Mechanical behavior of sandstone during post-peak cyclic loading and unloading under hydromechanical coupling

This paper investigates mechanical behaviours of sandstone during post-peak cyclic loading and unloading subjected to hydromechanical coupling effect, confirming the peak and residual strengths reduction laws of sandstone with water pressure, and revealing the influence of water pressure on the upper limit stress and deformation characteristics of sandstone during post-peak cyclic loading and unloading.Regarding the rock strength, the experimental study confirms that the peak strength σ_(p) and residual strength σ_(r) decrease as water pressure P increases. Especially, the normalized strength parameters σ_(p)/σ_(pk) and σ_(r)/σ_(re) was negatively and linearly correlated with the P/σ_(3). Moreover, the Hoek-Brown strength criterion can be applied to describe the relationship between effective peak strength and effective confining stress. During post-peak cyclic loading and unloading, both the upper limit stress σ_(p(i)) and crack damage threshold stress σ_(cd(i)) of each cycle tend to decrease with the increasing cycle number. A hysteresis loop exists among the loading and unloading stress–strain curves, indicating the unloading deformation modulus E_(unload) is larger than the loading deformation modulus E_(load). Based on experimental results,a post-peak strength prediction model related to water pressure and plastic shear strain is established.

Morphological evolution and flow conduction characteristics of fracture channels in fractured sandstone under cyclic loading and unloading

In coal mining,rock strata are fractured under cyclic loading and unloading to form fracture channels.Fracture channels are the main flow narrows for gas.Therefore,expounding the flow conductivity of fracture channels in rocks on fluids is significant for gas flow in rock strata.In this regard,graded incremental cyclic loading and unloading experiments were conducted on sandstones with different initial stress levels.Then,the three-dimensional models for fracture channels in sandstones were established.Finally,the fracture channel percentages were used to reflect the flow conductivity of fracture channels.The study revealed how the particle size distribution of fractured sandstone affects the formation and expansion of fracture channels.It was found that a smaller proportion of large blocks and a higher proportion of small blocks after sandstone fails contribute more to the formation of fracture channels.The proportion of fracture channels in fractured rock can indicate the flow conductivity of those channels.When the proportion of fracture channels varies gently,fluids flow evenly through those channels.However,if the proportion of fracture channels varies significantly,it can greatly affect the flow rate of fluids.The research results contribute to revealing the morphological evolution and flow conductivity of fracture channels in sandstone and then provide a theoretical basis for clarifying the gas flow pattern in the rock strata of coal mines.

Influence of volume compression on the unloading deformation behavior of red sandstone under damage-controlled cyclic triaxial loading

A reasonable evaluation of unloading deformation characteristics is of great significance for the effective analysis of deformation and stability of surrounding rocks after underground excavation.In this study,the damage-controlled cyclic triaxial loading tests were conducted to investigate the pore compaction mechanism and its influences on the unloading deformation behavior of red sandstone,including Young’s modulus,Poisson’s ratio,volumetric strain,and irreversible strain.The experimental results show that the increases of volumetric and irreversible strains of rocks can be attributed to the compaction mechanism,which almost dominates the entire pre-peak deformation process.The unloading deformation consists of the reversible linear and nonlinear strains,and the irreversible strain under the influence of the porous grain structure.The pre-peak Young’s modulus tends to increase and then decrease due to the influence of the unloading irreversible strain.However,it hardly changes with the increasing volumetric strain compaction under the influence of reversible nonlinear strain.Instead,the initial unloading tangent modulus is highly related to the volumetric strain,and clearly reflects the compaction state of red sandstone.Furthermore,both the reversible nonlinear and irreversible unloading deformations are independent of confining pressure.This study is beneficial for the theoretical modeling and prediction of cyclic unloading deformation behavior of red sandstone.

Mechanical and hydraulic properties of fault rocks under multi‑stage cyclic loading and unloading

The rock mass in fault zones is frequently subjected to cyclic loading and unloading during deep resource exploitation and tunnel excavation.Research on the mechanical and hydraulic characteristics of fault rock during the cyclic loading and unloading is of great signifcance for revealing the formation mechanism of water-conducting pathways in fault and preventing water inrush disasters.In this study,the mechanical and seepage tests of fault rock under the multi-stage cyclic loading and unloading of axial compression were carried out by using the fuid–solid coupling triaxial experimental device.The hysteresis loop of the stress–strain curve,peak strain rate,secant Young's modulus,and permeability of fault rock were obtained,and the evolution law of the dissipated energy of fault rock with the cyclic number of load and unloading was discussed.The experimental results show that with an increase in the cyclic number of loading and unloading,several changes occur.The hysteresis loop of the stress–strain curve of the fault rock shifts towards higher levels of strain.Additionally,both the peak strain rate and the secant Young's modulus of the fault rock increase,resulting in an increase in the secant Young's modulus of the fault rock mass.However,the growth rate of the secant Young's modulus gradually slows down with the increase of cyclic number of loading and unloading.The permeability evolution of fault rock under the multi-stage cyclic loading and unloading of axial compression can be divided into three stages:steady increase stage,cyclic decrease stage,and rapid increase stage.Besides,the calculation model of dissipated energy of fault rock considering the efective stress was established.The calculation results show that the relationship between the dissipated energy of fault rock and the cyclic number of loading and unloading conforms to an exponential function.

A Review of NILM Applications with Machine Learning Approaches

In recent years,Non-Intrusive LoadMonitoring (NILM) has become an emerging approach that provides affordableenergy management solutions using aggregated load obtained from a single smart meter in the power grid.Furthermore, by integrating Machine Learning (ML), NILM can efficiently use electrical energy and offer less ofa burden for the energy monitoring process. However, conducted research works have limitations for real-timeimplementation due to the practical issues. This paper aims to identify the contribution of ML approaches todeveloping a reliable Energy Management (EM) solution with NILM. Firstly, phases of the NILM are discussed,along with the research works that have been conducted in the domain. Secondly, the contribution of machinelearning approaches in three aspects is discussed: Supervised learning, unsupervised learning, and hybridmodeling.It highlights the limitations in the applicability of ML approaches in the field. Then, the challenges in the realtimeimplementation are concerned with six use cases: Difficulty in recognizing multiple loads at a given time,cost of running the NILM system, lack of universal framework for appliance detection, anomaly detection andnew appliance identification, and complexity of the electricity loads and real-time demand side management.Furthermore, options for selecting an approach for an efficientNILMframework are suggested. Finally, suggestionsare provided for future research directions.

Evolution of mechanical parameters of Shuangjiangkou granite under different loading cycles and stress paths

Surrounding rocks at different locations are generally subjected to different stress paths during the process of deep hard rock excavation.In this study,to reveal the mechanical parameters of deep surrounding rock under different stress paths,a new cyclic loading and unloading test method for controlled true triaxial loading and unloading and principal stress direction interchange was proposed,and the evolution of mechanical parameters of Shuangjiangkou granite under different stress paths was studied,including the deformation modulus,elastic deformation increment ratios,fracture degree,cohesion and internal friction angle.Additionally,stress path coefficient was defined to characterize different stress paths,and the functional relationships among the stress path coefficient,rock fracture degree difference coefficient,cohesion and internal friction angle were obtained.The results show that during the true triaxial cyclic loading and unloading process,the deformation modulus and cohesion gradually decrease,while the internal friction angle gradually increases with increasing equivalent crack strain.The stress path coefficient is exponentially related to the rock fracture degree difference coefficient.As the stress path coefficient increases,the degrees of cohesion weakening and internal friction angle strengthening decrease linearly.During cyclic loading and unloading under true triaxial principal stress direction interchange,the direction of crack development changes,and the deformation modulus increases,while the cohesion and internal friction angle decrease slightly,indicating that the principal stress direction interchange has a strengthening effect on the surrounding rocks.Finally,the influences of the principal stress interchange direction on the stabilities of deep engineering excavation projects are discussed.

Adaptive Load Balancing for Parameter Servers in Distributed Machine Learning over Heterogeneous Networks

In distributed machine learning(DML)based on the parameter server(PS)architecture,unbalanced communication load distribution of PSs will lead to a significant slowdown of model synchronization in heterogeneous networks due to low utilization of bandwidth.To address this problem,a network-aware adaptive PS load distribution scheme is proposed,which accelerates model synchronization by proactively adjusting the communication load on PSs according to network states.We evaluate the proposed scheme on MXNet,known as a realworld distributed training platform,and results show that our scheme achieves up to 2.68 times speed-up of model training in the dynamic and heterogeneous network environment.

Machine Learning: An Overview

Machine learning is an Artificial Intelligence (or AI) application, an idea that came into being by giving machines access to data and letting them learn by themselves. AI has been making headlines, especially since ChatGPT was introduced. Malaysia has taken many significant steps to embrace and integrate the technology into various sectors. These include encouraging large companies to build AI infrastructure, creating AI training opportunities (for example, the local media reported Microsoft and Google plan to invest USD 2.2 billion and USD 2 billion, respectively, in the said activities), and, as part of AI Talent Roadmap 2024-2030, establishing AI faculty in one of its public universities (i.e., “Universiti Teknologi Malaysia”) leading the way in the integration and teaching of AI throughout the country. This article introduces several products developed by the author (for the energy and transportation industries) and recommends their improvement by incorporating Machine learning.

Machine Learning-based Electric Load Forecasting for Peak Demand Control in Smart Grid

Increasing energy demands due to factors such as population,globalization,and industrialization has led to increased challenges for existing energy infrastructure.Efficient ways of energy generation and energy consumption like smart grids and smart homes are implemented to face these challenges with reliable,cheap,and easily available sources of energy.Grid integration of renewable energy and other clean distributed generation is increasing continuously to reduce carbon and other air pollutants emissions.But the integration of distributed energy sources and increase in electric demand enhance instability in the grid.Short-term electrical load forecasting reduces the grid fluctuation and enhances the robustness and power quality of the grid.Electrical load forecasting in advance on the basic historical data modelling plays a crucial role in peak electrical demand control,reinforcement of the grid demand,and generation balancing with cost reduction.But accurate forecasting of electrical data is a very challenging task due to the nonstationary and nonlinearly nature of the data.Machine learning and artificial intelligence have recognized more accurate and reliable load forecastingmethods based on historical load data.The purpose of this study is to model the electrical load of Jajpur,Orissa Grid for forecasting of load using regression type machine learning algorithms Gaussian process regression(GPR).The historical electrical data and whether data of Jajpur is taken for modelling and simulation and the data is decided in such a way that the model will be considered to learn the connection among past,current,and future dependent variables,factors,and the relationship among data.Based on this modelling of data the network will be able to forecast the peak load of the electric grid one day ahead.The study is very helpful in grid stability and peak load control management.

Short-Term Mosques Load Forecast Using Machine Learning and Meteorological Data

The tendency toward achieving more sustainable and green buildings turned several passive buildings into more dynamic ones.Mosques are the type of buildings that have a unique energy usage pattern.Nevertheless,these types of buildings have minimal consideration in the ongoing energy efficiency applications.This is due to the unpredictability in the electrical consumption of the mosques affecting the stability of the distribution networks.Therefore,this study addresses this issue by developing a framework for a short-term electricity load forecast for a mosque load located in Riyadh,Saudi Arabia.In this study,and by harvesting the load consumption of the mosque and meteorological datasets,the performance of four forecasting algorithms is investigated,namely Artificial Neural Network and Support Vector Regression(SVR)based on three kernel functions:Radial Basis(RB),Polynomial,and Linear.In addition,this research work examines the impact of 13 different combinations of input attributes since selecting the optimal features has a major influence on yielding precise forecasting outcomes.For the mosque load,the(SVR-RB)with eleven features appeared to be the best forecasting model with the lowest forecasting errors metrics giving RMSE,nRMSE,MAE,and nMAE values of 4.207 kW,2.522%,2.938 kW,and 1.761%,respectively.

Data-Driven Load Forecasting Using Machine Learning and Meteorological Data

Electrical load forecasting is very crucial for electrical power systems’planning and operation.Both electrical buildings’load demand and meteorological datasets may contain hidden patterns that are required to be investigated and studied to show their potential impact on load forecasting.The meteorological data are analyzed in this study through different data mining techniques aiming to predict the electrical load demand of a factory located in Riyadh,Saudi Arabia.The factory load and meteorological data used in this study are recorded hourly between 2016 and 2017.These data are provided by King Abdullah City for Atomic and Renewable Energy and Saudi Electricity Company at a site located in Riyadh.After applying the data pre-processing techniques to prepare the data,different machine learning algorithms,namely Artificial Neural Network and Support Vector Regression(SVR),are applied and compared to predict the factory load.In addition,for the sake of selecting the optimal set of features,13 different combinations of features are investigated in this study.The outcomes of this study emphasize selecting the optimal set of features as more features may add complexity to the learning process.Finally,the SVR algorithm with six features provides the most accurate prediction values to predict the factory load.

Machine Learning for Hybrid Line Stability Ranking Index in Polynomial Load Modeling under Contingency Conditions

In the conventional technique,in the evaluation of the severity index,clustering and loading suffer from more iteration leading to more com-putational delay.Hence this research article identifies,a novel progression for fast predicting the severity of the line and clustering by incorporating machine learning aspects.The polynomial load modelling or ZIP(constant impedances(Z),Constant Current(I)and Constant active power(P))is developed in the IEEE-14 and Indian 118 bus systems considered for analysis of power system security.The process of finding the severity of the line using a Hybrid Line Stability Ranking Index(HLSRI)is used for assisting the concepts of machine learning with J48 algorithm,infers the superior affected lines by adopting the IEEE standards in concern to be compensated in maintaining the power system stability.The simulation is performed in the WEKA environment and deals with the supervisor learning in order based on severity to ensure the safety of power system.The Unified Power Flow Controller(UPFC),facts devices for the purpose of compensating the losses by maintaining the voltage characteristics.The finite element analysis findings are compared with the existing procedures and numerical equations for authentications.

Mechanical properties and failure modes of stratified backfill under triaxial cyclic loading and unloading

Multiple filling of gobs will lead to a layered structure of the backfill.To explore the influence of layering structure on the mechanical properties and failure modes of backfill,different backfill specimens were prepared with a cement/sand ratio of 1:4,a slurry concentration of 75%,and backfilling times of 1,2,3 and 4,separately.Triaxial cyclic loading and unloading experiments were carried out.The results show that with an increase in backfilling time,the peak strength of backfill decreases as a polynomial function and the peak strain increases as an exponential function.The cyclic load enhances the linear characteristic of backfill deformation.The loading and unloading deformation moduli have a linear negative correlation with the backfilling time.The unloading deformation modulus is always slightly higher than the loading deformation modulus.The failure modes of stratified backfill are mainly characterized by conjugate shear failure at the upper layer and tensile failure across the layer plane,and there is usually no damage in the lower layer away from the loading area.

Effect of fatigue loading-confining stress unloading rate on marble mechanical behaviors: An insight into fracture evolution analyses

Rocks in underground works usually experience rather complex stress disturbance.For this,their fracture mechanism is significantly different from rocks subjected to conventional triaxial compression conditions.The effects of stress disturbances on rock geomechanical behaviors under fatigue loading conditions and triaxial unloading conditions have been reported in previous studies.However,little is known about the dependence of the unloading rate on fatigue loading and confining stress unloading(FL-CSU)conditions that influence rock failure.In this paper,we aimed at investigating the fracture behaviors of marble under FL-CSU conditions using the post-test X-ray computed tomography(CT)scanning technique and the GCTS RTR 2000 rock mechanics system.Results show that damage accumulation at the fatigue stage can influence the final fracture behaviors of marble.The stored elastic energy for rock samples under FL-CSU tests is relatively larger compared to those under conventional triaxial tests,and the dissipated energy used to drive damage evolution and crack propagation is larger for FL-CSU tests.In FL-CSU tests,as the unloading rate increases,the dissipated energy grows and elastic energy reduces.CT scanning after the test reveals the impacts of the unloading rate on the crack pattern and a fracture degree index is therein defined in this context to represent the crack dimension.It shows that the crack pattern after FL-CSU tests depends on the unloading rate,and the fracture degree is in agreement with the analysis of both the energy dissipation and the amount of energy released.The effect of unloading rate on fracture evolution characteristics of marble is revealed by a series of FL-CSU tests.

Mechanical Properties of Deep-buried Marble Material Under Loading and Unloading Tests

The mechanical properties are essentially different when rock material is subjected to loading or unloading conditions. In this study, loading and unloading tests with various confining pressures are conducted to investigate the mechanical properties of marble material samples taken from the deep diversion tunnels of Jinping II Hydropower Station. The stress-strain relationship, failure characteristics and strength criterion are compared and analyzed based on the experiment results. The results show： in the loading and unloading test, peak strength, lateral strain, axial strain and plastic deformation increase significantly as the confining pressure increases. Lateral strain increased significantly and obvious lateral dilatancy can be observed to the change of confining pressure; The fracture mode is mainly the single shear fracture for the triaxial compression test and post-peak test, angle between the failure surface and the ends of the rock material becomes smaller as the confining pressure increases. Hock-Brown strength criterion reflects the strength characteristics of marble material under two different unloading conditions, and has some supplementary effects to the rock material of mechanical field.

A liquid loading prediction method of gas pipeline based on machine learning

The liquid loading is one of the most frequently encountered phenomena in the transportation of gas pipeline,reducing the transmission efficiency and threatening the flow assurance.However,most of the traditional mechanism models are semi-empirical models,and have to be resolved under different working conditions with complex calculation process.The development of big data technology and artificial intelligence provides the possibility to establish data-driven models.This paper aims to establish a liquid loading prediction model for natural gas pipeline with high generalization ability based on machine learning.First,according to the characteristics of actual gas pipeline,a variety of reasonable combinations of working conditions such as different gas velocity,pipe diameters,water contents and outlet pressures were set,and multiple undulating pipeline topography with different elevation differences was established.Then a large number of simulations were performed by simulator OLGA to obtain the data required for machine learning.After data preprocessing,six supervised learning algorithms,including support vector machine(SVM),decision tree(DT),random forest(RF),artificial neural network(ANN),plain Bayesian classification(NBC),and K nearest neighbor algorithm(KNN),were compared to evaluate the performance of liquid loading prediction.Finally,the RF and KNN with better performance were selected for parameter tuning and then used to the actual pipeline for liquid loading location prediction.Compared with OLGA simulation,the established data-driven model not only improves calculation efficiency and reduces workload,but also can provide technical support for gas pipeline flow assurance.

The deformation and permeability of Yanji mudstone under cyclic loading and unloading

During the constructions of motorways and high-speed railway lines in the Yanji Basin,large amounts of excess mudstones due to the enormous tunnel excavations and slope cuts would be deposited as landfills.Assessing the deformation and permeability of Yanji mudstone became important for the design,construction and operation of the landfills.This paper presents an experimental study on the deformation and permeability of Yanji mudstone by carrying out a series of oedometer tests with loading/unloading cycles.The results show that the sample with a lower initial water content exhibited greater swelling deformation after inundation,a lower yield stress,greater deformation and a higher hydraulic conductivity during the loading/unloading cycles.As the number of loading/unloading cycles increased,the yield stress and accumulated plastic deformation increased,while the compression index,rebound index and hydraulic conductivity decreased.The samples became stiffer and their hydromechanical behaviour tended to be stable after three cycles.The compression curves could be divided into pre-yield and post-yield zones.The post-yield zones of compression curves and the rebound curves could be normalized into a unique line,and the pre-yield zones of the compression curves could be described as lines.Basic equations were developed to predict mudstone deformation under cyclic loading and unloading.Additionally,an empirical relationship between the hydraulic conductivity and void ratio was also proposed.The ability of the proposed methods was verified by the overall good agreement between the experimental results and predicted values.

Calculation of foundation pit deformation caused by deep excavation considering influence of loading and unloading

A new analytical solution for ground surface settlement induced by deep excavation is proposed based on the elastic half space Melan’s solution,and the analytical model is related to the physical and mechanical properties of soil with the loading and unloading action during excavation process.The change law of earth pressure of the normal consolidation soil after the foundation pit excavation was analyzed,and elastic displacement calculation methods of analytic solution were further established given the influence of excavation and unloading.According to the change of stress state in the excavation process of foundation pit,the planar mechanical analysis model of the foundation excavation problem was established.By combining this model with the physical equations and geometric equations of plane strain problem with consideration of the loading and unloading modulus of soil,constitutive equation of the plane strain problem was also established.The loading and unloading modulus formula was obtained by using the parameter calculation method in Duncan-Chang curve model.The constitutive equation obtained from the model was used to calculate the soil stress state of each point to determine its loading and unloading modulus.Finally,the foundation pit displacement change after excavation was calculated,and thus the soil pressure distribution after retaining structure deformation.The theoretical results calculated by making corresponding programs were applied to engineering practice.By comparing the conventional calculation results with monitoring results,the practicability and feasibility of the calculation model were verified,which should provide a theoretical basis for similar projects.

The design of automatic loading-and-unloading material manipulator for telescopic punch

To reduce the amount of labor in the sheet metal stamping industry, improve the processing efficiency and safety factor and realize the automatic production of stamping, this paper designs a new type of overall plan about automatic loading and unloading material manipulator for telescopic punch which can realize the telescopic movements with two degrees. The mechanical structure of the manipulator includes a lifting device and a telescopic device. Using PLC control program, the control system can automatically achieve continuous beat actions of drawing and stacking for the processing raw materials. According to the mechanical structure, the paper analyzes the working principle and control strategy of each component in the loading-and-unloading material manipulator systems.

A STUDY OF THE POSTBUCKLING PATH OF CYLINDRICALLY CURVED PANELS OF LAMINATED COMPOSITE MATERIALS DURING LOADING AND UNLOADING

In this paper, Dynamic Relaxation Method is applied to study the postbuckling path of cylindrically curved panels of laminated composite materials during loading and unloading. The phenomenon that loading paths do not coincide with unloading paths has been found. Numerical results are given for cylindrically curved cross-ply panels subjected to uniform uniaxial compression under two types of boundary conditions. The influence of the number of layers, the panels curvature and the initial imperfection on the postbuckling paths is discussed.