Based on the question of test papers in personalized learning, this paper makes special improvements and designs for the individual genotype, selection, crossover, and mutation processes in traditional genetic algorithms. At the same time, in the design of the fitness function, based on the disadvantages that the dimension cannot be unified when calculating the fitness function by linear weighting method in the traditional literature, a vector distance calculation method was selected to calculate the objective function, which solved the unification of different constraints Questions that differ between dimensions. In addition, based on the problem that duplicate questions may appear in one test paper, this paper designs a deduplication operator and adds it to the step of genetic algorithm.
{"title":"Improvement and Design of Genetic Algorithm in Personalized Test Paper Composition System","authors":"Liping Ma, Xun Zhu, Q. Feng","doi":"10.1145/3424978.3425008","DOIUrl":"https://doi.org/10.1145/3424978.3425008","url":null,"abstract":"Based on the question of test papers in personalized learning, this paper makes special improvements and designs for the individual genotype, selection, crossover, and mutation processes in traditional genetic algorithms. At the same time, in the design of the fitness function, based on the disadvantages that the dimension cannot be unified when calculating the fitness function by linear weighting method in the traditional literature, a vector distance calculation method was selected to calculate the objective function, which solved the unification of different constraints Questions that differ between dimensions. In addition, based on the problem that duplicate questions may appear in one test paper, this paper designs a deduplication operator and adds it to the step of genetic algorithm.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124042087","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}
Short-term power load forecasting plays a very important role in the entire smart grid system. The results of short-term power load forecasting have a great impact on the scheduling and production of power systems. Accurate and efficient short-term power load forecasting can help improve the safety and stability of power systems. Therefore, the design of the forecasting algorithm has always been a very core research direction in the field of power systems. Traditional forecasting methods cannot take into account both the time series and non-linear characteristics of the power load data when performing shortterm power load forecasting. To tackle this problem, we propose a short-term power load forecasting method based on Gate Recurrent Unit (GRU) to predict the power load. Moreover, given that the cloud computing platform can provide parallel computing capabilities and large-scale data storage capabilities, we build our model based on cloud computing methods. We conducted extensive experiments and compared our prediction results with traditional methods to demonstrate that our method is much more accurate and efficient.
{"title":"Short-term Power Load Forecasting Based on Gate Recurrent Unit Network and Cloud Computing Platform","authors":"Xiaohua Li, Weijin Zhuang, Hong Zhang","doi":"10.1145/3424978.3425007","DOIUrl":"https://doi.org/10.1145/3424978.3425007","url":null,"abstract":"Short-term power load forecasting plays a very important role in the entire smart grid system. The results of short-term power load forecasting have a great impact on the scheduling and production of power systems. Accurate and efficient short-term power load forecasting can help improve the safety and stability of power systems. Therefore, the design of the forecasting algorithm has always been a very core research direction in the field of power systems. Traditional forecasting methods cannot take into account both the time series and non-linear characteristics of the power load data when performing shortterm power load forecasting. To tackle this problem, we propose a short-term power load forecasting method based on Gate Recurrent Unit (GRU) to predict the power load. Moreover, given that the cloud computing platform can provide parallel computing capabilities and large-scale data storage capabilities, we build our model based on cloud computing methods. We conducted extensive experiments and compared our prediction results with traditional methods to demonstrate that our method is much more accurate and efficient.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124143151","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}
As a key part of digital power amplifier, Class D power amplifier circuit in traditional vehicle-ground communication system is prone to communication errors and signal distortion, which affect the effective transmission of signals between vehicles and ground. In view of the above problems, this design uses the design principle of Butterworth filter, through theoretical calculation and simulation analysis of the filter circuit, determines the optimal scheme of circuit parameters, and achieves the purpose of improving the performance of digital power amplifier. Experiments show that the design scheme can effectively reduce the signal distortion and improve the signal-to-noise ratio. It has high practicability in practical application.
{"title":"Optimal Design of Filter for Digital Power Amplifier in Vehicle-ground System","authors":"Shuai Han, Pengfei Dai, H. Ding, Xiguo Ren","doi":"10.1145/3424978.3425153","DOIUrl":"https://doi.org/10.1145/3424978.3425153","url":null,"abstract":"As a key part of digital power amplifier, Class D power amplifier circuit in traditional vehicle-ground communication system is prone to communication errors and signal distortion, which affect the effective transmission of signals between vehicles and ground. In view of the above problems, this design uses the design principle of Butterworth filter, through theoretical calculation and simulation analysis of the filter circuit, determines the optimal scheme of circuit parameters, and achieves the purpose of improving the performance of digital power amplifier. Experiments show that the design scheme can effectively reduce the signal distortion and improve the signal-to-noise ratio. It has high practicability in practical application.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126242545","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}
Ke Sun, Weilian Wang, Ruping Yao, Jiahua Pan, Hongbo Yang
At present, the recognition and analysis of heart sound signal was usually run by using high-performance PC. It was hardly done by embedded devices due to limited resources. Provide a portable device for assisting in the initial diagnosis of congenital heart disease (CHD) for doctors with outdated equipment in remote mountainous areas. A novel embedded heart sound analysis and recognition system based on Raspberry pi 3b+ with a NCS2 neural computing stick was put forward in this paper. Firstly, the OpenVINO software platform launched by Intel was used to transfer the ssd_inception_v2 model into the Raspberry Pi after performing transfer learning optimization. Then, reasoning calculation was carried out in Raspberry pi with neural computing stick. Neural computing stick is a deep learning and reasoning tool based on USB mode and an independent artificial intelligence accelerator. NCS2 neural computing stick was used to realize the heart sound analysis and recognition of embedded devices. The sensitivity of the experimental results is 80.7%, the specificity is 95.5%, and the accuracy is 91.4%. The experimental results show that the system has the advantages of low power dissipation, low cost, small size, fast speed, and high recognition rate. It can be used for machine assisted diagnosis of congenital heart disease.
{"title":"Analysis and Recognition of Heart Sound Based on NCS2 Neural Computing Stick","authors":"Ke Sun, Weilian Wang, Ruping Yao, Jiahua Pan, Hongbo Yang","doi":"10.1145/3424978.3425045","DOIUrl":"https://doi.org/10.1145/3424978.3425045","url":null,"abstract":"At present, the recognition and analysis of heart sound signal was usually run by using high-performance PC. It was hardly done by embedded devices due to limited resources. Provide a portable device for assisting in the initial diagnosis of congenital heart disease (CHD) for doctors with outdated equipment in remote mountainous areas. A novel embedded heart sound analysis and recognition system based on Raspberry pi 3b+ with a NCS2 neural computing stick was put forward in this paper. Firstly, the OpenVINO software platform launched by Intel was used to transfer the ssd_inception_v2 model into the Raspberry Pi after performing transfer learning optimization. Then, reasoning calculation was carried out in Raspberry pi with neural computing stick. Neural computing stick is a deep learning and reasoning tool based on USB mode and an independent artificial intelligence accelerator. NCS2 neural computing stick was used to realize the heart sound analysis and recognition of embedded devices. The sensitivity of the experimental results is 80.7%, the specificity is 95.5%, and the accuracy is 91.4%. The experimental results show that the system has the advantages of low power dissipation, low cost, small size, fast speed, and high recognition rate. It can be used for machine assisted diagnosis of congenital heart disease.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128121144","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}
Diabetes is a chronic disease characterized by hyperglycemia. Based on the rising incidence of the disease in recent years, diabetes is affecting more and more families. In 2017 alone, it caused 5 million deaths and cost $850 billion in global healthcare. In this paper, we proposed a method to predict the prevalence of diabetes based on a selected set of features from physical examination data. We used Fisher's score, RFE and decision tree to select features. Random forest, logistic regression, SVM and MLP were used to predict the prevalence of diabetes. EA and Fisher' s score helped us to reduce dimensions. We used random forest to classify diabetes accurately. Our results show that the highest accuracy (0.987) can be achieved by using random forest with 85 features. The prediction accuracy using Fisher's Score with 19 features also reached 0.986. We finally selected 5 features based on our method to form a new dataset for diabetes prediction. The 5 features are fasting plasma glucose, HbA1c, HDL, total cholesterol level and hypertension. The values of accuracy, precision, sensitivity, F1 score, MCC and AUC were 0.977, 0.968, 0.812, 0.883, 0.875, and 0.905, respectively. Results show that our method can be successfully used to select features for diabetes classifier and improve its performance, which will provide support for clinicians to quickly identify diabetes.
{"title":"Feature Selection and Prediction Model for Type 2 Diabetes in the Chinese Population with Machine Learning","authors":"Jiaqi Hou, Yongsheng Sang, Yuping Liu, Li Lu","doi":"10.1145/3424978.3425085","DOIUrl":"https://doi.org/10.1145/3424978.3425085","url":null,"abstract":"Diabetes is a chronic disease characterized by hyperglycemia. Based on the rising incidence of the disease in recent years, diabetes is affecting more and more families. In 2017 alone, it caused 5 million deaths and cost $850 billion in global healthcare. In this paper, we proposed a method to predict the prevalence of diabetes based on a selected set of features from physical examination data. We used Fisher's score, RFE and decision tree to select features. Random forest, logistic regression, SVM and MLP were used to predict the prevalence of diabetes. EA and Fisher' s score helped us to reduce dimensions. We used random forest to classify diabetes accurately. Our results show that the highest accuracy (0.987) can be achieved by using random forest with 85 features. The prediction accuracy using Fisher's Score with 19 features also reached 0.986. We finally selected 5 features based on our method to form a new dataset for diabetes prediction. The 5 features are fasting plasma glucose, HbA1c, HDL, total cholesterol level and hypertension. The values of accuracy, precision, sensitivity, F1 score, MCC and AUC were 0.977, 0.968, 0.812, 0.883, 0.875, and 0.905, respectively. Results show that our method can be successfully used to select features for diabetes classifier and improve its performance, which will provide support for clinicians to quickly identify diabetes.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121439958","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 is an important way to test the learning performance. Due to its advantages of intuition, interactivity, imagination, repeatability and non-dangerousness, virtual simulation experiments have been widely used in experimental teaching. It can complete experiments that cannot be done by traditional experiments, such as high-risk, high-consumption, unreachable and irreversible experiments. With the promotion and application, the learning performance of virtual simulation experiments is more and more concerned by teachers. The result has been brought is that the rough and fuzzy experimental feedback reduces students' learning efficiency and interest. This paper focuses on the method and content of evaluation in the virtual simulation experiment, and aims to ensure the learning performance of students. Paper proposes a set of technical evaluation indicators suitable for the evaluation content. The object of evaluation is the virtual simulation experiment. This evaluation method called "meta-evaluation". There are three main indicators, namely "objective evaluation", "subjective evaluation" and "assessment effectiveness". The five secondary indicators namely "have experimental process" and "have operational evaluation function" etc. In order to verify the scientificity and applicability of the indicators, paper has selected 527 items as the test objects, and obtained a series of scientific and objective evaluation data, hoping to provide references for virtual simulation experiment research.
{"title":"Evaluation of the Learning Performance for Virtual Simulation Experiment","authors":"Fuan Wen, Zhimin Ji","doi":"10.1145/3424978.3425151","DOIUrl":"https://doi.org/10.1145/3424978.3425151","url":null,"abstract":"Evaluation is an important way to test the learning performance. Due to its advantages of intuition, interactivity, imagination, repeatability and non-dangerousness, virtual simulation experiments have been widely used in experimental teaching. It can complete experiments that cannot be done by traditional experiments, such as high-risk, high-consumption, unreachable and irreversible experiments. With the promotion and application, the learning performance of virtual simulation experiments is more and more concerned by teachers. The result has been brought is that the rough and fuzzy experimental feedback reduces students' learning efficiency and interest. This paper focuses on the method and content of evaluation in the virtual simulation experiment, and aims to ensure the learning performance of students. Paper proposes a set of technical evaluation indicators suitable for the evaluation content. The object of evaluation is the virtual simulation experiment. This evaluation method called \"meta-evaluation\". There are three main indicators, namely \"objective evaluation\", \"subjective evaluation\" and \"assessment effectiveness\". The five secondary indicators namely \"have experimental process\" and \"have operational evaluation function\" etc. In order to verify the scientificity and applicability of the indicators, paper has selected 527 items as the test objects, and obtained a series of scientific and objective evaluation data, hoping to provide references for virtual simulation experiment research.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128951223","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}
Clinical medical document images are rich in rich text information, and the detection of text areas is the basis for subsequent text analysis. However, the existing text detection algorithms are mainly for a single language, and the results for mixed Chinese and English text detection are not ideal. In this regard, this paper proposes a hybrid Chinese and English text detection algorithm based on the stroke width transform (SWT) algorithm. The algorithm first preprocesses the image, then determines the connected domain, and determines and filters the text area based on the morphological rules of the connected domain, then connects the pixels into Chinese characters and English characters according to the stroke characteristics, and finally outputs the text area result of the image. The simulation experiment results show that the algorithm can detect the Chinese and English mixed text areas in clinical medical document images better than the traditional text detection algorithm, and the effect is better.
{"title":"Text Detection of Clinical Medical Documents Based on SWT Algorithm","authors":"Jingyi Wang, Zhao Liu","doi":"10.1145/3424978.3425119","DOIUrl":"https://doi.org/10.1145/3424978.3425119","url":null,"abstract":"Clinical medical document images are rich in rich text information, and the detection of text areas is the basis for subsequent text analysis. However, the existing text detection algorithms are mainly for a single language, and the results for mixed Chinese and English text detection are not ideal. In this regard, this paper proposes a hybrid Chinese and English text detection algorithm based on the stroke width transform (SWT) algorithm. The algorithm first preprocesses the image, then determines the connected domain, and determines and filters the text area based on the morphological rules of the connected domain, then connects the pixels into Chinese characters and English characters according to the stroke characteristics, and finally outputs the text area result of the image. The simulation experiment results show that the algorithm can detect the Chinese and English mixed text areas in clinical medical document images better than the traditional text detection algorithm, and the effect is better.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131257197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a gait phase detection method based on directed acyclic graph support vector machines (DAG-SVM) using weighted Euclidean distance optimization. Divide a gait cycle into six gait phases, including three stance phases and three swing phases. Heel, ball pressure, and knee and hip angle data fusion were used as input signals. When calculating the Euclidean distance between category samples, different coefficients are set for pressure data and angle data according to the category to which the gait phase to be classified belongs. The weighted Euclidean distance is obtained, and the topology of DAG-SVM is optimized according to the calculation results, so that it is applied to gait phase detection. This method can effectively solve the structural preference problem of DAG-SVM. Through experimental comparison, this method has higher detection accuracy than DAG-SVM with random structure.
{"title":"Gait Phase Detection of Exoskeleton Robot Based on Optimized DAG-SVM","authors":"Shuaishuai Hu, Jianbin Zheng, Liping Huang","doi":"10.1145/3424978.3425081","DOIUrl":"https://doi.org/10.1145/3424978.3425081","url":null,"abstract":"This paper proposes a gait phase detection method based on directed acyclic graph support vector machines (DAG-SVM) using weighted Euclidean distance optimization. Divide a gait cycle into six gait phases, including three stance phases and three swing phases. Heel, ball pressure, and knee and hip angle data fusion were used as input signals. When calculating the Euclidean distance between category samples, different coefficients are set for pressure data and angle data according to the category to which the gait phase to be classified belongs. The weighted Euclidean distance is obtained, and the topology of DAG-SVM is optimized according to the calculation results, so that it is applied to gait phase detection. This method can effectively solve the structural preference problem of DAG-SVM. Through experimental comparison, this method has higher detection accuracy than DAG-SVM with random structure.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075300","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}
Application of fuel tank status monitoring technology is studied during the operation of large and medium-sized vehicles. By means of sensor network technology, the vehicle on-board terminal periodic data was collected. Vehicle fuel oil of sensing historical data was analyzed and processed. Recognition algorithm of fuel state is studied in order that the status of each of the fuel sampling points are identified as 4 states: "Using, oil filling, oil leaking, Stopping", in order to automatically calculate and perceive the vehicle filling time, oil filling value, oil leaking time, oil leaking value and daily fuel oil consumption value. To overseeing and decision of illegal acts of drivers and conductors such as overstatement of the amount of fuel, stealing and selling fuel to provide the scientific basis for the decision to reduce the loss of company property. On the basis of the fuel status recognition, the calculated results and the actual vehicle oil filling data are analyzed and compared, indicating that the vehicle fuel status recognition algorithm can determine the state of each fuel sample point correctly. Calculated value compared to the actual oil filling values and fuel consumption values, errors between them are no more than 3%, meeting the requirements of the fuel control. Vehicle fuel Status recognition algorithm for each oil sample point fuel condition was the correct judgment, then monitoring fuel calculation and amount of oil used to control the enterprise cost of fuel. The result is satisfactory.
{"title":"Research on Monitoring Method of Fuel Consumption for Large and Medium-sized Vehicles Based on Sensor Network","authors":"Guohua Yue, Jingting Wang","doi":"10.1145/3424978.3425159","DOIUrl":"https://doi.org/10.1145/3424978.3425159","url":null,"abstract":"Application of fuel tank status monitoring technology is studied during the operation of large and medium-sized vehicles. By means of sensor network technology, the vehicle on-board terminal periodic data was collected. Vehicle fuel oil of sensing historical data was analyzed and processed. Recognition algorithm of fuel state is studied in order that the status of each of the fuel sampling points are identified as 4 states: \"Using, oil filling, oil leaking, Stopping\", in order to automatically calculate and perceive the vehicle filling time, oil filling value, oil leaking time, oil leaking value and daily fuel oil consumption value. To overseeing and decision of illegal acts of drivers and conductors such as overstatement of the amount of fuel, stealing and selling fuel to provide the scientific basis for the decision to reduce the loss of company property. On the basis of the fuel status recognition, the calculated results and the actual vehicle oil filling data are analyzed and compared, indicating that the vehicle fuel status recognition algorithm can determine the state of each fuel sample point correctly. Calculated value compared to the actual oil filling values and fuel consumption values, errors between them are no more than 3%, meeting the requirements of the fuel control. Vehicle fuel Status recognition algorithm for each oil sample point fuel condition was the correct judgment, then monitoring fuel calculation and amount of oil used to control the enterprise cost of fuel. The result is satisfactory.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131884161","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}
Nan Zhang, Hao Jiang, Chunbao Xu, Xuemei Liu, Zekun Quan, Yinfa Yan, Shuangxi Liu
In order to solve the problem of positionless sensor drive control of brushless DC motors, a fuzzy PID algorithm and virtual sensors are proposed to detect the rotor position. The construction of the virtual sensor of this method is to combine the zero-crossing detection of the line back EMF and the principle of the sensor to detect the rotor position, instead of the traditional sensor. The fuzzy PID instead of traditional PID control is used to improve its accuracy. Though simulation verification, the method proposed in this paper is compared with the traditional brushless DC motor control with a position sensor. This method requires a shorter time to reach a steady state. The load speed is still maintained at a given speed after 0.02s after operation. The results show that the method proposed in this paper is faster in control than the traditional BLDCM, and provides a theoretical basis for BLDCM dual-loop PWM control without position sensor.
{"title":"Research on BLDCM Double Loop PWM Control Based on Positionless Sensor","authors":"Nan Zhang, Hao Jiang, Chunbao Xu, Xuemei Liu, Zekun Quan, Yinfa Yan, Shuangxi Liu","doi":"10.1145/3424978.3425065","DOIUrl":"https://doi.org/10.1145/3424978.3425065","url":null,"abstract":"In order to solve the problem of positionless sensor drive control of brushless DC motors, a fuzzy PID algorithm and virtual sensors are proposed to detect the rotor position. The construction of the virtual sensor of this method is to combine the zero-crossing detection of the line back EMF and the principle of the sensor to detect the rotor position, instead of the traditional sensor. The fuzzy PID instead of traditional PID control is used to improve its accuracy. Though simulation verification, the method proposed in this paper is compared with the traditional brushless DC motor control with a position sensor. This method requires a shorter time to reach a steady state. The load speed is still maintained at a given speed after 0.02s after operation. The results show that the method proposed in this paper is faster in control than the traditional BLDCM, and provides a theoretical basis for BLDCM dual-loop PWM control without position sensor.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117001315","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：