Deep Learning Applied to Computational Mechanics:A Comprehensive Review,State of the Art,and the Classics

Three recent breakthroughs due to AI in arts and science serve as motivation:An award winning digital image,protein folding,fast matrix multiplication.Many recent developments in artificial neural networks,particularly deep learning(DL),applied and relevant to computational mechanics(solid,fluids,finite-element technology)are reviewed in detail.Both hybrid and pure machine learning(ML)methods are discussed.Hybrid methods combine traditional PDE discretizations with ML methods either(1)to help model complex nonlinear constitutive relations,(2)to nonlinearly reduce the model order for efficient simulation(turbulence),or(3)to accelerate the simulation by predicting certain components in the traditional integration methods.Here,methods(1)and(2)relied on Long-Short-Term Memory(LSTM)architecture,with method(3)relying on convolutional neural networks.Pure ML methods to solve(nonlinear)PDEs are represented by Physics-Informed Neural network(PINN)methods,which could be combined with attention mechanism to address discontinuous solutions.Both LSTM and attention architectures,together with modern and generalized classic optimizers to include stochasticity for DL networks,are extensively reviewed.Kernel machines,including Gaussian processes,are provided to sufficient depth for more advanced works such as shallow networks with infinite width.Not only addressing experts,readers are assumed familiar with computational mechanics,but not with DL,whose concepts and applications are built up from the basics,aiming at bringing first-time learners quickly to the forefront of research.History and limitations of AI are recounted and discussed,with particular attention at pointing out misstatements or misconceptions of the classics,even in well-known references.Positioning and pointing control of a large-deformable beam is given as an example.

Running safety and seismic optimization of a fault-crossing simply-supported girder bridge for high-speed railways based on a train-track-bridge coupling system

Bridges crossing active faults are more likely to suffer serious damage or even collapse due to the wreck capabilities of near-fault pulses and surface ruptures under earthquakes.Taking a high-speed railway simply-supported girder bridge with eight spans crossing an active strike-slip fault as the research object,a refined coupling dynamic model of the high-speed train-CRTS III slab ballastless track-bridge system was established based on ABAQUS.The rationality of the established model was thoroughly discussed.The horizontal ground motions in a fault rupture zone were simulated and transient dynamic analyses of the high-speed train-track-bridge coupling system under 3-dimensional seismic excitations were subsequently performed.The safe running speed limits of a high-speed train under different earthquake levels(frequent occurrence,design and rare occurrence)were assessed based on wheel-rail dynamic(lateral wheel-rail force,derailment coefficient and wheel-load reduction rate)and rail deformation(rail dislocation,parallel turning angle and turning angle)indicators.Parameter optimization was then investigated in terms of the rail fastener stiffness and isolation layer friction coefficient.Results of the wheel-rail dynamic indicators demonstrate the safe running speed limits for the high-speed train to be approximately 200 km/h and 80 km/h under frequent and design earthquakes,while the train is unable to run safely under rare earthquakes.In addition,the rail deformations under frequent,design and rare earthquakes meet the safe running requirements of the high-speed train for the speeds of 250,100 and 50 km/h,respectively.The speed limits determined for the wheel-rail dynamic indicators are lower due to the complex coupling effect of the train-track-bridge system under track irregularity.The running safety of the train was improved by increasing the fastener stiffness and isolation layer friction coefficient.At the rail fastener lateral stiffness of 60 kN/mm and isolation layer friction coefficients of 0.9 and 0.8,respectively,the safe running speed limits of the high-speed train increased to 250 km/h and 100 km/h under frequent and design earthquakes,respectively.

An Improved Particle Swarm Optimization Algorithm with Harmony Strategy for the Location of Critical Slip Surface of Slopes

The determination of optimal values for three parameters required in the original particle swarm optimization algorithm is very difficult. It is proposed that two new parameters simulating the harmony search strategy can be adopted instead of the three parameters which are required in the original particle swarm optimization algorithm to update the positions of all the particles. The improved particle swarm optimization is used in the location of the critical slip surface of soil slope, and it is found that the improved particle swarm optimization algorithm is insensitive to the two parameters while the original particle swarm optimization algorithm can be sensitive to its three parameters.

Allometric response of perennial Pennisetum centrasiaticum Tzvel to nutrient and water limitation in the Horqin Sand Land of China

Optimal partitioning theory （OPT） suggests that plants should allocate relatively more biomass to the organs that acquire the most limited resources. The assumption of this theory is that plants trade off the biomass allocation between leaves, stems and roots. However, variations in biomass allocation among plant parts can also occur as a plant grows in size. As an alternative approach, allometric biomass partitioning theory （APT） asserts that plants should trade off their biomass between roots, stems and leaves. This approach can minimize bias when comparing biomass allocation patterns by accounting for plant size in the analysis. We analyzed the biomass allo- cation strategy of perennial Pennisetum centrasiaticum Tzvel in the Horqin Sand Land of northern China by treating samples with different availabilities of soil nutrients and water, adding snow in winter and water in summer. We hypothesized that P. centrasiaticum alters its pattern of biomass allocation strategy in response to different levels of soil water content and soil nitrogen content. We used standardized major axis （SMA） to analyze the allometric rela- tionship （slope） and intercept between biomass traits （root, stem, leaf and total biomass） of nitrogen/water treat- ments. Taking plant size into consideration, no allometric relationships between different organs were significantly affected by differing soil water and soil nitrogen levels, while the biomass allocation strategy of P. centrasiaticum was affected by soil water levels, but not by soil nitrogen levels. The plasticity of roots, leaves and root/shoot ratios was ＇true＇ in response to fluctuations in soil water content, but the plasticity of stems was consistent for trade-offs between the effects of water and plant size. Plants allocated relatively more biomass to roots and less to leaves when snow was added in winter. A similar trend was observed when water was added in summer. The plasticity of roots, stems and leaves was a function of plant size, and remained unchanged in response to different soil nitrogen levels.

Optimization principle of combined surface and underground mining and its applications

The pit limit optimization is discussed, which is one of the most important problems in the combined min-ing method, on the basis of the economic model of ore-blocks. A new principle of the limit optimization is put for-ward through analyzing the limitations of moving cone method under such conditions. With a view to recovering asmuch mineral resource as possible and making the maximum profit from the whole deposit, the new principle is tomaximize the sum of gain from both open-pit and underground mining. The mathematical models along the horizon-tal and vertical directions and modules for software package (DM&MCAD) have been developed and tested inTonglushan Copper Mine. It has been proved to be rather effective in the mining practice.

Analyzing the Effect of the Intra-Pixel Position of Small PSFs for Optimizing the PL of Optical Subpixel Localization

Subpixel localization techniques for estimating the positions of point-like images captured by pixelated image sensors have been widely used in diverse optical measurement fields.With unavoidable imaging noise,there is a precision limit(PL)when estimating the target positions on image sensors,which depends on the detected photon count,noise,point spread function(PSF)radius,and PSF’s intra-pixel position.Previous studies have clearly reported the effects of the first three parameters on the PL but have neglected the intra-pixel position information.Here,we develop a localization PL analysis framework for revealing the effect of the intra-pixel position of small PSFs.To accurately estimate the PL in practical applications,we provide effective PSF(e PSF)modeling approaches and apply the Cramér–Rao lower bound.Based on the characteristics of small PSFs,we first derive simplified equations for finding the best PL and the best intra-pixel region for an arbitrary small PSF;we then verify these equations on real PSFs.Next,we use the typical Gaussian PSF to perform a further analysis and find that the final optimum of the PL is achieved at the pixel boundaries when the Gaussian radius is as small as possible,indicating that the optimum is ultimately limited by light diffraction.Finally,we apply the maximum likelihood method.Its combination with e PSF modeling allows us to successfully reach the PL in experiments,making the above theoretical analysis effective.This work provides a new perspective on combining image sensor position control with PSF engineering to make full use of information theory,thereby paving the way for thoroughly understanding and achieving the final optimum of the PL in optical localization.

Explosion limits estimation and process optimization of direct propylene epoxidation with H2 and O2

Direct propylene epoxidation with H2 and O2,an attractive process to produce propylene oxide(PO),has a potential explosion danger due to the coexistence of flammable gases(i.e.,C3 H6 and H2)and oxidizer(i.e.,O2).The unknown explosion limits of the multi-component feed gas mixture make it difficult to optimize the reaction process under safe operation conditions.In this work,a distribution method is proposed and verified to be effective by comparing estimated and experimental explosion limits of more than 200 kinds of flammable gas mixture.Then,it is employed to estimate the explosion limits of the feed gas mixture,some results of which are also validated by the classic Le Chatelier’s Rule and flammable resistance method.Based on the estimated explosion limits,process optimization is carried out using commercially high and inherently safe reactant concentrations to enhance reaction performance.The promising results are directly obtained through the interface called gOPT in gPROMS only by using a simple,easy-constructed and mature packed-bed reactor,such as the PO yield of 13.3%,PO selectivity of 85.1%and outlet PO fraction of 1.8%.These results can be rationalized by indepth analyses and discussion about the effects of the decision variables on the operation safety and reaction performance.The insights revealed here could shed new light on the process development of the PO production based on the estimation of the explosion limits of the multi-component feed gas mixture containing flammable gase s,inert gas and O2,followed by process optimization.

Linear Stability and Nonlinear Analysis of an Extended Optimal Velocity Model Considering the Speed Limit

In this paper, an extended car-following model is proposed based on an optimal velocity model (OVM), which takes the speed limit into consideration. The model is analyzed by using the linear stability theory and nonlinear analysis method. The linear stability condition shows that the speed limit can enlarge the stable region of traffic flow. By applying the reductive perturbation method, the time-dependent Ginzburg-Landau (TDGL) equation and the modified Korteweg-de Vries (mKdV) equation are derived to describe the traffic flow near the critical point. Furthermore, the relation between TDGL and mKdV equations is also given. It is clarified that the speed limit is essentially equivalent to the parameter adjusting of the driver’s sensitivity.

High Dynamic Bounding and Jumping Motion of Quadruped Robot Based on Stable Optimization Control

Aiming at the environment such as ravines and obstacles that may be encountered in the actual movement,this paper proposes a method for optimizing the bounding and jumping motion based on the ground touching force trajectory and the air motion trajectory of the quadruped robot.The method of optimizing the ground reaction force according to the speed of the demand and the height of the jump,and adjusting the stance and swing time according to the relationship of dynamics and momentum conservation.At the same time,under the constraints of dynamics and energy consumption of the robot system,considering the jumping distance and height,a method for optimizing the air trajectory of bounding and jumping is proposed.State switching and landing stability control are also added.Finally,the experimental results show that the quadruped robot has strong bounding and jumping ability,and has achieved stable bounding movement and forward jump movement of 0.8 m.

Discontinuous flying particle swarm optimization algorithm and its application to slope stability analysis

A new version of particle swarm optimization(PSO) called discontinuous flying particle swarm optimization(DFPSO) was proposed,where not all of the particles refreshed their positions and velocities during each iteration step and the probability of each particle in refreshing its position and velocity was dependent on its objective function value.The effect of population size on the results was investigated.The results obtained by DFPSO have an average difference of 6% compared with those by PSO,whereas DFPSO consumes much less evaluations of objective function than PSO does.

H-infinity performance optimization for networked control systems with limited communication channels

This paper studies the problems of H-infinity performance optimization and controller design for continuous-time NCSs with both sensor-to-controller and controller-to-actuator communication constraints （limited communication channels）. By taking the derivative character of network-induced delay into full consideration and defining new Lyapunov functions, linear matrix inequalities （LMIs）-based H-infinity performance optimization and controller design are presented for NCSs with limited communication channels. If there do not exist any constraints on the communication channels, the proposed design methods are also applicable. The merit of the proposed methods lies in their Jess conservativeness, which is achieved by avoiding the utilization of bounding inequalities for cross products of vectors. The simulation results illustrate the merit and effectiveness of the proposed H-infinity controller design for NCSs with limited communication channels.

Raising the Speed Limit of Axial Piston Pumps by Optimizing the Suction Duct

The maximum delivery pressure and the maximum rotational speed determine the power density of axial piston pumps.However,increasing the speed beyond the limit always accompanies cavitation,leading to the decrease of the volumetric efficiency.The pressure loss in the suction duct is considered a significant reason for the cavitation.Therefore,this paper proposes a methodology to optimize the shape of the suction duct aiming at reducing the intensity of cavitation and increasing the speed limit.At first,a computational fluid dynamics(CFD)model based on the full cavitation model(FCM)is developed to simulate the fluid field of the axial piston pump and a test rig is set to validate the model.Then the topology optimization is conducted for obtaining the minimum pressure loss in the suc-tion duct.Comparing the original suction duct with the optimized one in the simulation model,the pressure loss in the suction duct gets considerable reduction,which eases the cavitation intensity a lot.The simulation results prove that the speed limit can increase under several different inlet pressures.

APPLICATION OF WAVE LETS TO OPTIMAL SHOCK AND IMPACT ISOLATION

The limiting performa nce analysis is used to study the optimal shock and impact isolation of mechanic al systems. The use of wavelets to approximate time-domain control functions is investigated. The formulation for numerical computation is developed. Numerical examples include the optimal shock isolation of a SDOF system and the optimal i mpact isolation of a MDOF system. Computational results show that compactly supp orted wavelets can represent abrupt changes in control functions better than tri gonometric series and considerably increase computational efficiency.

Analysis of drilling difficulty of extended-reach wells based on drilling limit theory

With the continuous increase in vertical depths and horizontal displacements of directional wells,the difficulties of drilling operations continue to increase,and more accurate methods of drilling difficulty evaluation are needed.In this paper,a drilling difficulty evaluation method is built by combining drilling limit model and expert evaluation.Firstly,the concept of drilling difficulty index is introduced,and the method to calculate drilling difficulty index is established.Next,the meanings of five drilling difficulty levels are explained and the optimization design method with drilling difficulty as the target is built.At last,the theoretical model is applied to the extended-reach drilling of the Liuhua oilfield in the South China Sea,in which drilling difficulties are evaluated and the relationship between drilling difficulty and development control radius is revealed.The results indicate that extended-reach drilling in the Liuhua oilfield is on the“normal”difficulty level on average,rotary drilling in 8_(1/2)-in.section is the most difficult,and the main constraint conditions are excessive torque and high friction.Through technology upgradation,the drilling difficulties are decreased,the development control radius increases from 6.6 to 11.4 km,and the maximum horizontalto-vertical ratio increases from 5.3 to 8.7.Then,the development wells in marginal oilfields and adjustment wells in old oilfields can be drilled on“normal”difficulty level.Therefore,technology upgradation,especially drilling rig upgradation,is the most important development direction for extended-reach drilling in the South China Sea.

CRISPR/Cas9系统在临床医学研究的应用与改进

癌症与遗传疾病等难治性疾病的发生发展一般是多因素协同的结果,涉及复杂的信号网络及多生物分子的相互作用。了解其中驱动的关键元素有助于为临床上的治疗和研究打开新的突破口。然而,探究驱动元素用于难治性疾病治疗的挑战之一是缺乏方便、可编程的基因编辑工具。近年来,新型的CRISPR/Cas9系统由于其组分简单、基因编辑效率高等特点逐渐成为临床医学研究中应用最为广泛的基因编辑工具。本文介绍了CRISPR系统应用于临床研究中的相应进展和潜在挑战。阐述了基于CRISPR系统sgRNA序列重构能改变靶向性及系统本身的可编程性等特性,其可在进行适当的改造和修饰后实现对活细胞染色体的实时成像,用以了解生物体在面临外界刺激时基因组的时空调节。评估了CRISPR系统在基因筛选、免疫治疗和遗传疾病治疗方面的重大价值,尤其是CRISPR系统进行相应改造后系统用在临床研究中安全性与功能性的提升。介绍了CRISPR系统在临床研究中的应用障碍、局限以及对其相应的优化改造,展望CRISPR/Cas9基因编辑技术的应用前景及其在临床医学领域的发展优势,以期能为CRISPR系统的进一步应用与优化提供参考。

OPTIMAL DYNAMICAL BALANCE HARVESTING FOR A CLASS OF RENEWABLE RESOURCES SYSTEM

An optimal utilization problem for a class of renewable resources system is investigated. Firstly, a control problem was proposed by introducing a new utility function which depends on the harvesting effort and the stock of resources.Secondly, the existence of optimal solution for the problem was discussed. Then, using a maximum principle for infinite horizon problem, a nonlinear four-dimensional differential equations system was attained. After a detailed analysis of the unique positive equilibrium solution, the existence of limit cycles for the system is demonstrated. Next a reduced system on the central manifold is carefully derived, which assures the stability of limit cycles. Finally significance of the results in bioeconomics is explained.

Effect of calibration data series length on performance and optimal parameters of hydrological model

In order to assess the effects of calibration data series length on the performance and optimal parameter values of a hydrological model in ungauged or data-limited catchments （data are non-continuous and fragmental in some catchments）, we used non-continuous calibration periods for more independent streamflow data for SIMHYD （simple hydrology） model calibration. Nash-Sutcliffe efficiency and percentage water balance error were used as performance measures. The particle swarm optimization （PSO） method was used to calibrate the rainfall-runoff models. Different lengths of data series ranging from one year to ten years, randomly sampled, were used to study the impact of calibration data series length. Fifty-five relatively unimpaired catchments located all over Australia with daily precipitation, potential evapotranspiration, and streamflow data were tested to obtain more general conclusions. The results show that longer calibration data series do not necessarily result in better model performance. In general, eight years of data are sufficient to obtain steady estimates of model performance and parameters for the SIMHYD model. It is also shown that most humid catchments require fewer calibration data to obtain a good performance and stable parameter values. The model performs better in humid and semi-humid catchments than in arid catchments. Our results may have useful and interesting implications for the efficiency of using limited observation data for hydrological model calibration in different climates.

NON-CONFLICTING ORDERING CONES AND VECTOR OPTIMIZATION IN INDUCTIVE LIMITS

Let （E,ξ）=ind（En,ξn） be an inductive limit of a sequence （En,ξn）n∈N of locally convex spaces and let every step （En,ξn） be endowed with a partial order by a pointed convex （solid） cone Sn. In the framework of inductive limits of partially ordered locally convex spaces, the notions of lastingly efficient points, lastingly weakly efficient points and lastingly globally properly efficient points are introduced. For several ordering cones, the notion of non-conflict is introduced. Under the requirement that the sequence （Sn）n∈N of ordering cones is non-conflicting, an existence theorem on lastingly weakly efficient points is presented. From this, an existence theorem on lastingly globally properly efficient points is deduced.

A Novel PSO Algorithm for Optimal Production Cost of the Power Producers with Transient Stability Constraints

The application of a novel Particle Swarm Optimization (PSO) method called Fitness Distance Ratio PSO (FDR PSO) algorithm is described in this paper to determine the optimal power dispatch of the Independent Power Producers (IPP) with linear ramp model and transient stability constraints of the power producers. Generally the power producers must respond quickly to the changes in load and wheeling transactions. Moreover, it becomes necessary for the power producers to reschedule their power generation beyond their power limits to meet vulnerable situations like credible contingency and increase in load conditions. During this process, the ramping cost is incurred if they violate their permissible elastic limits. In this paper, optimal production costs of the power producers are computed with stepwise and piecewise linear ramp rate limits. Transient stability limits of the power producers are also considered as addi-tional rotor angle inequality constraints while solving the Optimal Power Flow (OPF) problem. The proposed algo-rithm is demonstrated on practical 10 bus and 26 bus systems and the results are compared with other optimization methods.

Reliability Analysis of Wind Turbine Gearbox Based on the Optimal Confidence Limit Method

Based on the zero-failure data of 30 Chinese 1. 5 MW wind turbine gearboxes( WTGs),the optimal confidence limit method was developed to predict the reliability and reliability lifetime of WTG. Firstly,Bayesian method and classical probability estimation method were introduced to estimate the value interval of shape parameter considering the engineering practice. Secondly,taking this value interval into the optimal confidence limit method,the reliability and reliability lifetime of WTG could be obtained under different confidence levels. Finally,the results of optimal confidence limit method and Bayesian method were compared. And the comparison results show that the rationality of this estimated range.Meantime, the rule of confidence level selection in the optimal confidence limit method is provided, and the reliability and reliability lifetime prediction of WTG can be acquired.