Detection","authors":"Conglei Lv, Xiwang Li, Wen Wang","doi":"10.1109/ICTech55460.2022.00040","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00040","url":null,"abstract":"With the development of network scale, network technology affects every aspect of people's life. It is of great significance to detect network intrusion. Traditional research is mostly based on open data sets, the open data sets lack timeliness, and the validity of the research results is unknown. Based on the previous research, this paper proposed a novel intrusion detection method based on convolutional neural network. Firstly, real abnormal data packets were obtained by building a network environment and using real network attack tools. Second, abnormal data packets were used to generate features. Furthermore those futures are transformed into gray images for visual analysis. In order to evaluate effectiveness and superiority of proposed method, several evaluating indicators were introduced. The experimental result shows that precision, recall and F1 value of the proposed method reached 0.99, 0.99 and 0.99 respectively, which were all superior to the traditional machine learning methods.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125089426","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00108
Zhimin He, Aidi Dong, Jianhong Pan
With the rapid development of the digital economy, combined with changes in the company's internal and external development situations, the digitization of grid companies is extending from supporting management digitization to serving energy Internet digitization applications, extending from serving internally to internally and externally, and helping to improve quality and efficiency. To empower emerging industries to upgrade and extend, the digital construction of power grid companies will become an important core task for the construction of the energy Internet. This article is based on the quantitative control dynamic technology of digital economic benefit evaluation, through the analysis of business types, project cycles., new business development, etc., using big data analysis., data governance, machine learning and other technologies to capture, integrate, and analyze project data, To form an architectural feature model, to screen and effectively correlate digital economic benefit evaluation indicators, and finally complete the construction of a dynamic analysis model for digital economic benefit evaluation intelligent quantitative control.
{"title":"Research on Dynamic Technology of Digital Benefit Intelligent Quantitative Control","authors":"Zhimin He, Aidi Dong, Jianhong Pan","doi":"10.1109/ICTech55460.2022.00108","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00108","url":null,"abstract":"With the rapid development of the digital economy, combined with changes in the company's internal and external development situations, the digitization of grid companies is extending from supporting management digitization to serving energy Internet digitization applications, extending from serving internally to internally and externally, and helping to improve quality and efficiency. To empower emerging industries to upgrade and extend, the digital construction of power grid companies will become an important core task for the construction of the energy Internet. This article is based on the quantitative control dynamic technology of digital economic benefit evaluation, through the analysis of business types, project cycles., new business development, etc., using big data analysis., data governance, machine learning and other technologies to capture, integrate, and analyze project data, To form an architectural feature model, to screen and effectively correlate digital economic benefit evaluation indicators, and finally complete the construction of a dynamic analysis model for digital economic benefit evaluation intelligent quantitative control.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117295304","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00094
Xiaoxing Zhang, R. Guo, Z. Tong, Hongliang Wang, Chao Fu, Yuan Liu
Determining an accurate surgical target is vitally important in reducing trauma and risk of carotid endarterectomy. This study aims to design and implement a surgical target position determination system, which is used to assist the doctor to determine the location of the surgical target in carotid endarterectomy. Based on mixed reality technology, through a novel method of matching digital virtual organ models and real physical entities, the target assisted positioning system realizes the surgical target auxiliary determination in the analysis of carotid endarterectomy process. The multiple digital three-dimensional models of ROI were visualization in mixed reality vision through the model fusion and RGBA adjustment. During the operation, the doctor aligns the digital 3D models with the physical entity in the mixed reality environment, and then determining the surgical target position through the spatial position of digital models of the carotid stenosis area. The assisted system has been implemented and verified in three carotid endarterectomy operations. To verify the feasibility and practical application value of the system, the cost time of assisted positioning process and the evaluation of doctors' used experience are counted. The results show that the clinicians could achieve intuitive visualization of surgical targets in deep spine positions with mixed reality and the target determining process of carotid endarterectomy takes a shorter time than the traditional image guided system. Conclusion is that the designed surgical target assisted positioning system makes the process of determining the surgical target of the carotid endarterectomy more intuitive. To a large extent, the method helps doctors determine the surgical target and improve the quality and efficiency in operation.
{"title":"Design and Implementation of An Assisted Positioning System for Carotid Endarterectomy Based on Mixed Reality","authors":"Xiaoxing Zhang, R. Guo, Z. Tong, Hongliang Wang, Chao Fu, Yuan Liu","doi":"10.1109/ICTech55460.2022.00094","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00094","url":null,"abstract":"Determining an accurate surgical target is vitally important in reducing trauma and risk of carotid endarterectomy. This study aims to design and implement a surgical target position determination system, which is used to assist the doctor to determine the location of the surgical target in carotid endarterectomy. Based on mixed reality technology, through a novel method of matching digital virtual organ models and real physical entities, the target assisted positioning system realizes the surgical target auxiliary determination in the analysis of carotid endarterectomy process. The multiple digital three-dimensional models of ROI were visualization in mixed reality vision through the model fusion and RGBA adjustment. During the operation, the doctor aligns the digital 3D models with the physical entity in the mixed reality environment, and then determining the surgical target position through the spatial position of digital models of the carotid stenosis area. The assisted system has been implemented and verified in three carotid endarterectomy operations. To verify the feasibility and practical application value of the system, the cost time of assisted positioning process and the evaluation of doctors' used experience are counted. The results show that the clinicians could achieve intuitive visualization of surgical targets in deep spine positions with mixed reality and the target determining process of carotid endarterectomy takes a shorter time than the traditional image guided system. Conclusion is that the designed surgical target assisted positioning system makes the process of determining the surgical target of the carotid endarterectomy more intuitive. To a large extent, the method helps doctors determine the surgical target and improve the quality and efficiency in operation.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115392845","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00043
Baofeng Hui, Y. Ma
The early alarm system is a mechanical alarm, which only monitors a single point. As long as an object enters the monitored place, it will send out an alarm signal mechanically and without analysis. In the image processing part, the difference or gray value comparison between the image of the foreign body and the reference image is mainly carried out to obtain the foreign body, and the obtained foreign body is segmented and edge detected to calculate the parameters such as the area, perimeter and proportional characteristics of the foreign body, and the foreign body is identified and classified by understanding the parameters, so as to further judge whether the foreign body is harmful or not. In recent years, with the rapid development of big data technology application, deep learning has maintained a strong development trend, and has realized large-scale promotion and application in important fields such as data processing, image recognition and text understanding. This paper discusses the image recognition technology of deep learning in monitoring intelligent alarm system, and further studies how to effectively recognize video images and strengthen monitoring intelligent alarm system.
{"title":"Image Recognition Technology of Monitoring Intelligent Alarm System Based on Deep Learning","authors":"Baofeng Hui, Y. Ma","doi":"10.1109/ICTech55460.2022.00043","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00043","url":null,"abstract":"The early alarm system is a mechanical alarm, which only monitors a single point. As long as an object enters the monitored place, it will send out an alarm signal mechanically and without analysis. In the image processing part, the difference or gray value comparison between the image of the foreign body and the reference image is mainly carried out to obtain the foreign body, and the obtained foreign body is segmented and edge detected to calculate the parameters such as the area, perimeter and proportional characteristics of the foreign body, and the foreign body is identified and classified by understanding the parameters, so as to further judge whether the foreign body is harmful or not. In recent years, with the rapid development of big data technology application, deep learning has maintained a strong development trend, and has realized large-scale promotion and application in important fields such as data processing, image recognition and text understanding. This paper discusses the image recognition technology of deep learning in monitoring intelligent alarm system, and further studies how to effectively recognize video images and strengthen monitoring intelligent alarm system.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126977356","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00055
Ying Gao, Xiaojun Xia
In the industrial production process, the rolling bearing failures of huge mechanical equipment such as CNC machine tools frequently occur, which seriously affects the production performance and service life of the machine tools. In order to identify the types of faults in rolling bearings and improve the safety of the equipment, this paper presents a fault diagnosis method on account of an improved Convolution Neural Network (CNN). The improved CNN model is to add a convolutional layer before the fully connected layer, after several convolutional layers and several pooling layers, and use an improved stochastic gradient descent training algorithm with momentum to speed up the training speed to enhance the serviceability of the model. Traditional fault diagnosis methods are time-consuming, high in labor costs and low in work efficiency. The method in this paper improves the intelligence of the rolling bearing of CNC machine tools fault diagnosis process, improves the correctness of fault diagnosis, and adapts to the characteristics of big data fault diagnosis. Finally, the data set of Case Western Reserve University's rolling bearing database is used for experimental verification. The experimental results reveal that this method has a high recognition accuracy rate for various types and severity of rolling bearing faults, and has good practicability and application prospect.
{"title":"A Fault Diagnosis Method of Rolling Bearing of CNC Machine Tool Based on Improved Convolutional Neural Network","authors":"Ying Gao, Xiaojun Xia","doi":"10.1109/ICTech55460.2022.00055","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00055","url":null,"abstract":"In the industrial production process, the rolling bearing failures of huge mechanical equipment such as CNC machine tools frequently occur, which seriously affects the production performance and service life of the machine tools. In order to identify the types of faults in rolling bearings and improve the safety of the equipment, this paper presents a fault diagnosis method on account of an improved Convolution Neural Network (CNN). The improved CNN model is to add a convolutional layer before the fully connected layer, after several convolutional layers and several pooling layers, and use an improved stochastic gradient descent training algorithm with momentum to speed up the training speed to enhance the serviceability of the model. Traditional fault diagnosis methods are time-consuming, high in labor costs and low in work efficiency. The method in this paper improves the intelligence of the rolling bearing of CNC machine tools fault diagnosis process, improves the correctness of fault diagnosis, and adapts to the characteristics of big data fault diagnosis. Finally, the data set of Case Western Reserve University's rolling bearing database is used for experimental verification. The experimental results reveal that this method has a high recognition accuracy rate for various types and severity of rolling bearing faults, and has good practicability and application prospect.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128864366","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：