{"title":"Integrated Forecasting Models Based on LSTM and TCN for Short-Term Electricity Load Forecasting","authors":"Kewen Zuo","doi":"10.1109/EECR56827.2023.10149951","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10149951","url":null,"abstract":"Electricity load forecasting is an important prerequisite for ensuring the stability and reliability of regional power systems. Researchers have proposed many combined forecasting models, but most of them cannot capture the global characteristics of the data properly. To further improve the accuracy of short-term power load forecasting, this paper proposes a combined forecasting model based on long short-term memory (LSTM) and temporal convolutional network (TCN). For the electricity load data, the LSTM forecasting model and TCN forecasting model are first established, and then the output results of LSTM and TCN are weighted together according to the inverse squared error ratio to obtain the combined LSTM-TCN forecasting model. The LSTM-TCN model has more advanced model performance and its error is significantly lower than that of the single forecasting model and other classical network models. The results show that the LSTM-TCN model has higher accuracy in short-term load forecasting.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121236155","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}
{"title":"Improved Golden Jackal Optimization-based 3D Path Planning of UAV in Distribution Network Inspection","authors":"Zhisheng Chen, Tao Zhou, Junjun Jiao","doi":"10.1109/EECR56827.2023.10149983","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10149983","url":null,"abstract":"This paper proposes an improved Golden Jackal optimization (IGJO) to solve the three-dimensional path planning of unmanned aerial vehicle (UAV) in the complex inspection environment of distribution network. The proposed Golden Jackal observation strategy improves the location update formula by considering the boundary information of the search space of the solution. At the same time, a balanced renewal mechanism is proposed to enhance the ability of the population to jump out of the local extremum. According to the inspection task and environment characteristics of distribution network of UAV, the fitness function model of route planning is constructed, and a three-dimension (3D) simulation map model is built. The effect of IGJO is verified by two groups of simulation experiments. The experimental results show that IGJO has better solution quality, good algorithm robustness and fast convergence characteristics, which verify the feasibility and superiority of IGJO in solving complex 3D path planning problems.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134459722","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}
Tingyu Fei, Shiyang Liu, J. Luo, Biwei Tang, Muye Pang, Kui Xiang, Zhongbai Lu
{"title":"Mechanical Structure and Motion Analysis of Supernumerary Robotic Limb","authors":"Tingyu Fei, Shiyang Liu, J. Luo, Biwei Tang, Muye Pang, Kui Xiang, Zhongbai Lu","doi":"10.1109/EECR56827.2023.10150040","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10150040","url":null,"abstract":"In this paper, a three degrees-of-freedom (DOFs) Supernumerary Robotic Limb (SRL) with simple structure and easy wearable character is designed. Firstly, modified DenavitHartenberg model of three-DOFs SRL is constructed. And then forward and inverse solutions of its kinematics model are obtained, and the results of kinematics model are verified. In addition, Monte Carlo method is used for solving the issue of SRL workspace, and a simulated SRL is modeled in Recurdyn simulation platform according to the actual parameters. By planning a path for the SRL, the position of the end effector and the torque of each joint can be obtained.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115944246","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}
Xiaobin Li, Yuxin Zhang, Yi Peng, Wenqing Zhang, Shiyue Zhang, Xuefang Li
{"title":"Reinforcement Learning-Based Energy Management for Plug-in Hybrid Electric Vehicles","authors":"Xiaobin Li, Yuxin Zhang, Yi Peng, Wenqing Zhang, Shiyue Zhang, Xuefang Li","doi":"10.1109/EECR56827.2023.10150124","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10150124","url":null,"abstract":"In this work, two reinforcement-learning-based energy management strategies are investigated for plug-in hybrid electric vehicles (PHEVs). The strategies are developed based on the Toyota Prius model, for which the dynamics are firstly established. Then, both the deep Q-learning (DQN) and deep deterministic policy gradient (DDPG) algorithms are formulated based on the vehicle model. Furthermore, to verify the effectiveness, the reinforcement-learning-based strategies are also benchmarked against the dynamic programming under the New European Driving Cycle (NEDC). The simulation results indicate that the DQN and DDPG algorithms lag the global optimizationbased DP by around 9% and 4% in fuel efficiency, respectively.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116111561","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}
{"title":"Two-wheeled Robot Motion Planning Based on A* Algorithm with Anti-collision Mechanism and Immune Algorithm with Cloning Mechanism","authors":"Bingzheng Jiang, Lin Xu, Dinghui Xie","doi":"10.1109/EECR56827.2023.10149909","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10149909","url":null,"abstract":"The two-wheeled robot motion control and route planning are studied from two perspectives. Firstly, based on the simplified model and basic data assumptions of the two-wheeled robot, a set of dynamics equations based on the basic mechanics of the robot is derived. Then a three-dimensional motion model based on the Newton Euler method is further established to derive a set of differential equations. After that, a two-wheeled robot motion planning model based on the A* algorithm with anti-collision mechanism and the immune algorithm with cloning mechanism is proposed by analyzing the ergonomics, safety, rationality and stability. In order to further consider the rationality, stability comprehensively and combine the characteristics that the shortest motion trajectory consists of a series of unit displacement points, a multi-objective motion planning evaluation function is constructed, and the clone-immune algorithm is used for the optimal solution, so as to derive the optimal velocity, acceleration, vehicle inclination angle, and vehicle inclination velocity on each displacement point. Finally, the transformed relations are imported into the simulation model constructed by Simulink to obtain the relational curves that yield the variation of the torque on the wheels with time, which leads to the robot motion control strategy for the robot operating environment map.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123692964","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}
Wei Shuai, Yang Gao, Peichen Wu, Guowei Cui, Xiaoping Chen
{"title":"Sample-Based Passively Compliant Manipulation for Senserless Contact-Rich Scenarios with Uncertainties","authors":"Wei Shuai, Yang Gao, Peichen Wu, Guowei Cui, Xiaoping Chen","doi":"10.1109/EECR56827.2023.10150153","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10150153","url":null,"abstract":"In this paper, we present a novel incremental approach to addressing uncertainty in robotic manipulation tasks for contact-rich environments. Traditional methods in contact-rich environments often rely on continuous perception, force/torque sensors and high-frequency controllers. The key idea of our approach is leveraging the passive deformation of flexible components as a feedback mechanism to generate passively adaptable trajectories that can cope with uncertainty. Our algorithm focused on planning the high-level trajectory and introduced the path planning problem in the deviation-fusion process. Our approach doesn’t require high-frequency controllers, force/torque sensors, and high-precision simulation. Instead, we incorporate errors into uncertainties to ensure the validity of our common planned trajectories even if the environment’s state is not perfectly obtained.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128093206","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}
Gang Zhang, Shan Li, Jianqiang Dai, Long Zhao, Yang Liu, Liang Wei, Shih-ying Wang
{"title":"Probability Prediction of Transient Current-carrying Capacity of the Overhead Conductor with the Consideration of the Correlation of Conductor Temperature and Meteorological Elements","authors":"Gang Zhang, Shan Li, Jianqiang Dai, Long Zhao, Yang Liu, Liang Wei, Shih-ying Wang","doi":"10.1109/EECR56827.2023.10149913","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10149913","url":null,"abstract":"The prediction of the transient current-carrying capacity (TCCC) of the overhead conductor is of great significance for conducting corrective control of the power system. At present, the research on the prediction of the TCCC does not take into account the correlation of conductor temperature and meteorological elements in the allowable temperature rise time, which will lead to the inaccuracy of the prediction results. In this paper, a probability prediction method for TCCC of the overhead conductor considering the correlation of conductor temperature and meteorological elements in the prediction period is proposed. Specifically, probability density functions of the initial conductor temperature and meteorological elements in the target period are first predicted based on the quantile regression long short-term memory (QRLSTM) model, and the correlation processing is conducted based on rank correlation theory. Then the probability distribution of the TCCC of the overhead conductor is predicted by the thermal dynamic process simulation. The case study shows that compared with the traditional method, the proposed method can significantly improve the prediction results.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131202509","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}
{"title":"Semantic and Moving Object Segmentation-assisted LiDAR Odometry and Mapping","authors":"Fei Wang, Chao Sun, Guoqi Zhong, Weiqiang Liang","doi":"10.1109/EECR56827.2023.10150083","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10150083","url":null,"abstract":"For autonomous vehicles, Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities. Accurate and reliable SLAM are important for autonomous vehicles. In this work, we propose a novel LiDAR odometry and mapping method assisted by semantic segmentation and moving object segmentation. First, to acquire semantic information of point clouds and distinguish moving objects, a framework for segmenting LiDAR point clouds is proposed. Then an effective method for integrating semantic information and moving object information into feature-based LiDAR SLAM is proposed. With the assistance of semantic information and moving object information, moving points are filtered out, and semantic constrains are added in feature extraction and pose estimation to improve the localization accuracy. The experiment results on public datasets show that, compared to the baseline, the average relative pose estimation error of our proposed method is reduced by21.4% in rotation and 29.4% in translation.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128364971","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}
{"title":"Output Power Design of Wave Energy Conversion Device Based on Vertical Oscillation-longitudinal Rocking Coupling","authors":"Wenxin Ye, Zheng Tang","doi":"10.1109/EECR56827.2023.10149963","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10149963","url":null,"abstract":"As a renewable and clean energy source, the utilization and conversion of wave energy has received more and more attention. For the oscillating float type wave energy conversion device, this paper conducts force analysis and moment analysis from four degrees of freedom of the float and the oscillator’s vertical oscillation and longitudinal rocking, establishes a system of second-order differential equations for the coupled vertical oscillation-longitudinal rocking, and analyzes the vertical oscillation displacement and velocity and the longitudinal rocking angular displacement and angular velocity of the float and the oscillator. The improved whale algorithm is used to solve the bivariate single-objective programming model with the damping coefficients of two dampers as the decision variables and the sum of the maximum average output power as the objective function, and the global search capability of the algorithm is improved by convergence factor update and simplex method optimization, which effectively avoids the local optimal solution and makes the results more accurate and reliable.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125573097","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}
{"title":"Optimal Design of Cylindrical Coils with a High Uniformity Magnetic Field","authors":"Weiqian Wang, Xiangyang Zhou, Fengwen Zhao, Xiaoxuan Xie","doi":"10.1109/EECR56827.2023.10150125","DOIUrl":"https://doi.org/10.1109/EECR56827.2023.10150125","url":null,"abstract":"In order to meet the requirement of high uniformity magnetic field in atomic magnetometer and magnetocardiography system, an optimal design method of cylindrical coils with a high uniformity magnetic field is proposed in this paper. Firstly, the expression of the magnetic field generated by the cylindrical coils at any point is derived. Then, taking the absolute value of magnetic field error in the target area as the objective function, combined with the wolf pack algorithm, the loop position and current of the coils are directly adjusted, which avoids the problem of solving complex equations by the traditional Taylor expansion method. Finally, the high uniformity of the designed coil is verified by simulation. The results show that in the target area, compared with the LeeWhiting coil, the uniformity of the designed coil is increased by an order of magnitude, and the area of the magnetic field error less than 1× 1$0^{-5}$ is increased by 4.9 times.","PeriodicalId":338360,"journal":{"name":"2023 9th International Conference on Electrical Engineering, Control and Robotics (EECR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127735777","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}