Pub Date : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021551
W. Fan, M. Lin, M. Zhao, Q. Xie, B. Wang
With the continuous improvement of medical technology, the application of automatic biochemical test technology is more and more extensive, users and the market put forward higher and higher requirements for the high speed, stability and accuracy of biochemical detection. This paper introduces a high-speed automatic biochemical immune assembly line with biosafety protection function, the assembly line uses a variety of technical means such as multi-channel transportation, superfine sample addition, ultrasonic blending, photon counter darkroom and biosafety protection, and it can realize the high-speed detection of biochemical items and also ensure the accuracy of detection results.
{"title":"High-speed automatic biochemical immune assembly line","authors":"W. Fan, M. Lin, M. Zhao, Q. Xie, B. Wang","doi":"10.1109/WCMEIM56910.2022.10021551","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021551","url":null,"abstract":"With the continuous improvement of medical technology, the application of automatic biochemical test technology is more and more extensive, users and the market put forward higher and higher requirements for the high speed, stability and accuracy of biochemical detection. This paper introduces a high-speed automatic biochemical immune assembly line with biosafety protection function, the assembly line uses a variety of technical means such as multi-channel transportation, superfine sample addition, ultrasonic blending, photon counter darkroom and biosafety protection, and it can realize the high-speed detection of biochemical items and also ensure the accuracy of detection results.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122117239","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021438
Fei Li, Lihao Cheng, Hao Wu, Wenxuan Zhao
To resolve the limitations of downhole turbine generators, such as insufficient power generation, low adaptability of output voltage, and complicated testing of directional drilling tools, the performance study of a turbine generator with high-power capacity and magnetic field excitation was conducted. Based on the Simulink model of the turbine generator and excitation control system, the excitation control system and hardware circuit were designed according to the voltage management requirement of the tool. The external characteristics of the generator at different speeds and loads, the excitation control circuit board's real-time excitation current regulation performance, and the overall closed-loop control performance were simulated and tested. The results show that the model effectively verifies the feasibility of the excitation control principle, the model and prototype version have similar characteristics, and the model can accurately match the prototype. The output voltage range meets the regular operation of directional drilling tools, and the output power can reach 4kW within the rated speed of 6000r/min. The designed excitation regulation system model and hardware circuit meet the tool power management requirements, and the excitation voltage regulation rate is about ±20%. This study solves the relationship between mud flow rates and output power and intuitively guides actual drilling operations and workshop maintenance. As a result, this research can reduce the testing cost and complexity of directional drilling tools.
{"title":"Simulation and Experiment Research on Performance of High Power While-drilling Turbine Generator","authors":"Fei Li, Lihao Cheng, Hao Wu, Wenxuan Zhao","doi":"10.1109/WCMEIM56910.2022.10021438","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021438","url":null,"abstract":"To resolve the limitations of downhole turbine generators, such as insufficient power generation, low adaptability of output voltage, and complicated testing of directional drilling tools, the performance study of a turbine generator with high-power capacity and magnetic field excitation was conducted. Based on the Simulink model of the turbine generator and excitation control system, the excitation control system and hardware circuit were designed according to the voltage management requirement of the tool. The external characteristics of the generator at different speeds and loads, the excitation control circuit board's real-time excitation current regulation performance, and the overall closed-loop control performance were simulated and tested. The results show that the model effectively verifies the feasibility of the excitation control principle, the model and prototype version have similar characteristics, and the model can accurately match the prototype. The output voltage range meets the regular operation of directional drilling tools, and the output power can reach 4kW within the rated speed of 6000r/min. The designed excitation regulation system model and hardware circuit meet the tool power management requirements, and the excitation voltage regulation rate is about ±20%. This study solves the relationship between mud flow rates and output power and intuitively guides actual drilling operations and workshop maintenance. As a result, this research can reduce the testing cost and complexity of directional drilling tools.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124573396","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021397
Y. Hancheng, Jin Yanjun, Zhu Xihao, Jiang Seqi
Given the growing demand for intelligence in industrial production, the key technology of robotic arm automatically crawling is being studied and realized using random stacking components as the research object. To begin, the global feature descriptor PPF algorithm is used to extract part features. The visible points that meet the conditions are then combined pairwise in the off-line training stage, and the characteristics of point pairs are calculated to obtain the model describing the object's global information. The components are identified during the online matching stage by employing a voting strategy based on the Hough transform. The RANSAC algorithm is then used for rough pose estimation, and the ICP algorithm is used to fine-tune the pose result to obtain the target's optimal pose estimation. Finally, the transformation matrix after hand-eye calibration based on differential evolution algorithm determines the position and posture of the parts in the real world coordinate system, guiding the manipulator to accurately grab and place the stacked parts. A grab system was built to test it as part of a water pump production line reconstruction project. Using the pump body as an example, the results show that the number of features of the selected point pair is 730,830, the matching accuracy can reach 94.64%, and the matching time consumption is 1.1424 s; the overall average grabbing success rate is 92.3%, which is practical.
{"title":"Research on key technologies of random stacking components automatically crawl","authors":"Y. Hancheng, Jin Yanjun, Zhu Xihao, Jiang Seqi","doi":"10.1109/WCMEIM56910.2022.10021397","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021397","url":null,"abstract":"Given the growing demand for intelligence in industrial production, the key technology of robotic arm automatically crawling is being studied and realized using random stacking components as the research object. To begin, the global feature descriptor PPF algorithm is used to extract part features. The visible points that meet the conditions are then combined pairwise in the off-line training stage, and the characteristics of point pairs are calculated to obtain the model describing the object's global information. The components are identified during the online matching stage by employing a voting strategy based on the Hough transform. The RANSAC algorithm is then used for rough pose estimation, and the ICP algorithm is used to fine-tune the pose result to obtain the target's optimal pose estimation. Finally, the transformation matrix after hand-eye calibration based on differential evolution algorithm determines the position and posture of the parts in the real world coordinate system, guiding the manipulator to accurately grab and place the stacked parts. A grab system was built to test it as part of a water pump production line reconstruction project. Using the pump body as an example, the results show that the number of features of the selected point pair is 730,830, the matching accuracy can reach 94.64%, and the matching time consumption is 1.1424 s; the overall average grabbing success rate is 92.3%, which is practical.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123236836","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021530
Xu Kehui, Xue Kairui, Fan Shixun, Wen Zhijie, Fan Dapeng
Swaying is the main factor restricting the precision docking of shipboard thin-walled parts. Aiming at the assembly error analysis problem of thin-walled cylindrical parts under ship oscillation, this paper presents a simulation analysis method of butt surface center error based on finite element analysis and dynamic analysis. The method integrates the control performance of the electromechanical system, the dynamic deformation of the structure and the transmission clearance. In swaying environment, establishing the simulation model of cylinder parts docking test system based on Stewart platform. Based on finite element analysis and dynamic simulation, the safety characteristics of the system are verified and the center error of the docking surface is calculated. The results show that the center error of the test system docking is 0.75mm when the ship roll amplitude is 6.25° and 2.5°. And the effectiveness of this error analysis method is verified by comparing the simulation and test results of the test system in gravity environment.
{"title":"Simulation of thin-walled cylindrical parts assembly under ship oscillation","authors":"Xu Kehui, Xue Kairui, Fan Shixun, Wen Zhijie, Fan Dapeng","doi":"10.1109/WCMEIM56910.2022.10021530","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021530","url":null,"abstract":"Swaying is the main factor restricting the precision docking of shipboard thin-walled parts. Aiming at the assembly error analysis problem of thin-walled cylindrical parts under ship oscillation, this paper presents a simulation analysis method of butt surface center error based on finite element analysis and dynamic analysis. The method integrates the control performance of the electromechanical system, the dynamic deformation of the structure and the transmission clearance. In swaying environment, establishing the simulation model of cylinder parts docking test system based on Stewart platform. Based on finite element analysis and dynamic simulation, the safety characteristics of the system are verified and the center error of the docking surface is calculated. The results show that the center error of the test system docking is 0.75mm when the ship roll amplitude is 6.25° and 2.5°. And the effectiveness of this error analysis method is verified by comparing the simulation and test results of the test system in gravity environment.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114641721","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021507
Ruining Li
Path Planning is an essential aspect of the navigation of mobile service robots. The problem of path planning includes low time efficiency, large memory cost, local optimum, and slow speed in finding the global optimum. This paper reviews three main path planning algorithms and their extensions for the service robots. The first one is Ant Colony Optimization (ACO). The second algorithm is Particle Swarm Optimization (PSO) and some hybrid PSO-related algorithms. The third one is a conventional algorithm named Rapidly Exploring Random Tree (RRT).
{"title":"Path Planning for Service Robots","authors":"Ruining Li","doi":"10.1109/WCMEIM56910.2022.10021507","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021507","url":null,"abstract":"Path Planning is an essential aspect of the navigation of mobile service robots. The problem of path planning includes low time efficiency, large memory cost, local optimum, and slow speed in finding the global optimum. This paper reviews three main path planning algorithms and their extensions for the service robots. The first one is Ant Colony Optimization (ACO). The second algorithm is Particle Swarm Optimization (PSO) and some hybrid PSO-related algorithms. The third one is a conventional algorithm named Rapidly Exploring Random Tree (RRT).","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116346719","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021444
Zhuolin Wang
This design comprehensively uses the relevant knowledge of machinery, hydraulic pressure, electromechanical transmission, and PLC to design a set of small automatic loading mechanism that can complete automatic stick insertion. In order to reduce the labor intensity of workers and improve the workload of unit man hour, this paper designs the automatic feeding, transportation, loading and control device of the ice cream stick during the production of ice cream. The design mainly includes the mechanical transmission system, hydraulic system and PLC control system when inserting the ice cream stick into the mold. Finally, the following processes are automatically realized: the mold is sent to the designated position with a conveyor belt; The hydraulic device at the lower end lifts it to align with the distributor; Then use the conveyor belt to arrange the ice cream sticks orderly and transport them upward. The ice cream sticks are transported to another conveyor belt through the transition gear. When enough ice cream sticks are transported, stop feeding; The hydraulic devices on both sides of the conveyor belt push the blanking plate to push the ice cream stick into the distributor and then retract it. The ice cream stick is inserted into the lower mold orderly through the distributor; The mould with the rod loaded falls back to the conveyor belt through the hydraulic device and is transported away. The design content of this paper includes CAD design drawing, part drawing, hydraulic schematic diagram, PLC control sequence function diagram and the selection of main components. The designed equipment has the advantages of simple structure, convenient maintenance, low cost, high controllability and labor saving.
{"title":"Design of Automatic Loading Mechanism Based on PLC Control","authors":"Zhuolin Wang","doi":"10.1109/WCMEIM56910.2022.10021444","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021444","url":null,"abstract":"This design comprehensively uses the relevant knowledge of machinery, hydraulic pressure, electromechanical transmission, and PLC to design a set of small automatic loading mechanism that can complete automatic stick insertion. In order to reduce the labor intensity of workers and improve the workload of unit man hour, this paper designs the automatic feeding, transportation, loading and control device of the ice cream stick during the production of ice cream. The design mainly includes the mechanical transmission system, hydraulic system and PLC control system when inserting the ice cream stick into the mold. Finally, the following processes are automatically realized: the mold is sent to the designated position with a conveyor belt; The hydraulic device at the lower end lifts it to align with the distributor; Then use the conveyor belt to arrange the ice cream sticks orderly and transport them upward. The ice cream sticks are transported to another conveyor belt through the transition gear. When enough ice cream sticks are transported, stop feeding; The hydraulic devices on both sides of the conveyor belt push the blanking plate to push the ice cream stick into the distributor and then retract it. The ice cream stick is inserted into the lower mold orderly through the distributor; The mould with the rod loaded falls back to the conveyor belt through the hydraulic device and is transported away. The design content of this paper includes CAD design drawing, part drawing, hydraulic schematic diagram, PLC control sequence function diagram and the selection of main components. The designed equipment has the advantages of simple structure, convenient maintenance, low cost, high controllability and labor saving.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125672415","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}
Aiming at the test problems caused by the limited cycle of existing automatic processing equipment, this paper takes the chamfering device as the research object, and develops a small PLC half-physical simulation system by using virtual reality technology. The system includes PLC, virtual communication module and virtual 3D model. Mitsubishi FX5U series PLC for the host computer, use programming to control the 3D model. Virtual communication module transmits data by serial communication. The virtual 3D model acts as the lower machine and drives the motion of the model through the received data. The simulation results show that the system can verify the correctness of PLC program and provide a new test method for automatic equipment production line.
{"title":"Half-physical Simulation System Design of Chamfering Device Based on PLC","authors":"Yunhao Fu, Qingzhu Zhang, Hongtao Han, Qiang Zhang, Liang Li, Bing Li","doi":"10.1109/WCMEIM56910.2022.10021471","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021471","url":null,"abstract":"Aiming at the test problems caused by the limited cycle of existing automatic processing equipment, this paper takes the chamfering device as the research object, and develops a small PLC half-physical simulation system by using virtual reality technology. The system includes PLC, virtual communication module and virtual 3D model. Mitsubishi FX5U series PLC for the host computer, use programming to control the 3D model. Virtual communication module transmits data by serial communication. The virtual 3D model acts as the lower machine and drives the motion of the model through the received data. The simulation results show that the system can verify the correctness of PLC program and provide a new test method for automatic equipment production line.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121736019","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021461
Chao Liang, Wen-An Mo, Jing Tang, Ji Wang, Chuangmian Huang, Gao-Yi Luo
Aiming at the problems existing in accurate monitoring of tool wear status and accurate prediction of tool life, there is no reliable basis for decision-making on tool selection, replacement and grinding, which seriously affects the optimization and control of precise tool utilization and the dynamic regulation of production systems. Aiming at this problem, based on the concept of digital twin, a digital twin model for tool wear monitoring and life prediction is proposed. The model consists of three parts: digital model, analysis data model and evaluation model. Complete the collection and fusion of heterogeneous data and the evaluation and prediction for different targets. According to the different wear stages of the tool, three monitoring and prediction modes are proposed. Make full use of the value of multi-dimensional data information. Monitoring and forecasting services are provided for different demand levels, taking the cost, efficiency and accuracy of forecasting. into account, Supports the precise use of tools.
{"title":"Construction and application of digital twin model for tool wear monitoring and life prediction","authors":"Chao Liang, Wen-An Mo, Jing Tang, Ji Wang, Chuangmian Huang, Gao-Yi Luo","doi":"10.1109/WCMEIM56910.2022.10021461","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021461","url":null,"abstract":"Aiming at the problems existing in accurate monitoring of tool wear status and accurate prediction of tool life, there is no reliable basis for decision-making on tool selection, replacement and grinding, which seriously affects the optimization and control of precise tool utilization and the dynamic regulation of production systems. Aiming at this problem, based on the concept of digital twin, a digital twin model for tool wear monitoring and life prediction is proposed. The model consists of three parts: digital model, analysis data model and evaluation model. Complete the collection and fusion of heterogeneous data and the evaluation and prediction for different targets. According to the different wear stages of the tool, three monitoring and prediction modes are proposed. Make full use of the value of multi-dimensional data information. Monitoring and forecasting services are provided for different demand levels, taking the cost, efficiency and accuracy of forecasting. into account, Supports the precise use of tools.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132037275","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021542
Zhiyong Yu, Zhaoyao Shi, H. Yue, Lintao Zhang
Transmission error is a key indicator to characterize the performance of precision reducer. The test result of transmission error will be influenced by input speed and load torque. In this study, a morphological construction method of transmission error of precision reducer based on BP neural network was proposed to obtain the morphology of transmission error under different input speeds and load torques. Then the transmission accuracy of precision reducer could be accurately evaluated. With RV-40E reducer as an example, the morphological structure of its transmission error was obtained. The experimental results demonstrate that the model established by the proposed method can reflect the morphology of transmission error.
{"title":"Morphological Construction of Transmission Error of Precision Reducer Based on BP Neural Network","authors":"Zhiyong Yu, Zhaoyao Shi, H. Yue, Lintao Zhang","doi":"10.1109/WCMEIM56910.2022.10021542","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021542","url":null,"abstract":"Transmission error is a key indicator to characterize the performance of precision reducer. The test result of transmission error will be influenced by input speed and load torque. In this study, a morphological construction method of transmission error of precision reducer based on BP neural network was proposed to obtain the morphology of transmission error under different input speeds and load torques. Then the transmission accuracy of precision reducer could be accurately evaluated. With RV-40E reducer as an example, the morphological structure of its transmission error was obtained. The experimental results demonstrate that the model established by the proposed method can reflect the morphology of transmission error.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131217558","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 : 2022-11-18DOI: 10.1109/WCMEIM56910.2022.10021531
Fei Ying Li, Jin-feng Xiao
In order to fully consider the influence of uncertain factors such as complex and changeable weather conditions and social events, a multi-channel LSTM-CNN (Long Short Term Memory-Convolutional Neural Network) power load multi-step forecasting model based on feature fusion is proposed for the first time, by modeling the sequential data with different time scales and using the neural network model composed of multiple LSTM networks in parallel, the multi-scale time feature representation is learned, the output time step of each LSTM is convoluted by CNN, and its output characteristics are extracted.
{"title":"Multi-channel LSTM-CNN power load multi-step prediction based on feature fusion","authors":"Fei Ying Li, Jin-feng Xiao","doi":"10.1109/WCMEIM56910.2022.10021531","DOIUrl":"https://doi.org/10.1109/WCMEIM56910.2022.10021531","url":null,"abstract":"In order to fully consider the influence of uncertain factors such as complex and changeable weather conditions and social events, a multi-channel LSTM-CNN (Long Short Term Memory-Convolutional Neural Network) power load multi-step forecasting model based on feature fusion is proposed for the first time, by modeling the sequential data with different time scales and using the neural network model composed of multiple LSTM networks in parallel, the multi-scale time feature representation is learned, the output time step of each LSTM is convoluted by CNN, and its output characteristics are extracted.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131116872","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：