Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

Enhanced asphalt dynamic modulus prediction: A detailed analysis of artificial hummingbird algorithm-optimised boosted trees

This study introduces and evaluates a novel artificial hummingbird algorithm-optimised boosted tree(AHAboosted)model for predicting the dynamic modulus(E*)of hot mix asphalt concrete.Using a substantial dataset from NCHRP Report-547,the model was trained and rigorously tested.Performance metrics,specifically RMSE,MAE,and R2,were employed to assess the model's predictive accuracy,robustness,and generalisability.When benchmarked against well-established models like support vector machines(SVM)and gaussian process regression(GPR),the AHA-boosted model demonstrated enhanced performance.It achieved R2 values of 0.997 in training and 0.974 in testing,using the traditional Witczak NCHRP 1-40D model inputs.Incorporating features such as test temperature,frequency,and asphalt content led to a 1.23%increase in the test R2,signifying an improvement in the model's accuracy.The study also explored feature importance and sensitivity through SHAP and permutation importance plots,highlighting binder complex modulus|G*|as a key predictor.Although the AHA-boosted model shows promise,a slight decrease in R2 from training to testing indicates a need for further validation.Overall,this study confirms the AHA-boosted model as a highly accurate and robust tool for predicting the dynamic modulus of hot mix asphalt concrete,making it a valuable asset for pavement engineering.

NUMERICAL PREDICTION OF AIRCRAFT HYDRAULIC SYSTEM BASED ON THERMAL DYNAMIC ANALYSIS

A mathematical model of principal elements of the aircraft hydraulic system is presented based on the heat transfer theory. The dynamic heat transfer process of the hydraulic oil and the pump shells within an aircraft hydraulic system are analyzed by the difference method. A kind of means for the prediction to variational trends of the aircraft hydraulic system temperature is provided during operation. The numerical prediction and simulation under the operational conditions are presented for ground trial running and the decelerated operation in flight. Computational results show that there is a good coincidence between the experimental data and the numerical predictions.

Rapid prediction of flow and concentration fields in solid-liquid suspensions of slurry electrolysis tanks

Slurry electrolysis(SE),as a hydrometallurgical process,has the characteristic of a multitank series connection,which leads to various stirring conditions and a complex solid suspension state.The computational fluid dynamics(CFD),which requires high computing resources,and a combination with machine learning was proposed to construct a rapid prediction model for the liquid flow and solid concentration fields in a SE tank.Through scientific selection of calculation samples via orthogonal experiments,a comprehensive dataset covering a wide range of conditions was established while effectively reducing the number of simulations and providing reasonable weights for each factor.Then,a prediction model of the SE tank was constructed using the K-nearest neighbor algorithm.The results show that with the increase in levels of orthogonal experiments,the prediction accuracy of the model improved remarkably.The model established with four factors and nine levels can accurately predict the flow and concentration fields,and the regression coefficients of average velocity and solid concentration were 0.926 and 0.937,respectively.Compared with traditional CFD,the response time of field information prediction in this model was reduced from 75 h to 20 s,which solves the problem of serious lag in CFD applied alone to actual production and meets real-time production control requirements.

Dynamic Downscaling of Summer Precipitation Prediction over China in 1998 Using WRF and CCSM4

To study the prediction of the anomalous precipitation and general circulation for the summer（June–July–August） of1998, the Community Climate System Model Version 4.0（CCSM4.0） integrations were used to drive version 3.2 of the Weather Research and Forecasting（WRF3.2） regional climate model to produce hindcasts at 60 km resolution. The results showed that the WRF model produced improved summer precipitation simulations. The systematic errors in the east of the Tibetan Plateau were removed, while in North China and Northeast China the systematic errors still existed. The improvements in summer precipitation interannual increment prediction also had regional characteristics. There was a marked improvement over the south of the Yangtze River basin and South China, but no obvious improvement over North China and Northeast China. Further analysis showed that the improvement was present not only for the seasonal mean precipitation, but also on a sub-seasonal timescale. The two occurrences of the Mei-yu rainfall agreed better with the observations in the WRF model,but were not resolved in CCSM. These improvements resulted from both the higher resolution and better topography of the WRF model.

A Correction Method Suitable for Dynamical Seasonal Prediction

Based on the hindcast results of summer rainfall anomalies over China for the period 1981-2000 by the Dynamical Climate Prediction System （IAP-DCP） developed by the Institute of Atmospheric Physics, a correction method that can account for the dependence of model＇s systematic biases on SST anomalies is proposed. It is shown that this correction method can improve the hindcast skill of the IAP-DCP for summer rainfall anomalies over China, especially in western China and southeast China, which may imply its potential application to real-time seasonal prediction.

Prediction of Dynamic Cutting Force and Regenerative Chatter Stability in Inserted Cutters Milling

Currently, the modeling of cutting process mainly focuses on two aspects: one is the setup of the universal cutting force model that can be adapted to a broader cutting condition; the other is the setup of the exact cutting force model that can accurately reflect a true cutting process. However, there is little research on the prediction of chatter stablity in milling. Based on the generalized mathematical model of inserted cutters introduced by ENGIN, an improved geometrical, mechanical and dynamic model for the vast variety of inserted cutters widely used in engineering applications is presented, in which the average directional cutting force coefficients are obtained by means of a numerical approach, thus leading to an analytical determination of stability lobes diagram (SLD) on the axial depth of cut. A new kind of SLD on the radial depth of cut is also created to satisfy the special requirement of inserted cutter milling. The corresponding algorithms used for predicting cutting forces, vibrations, dimensional surface finish and stability lobes in inserted cutter milling under different cutting conditions are put forward. Thereafter, a dynamic simulation module of inserted cutter milling is implemented by using hybrid program of Matlab with Visual Basic. Verification tests are conducted on a vertical machine center for Aluminum alloy LC4 by using two different types of inserted cutters, and the effectiveness of the model and the algorithm is verified by the good agreement of simulation result with that of cutting tests under different cutting conditions. The proposed model can predict the cutting process accurately under a variety of cutting conditions, and a high efficient and chatter-free milling operation can be achieved by a cutting condition optimization in industry applications.

Fault Prediction Based on Dynamic Model and Grey Time Series Model in Chemical Processes

This paper combines grey model with time series model and then dynamic model for rapid and in-depth fault prediction in chemical processes. Two combination methods are proposed. In one method, historical data is introduced into the grey time series model to predict future trend of measurement values in chemical process. These predicted measurements are then used in the dynamic model to retrieve the change of fault parameters by model based diagnosis algorithm. In another method, historical data is introduced directly into the dynamic model to retrieve historical fault parameters by model based diagnosis algorithm. These parameters are then predicted by the grey time series model. The two methods are applied to a gravity tank example. The case study demonstrates that the first method is more accurate for fault prediction.

Modeling and scenario prediction of a natural gas demand system based on a system dynamics method

Based on the study of the relationship between structure and feedback of China’s natural gas demand system, this paper establishes a system dynamics model. In order to simulate the total demand and consumption structure of natural gas in China, we set up seven scenarios by changing some of the parameters of the model. The results showed that the total demand of natural gas would increase steadily year by year and reach in the range from 3600 to 4500 billion cubic meters in 2035. Furthermore, in terms of consumption structure, urban gas consumption would still be the largest term, followed by the gas consumption as industrial fuel, gas power generation and natural gas chemical industry. In addition, compared with the population growth, economic development still plays a dominant role in the natural gas demand growth, the impact of urbanization on urban gas consumption is significant, and the promotion of natural gas utilization technology can effectively reduce the total consumption of natural gas.

Formation Dynamics and Quantitative Prediction of Hydrocarbons of the Superpressure System in the Dongying Sag

Based on the theory of formation dynamics of oil/gas pools, the Dongying sag can be divided into three dynamic systems regarding the accumulation of oil and gas： the superpressure closed system, the semi-closed system and the normal pressure open system. Based on the analysis of genesis of superpressure in the superpressure closed system and the rule of hydrocarbon expulsion, it is found that hydrocarbon generation is related to superpressure, which is the main driving factor of hydrocarbon migration. Micro fractures formed by superpressure are the main channels for hydrocarbon migration. There are three dynamic patterns for hydrocarbon expulsion： free water drainage, hydrocarbon accumulation and drainage through micro fissures. In the superpressure closed system, the oil-driving-water process and oil/gas accumulation were completed in lithologic traps by way of such two dynamic patterns as episodic evolution of superpressure systems and episodic pressure release of faults. The oil-bearing capacity of lithologic traps is intimately related to reservoir-forming dynamic force. Quantitative evaluation of dynamic conditions for pool formation can effectively predict the oil-bearing capability of traps.

Life Prediction Based on Transient Dynamics Analysis of Van Semi-trailer with Air Suspension System

The early fatigue damage in the van-body of the semi-trailer is often caused by the unique mechanical characteristics and the dynamic impact of the loads.The traditional finite element method with static strength analysis cannot support the fatigue design of van-body;thus,the dynamics analysis should be adopted for the endurance performance.The accurate dynamics model to describe the transient impacts of all kinds of uneven road and the proper system transfer functions to calculate the load transfer effects from tire to van-body are two critical factors for transient dynamics analysis.In order to evaluate the dynamic performance,the dynamics model of the trailer with the air suspension is brought forward.Then the analysis method of the power spectral density （PSD） is set up to study the transient responses of the road dynamic impacts.The transient responses transferred from axles to van-body are calculated,such as dynamic stress,dynamic RMS acceleration,and dynamic load factors.Based on the above dynamic responses,the fatigue life of van-body is predicted with the finite element analysis （FEA） method.Applying the test parameters of the trailer with air suspension,the simulation system with Matlab/Simulink is constructed to describe the dynamic responses of the impacts of the tested PSD of the vehicle axles,and then the fatigue life is predicted with FEA method.The simulated results show that the vibration level of the van-body with air suspension is reduced and the fatigue life is improved.The real vehicle tests on different roads are carried out,and the test results validate the accuracy of the simulation system.The proposed fatigue life prediction method is effective for the virtual design of auto-body.

Fuzzy Shape Control Based on El man Dynamic Recursion Network Prediction Model

In the strip rolling process, shape control system possesses the characteristics of nonlinearity, strong coupling, time delay and time variation. Based on self adapting Elman dynamic recursion network prediction model, the fuzzy control method was used to control the shape on four-high cold mill. The simulation results showed that the system can be applied to real time on line control of the shape.

Dynamic prediction of gas emission based on wavelet neural network toolbox

This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time intervals through training the WNN with even time-interval samples. The method builds successive new model with the width of sliding window remaining invariable so as to obtain a dynamic prediction method for gas emission quantity. Furthermore, the method performs prediction by a self-developed WNN toolbox. Experiments indicate that such a model can overcome the deficiencies of the traditional static prediction model and can fully make use of the feature extraction capability of wavelet base function to reflect the geological feature of gas emission quantity dynamically. The method is characterized by simplicity, flexibility, small data scale, fast convergence rate and high prediction precision. In addition, the method is also characterized by certainty and repeatability of the predicted results. The effectiveness of this method is confirmed by simulation results. Therefore, this method will exert practical significance on promoting the application of WNN.

Prediction of Dynamic Wellbore Pressure in Gasified Fluid Drilling

The basis of designing gasified drilling is to understand the behavior of gas/liquid two-phase flow in the wellbore. The equations of mass and momentum conservation and equation of fluid flow in porous media were used to establish a dynamic model to predict wellbore pressure according to the study results of Ansari and Beggs-Brill on gas-liquid two-phase flow. The dynamic model was solved by the finite difference approach combined with the mechanistic steady state model. The mechanistic dynamic model was numerically implemented into a FORTRAN 90 computer program and could simulate the coupled flow of fluid in wellbore and reservoir. The dynamic model revealed the effects of wellhead back pressure and injection rate of gas/liquid on bottomhole pressure. The model was validated against full-scale experimental data, and its 5.0% of average relative error could satisfy the accuracy requirements in engineering design.

Quantitative prediction and ranking of the shock sensitivity ofexplosives via reactive molecular dynamics simulations

A deep understanding of explosive sensitivities and their factors is important for safe and reliable applications.However,quantitative prediction of the sensitivities is difficult.Here,reactive molecular dynamics simulation models for high-speed piston impacts on explosive supercells were established.Simulations were also performed to investigate shock-induced reactions of various high-energy explosives.The fraction of reacted explosive molecules in an initial supercell changed linearly with the propagation distance of the shock-wave front.The corresponding slope could be used as a reaction rate for a specific shock-loading velocity.Reaction rates that varied with the shock-loading pressure exhibited two-stage linearities with different slopes.The two inflection points corresponded to the initial and accelerated reactions,which respectively correlated to the thresholds of shock-induced ignition and detonation.Therefore,the ignition and detonation critical pressures could be determined.The sensitivity could then be a quantitative prediction of the critical pressure.The accuracies of the quantitative shock sensitivity predictions were verified by comparing the impact and shock sensitivities of common explosives and the characteristics of anisotropic shock-induced reactions.Molecular dynamics simulations quantitatively predict and rank shock sensitivities by using only crystal structures of the explosives.Overall,this method will enable the design and safe use of explosives.

Preliminary Studies on Predicting the Tropical Indian Ocean Sea Surface Temperature through Combined Statistical Methods and Dynamic ENSO Prediction

The sea surface temperature （SST） in the In- dian Ocean affects the regional climate over the Asian continent mostly through a modulation of the monsoon system. It is still difficult to provide an a priori indication of the seasonal variability over the Indian Ocean. It is widely recognized that the warm and cold events of SST over the tropical Indian Ocean are strongly linked to those of the equatorial eastern Pacific. In this study, a statistical prediction model has been developed to predict the monthly SST over the tropical Indian Ocean. This model is a linear regression model based on the lag relationship between the SST over the tropical Indian Ocean and the Nino3.4 （5°S-5°N, 170°W-120°W） SST Index. The pre- dictor （i.e., Nino3.4 SST Index） has been operationally predicted by a large size ensemble E1 Nifio and the Southern Oscillation （ENSO） forecast system with cou- pled data assimilation （Leefs_CDA）, which achieves a high predictive skill of up to a 24-month lead time for the equatorial eastern Pacific SST. As a result, the prediction skill of the present statistical model over the tropical In- dian Ocean is better than that of persistence prediction for January 1982 through December 2009.

Dynamic globularization prediction during cogging process of large size TC11 titanium alloy billet with lamellar structure

The flow behavior and dynamic globularization of TC11 titanium alloy during subtransus deformation are investigated through hot compression tests. A constitutive model is established based on physical-based hardening model and phenomenological softening model. And based on the recrystallization mechanisms of globularization, the Avrami type kinetics model is established for prediction of globularization fraction and globularized grain size under large strain subtransus deformation of TC11 alloy. As the preliminary application of the previous results, the cogging process of large size TC11 alloy billet is simulated. Based on subroutine development of the DEFORM software, the coupled simulation of one fire cogging process is developed. It shows that the predicted results are in good agreement with the experimental results in forging load and microstructure characteristic, which validates the reliability of the developed FEM subroutine models.

A Novel Search Engine for Internet of Everything Based on Dynamic Prediction

In recent years, with the rapid development of sensing technology and deployment of various Internet of Everything devices, it becomes a crucial and practical challenge to enable real-time search queries for objects, data, and services in the Internet of Everything. Moreover, such efficient query processing techniques can provide strong facilitate the research on Internet of Everything security issues. By looking into the unique characteristics in the IoE application environment, such as high heterogeneity, high dynamics, and distributed, we develop a novel search engine model, and build a dynamic prediction model of the IoE sensor time series to meet the real-time requirements for the Internet of Everything search environment. We validated the accuracy and effectiveness of the dynamic prediction model using a public sensor dataset from Intel Lab.

Prediction of visibility in the Arctic based on dynamic Bayesian network analysis

With the accelerated warming of the world,the safety and use of Arctic passages is receiving more attention.Predicting visibility in the Arctic has been a hot topic in recent years because of navigation risks and opening of ice-free northern passages.Numerical weather prediction and statistical prediction are two methods for predicting visibility.As microphysical parameterization schemes for visibility are so sophisticated,visibility prediction using numerical weather prediction models includes large uncertainties.With the development of artificial intelligence,statistical prediction methods have received increasing attention.In this study,we constructed a statistical model with a physical basis,to predict visibility in the Arctic based on a dynamic Bayesian network,and tested visibility prediction over a 1°×1°grid area averaged daily.The results show that the mean relative error of the predicted visibility from the dynamic Bayesian network is approximately 14.6%compared with the inferred visibility from the artificial neural network.However,dynamic Bayesian network can predict visibility for only 3 days.Moreover,with an increase in predicted area and period,the uncertainty of the predicted visibility becomes larger.At the same time,the accuracy of the predicted visibility is positively correlated with the time period of the input evidence data.It is concluded that using a dynamic Bayesian network to predict visibility can be useful over Arctic regions for projected climatic changes.

Dynamic prediction of landslide displacement using singular spectrum analysis and stack long short-term memory network

An accurate landslide displacement prediction is an important part of landslide warning system. Aiming at the dynamic characteristics of landslide evolution and the shortcomings of traditional static prediction models, this paper proposes a dynamic prediction model of landslide displacement based on singular spectrum analysis(SSA) and stack long short-term memory(SLSTM) network. The SSA is used to decompose the landslide accumulated displacement time series data into trend term and periodic term displacement subsequences. A cubic polynomial function is used to predict the trend term displacement subsequence, and the SLSTM neural network is used to predict the periodic term displacement subsequence. At the same time, the Bayesian optimization algorithm is used to determine that the SLSTM network input sequence length is 12 and the number of hidden layer nodes is 18. The SLSTM network is updated by adding predicted values to the training set to achieve dynamic displacement prediction. Finally, the accumulated landslide displacement is obtained by superimposing the predicted value of each displacement subsequence. The proposed model was verified on the Xintan landslide in Hubei Province, China. The results show that when predicting the displacement of the periodic term, the SLSTM network has higher prediction accuracy than the support vector machine(SVM) and auto regressive integrated moving average(ARIMA). The mean relative error(MRE) is reduced by 4.099% and 3.548% respectively, while the root mean square error(RMSE) is reduced by 5.830 mm and 3.854 mm respectively. It is concluded that the SLSTM network model can better simulate the dynamic characteristics of landslides.