Intraday economic optimal dispatch of distribution networks based on fuzzy set predictionZhang, Chunyu; Zhang, Maosong; Wu, Di; Yang, Jie; Zhao, Hongsheng; Zhang, Luyao
doi: 10.1088/1742-6596/2963/1/012004pmid: N/A
Aiming at the uncertainty problem of electric vehicle charging and discharging, this paper proposes an intraday scheduling model and its solution method based on fuzzy set theory and an improved subtraction optimizer algorithm. The charging station dispatchable resource prediction model is constructed based on event-wise fuzzy set theory. On this basis, the intraday optimal scheduling model is constructed by comprehensively utilizing the dispatchable resources of the charging station to collaborate with the photovoltaic and energy storage outputs and is solved by the improved subtractive optimizer algorithm to realize the optimal scheduling to minimize the operating cost. Finally, the effectiveness of the proposed method is demonstrated by simulation analysis based on the IEEE-33 node arithmetic system.
Motion path planning algorithm for dynamic graphics in visual artsZhang, Yingyu
doi: 10.1088/1742-6596/2963/1/012008pmid: N/A
Aiming at the problems of non-smooth motion and unnatural trajectory in motion path planning of dynamic graphics in visual arts, this paper proposes a path planning algorithm based on multi-stage optimization. Firstly, the initial motion path is fitted and smoothed by using Bezier curves to ensure that the motion trajectory of dynamic graphics has high continuity and naturalness. Next, a multi-objective optimization strategy based on a genetic algorithm is introduced to comprehensively optimize the path smoothness, motion speed change, and visual comfort through the adaptive evaluation function. Finally, a dynamic weight adjustment mechanism is adopted to adapt to the changes in the requirements of different visual scenes in real time. Specifically, the standard deviation of the curvature variation of the path generated by the multi-stage optimization-based path planning algorithm is 0.0459, which is much lower than that of the other two algorithms; the mean squared error (MSE) of the speed change rate is 0.65, which is significantly reduced compared with other methods; in the visual comfort test, the fixation point dwell time is 360 ms, which is significantly higher than other methods. The dynamic deviation is the lowest. Experimental data shows that the algorithm in this paper effectively solves the problem of unsmooth motion trajectories of dynamic graphics, significantly improves the naturalness and visual experience of the path, and proves the practicability and superiority of the algorithm in visual art creation.
Train delay prediction in Guangzhou-Shenzhen-Hong Kong High-speed Railway with improved CNN-LSTM ModelWang, Haoyu; Wang, Yuqing; Song, Ziyi; Shang, Hengchen; Zhai, Tianyu
doi: 10.1088/1742-6596/2963/1/012003pmid: N/A
To address the issue of enhancing the accuracy of delay predictions for high-speed trains, a novel model based on CNN and LSTM architectures has been proposed. This model incorporates the KAN model to supplant the traditional fully connected layer, thereby augmenting the model’s predictive accuracy. The proposed architecture comprises three primary layers: the CNN layer, which is tasked with processing spatial features; the LSTM layer, which serves as the core of the model and is dedicated to the analysis of time series data; and the KAN layer, which replaces the fully connected layer to generate the output results. Additionally, an integrated feature selection algorithm has been developed to identify relevant features, with the selected feature variables subsequently input into the CNN-LSTM-KAN model. Experiments conducted on the Guangzhou-Shenzhen-Hong Kong (GSH) high-speed Railway dataset from early 2020 demonstrate that our CNN-LSTM-KAN model surpasses the performance of XGBoost, SVR, BiLSTM, and CNN-LSTM models, as indicated by the metrics of MAE, RMSE, and R-squared. The model’s prediction accuracy within a three-minute error margin reached as high as 96.11%, which is an improvement of 5.8% compared to the highest accuracy without the KAN layer.
Super twisting algorithm for power conversion system based on LCL filterLi, Chao; Gao, Ning
doi: 10.1088/1742-6596/2963/1/012026pmid: N/A
New energy represented by wind and solar energy is often used in conjunction with energy storage devices due to its changing characteristics. For the three-phase two-level power conversion system (PCS), a super twisting algorithm (STA) control strategy based on the system error model is proposed in this paper. This method can maintain the quality of the grid current when the grid has large harmonics; it can operate in different modes to meet different power factor requirements. The proposed method has high parameter robustness and can resist the parameter drift of components. Theoretical analysis and simulation results prove the correctness of the proposed control strategy.
Low-temperature drift and high-accuracy MEMS pressure sensor with inverted package structureWang, Shengqi; Shi, Zhou; Han, Xiangguang; Zhao, Libo; Wang, Jiuhong
doi: 10.1088/1742-6596/2963/1/012025pmid: N/A
For the application requirements in the temperature range of-40 to 150°C, A pressure sensor with high accuracy and low-temperature drift has been developed by using MEMS (MEMS, Micro-Electro-Mechanical System) technology and SOI (Silicon-On-Insulator) substrate. The silica isolation of SOI is utilized to address the electrical failure of the force-sensitive chip at elevated temperatures. The ion implantation process was optimized to reduce output drift and accuracy drift of the chip with temperature. The back bottom pressure-bearing flushed package structure is designed, and the glass sintering process is used to reduce the lumen effect and improve the frequency response and anti-interference capability of the sensor. The test results show that the sensor has an accuracy error of ±0.2% of Full Scale (FS) over the temperature range of -40 to 150°C. The sensor displays the thermal sensitivity drift of -0.07% FS and the thermal zero drift of +0.006% FS.
Reconfiguration of distribution networks considering high penetration of renewable energy: an application of the QPSO algorithmYang, Junwen; Ran, Fusheng; Xu, Bin; Zhong, Pengzhuang; Li, Fangfang
doi: 10.1088/1742-6596/2963/1/012009pmid: N/A
The increasing variety of distributed generation (DG) types introduces significant power fluctuations and uncertainties when integrated into the distribution network. This imposes significant challenges in ensuring the stability and safety of the power system. Flexible configuring the distribution network’s topology can reduce active power losses and improve node voltage levels. However, traditional heuristic algorithms often fall short when addressing the reconfiguration of distribution networks with multiple DG types. In this paper, an enhanced Quantum Particle Swarm Optimization (QPSO) algorithm is proposed for optimizing active power losses and minimizing node voltage deviations in the distribution network. Simulations conducted using the modified IEEE 33-node system as a case study demonstrate that the proposed algorithm effectively reconfigures distribution networks with various DG types. It significantly reduces network losses, enhances node voltage levels, and achieves high computational accuracy.
Research on indoor temperature and humidity coupling system based on fuzzy adaptive PD controlLi, Hui; Yang, Hao; Zhang, Suli; Miao, Jiahao
doi: 10.1088/1742-6596/2963/1/012032pmid: N/A
In this research, a fuzzy adaptive PD control approach is introduced for managing the coupled indoor temperature and humidity system. Initially, the mathematical framework of indoor temperature and humidity is analyzed. For the coupled system, a decoupling control strategy is introduced, which eliminates the mutual influence between temperature and humidity by incorporating decoupling components, thereby enabling the system to be equivalently controlled as two independent single-input single-output systems. Secondly, a fuzzy adaptive PD control method is employed to achieve parameter self-tuning. Finally, to assess the efficacy of the introduced control approach, the present study undertakes a simulation analysis, utilizing a medium-sized office as a case study. The outcomes of the simulation suggest that upon implementing the fuzzy adaptive PD control methodology, the modulation of indoor temperature and humidity achieves enhanced precision and swiftness, notably demonstrating greater robustness in the presence of disturbance signals.
An active distribution network optimization method considering new energy scenario access and electric vehicle transportation loadsHou, Yucheng; Hou, Yuxing; Shao, Yalin; Hu, Yingying; Wang, Yao; Ji, Zhe
doi: 10.1088/1742-6596/2963/1/012005pmid: N/A
China’s rapid renewable energy growth has introduced challenges to the stability and reactive power balance of distribution networks due to the uncertainty of wind and photovoltaic (PV) output and the integration of flexible transportation loads. To address these issues, this paper presents an optimization method for active distribution networks. A Monte Carlo-based scenario simulation and a fast scenario reduction technique are used to manage wind and PV uncertainty. Additionally, an optimization model for reactive power is developed to minimize active power losses and voltage deviations while integrating wind, PV, and transportation loads. The model, solved via an improved second-order cone programming method using the GUROBI solver, optimizes transportation load configuration over time. Simulation results based on the IEEE 33-bus system show that the method enhances voltage quality and reduces network losses, achieving cost and efficiency improvements.
Research on fault diagnosis method of synchronous generator based on ResNet-18Xu, Jiancheng; Gao, Liming; Liu, Zhonghua; Yun, Qinsheng
doi: 10.1088/1742-6596/2963/1/012021pmid: N/A
Based on the excitation fault mechanism model of marine synchronous generators, this paper builds a synchronous generator model and simulates the output waveforms of voltage, current, and speed under different operating conditions. With the help of simulation data, the fault mechanism of synchronous generators is analyzed, and the mathematical morphological features in the output waveforms of synchronous generators are extracted using neural networks. A fault diagnosis model for marine synchronous generators based on the ResNet-18 residual neural network is established. Finally, the test simulation data is input into the fault diagnosis model to obtain the F1 score of the model, which has been verified to meet the accuracy requirements for internal fault diagnosis of marine synchronous generators.
Optimization of wind shear escape training for civil aviation pilot trainees via reinforcement learning and sequential pattern miningZhang, Yangyang; Gao, Zhenxing; Gu, Hongbin; Xiang, Zhiwei
doi: 10.1088/1742-6596/2963/1/012010pmid: N/A
In wind shear escape training, the operation manual-based operations, which were developed by experts in the field of civil aviation, obtained via qualitative analysis would perhaps cause untimely, redundant, omitted, and out-of-sequence operations when under complex conditions. To improve windshear escape training, this study starts with an actor-separated proximal policy optimization (ASPPO) algorithm to generate optimal agents, considering that operations in flight involve both discrete and continuous actions. Further based on the action sequence generated from the optimal agent, sequential pattern mining is used for quantitative analysis to obtain the maximum frequent action sequence. The results of the wind shear escape test, as an example, revealed that the optimal agent based on ASPPO could make an aircraft escape fast with stable attitudes. Meanwhile, the comparison of action sequences obtained from the PrefixSpan algorithm and pilot trainees indicated the imperfections in pilot trainees’ operations.