Mapping Network-Coordinated Stacked Gated Recurrent Units for Turbulence Prediction

Accurately predicting fluid forces acting on the sur-face of a structure is crucial in engineering design.However,this task becomes particularly challenging in turbulent flow,due to the complex and irregular changes in the flow field.In this study,we propose a novel deep learning method,named mapping net-work-coordinated stacked gated recurrent units(MSU),for pre-dicting pressure on a circular cylinder from velocity data.Specifi-cally,our coordinated learning strategy is designed to extract the most critical velocity point for prediction,a process that has not been explored before.In our experiments,MSU extracts one point from a velocity field containing 121 points and utilizes this point to accurately predict 100 pressure points on the cylinder.This method significantly reduces the workload of data measure-ment in practical engineering applications.Our experimental results demonstrate that MSU predictions are highly similar to the real turbulent data in both spatio-temporal and individual aspects.Furthermore,the comparison results show that MSU predicts more precise results,even outperforming models that use all velocity field points.Compared with state-of-the-art methods,MSU has an average improvement of more than 45%in various indicators such as root mean square error(RMSE).Through comprehensive and authoritative physical verification,we estab-lished that MSU’s prediction results closely align with pressure field data obtained in real turbulence fields.This confirmation underscores the considerable potential of MSU for practical applications in real engineering scenarios.The code is available at https://github.com/zhangzm0128/MSU.

PREDICTION OF FATIGUE LIVES OF RC BEAMS STRENGTHENED WITH CFL UNDER RANDOM LOADING

The investigation on fatigue lives of reinforced concrete （RC） structures strength- ened with fiber laminate under random loading is important for the repairing or the strengthening of bridges and the safety of the traffic. In this paper, two methods are developed for predicting the fatigue lives of RC structures strengthened with carbon fiber [aminate （CFL） under random loading based on a residual life and a residual strength model. To discuss the efficiency of the model, 12 RC beams strengthened with CFL are tested under random loading by the MTS810 testing system. The predicted residual strength approximately agrees with test results.

Prediction of Rolling Load in Hot Strip Mill byInnovations Feedback Neural Networks

Because the structure of the classical mathematical model of rolling load is simple, even with the self-adapting technology, it is difficult to accommodate the increasing dimensional accuracy. Motivated by this fact, an Innovations Feedback Neural Networks （IFNN） was presented based on the idea of Kalman prediction. The neural networks used the Back Propagation （BP） algorithm and applied it to the prediction of rolling load in hot strip mill. The theoretical results and the off-line simulation show that the prediction capability of IFNN is better than that of normal BP networks, namely, for the prediction of the rolling load in hot strip mill, the prediction precision of IFNN is higher than that of normal BP networks. Finally, a relative complete rolling load prediction system was developed on Windows 2003/XP platform using the OOP programming method and the SQL server2000 database. With this sys- tem, the rolling load of a 1700 strip mill was calculated, and the prediction results obtained correspond well with the field data. It shows that IFNN is valid for rolling load prediction.

Prediction of Load Carrying Capacity of Corroded Reinforced Concrete Beam

A novel method for prediction of the load carrying capacity of a corroded reinforced concrete beam (CRCB) is presented in the paper. Nine reinforced concrete beams, which had been working in an aggressive environment for more than 10 years, were tested in the laboratory. Comprehensive tests, including flexural test, strength test for corroded concrete and rusty rebar, and pullout test for bond strength between concrete and rebar, were conducted. ne flexural test results of CRCBs reveal that the distribution of surface cracks on the beams shows a fractal behavior. The relationship between the fractal dimensions and mechanical properties of CRCBs is then studied. A prediction model based on artificial neural network (ANN) is established by the use of the fractal dimension as the corrosion index, together with the basic information of the beam. The validity of the prediction model is demonstrated through the experimental data, and satisfactory results are achieved.

Theoretical prediction on corrugated sandwich panels under bending loads

In this paper,an aluminum corrugated sandwich panel with triangular core under bending loads was investigated.Firstly,the equivalent material parameters of the triangular corrugated core layer,which could be considered as an orthotropic panel,were obtained by using Castigliano's theorem and equivalent homogeneous model.Secondly,contributions of the corrugated core layer and two face panels were both considered to compute the equivalent material parameters of the whole structure through the classical lamination theory,and these equivalent material parameters were compared with finite element analysis solutions.Then,based on the Mindlin orthotropic plate theory,this study obtain the closed-form solutions of the displacement for a corrugated sandwich panel under bending loads in specified boundary conditions,and parameters study and comparison by the finite element method were executed simultaneously.

ACO-Inspired Load Balancing Strategy for Cloud-Based Data Centre with Predictive Machine Learning Approach

Virtual Machines are the core of cloud computing and are utilized toget the benefits of cloud computing. Other essential features include portability,recovery after failure, and, most importantly, creating the core mechanismfor load balancing. Several study results have been reported in enhancing loadbalancingsystems employing stochastic or biogenetic optimization methods.It examines the underlying issues with load balancing and the limitationsof present load balance genetic optimization approaches. They are criticizedfor using higher-order probability distributions, more complicated solutionsearch spaces, and adding factors to improve decision-making skills. Thus, thispaper explores the possibility of summarizing load characteristics. Second,this study offers an improved prediction technique for pheromone level predictionover other typical genetic optimization methods during load balancing.It also uses web-based third-party cloud service providers to test and validatethe principles provided in this study. It also reduces VM migrations, timecomplexity, and service level agreements compared to other parallel standardapproaches.

Deep Learning for Multivariate Prediction of Building Energy Performance of Residential Buildings

In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest energy.Therefore,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become paramount.In this vein,efforts have been made to predict the HL and CL using a univariate approach.However,this approach necessitates two models for learning HL and CL,requiring more computational time.Moreover,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware requirement.In this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D CNN.Considering the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and CL.As the 1D data are not affected by excessive parameters,the pooling layer is not applied in this implementation.Besides,the use of pooling has been questioned by recent studies.The performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.

Lateral earth pressure of granular backfills on retaining walls with expanded polystyrene geofoam inclusions under limited surcharge loading

Existing studies have focused on the behavior of the retaining wall equipped with expanded polystyrene(EPS)geofoam inclusions under semi-infinite surcharge loading rather than limited surcharge loading.In this paper,the failure mode and the earth pressure acting on the rigid retaining wall with EPS geofoam inclusions and granular backfills(henceforth referred to as EPS-wall),under limited surcharge loading are investigated through two-and three-dimensional model tests.The testing results show that different from the sliding of almost all the backfill in the EPS-wall under semi-infinite surcharge loading,only an approximately triangular backfill slides in the wall under limited surcharge loading.The distribution of the lateral earth pressure on the EPS-wall under limited surcharge loading is non-linear,and the distribution changes from the increase of the wall depth to the decrease with the increase of the limited surcharge loading.An approach based on the force equilibrium of a differential element is developed to predict the lateral earth pressure behind the EPS-wall subjected to limited surcharge loading,and its performance was fully validated by the three-dimensional model tests.

Finite-time economic model predictive control for optimal load dispatch and frequency regulation in interconnected power systems

This paper presents a finite-time economic model predictive control(MPC)algorithm that can be used for frequency regulation and optimal load dispatch in multi-area power systems.Economic MPC can be used in a power system to ensure frequency stability,real-time economic optimization,control of the system and optimal load dispatch from it.A generalized terminal penalty term was used,and the finite-time convergence of the system was guaranteed.The effectiveness of the proposed model predictive control algorithm was verified by simulating a power system,which had two areas connected by an AC tie line.The simulation results demonstrated the effectiveness of the algorithm.

Server load prediction algorithm based on CM-MC for cloud systems

Accurate prediction of server load is important to cloud systems for improving the resource utilization, reducing the energy consumption and guaranteeing the quality of service(QoS).This paper analyzes the features of cloud server load and the advantages and disadvantages of typical server load prediction algorithms, integrates the cloud model(CM) and the Markov chain(MC) together to realize a new CM-MC algorithm, and then proposes a new server load prediction algorithm based on CM-MC for cloud systems. The algorithm utilizes the historical data sample training method of the cloud model, and utilizes the Markov prediction theory to obtain the membership degree vector, based on which the weighted sum of the predicted values is used for the cloud model. The experiments show that the proposed prediction algorithm has higher prediction accuracy than other typical server load prediction algorithms, especially if the data has significant volatility. The proposed server load prediction algorithm based on CM-MC is suitable for cloud systems, and can help to reduce the energy consumption of cloud data centers.

Research on AC Electronic Load with Energy Recovery Based on Finite Control Set Model Predictive Control

Nowadays,AC electronic loads with energy recovery are widely used in the testing of uninterruptible power supplies and power supply equipment.To tackle the problems of control difficulty,strategy complexity,and poor dynamic performance of AC electronic load with energy recovery of the conventional control strategy,a control strategy of AC electronic load with energy recovery based on Finite Control Set Model Predictive Control(FCSMPC)is developed.To further reduce the computation burden of the FCS-MPC,a simplified FCS-MPC with transforming the predicted variables and using sector to select expected state is proposed.Through simplified model and equivalent approximation analysis,the transfer function of the system is obtained,and the stability and robustness of the system are analyzed.The performance of the simplified FCS-MPC is compared with space vector control(SVPWM)and conventional FCS-MPC.The results show that the FCS-MPC method performs better dynamic response and this advantage is more obvious when simulating high power loads.The simplified FCS-MPC shows similar control performance to conventional FCS-MPC at less computation burden.The control performance of the system also shows better simulation results.

Novel Hybrid Physics‑Informed Deep Neural Network for Dynamic Load Prediction of Electric Cable Shovel

Electric cable shovel(ECS)is a complex production equipment,which is widely utilized in open-pit mines.Rational valuations of load is the foundation for the development of intelligent or unmanned ECS,since it directly influences the planning of digging trajectories and energy consumption.Load prediction of ECS mainly consists of two types of methods:physics-based modeling and data-driven methods.The former approach is based on known physical laws,usually,it is necessarily approximations of reality due to incomplete knowledge of certain processes,which introduces bias.The latter captures features/patterns from data in an end-to-end manner without dwelling on domain expertise but requires a large amount of accurately labeled data to achieve generalization,which introduces variance.In addition,some parts of load are non-observable and latent,which cannot be measured from actual system sensing,so they can’t be predicted by data-driven methods.Herein,an innovative hybrid physics-informed deep neural network(HPINN)architecture,which combines physics-based models and data-driven methods to predict dynamic load of ECS,is presented.In the proposed framework,some parts of the theoretical model are incorporated,while capturing the difficult-to-model part by training a highly expressive approximator with data.Prior physics knowledge,such as Lagrangian mechanics and the conservation of energy,is considered extra constraints,and embedded in the overall loss function to enforce model training in a feasible solution space.The satisfactory performance of the proposed framework is verified through both synthetic and actual measurement dataset.

The Experimental Simulation of Rocks on Load/Unload Response Ratio for Earthquake Prediction

The load/unload experiments on rock failure under pressure have been carried out in Material Test System (MTS) in the Laboratory for Non-linear Mechanics of Continuous Media (LNM), Institute of Mechanics, Chinese Academy of Sciences, and load/unload response ratio (LURR) values with strain as response (i.e. inverse elastic constant as response rate) have been obtained. The experimental results are in accordance with theoretical results and those in real earthquakes: LURR rises just before rock failure. So LURR can be used as the precursor of rock failure and earthquake prediction.

Two-Stage IoT Computational Task Offloading Decision-Making in MEC with Request Holding and Dynamic Eviction

The rapid development of Internet of Things(IoT)technology has led to a significant increase in the computational task load of Terminal Devices(TDs).TDs reduce response latency and energy consumption with the support of task-offloading in Multi-access Edge Computing(MEC).However,existing task-offloading optimization methods typically assume that MEC’s computing resources are unlimited,and there is a lack of research on the optimization of task-offloading when MEC resources are exhausted.In addition,existing solutions only decide whether to accept the offloaded task request based on the single decision result of the current time slot,but lack support for multiple retry in subsequent time slots.It is resulting in TD missing potential offloading opportunities in the future.To fill this gap,we propose a Two-Stage Offloading Decision-making Framework(TSODF)with request holding and dynamic eviction.Long Short-Term Memory(LSTM)-based task-offloading request prediction and MEC resource release estimation are integrated to infer the probability of a request being accepted in the subsequent time slot.The framework learns optimized decision-making experiences continuously to increase the success rate of task offloading based on deep learning technology.Simulation results show that TSODF reduces total TD’s energy consumption and delay for task execution and improves task offloading rate and system resource utilization compared to the benchmark method.

Novel cyber-physical collaborative detection and localization method against dynamic load altering attacks in smart energy grids

Owing to the integration of energy digitization and artificial intelligence technology,smart energy grids can realize the stable,efficient and clean operation of power systems.However,the emergence of cyber-physical attacks,such as dynamic load-altering attacks(DLAAs)has introduced great challenges to the security of smart energy grids.Thus,this study developed a novel cyber-physical collaborative security framework for DLAAs in smart energy grids.The proposed framework integrates attack prediction in the cyber layer with the detection and localization of attacks in the physical layer.First,a data-driven method was proposed to predict the DLAA sequence in the cyber layer.By designing a double radial basis function network,the influence of disturbances on attack prediction can be eliminated.Based on the prediction results,an unknown input observer-based detection and localization method was further developed for the physical layer.In addition,an adaptive threshold was designed to replace the traditional precomputed threshold and improve the detection performance of the DLAAs.Consequently,through the collaborative work of the cyber-physics layer,injected DLAAs were effectively detected and located.Compared with existing methodologies,the simulation results on IEEE 14-bus and 118-bus power systems verified the superiority of the proposed cyber-physical collaborative detection and localization against DLAAs.

Prediction of Reinforcement Corrosion based on Electrochemical Equivalent under Loading

Experiment was carried out to simulate different loading level elements under coupling of stray current and 5% chlorine salt solution. When calculating corrosion of reinforcement, the influence of loading should be considered based on the first law of Faraday electrolysis. The current density of the corrosion was measured by the linear polarization resistance method. The function of corrosion current density was obtained by nonlinear fitting method, and the influence coefficient of loading level to electrochemical equivalent was obtained base on the function of corrosion current density. The experimental results show that the corrosion current density increases with stress ratio of concrete structures. The reinforcement corrosion weight can be calculated through the influence coefficients of electrochemical equivalent and the result is in line with the actual situation.

Multi-Time Scale Optimal Scheduling of a Photovoltaic Energy Storage Building System Based on Model Predictive Control

Building emission reduction is an important way to achieve China’s carbon peaking and carbon neutrality goals.Aiming at the problem of low carbon economic operation of a photovoltaic energy storage building system,a multi-time scale optimal scheduling strategy based on model predictive control(MPC)is proposed under the consideration of load optimization.First,load optimization is achieved by controlling the charging time of electric vehicles as well as adjusting the air conditioning operation temperature,and the photovoltaic energy storage building system model is constructed to propose a day-ahead scheduling strategy with the lowest daily operation cost.Second,considering inter-day to intra-day source-load prediction error,an intraday rolling optimal scheduling strategy based on MPC is proposed that dynamically corrects the day-ahead dispatch results to stabilize system power fluctuations and promote photovoltaic consumption.Finally,taking an office building on a summer work day as an example,the effectiveness of the proposed scheduling strategy is verified.The results of the example show that the strategy reduces the total operating cost of the photovoltaic energy storage building system by 17.11%,improves the carbon emission reduction by 7.99%,and the photovoltaic consumption rate reaches 98.57%,improving the system’s low-carbon and economic performance.

Errors Prediction for Vector-to-Raster Conversion Based on Map Load and Cell Size

Vector-to-raster conversion is a process accompanied with errors.The errors are classified into predicted errors before rasterization and actual errors after that.Accurate prediction of the errors is beneficial to developing reasonable rasterization technical schemes and to making products of high quality.Analyzing and establishing a quantitative relationship between the error and its affecting factors is the key to error prediction.In this study,land cover data of China at a scale of 1:250 000 were taken as an example for analyzing the relationship between rasterization errors and the density of arc length(DA),the density of polygon(DP) and the size of grid cells(SG).Significant correlations were found between the errors and DA,DP and SG.The correlation coefficient(R2) of a model established based on samples collected in a small region(Beijing) reaches 0.95,and the value of R2 is equal to 0.91 while the model was validated with samples from the whole nation.On the other hand,the R2 of a model established based on nationwide samples reaches 0.96,and R2 is equal to 0.91 while it was validated with the samples in Beijing.These models depict well the relationships between rasterization errors and their affecting factors(DA,DP and SG).The analyzing method established in this study can be applied to effectively predicting rasterization errors in other cases as well.

Physical meaning and prediction efficiency of the load/unload response ratio of rocks in strain-weakening phase before failure

Rock experiment results indicate that the load/unload response ratio (LURR) of rocks expressed via strain energy may have singular or negative value after the stress in the rock reaches its maximum before rock failure or when the rock goes into the strain-weakening phase. The universality of this phenomenon is discussed. Expressed via strain or strain energy and the travel time of P wave, the variation form of the reciprocal of LURR during the process of rock failure preparation is derived. The results show that after a sharp decrease the reciprocal of LURR reaches its minimum when the main fracture of the rock is about to appear. This feature can be taken as an indication that the rock main fracture is impending.

Spine system changes in soldiers after load carriage training in a plateau environment: A prediction model research

Background: Low back pain is the most common spinal disorder among soldiers, and load carriage training(LCT) is considered the main cause. We aimed to investigate changes in the spine system of soldiers after LCT at high altitudes and the change trend of the lumbar spine and surrounding soft tissues under different load conditions.Methods: Magnetic resonance imaging scans of the lumbar spines of nine soldiers from plateau troops were collected and processed. We used ImageJ and Surgimap software to analyze changes in the lumbar paraspinal muscles, intervertebral discs(IVDs), intervertebral foramina, and curvature. Furthermore, the multiple linear regression equation for spine injury owing to LCT at high altitudes was established as the mathematical prediction model using SPSS Statistics version 23.0 software.Results: In the paraspinal muscles, the cross-sectional area(CSA) increased significantly from(9126.4±691.6) mm~2 to(9862.7±456.4) mm~2, and the functional CSA(FCSA) increased significantly from(8089.6±707.7) mm~2 to(8747.9±426.2) mm~2 after LCT(P<0.05);however, the FCSA/CSA was not significantly different. Regarding IVD, the total lumbar spine showed a decreasing trend after LCT with a significant difference(P<0.05). Regarding the lumbar intervertebral foramen, the percentage of the effective intervertebral foraminal area of L3/4 significantly decreased from 91.6%±2.0% to 88.1%±2.9%(P<0.05). For curvature, the lumbosacral angle after LCT(32.4°±6.8°) was significantly higher(P<0.05) than that before LCT(26.6°±5.3°), while the lumbar lordosis angle increased significantly from(24.0°±7.1°) to(30.6°±7.4°)(P<0.05). The linear regression equation of the change rate, ΔFCSA%=–0.718+23.085×load weight, was successfully established as a prediction model of spinal injury after LCT at high altitudes.Conclusion: The spinal system encountered increased muscle volume, muscle congestion, tissue edema, IVD compression, decreased effective intervertebral foramen area, and increased lumbar curvature after LCT, which revealed important pathophysiological mechanisms of lumbar spinal disorders in soldiers following short-term and high-load weight training. The injury prediction model of the spinal system confirmed that a load weight <60% of soldiers' weight cannot cause acute pathological injury after short-term LCT, providing a reference supporting the formulation of the load weight standard for LCT.