Short-Term Household Load Forecasting Based on Attention Mechanism and CNN-ICPSO-LSTM

Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.

Online Identification of Power Battery Parameters for Electric Vehicles Using a Decoupling Multiple Forgetting Factors Recursive Least Squares Method

Li-ion batteries are widely used in electric vehicles(EVs).However,the accuracy of online SOC estimation is still challenging due to the time-varying parameters in batteries.This paper proposes a decoupling multiple forgetting factors recursive least squares method(DMFFRLS)for EV battery parameter identification.The errors caused by the different parameters are separated and each parameter is tracked independently taking into account the different physical characteristics of the battery parameters.The Thevenin equivalent circuit model(ECM)is employed considering the complexity of battery management system(BMS)on the basis of comparative analysis of several common battery ECMs.In addition,decoupling multiple forgetting factors are used to update the covariance due to different degrees of error of each parameter in the identification process.Numerous experiments are employed to verify the proposed DMFFRLS method.The parameters for commonly used LiFePO4(LFP),Li(NiCoMn)O2(NCM)battery cells and battery packs are identified based on the proposed DMFFRLS method and three conventional methods.The experimental results show that the error of the DMFFRLS method is less than 15 mV,which is significantly lower than the conventional methods.The proposed DMFFRLS shows good performance for parameter identification on different kind of batteries,and provides a basis for state of charge(SOC)estimation and BMS design of EVs.

Study on Domestication of Ultra-Supercritical P92 Steel Pipe Fittings

P92 steel pipe fittings are key components for domestic ultra-supercritical power units. Although under booming development in some countries, presently only a few foreign units under commercial operation are using P92 steel and the experience on fabrication and operation of P92 steel pipe fittings is insufficient. The research on P92 steel pipe fittings is still in an initial stage in China. To turn the passive situation of relying on foreign products, an urgent task is to realize the domestication of P92 steel pipe fittings as early as possible.

Process Analysis of Double Circuit Transmission Line Trip-out on the Same Tower Due to Lightning

In recent years,several failures of double circuit transmission line on the same tower due to lightning were happened in Beijing power grid.Although it can be reclosed successful,the lightning strike caused a grave threat to the power grid security.The cause of the accident and the accident process were studied for the sake of further understanding of the impact of lightning on power grid.As an example,110 kV double circuit transmission line(Xilong-line) was analyzed.At first,the system topology was given.Through the analysis on relay protection actions and the fault recorder data,over voltage on the insulator strings was calculated.Based on the analysis and the calculation,accident cause and the process were presented respectively.Secondly,it comes to the conclusion that the lightning failure was caused by counterattack.The wave of the lightning over voltage would spread to the not grounded neutral point of the transformers,and make the neutral protective gap breakdown,then cause freewheeling with the frequency of 50 Hz.As results of the relay protection,the double circuit transmission line all tripped out.Finally,the causes of the accident were proposed that included terrain features,large corner towers,strong thunderstorm weather and poor grounded contact of the tower.

Model Free Adaptive Predictive Control of Desulfurization Slurry pH Based on CPS Framework

In order to improve the slurry pH control accuracy of the absorption tower in the wet flue gas desulfurization process,a model free adaptive predictive control algorithm for the desulfurization slurry pH which is based on a cyber physical systems framework is proposed.First,aiming to address system characteristics of non-linearity and pure hysteresis in slurry pH change process,a model free adaptive predictive control algorithm based on compact form dynamic linearization is proposed by combining model free adaptive control algorithm with model predictive control algorithm.Then,by integrating information resources with the physical resources in the absorption tower slurry pH control process,an absorption tower slurry pH optimization control system based on cyber physical systems is constructed.It is turned out that the model free adaptive predictive control algorithm under the framework of the cyber physical systems can effectively realize the high-precision tracking control of the slurry pH of the absorption tower,and it has strong robustness.

Evolution of In783 alloy in microstructure and properties enduring different service times

Impact, tensile, and fatigue tests were performed in In783 alloy serving 4000, 23,000 and 48,000 h. The microstructure was then analysed by optical microscopy(OM), scanning electron microscopy(SEM), and transmission electron microscopy(TEM) to probe the relationship between microstructure and properties. The results show that a new Ni_(5)Al_(3) phase is found, which grows gradually in β phase with serving time increasing,destroying the martensitic structure of the β phase, and degenerating the toughness of the β phase(approximately13.88% reduction). Therefore, the degradation of the βphase results in a sharp dropping of the resistance to stress accelerated grain boundary oxygen(SAGBO) during serving;thus, the intergranular fracture morphology degree increases with duration of service(almost 40% increase from the fractured surface). In addition, the strength of alloy will be gradually enhanced when the γ'phase becomes relatively bulky with serving time increasing due to considerable distortion of the dislocations as a result of the spacing of individual particles, in which any movement of the dislocation will have to overcome a larger number of obstacles per unit length.

Optimal Planning of Hybrid AC/DC Low-voltage Distribution Networks Considering DC Conversion of Three-phase Four-wire Low-voltage AC Systems

The increasing integration of distributed household photovoltaics(PVs)and electric vehicles(EVs)may further ag gravate voltage violations and unbalance of low-voltage distribu tion networks(LVDNs).DC distribution networks can increase the accommodation of PVs and EVs and mitigate mutilple pow er quality problems by the flexible power regulation capability of voltage source converters.This paper proposes schemes to es tablish hybrid AC/DC LVDNs considering the conversion of the existing three-phase four-wire low-voltage AC systems to DC op eration.The characteristics and DC conversion constraints of typical LVDNs are analyzed.In addition,converter configura tions for typical LVDNs are proposed based on the three-phase four-wire characteristics and quantitative analysis of various DC configurations.Moreover,an optimal planning method of hybrid AC/DC LVDNs is proposed,which is modeled as a bi-level programming model considering the annual investments and three-phase unbalance.Simulations are conducted to verify the effectiveness of the proposed optimal planning method.Sim ulation results show that the proposed optimal planning method can increase the integration of PVs while simultaneously reduc ing issues related to voltage violation and unbalance.

Coordinated Restoration Method for Electric Buses and Network Reconfigurations in Distribution Systems Under Extreme Events

Distribution systems are facing challenges in serving lifeline loads after extreme events.Network reconfiguration is a traditional and practical method for power supply restoration,which has strong but inflexible power transfer capabilities influenced by network topology.Multiple failures of utility power under extreme events will further limit the efficiency of network reconfiguration.Electric buses(EBs)can be utilized to achieve power supply considering their discharging capabilities as mobile storage devices.However,the mobility of EBs and the influences of transport systems must be carefully considered to enhance the resilience of distribution systems.Reconfiguration and EBs are complementary in terms of recovery capabilities and location flexibility,and more important loads can be recovered by the coordination between EBs and network reconfiguration.This paper proposes a coordinated restoration method for EBs and reconfigurations considering the influences of transport systems.The post-disaster restoration problem is formulated as a bi-level model,in which the network topology is optimized in the upperlevel aiming at maximizing restoration loads through the main grid and EBs,while the traffic paths of all EBs are optimized with the goal of maximizing the restoration loads by the EBs in the lower-level considering time consumption and energy consumption during movement.The PSO and a genetic algorithm are used to solve the proposed bi-level optimization problem.Simulation studies are performed to verify the superiority of the proposed method.

Operation, Analysis and Experiments of DC Transformers Based on Modular Multilevel Converters for HVDC Applications

This paper studies the operation,analysis and experiments of multilevel high frequency link transformers(MHFLT)based on modular multilevel converters(MMC)for high voltage DC applications.The multilevel dual active phase shift is proposed to operate the MHFLT using a high switching frequency,which brings about many advantages and makes the operation quite different from that of the traditional DC transformer(DCT)based on a dual active bridge and the fundamental frequency MMC widely used in flexible HVDC transmission.Specifically,MHFLT is suitable for high voltage levels,which is due to its good switching characterization,ability to cut itself off from an external fault,and it can also achieve redundancy operations when a sub-module fault occurs.In this paper,the operation,modulation method,multilevel high frequency link voltage,current,and power characterization,high frequency commutation,and switching characterization are analyzed comprehensively;the pulse rotation and distributed delay control,and fault handling strategies of MHFLT are then proposed.Finally,a prototype is built,and the experimental results verify the correctness and effectiveness of the proposed solution.

Creep behavior and damage evolution of T92/Super304H dissimilar weld joints

Creep tests of T92/Super304H joints were performed at 923 K under the stress of 85-165 MPa. Microstructure evolution was characterized by light microscopy, scanning electron microcopy and transmission electron microscopy to probe the relationship between creep performance deterioration and microstructure evolution. Results showed that for all the creep tests, failure occurred at fine-grained heat-affected zone of T92, and the joints have lower creep strength than the base metal T92. However, as the stress increased from 85 to 165 MPa, the creep fracture changed from a mixed mode, i.e., intergranular fracture in the center part and transgranular fracture in the edge part to total transgranular fracture. The longer the creep life, the greater is the proportion of the intergranular fracture. The M23C6 coarsened and the Laves phase precipitated along grain boundaries during long-term creep. Vacancies nucleate and propagate at the interface between coarse M23C6, Laves phase and matrix. Finally, cracks forming along grain boundaries are responsible for intergranular fracture.