Pub Date : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995798
Jixiang Du, Changqing Cai, Peisen Zhang, Jianwen Tan
Aiming at the problems of long planning time and long path distance in the path planning of the robotic arm, a path planning strategy based on the improved RRT* (rapid random search tree) algorithm was proposed. First, in order to reduce the randomness of the traditional RRT* path search, adding the node gravitational field function could reduce the generation of redundant nodes, thereby improving the path convergence rate; Secondly, in order to change the folding problem in the traditional RRT* algorithm path, the B-spline function was imported to smooth the planned path, which could reduce the vibration of the joint axis and prolong the service life of the robotic arm. Simulations in MATLAB showed that the average planning time of the improved RRT* algorithm was shortened by 76%, the average path distance was shortened by 14%, and the total number of nodes was reduced by 31.9%. After improving the algorithm, the lines convergence quickly and the line -seeking efficiency is high. The algorithm has good feasibility and effectiveness, and has reference value for the planning of robotic arm path.
{"title":"Path Planning Method of Robot Arm Based on Improved RRT* Algorithm","authors":"Jixiang Du, Changqing Cai, Peisen Zhang, Jianwen Tan","doi":"10.1109/RCAE56054.2022.9995798","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995798","url":null,"abstract":"Aiming at the problems of long planning time and long path distance in the path planning of the robotic arm, a path planning strategy based on the improved RRT* (rapid random search tree) algorithm was proposed. First, in order to reduce the randomness of the traditional RRT* path search, adding the node gravitational field function could reduce the generation of redundant nodes, thereby improving the path convergence rate; Secondly, in order to change the folding problem in the traditional RRT* algorithm path, the B-spline function was imported to smooth the planned path, which could reduce the vibration of the joint axis and prolong the service life of the robotic arm. Simulations in MATLAB showed that the average planning time of the improved RRT* algorithm was shortened by 76%, the average path distance was shortened by 14%, and the total number of nodes was reduced by 31.9%. After improving the algorithm, the lines convergence quickly and the line -seeking efficiency is high. The algorithm has good feasibility and effectiveness, and has reference value for the planning of robotic arm path.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129668678","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9996029
Gaojian Cui, Hong-mei He, Qingbin Zhou, Junchen Jiang, Shaosong Li
A target detection method based on convolutional neural network for multiple complex environments is proposed to address the problem that current target detection methods are prone to miss detection and false detection under complex environment conditions, resulting in reduced detection accuracy. First, an environment recognition architecture is constructed based on convolutional neural networks to classify the images acquired in different environments. Then, the images in different environments are enhanced separately using an image enhancement algorithm. Finally, the enhanced images under different environments are trained based on the YOLOX detection algorithm to achieve real-time detection of the images, and the NUSCENES dataset is used for experimental evaluation. The results show that the proposed detection method improves the average accuracy AP for target detection in sunny, rainy, cloudy and night environments by 6.5%, 13.56%, 6.52% and 6.82%, respectively, improving the detection of small targets.
{"title":"Research on Camera-Based Target Detection Enhancement Method in Complex Environment","authors":"Gaojian Cui, Hong-mei He, Qingbin Zhou, Junchen Jiang, Shaosong Li","doi":"10.1109/RCAE56054.2022.9996029","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9996029","url":null,"abstract":"A target detection method based on convolutional neural network for multiple complex environments is proposed to address the problem that current target detection methods are prone to miss detection and false detection under complex environment conditions, resulting in reduced detection accuracy. First, an environment recognition architecture is constructed based on convolutional neural networks to classify the images acquired in different environments. Then, the images in different environments are enhanced separately using an image enhancement algorithm. Finally, the enhanced images under different environments are trained based on the YOLOX detection algorithm to achieve real-time detection of the images, and the NUSCENES dataset is used for experimental evaluation. The results show that the proposed detection method improves the average accuracy AP for target detection in sunny, rainy, cloudy and night environments by 6.5%, 13.56%, 6.52% and 6.82%, respectively, improving the detection of small targets.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126063071","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995950
Xuanyi Wang, Jianlei Zhang
In this work, we propose an integration algorithm of rapidly-exploring random trees method and artificial potential field method in path planning for a multi-quadrotor unmanned aerial vehicles formation with a load. Specifically, we establish potential field to guide the stretch direction of branches and extract the key points of the final planned path for optimization. For the lack of intelligence of the artificial potential field method, the sampling method gets improvements both on that and rapidity. In the same way, the artificial potential field method also makes up for the lack of planned path's smoothness with the sampling method. Aiming at the complicated structure of the transporting system, we set strict safety constraints to ensure the success of obstacle avoidance. In addition, an algorithm of searching along the wall is proposed to fit in the scene with unknown information obstacles. The methods' feasibility and effectiveness are verified by simulation results and relevant comparative analyses.
{"title":"Path Planning of Load Transportation by Multi-Quadrotor Formation Based on RRT-APF Method","authors":"Xuanyi Wang, Jianlei Zhang","doi":"10.1109/RCAE56054.2022.9995950","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995950","url":null,"abstract":"In this work, we propose an integration algorithm of rapidly-exploring random trees method and artificial potential field method in path planning for a multi-quadrotor unmanned aerial vehicles formation with a load. Specifically, we establish potential field to guide the stretch direction of branches and extract the key points of the final planned path for optimization. For the lack of intelligence of the artificial potential field method, the sampling method gets improvements both on that and rapidity. In the same way, the artificial potential field method also makes up for the lack of planned path's smoothness with the sampling method. Aiming at the complicated structure of the transporting system, we set strict safety constraints to ensure the success of obstacle avoidance. In addition, an algorithm of searching along the wall is proposed to fit in the scene with unknown information obstacles. The methods' feasibility and effectiveness are verified by simulation results and relevant comparative analyses.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128571149","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995799
Cong Xu, Chunlai Yan, Xiuliang Wu, Changchun Pan, Kai Sun
In this study, sensitivity analysis and nonnegative garrote (NNG) are combined to realize adaptive variable selection for gated recurrent unit (GRU). Firstly, the sensitivity analysis based on variance decomposition is used to quantify the correlation between each input variable and the output variable, and the total sensitivity index of each input variable is calculated. Secondly, the total sensitivity index is added to the NNG as an adaptive weight vector to achieve adaptive variable selection. Finally, an artificial dataset with the characteristic of time series is used to verify the effectiveness of the proposed algorithm. Simulation results show that the proposed algorithm can identify the relevant variables effectively and improve the predictive performance of the model.
{"title":"An Adaptive Variable Selection Algorithm for Gated Recurrent Unit Based on Sensitivity Analysis and Nonnegative Garrote","authors":"Cong Xu, Chunlai Yan, Xiuliang Wu, Changchun Pan, Kai Sun","doi":"10.1109/RCAE56054.2022.9995799","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995799","url":null,"abstract":"In this study, sensitivity analysis and nonnegative garrote (NNG) are combined to realize adaptive variable selection for gated recurrent unit (GRU). Firstly, the sensitivity analysis based on variance decomposition is used to quantify the correlation between each input variable and the output variable, and the total sensitivity index of each input variable is calculated. Secondly, the total sensitivity index is added to the NNG as an adaptive weight vector to achieve adaptive variable selection. Finally, an artificial dataset with the characteristic of time series is used to verify the effectiveness of the proposed algorithm. Simulation results show that the proposed algorithm can identify the relevant variables effectively and improve the predictive performance of the model.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128544490","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995905
Suichun Qu, Xue Li, Zhikang Fan, Bin Chen
This paper investigates an integrated design framework for feedback control and fault detection based on a reduced-order observer. Firstly, all stabilizing controllers can be described as a reduced-order observer, which is the joint form of state, output and residual feedback, based on well-known Youla parameterization of all stabilizing controllers. Furthermore, an integrated design framework for feedback control and fault detection is proposed, the advantages of which are low online computation, convenient fault detection, etc. Finally, the simulation of the Heating, Ventilation, and Air conditioning (HVAC) system is adopted to demonstrate the effectiveness and superiority of the proposed design framework.
{"title":"Integrated Design of Feedback Control and Fault Detection Based on Reduced-Order Observer","authors":"Suichun Qu, Xue Li, Zhikang Fan, Bin Chen","doi":"10.1109/RCAE56054.2022.9995905","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995905","url":null,"abstract":"This paper investigates an integrated design framework for feedback control and fault detection based on a reduced-order observer. Firstly, all stabilizing controllers can be described as a reduced-order observer, which is the joint form of state, output and residual feedback, based on well-known Youla parameterization of all stabilizing controllers. Furthermore, an integrated design framework for feedback control and fault detection is proposed, the advantages of which are low online computation, convenient fault detection, etc. Finally, the simulation of the Heating, Ventilation, and Air conditioning (HVAC) system is adopted to demonstrate the effectiveness and superiority of the proposed design framework.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130003085","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995729
Tongchen Lin, Guocai Zhang
In this study, we design a two-wheeled self-balancing traction vehicle. The common scheme of camera collecting road information of autonomous tracing intelligent vehicles is applied to a balancing vehicle to realize autonomous tracing of the balancing vehicle. This device uses the STM32C8T6F103 chip as the main control chip, combined with the attitude sensor MPU6050, a new vision sensor OpenMV, and other peripheral drive circuits are used with the software program based on PID and Kalman filter. The result meet the design requirements for promotional applications.
{"title":"Design of Two-wheeled Self-balancing Traction Vehicle Based on OpenMV","authors":"Tongchen Lin, Guocai Zhang","doi":"10.1109/RCAE56054.2022.9995729","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995729","url":null,"abstract":"In this study, we design a two-wheeled self-balancing traction vehicle. The common scheme of camera collecting road information of autonomous tracing intelligent vehicles is applied to a balancing vehicle to realize autonomous tracing of the balancing vehicle. This device uses the STM32C8T6F103 chip as the main control chip, combined with the attitude sensor MPU6050, a new vision sensor OpenMV, and other peripheral drive circuits are used with the software program based on PID and Kalman filter. The result meet the design requirements for promotional applications.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131665699","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995845
Chenli Song, Lifeng Li, Lixia Zhu, Shuai Wang
Based on the comprehensive analysis of the complex structure and material characteristics of a large U-shaped heat exchanger, combined with the thin-shell heat transfer model and the similarity principle, the 3D geometric model of the heat exchanger of the original stabilizing device is constructed. Then, the grid size is greatly reduced by using boundary layer meshing technology. Finally, the temperature field and flow field distribution of the fluid in the heat exchanger are obtained by finite element calculation. The results show that, on the one hand, the condensate temperature is in a local overheating state and the oil flow rate is too low, and there is a retention zone; on the other hand, the temperature in the overheating region decreases with the increase of the shell flow rate. Therefore, the coupling effect of condensate oil retention and local overheating may accelerate the corrosion rate of heat exchanger tube bundle. It is suggested to adjust the operation parameters of the heat exchanger and optimize the internal structure to make the internal flow rate and temperature distribution more reasonable, so as to improve the service safety and reliability of the heat exchanger.
{"title":"Numerical Simulation Analysis of Flow and Temperature Fields in Large U-Shaped Heat Exchanger","authors":"Chenli Song, Lifeng Li, Lixia Zhu, Shuai Wang","doi":"10.1109/RCAE56054.2022.9995845","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995845","url":null,"abstract":"Based on the comprehensive analysis of the complex structure and material characteristics of a large U-shaped heat exchanger, combined with the thin-shell heat transfer model and the similarity principle, the 3D geometric model of the heat exchanger of the original stabilizing device is constructed. Then, the grid size is greatly reduced by using boundary layer meshing technology. Finally, the temperature field and flow field distribution of the fluid in the heat exchanger are obtained by finite element calculation. The results show that, on the one hand, the condensate temperature is in a local overheating state and the oil flow rate is too low, and there is a retention zone; on the other hand, the temperature in the overheating region decreases with the increase of the shell flow rate. Therefore, the coupling effect of condensate oil retention and local overheating may accelerate the corrosion rate of heat exchanger tube bundle. It is suggested to adjust the operation parameters of the heat exchanger and optimize the internal structure to make the internal flow rate and temperature distribution more reasonable, so as to improve the service safety and reliability of the heat exchanger.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131685084","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995967
Haiyang Cao, Yongting Deng, Hongwen Li, Jianli Wang, Xiufeng Liu
This paper presents a modified active disturbance rejection controller (MADRC) based on a modified extended state observer (MESO) for PMSM speed control. The presented MESO introduces a cascade structure based on traditional ESO (TESO) to avoid using high gain for disturbance rejection. The advantages of MESO compared to TESO are analyzed from the perspective of frequency domain. The analysis results show that MESO can improve the noise immunity performance while maintaining the anti-disturbance performance of TESO. The simulation results indicate that the proposed MADRC behaves better than the PI controller and the TADRC.
{"title":"An Active Disturbance Rejection Control Based on Modified Extended State Observer for PMSM Speed Control Considering Measurement Noise","authors":"Haiyang Cao, Yongting Deng, Hongwen Li, Jianli Wang, Xiufeng Liu","doi":"10.1109/RCAE56054.2022.9995967","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995967","url":null,"abstract":"This paper presents a modified active disturbance rejection controller (MADRC) based on a modified extended state observer (MESO) for PMSM speed control. The presented MESO introduces a cascade structure based on traditional ESO (TESO) to avoid using high gain for disturbance rejection. The advantages of MESO compared to TESO are analyzed from the perspective of frequency domain. The analysis results show that MESO can improve the noise immunity performance while maintaining the anti-disturbance performance of TESO. The simulation results indicate that the proposed MADRC behaves better than the PI controller and the TADRC.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132918138","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 : 2022-10-28DOI: 10.1109/RCAE56054.2022.9995920
Dongnan Su, Cuihong Wu, Xijia Tao, Lei Wang, Yongfu Hai, Yang Cong
The body corbel is the link of traction transmission between train and bogie. It is a key component on the car body that bears both tensile and compressive loads. Its strength and stiffness have an important impact on the safety and reliability of vehicle operation. In this paper, according to the structural and technological requirements of aluminum alloy corbel products,A research plan for an automated welding system with high productivity and good welding quality was developed. Through the comparison of welding quality between manual welding and automatic welding system, the advantages of automatic welding system are summarized.
{"title":"Application of Automatic Welding System on Aluminum Alloy Corbel","authors":"Dongnan Su, Cuihong Wu, Xijia Tao, Lei Wang, Yongfu Hai, Yang Cong","doi":"10.1109/RCAE56054.2022.9995920","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995920","url":null,"abstract":"The body corbel is the link of traction transmission between train and bogie. It is a key component on the car body that bears both tensile and compressive loads. Its strength and stiffness have an important impact on the safety and reliability of vehicle operation. In this paper, according to the structural and technological requirements of aluminum alloy corbel products,A research plan for an automated welding system with high productivity and good welding quality was developed. Through the comparison of welding quality between manual welding and automatic welding system, the advantages of automatic welding system are summarized.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"734 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132409638","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}
In this paper, a control system is designed for SLPM (Spherical-Linkage Parallel Mechanism) based deployable robot to realize the robot's functions based on the parameters collected by the sensors. The motion planning of obstacle avoidance was completed and the corresponding line driven control was proposed. The prototype was fabricated and experimentally verified. Thus, the characteristics of the deployable robot adaptable to various complex environments were fully exploited.
{"title":"Control and Obstacle Avoidance for Deployable Robot Based on SLPM","authors":"Zheming Zhuang, Ze-Sheng Zhang, Yuntao Guan, Yong-Xin Liu, Erke Qin, Jiansheng Dai","doi":"10.1109/RCAE56054.2022.9995811","DOIUrl":"https://doi.org/10.1109/RCAE56054.2022.9995811","url":null,"abstract":"In this paper, a control system is designed for SLPM (Spherical-Linkage Parallel Mechanism) based deployable robot to realize the robot's functions based on the parameters collected by the sensors. The motion planning of obstacle avoidance was completed and the corresponding line driven control was proposed. The prototype was fabricated and experimentally verified. Thus, the characteristics of the deployable robot adaptable to various complex environments were fully exploited.","PeriodicalId":165439,"journal":{"name":"2022 5th International Conference on Robotics, Control and Automation Engineering (RCAE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117137650","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：