Transformer-based correction scheme for short-term bus load prediction in holidays

To tackle the problem of inaccurate short-term bus load prediction,especially during holidays,a Transformer-based scheme with tailored architectural enhancements is proposed.First,the input data are clustered to reduce complexity and capture inherent characteristics more effectively.Gated residual connections are then employed to selectively propagate salient features across layers,while an attention mechanism focuses on identifying prominent patterns in multivariate time-series data.Ultimately,a pre-trained structure is incorporated to reduce computational complexity.Experimental results based on extensive data show that the proposed scheme achieves improved prediction accuracy over comparative algorithms by at least 32.00%consistently across all buses evaluated,and the fitting effect of holiday load curves is outstanding.Meanwhile,the pre-trained structure drastically reduces the training time of the proposed algorithm by more than 65.75%.The proposed scheme can efficiently predict bus load results while enhancing robustness for holiday predictions,making it better adapted to real-world prediction scenarios.

Seasonal Short-Term Load Forecasting for Power Systems Based onModal Decomposition and Feature-FusionMulti-Algorithm Hybrid Neural NetworkModel

To enhance the refinement of load decomposition in power systems and fully leverage seasonal change information to further improve prediction performance,this paper proposes a seasonal short-termload combination prediction model based on modal decomposition and a feature-fusion multi-algorithm hybrid neural network model.Specifically,the characteristics of load components are analyzed for different seasons,and the corresponding models are established.First,the improved complete ensemble empirical modal decomposition with adaptive noise(ICEEMDAN)method is employed to decompose the system load for all four seasons,and the new sequence is obtained through reconstruction based on the refined composite multiscale fuzzy entropy of each decomposition component.Second,the correlation between different decomposition components and different features is measured through the max-relevance and min-redundancy method to filter out the subset of features with strong correlation and low redundancy.Finally,different components of the load in different seasons are predicted separately using a bidirectional long-short-term memory network model based on a Bayesian optimization algorithm,with a prediction resolution of 15 min,and the predicted values are accumulated to obtain the final results.According to the experimental findings,the proposed method can successfully balance prediction accuracy and prediction time while offering a higher level of prediction accuracy than the current prediction methods.The results demonstrate that the proposedmethod can effectively address the load power variation induced by seasonal differences in different regions.

Mechanical behavior and failure mechanisms of rock bolts subjected to static-dynamic loads

This study explores the effects of dynamic and static loading on rock bolt performance a key factor in maintaining the structural safety of coal mine roadways susceptible to coal bursts.Employing a housemade load frame to simulate various failure scenarios,pretension-impact-pull tests on rock bolts were conducted to scrutinize their dynamic responses under varied static load conditions and their failure traits under combined loads.The experimental results denote that with increased impact energy,maximum and average impact loads on rock bolts escalate significantly under pretension,initiating plastic deformation beyond a certain threshold.Despite minor reductions in the yield load due to impactinduced damage,pretension aids in constraining post-impact deformation rate and fluctuation degree of rock bolts.Moreover,impact-induced plastic deformation causes internal microstructure dislocation,fortifying the stiffness of the rock bolt support system.The magnitude of this fortification is directly related to the plastic deformation induced by the impact.These findings provide crucial guidance for designing rock bolt support in coal mine roadway excavation,emphasizing the necessity to consider both static and dynamic loads for improved safety and efficiency.

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.

Energy mechanism of bolt supporting effect to fissured rock under static and dynamic loads in deep coal mines

The stability control of fissured rock is difficult,especially under static and dynamic loads in deep coal mines.In this paper,the dynamic mechanical properties,strain rate evolution and energy dissipation of fissured and anchored rocks were respectively obtained by SHPB tests.It was found that bolt can provide supporting efficiency-improving effect for fissured rock against dynamic disturbance,and this effect increased quadratically with decrease in anchoring angles.Then,the energy dissipation mechanism of anchored rock was obtained by slipping model.Furthermore,bolt energy-absorbing mechanism by instantaneous tensile-shear deformation was expressed based on material mechanics,which was the larger the anchoring angle,the smaller the energy absorption,and the less the contribution to supporting efficiency improvement.On this basis,the functional relationship between energy dissipation of anchored rock and energy absorption of bolt was established.Taking the coal-gangue separation system of Longgu coal mine as an example,the optimal anchoring angle can be determined as 57.5°–67.5°.Field monitoring showed fissured rock with the optimal anchoring angle,can not only effectively control the deformation,but also fully exert the energy-absorbing and efficiency-improving effect of bolt itself.This study provides guidance to the stability control and supporting design for deep engineering under the same or similar conditions.

A novel approach to the dynamic response analysis of Euler-Bernoulli beams resting on a Winkler soil model and subjected to impact loads

This work presents a novel approach to the dynamic response analysis of a Euler-Bernoulli beam resting on a Winkler soil model and subjected to an impact loading.The approach considers that damping has much less importance in controlling the maximum response to impulsive loadings because the maximum response is reached in a very short time,before the damping forces can dissipate a significant portion of the energy input into the system.The development of two sine series solutions,relating to different types of impulsive loadings,one involving a single concentrated force and the other a distributed line load,are presented.This study revealed that when a simply supported Euler-Bernoulli beam,resting on a Winkler soil model,is subject to an impact load,the resulting vertical displacements,bending moments and shear forces produced along the span of the beam are considerably affected.In particular,the quantification of this effect is best observed,relative to the corresponding static solution,via an amplification factor.The computed impact amplification factors,for the sub-grade moduli used in this study,were in magnitude greater than 2,thus confirming the multiple-degree-of-freedom nature of the problem.

Numerical analysis of geosynthetic-reinforced embankment performance under moving loads

The performance of geosynthetic-reinforced embankments under traffic moving loads is always a hotspot in the geotechnical engineering field.A three-dimensional(3D)model of a geosynthetic-reinforced embankment without drainage consolidation was established using the finite element software ABAQUS.In this model,the traffic loads were simulated by two moving loads of rectangular pattern,and their amplitude,range,and moving speed were realized by a Fortran subroutine.The embankment fill was simulated by an equivalent linear viscoelastic model,which can reflect its viscoelasticity.The geogrid was simulated by the truss element,and the geocell was simulated by the membrane element.Infinite elements were utilized to weaken the boundary effect caused by the model geometry at the boundaries.Validation of the established numerical model was conducted by comparing the predicted deformations in the cross-section of the geosynthetic-reinforced embankment with those from the existing literature.On this basis,the dynamic stress and strain distribution in the pavement structure layer of the geosynthetic-reinforced embankment under a moving load was also analyzed.Finally,a parametric study was conducted to examine the influences of the different types of reinforcement,overload,and the moving load velocity on the geosynthetic-reinforced embankment.

Similarity Criterion and Scale Effect for Ship Distortion Model Under Combined Loads

For the ultimate strength model test evaluation of large ship structures, the distortion model with non-uniform ratio between the main size and the plate thickness size is usually adopted. It is the key to carry out scale model test to establish a distortion model similar to the real ship structure under combined load. A similarity criterion for ship distortion model under the combined action of bending moment and surface pressure was proposed, and the scale effect for the criterion was verified by a se ries of numerical analysis and model tests. The results show that the similarity criterion for ship distor tion model under combined loads has a certain scale effect. For the model tests of ship cabin struc tures, it is suggested that the scale range between the plate thickness scale and the main dimension scale should be controlled within 2:1, which can be used as a reference for distortion model design and ultimate strength test of large-scale ship structures.

Loads and Dynamic Response Characteristic on FPSO Under Internal Solitary Waves

According to the established prediction model of internal solitary wave loads on FPSO in the previous work,the lumped mass model and the movement equations of finite displacement in time domain,the dynamic response model of interaction between internal solitary waves and FPSO with mooring lines were established.Through calculations and analysis,time histories of dynamic loads of FPSO exerted by internal solitary waves,FPSO’s motion and dynamic tension of mooring line were obtained.The effects of the horizontal pretension of mooring line,the amplitude of internal solitary wave and layer fluid depth on dynamic response behavior of FPSO were mastered.It was shown that the internal solitary waves had significant influence on FPSO,such as the large magnitude horizontal drift and a sudden tension increment.With internal solitary wave of −170 m amplitude in the ocean with upper and lower layer fluid depth ratio being 60:550,the dynamic loads reached 991.132 kN(horizontal force),18067.3 kN(vertical force)and−5042.92 kN·m(pitching moment).Maximum of FPSO’s horizontal drift was 117.56 m.Tension increment of upstream mooring line approached 401.48 kN and that of backflow mooring line was−140 kN.Moreover,the loads remained nearly constant with different pretension but increased obviously with the changing amplitude and layer fluid depth ratio.Tension increments of mooring lines also changed little with the pretension but increased rapidly when amplitude and layer fluid depth ratio increased.However,FPSO’s motion increased quickly with not only the horizontal pretension but also the amplitude of internal solitary wave and layer fluid depth ratio.

Investigating Periodic Dependencies to Improve Short-Term Load Forecasting

With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power grids.The electrical load series exhibit periodic patterns and share high associations with metrological data.However,current studies have merely focused on point-wise models and failed to sufficiently investigate the periodic patterns of load series,which hinders the further improvement of short-term load forecasting accuracy.Therefore,this paper improved Autoformer to extract the periodic patterns of load series and learn a representative feature from deep decomposition and reconstruction.In addition,a novel multi-factor attention mechanism was proposed to handle multi-source metrological and numerical weather prediction data and thus correct the forecasted electrical load.The paper also compared the proposed model with various competitive models.As the experimental results reveal,the proposed model outperforms the benchmark models and maintains stability on various types of load consumers.

Finite element modeling and injury criteria investigation for the lower leg of the Chinese human body under impact loads

The widely used human body injury criteria were established based on the biomechanical response of the EuroAmerican human body,without considering the differences in anthropometry and injury characteristics among different races,particularly the Chinese human body which typically has the smaller body size.The absence of such race specific design considerations negatively influences the injury prevention capability for these populations,and weakens the applicability of injury criteria.To resolve these issues,this study aims to develop a lower leg finite element model of a 50th percentile Chinese male.The model is built based on the medical images of an average size Chinese male with detailed ankle ligaments and lower leg muscles modeled.Data from sixty experiments available in the literature are used to validate its biofidelity.Using the validated model,the lower leg model is subjected to combined axial compression and bending loads to evaluate its injury criteria.Compared with a typical Euro-American human body mode,the Chinese lower leg presents reduced mechanical tolerance,and the revised tibia index may be an appropriate injury criteria for the Chinese lower leg.Additionally,the validated model reproduces the pedestrian lower leg fracture in a domestic accident.

Modelling dynamic pantograph loads with combined numerical analysis

Appropriate interaction between pantograph and catenary is imperative for smooth operation of electric trains.Changing heights of overhead lines to accommodate level crossings,overbridges,and tunnels pose significant challenges in maintaining consistent current collection performance as the pantograph aerodynamic profile,and thus aerodynamic load changes significantly with operational height.This research aims to analyse the global flow characteristics and aerodynamic forces acting on individual components of an HSX pantograph operating in different configurations and orientations,such that the results can be combined with multibody simulations to obtain accurate dynamic insight into contact forces.Specifically,computational fluid dynamics simulations are used to investigate the pantograph component loads in a representative setting,such as that of the recessed cavity on a Class 800 train.From an aerodynamic perspective,this study indicates that the total drag force acting on non-fixed components of the pantograph is larger for the knuckle-leading orientation rather than the knuckle-trailing,although the difference between the two is found to reduce with increasing pantograph extension.Combining the aerodynamic loads acting on individual components with multibody tools allows for realistic dynamic insight into the pantograph behaviour.The results obtained show how considering aerodynamic forces enhance the realism of the models,leading to behaviour of the pantograph-catenary contact forces closely matching that seen in experimental tests.

Data-Driven Modeling for Wind Turbine Blade Loads Based on Deep Neural Network

Blades are essential components of wind turbines.Reducing their fatigue loads during operation helps to extend their lifespan,but it is difficult to quickly and accurately calculate the fatigue loads of blades.To solve this problem,this paper innovatively designs a data-driven blade load modeling method based on a deep learning framework through mechanism analysis,feature selection,and model construction.In the mechanism analysis part,the generation mechanism of blade loads and the load theoretical calculationmethod based on material damage theory are analyzed,and four measurable operating state parameters related to blade loads are screened;in the feature extraction part,15 characteristic indicators of each screened parameter are extracted in the time and frequency domain,and feature selection is completed through correlation analysis with blade loads to determine the input parameters of data-driven modeling;in the model construction part,a deep neural network based on feedforward and feedback propagation is designed to construct the nonlinear coupling relationship between the unit operating parameter characteristics and blade loads.The results show that the proposed method mines the wind turbine operating state characteristics highly correlated with the blade load,such as the standard deviation of wind speed.The model built using these characteristics has reasonable calculation and fitting capabilities for the blade load and shows a better fitting level for untrained out-of-sample data than the traditional scheme.Based on the mean absolute percentage error calculation,the modeling accuracy of the two blade loads can reach more than 90%and 80%,respectively,providing a good foundation for the subsequent optimization control to suppress the blade load.

Evaluation of the dynamic sealing performance of cap rocks of underground gas storage under multi-cycle alternating loads

The static sealing of underground gas storage(UGS),including the integrity of cap rocks and the stability of faults,is analyzed from a macro perspective using a comprehensive geological evaluation method.Changes in pore structure,permeability,and mechanical strength of cap rocks under cyclic loads may impact the rock sealing integrity during the injection and recovery phases of UGS.In this work,the mechanical deformation and failure tests of rocks,as well as rock damage tests under alternating loads,are conducted to analyze the changes in the strength and permeability of rocks under multiple-cycle intense injection and recovery of UGS.Additionally,this study proposes an evaluation method for the dynamic sealing performance of UGS cap rocks under multi-cycle alternating loads.The findings suggest that the failure strength(70%)can be used as the critical value for rock failure,thus providing theoretical support for determining the upper limit of operating pressure and the number of injection-recovery cycles for the safe operation of a UGS system.

ATwo-LayerOptimal Scheduling Strategy forRural Microgrids Accounting for Flexible Loads

In the context of China’s“double carbon”goals and rural revitalization strategy,the energy transition promotes the large-scale integration of distributed renewable energy into rural power grids.Considering the operational characteristics of rural microgrids and their impact on users,this paper establishes a two-layer scheduling model incorporating flexible loads.The upper-layer aims to minimize the comprehensive operating cost of the rural microgrid,while the lower-layer aims to minimize the total electricity cost for rural users.An Improved Adaptive Genetic Algorithm(IAGA)is proposed to solve the model.Results show that the two-layer scheduling model with flexible loads can effectively smooth load fluctuations,enhance microgrid stability,increase clean energy consumption,and balance microgrid operating costs with user benefits.

Influence of railway wheel tread damage on wheel-rail impact loads and the durability of wheelsets

Dynamic wheel-rail contact forces induced by a severe form of wheel tread damage have been measured by a wheel impact load detector during full-scale field tests at different vehicle speeds.Based on laser scanning,the measured three-dimensional damage geometry is employed in simulations of dynamic vehicle-track interaction to calibrate and verify a simulation model.The relation between the magnitude of the impact load and various operational parameters,such as vehicle speed,lateral position of wheel-rail contact,track stiffness and position of impact within a sleeper bay,is investigated.The calibrated model is later employed in simulations featuring other forms of tread damage;their effects on impact load and subsequent fatigue impact on bearings,wheel webs and subsurface initiated rolling contact fatigue of the wheel tread are assessed.The results quantify the effects of wheel tread defects and are valuable in a shift towards condition-based maintenance of running gear,and for general assessment of the severity of different types of railway wheel tread damage.

Research on Demand Response Potential of Adjustable Loads in Demand Response Scenarios

To address the issues of limited demand response data,low generalization of demand response potential evaluation,and poor demand response effect,the article proposes a demand response potential feature extraction and prediction model based on data mining and a demand response potential assessment model for adjustable loads in demand response scenarios based on subjective and objective weight analysis.Firstly,based on the demand response process and demand response behavior,obtain demand response characteristics that characterize the process and behavior.Secondly,establish a feature extraction and prediction model based on data mining,including similar day clustering,time series decomposition,redundancy processing,and data prediction.The predicted values of each demand response feature on the response day are obtained.Thirdly,the predicted data of various characteristics on the response day are used as demand response potential evaluation indicators to represent different demand response scenarios and adjustable loads,and a demand response potential evaluation model based on subjective and objective weight allocation is established to calculate the demand response potential of different adjustable loads in different demand response scenarios.Finally,the effectiveness of the method proposed in the article is verified through examples,providing a reference for load aggregators to formulate demand response schemes.

The loaded matrix:neurotrophin-enriched hydrogels for stem cell brain repair in Parkinson's disease

More than 200 years after Parkinson's disease was first described by the English surgeon whose name would eventually be given to the condition,available treatments remain purely symptomatic,leaving a critical unmet clinical need for a diseasemodifying therapy.

High Fe‑Loading Single‑Atom Catalyst Boosts ROS Production by Density Effect for Efficient Antibacterial Therapy

The current single-atom catalysts(SACs)for medicine still suffer from the limited active site density.Here,we develop a synthetic method capable of increasing both the metal loading and mass-specific activity of SACs by exchanging zinc with iron.The constructed iron SACs(h^(3)-FNC)with a high metal loading of 6.27 wt%and an optimized adjacent Fe distance of~4 A exhibit excellent oxidase-like catalytic performance without significant activity decay after being stored for six months and promising antibacterial effects.Attractively,a“density effect”has been found at a high-enough metal doping amount,at which individual active sites become close enough to interact with each other and alter the electronic structure,resulting in significantly boosted intrinsic activity of single-atomic iron sites in h^(3)-FNCs by 2.3 times compared to low-and medium-loading SACs.Consequently,the overall catalytic activity of h^(3)-FNC is highly improved,with mass activity and metal mass-specific activity that are,respectively,66 and 315 times higher than those of commercial Pt/C.In addition,h^(3)-FNCs demonstrate efficiently enhanced capability in catalyzing oxygen reduction into superoxide anion(O_(2)·^(−))and glutathione(GSH)depletion.Both in vitro and in vivo assays demonstrate the superior antibacterial efficacy of h^(3)-FNCs in promoting wound healing.This work presents an intriguing activity-enhancement effect in catalysts and exhibits impressive therapeutic efficacy in combating bacterial infections.

Resilience of coastal bridges under extreme wave-induced loads

Records of wave-induced damage on coastal bridges during natural hazards have been well documented over the past two decades.It is of utmost importance to decipher the loading mechanism and enhance the resilience of coastal bridges during extreme wave-inducing events.Quantification of vulnerability of these structures is an essential step in designing a resilient bridge system.Recently,considerable efforts have been made to study the force applied and the response of coastal bridge systems during extreme wave loading conditions.Although remarkable progress can be found in the quantification of load and response of coastal superstructures,very few studies assessed coastal bridge resiliency against extreme wave-induced loads.This paper adopts a simplified and practical technique to analyze and assess the resilience of coastal bridges exposed to extreme waves.Component-level and system-level fragility analyses form the basis of the resiliency analysis where the recovery functions are adopted based on the damage levels.It is shown that wave period has the highest contribution to the variation of bridge resiliency.Moreover,this study presents the uncertainty quantification in resiliency variation due to changes in wave load intensity.Results show that the bridge resiliency becomes more uncertain as the intensity of wave parameters increases.Finally,possible restoration strategies based on the desired resilience level and the attitude of decision-makers are also discussed.