Damage assessment of aircraft wing subjected to blast wave with finite element method and artificial neural network tool

Damage assessment of the wing under blast wave is essential to the vulnerability reduction design of aircraft. This paper introduces a critical relative distance prediction method of aircraft wing damage based on the back-propagation artificial neural network(BP-ANN), which is trained by finite element simulation results. Moreover, the finite element method(FEM) for wing blast damage simulation has been validated by ground explosion tests and further used for damage mode determination and damage characteristics analysis. The analysis results indicate that the wing is more likely to be damaged when the root is struck from vertical directions than others for a small charge. With the increase of TNT equivalent charge, the main damage mode of the wing gradually changes from the local skin tearing to overall structural deformation and the overpressure threshold of wing damage decreases rapidly. Compared to the FEM-based damage assessment, the BP-ANN-based method can predict the wing damage under a random blast wave with an average relative error of 4.78%. The proposed method and conclusions can be used as a reference for damage assessment under blast wave and low-vulnerability design of aircraft structures.

Speed Control of Travelling Wave Type Ultrasonic Motors Using Artificial Neural Network

Ultrasonic motor (USM) is a newly developed motor, and it has some excellent performances and useful features, therefore, it has been expected to be of practical use. However, the driving principle of USM is different from that of other electromagnetic type motors, and the mathematical model is complex to apply to motor control. Furthermore, the speed characteristics of the motor have heavy nonlinearity and vary with driving conditions. Hence, the precise speed control of USM is generally difficult. This paper proposes a new speed control scheme for USM using an artificial neural network. An accurate tracking response can be obtained by random initialization of the weights of the network owing to the powerful on line learning capability. Two prototype ultrasonic motors of travelling wave type were fabricated, both having 100 mm outer diameters of stator and piezoelectric ceramic. The usefulness and validity of the proposed control scheme are examined in experiments.

Prediction about residual stress and microhardness of material subjected to multiple overlap laser shock processing using artificial neural network

In this work,the nickel-based powder metallurgy superalloy FGH95 was selected as experimental material,and the experimental parameters in multiple overlap laser shock processing(LSP)treatment were selected based on orthogonal experimental design.The experimental data of residual stress and microhardness were measured in the same depth.The residual stress and microhardness laws were investigated and analyzed.Artificial neural network(ANN)with four layers(4-N-(N-1)-2)was applied to predict the residual stress and microhardness of FGH95 subjected to multiple overlap LSP.The experimental data were divided as training-testing sets in pairs.Laser energy,overlap rate,shocked times and depth were set as inputs,while residual stress and microhardness were set as outputs.The prediction performances with different network configuration of developed ANN models were compared and analyzed.The developed ANN model with network configuration of 4-7-6-2 showed the best predict performance.The predicted values showed a good agreement with the experimental values.In addition,the correlation coefficients among all the parameters and the effect of LSP parameters on materials response were studied.It can be concluded that ANN is a useful method to predict residual stress and microhardness of material subjected to LSP when with limited experimental data.

Application of artificial neural network to calculation of solitary wave run-up

The prediction of solitary wave run-up has important practical significance in coastal and ocean engineering, but the calculation precision is limited in the existing models. For improving the calculation precision, a solitary wave run-up calculation model was established based on artificial neural networks in this study. A back-propagation （BP） network with one hidden layer was adopted and modified with the additional momentum method and the auto-adjusting learning factor. The model was applied to calculation of solitary wave run-up. The correlation coefficients between the neural network model results and the experimental values was 0.996 5. By comparison with the correlation coefficient of 0.963 5, between the Synolakis formula calculation results and the experimental values, it is concluded that the neural network model is an effective method for calculation and analysis of solitary wave ran-up.

Artificial neural network model of constitutive relations for shock-prestrained copper

Data from the deformation on Split Hopkinson Bar were used for constructing an artificial neural network model. When putting the thermodynamic parameters of the metals into the trained network model, the corresponding yielding stress can be predicted. The results show that the systematic error is small when the objective function is 0.5 , the number of the nodes in the hidden layer is 6 and the learning rate is about 0.1 , and the accuracy of the rate error is less than 3%. [

An artificial neural network based deep collocation method for the solution of transient linear and nonlinear partial differential equations

A combined deep machine learning(DML)and collocation based approach to solve the partial differential equations using artificial neural networks is proposed.The developed method is applied to solve problems governed by the Sine–Gordon equation(SGE),the scalar wave equation and elasto-dynamics.Two methods are studied:one is a space-time formulation and the other is a semi-discrete method based on an implicit Runge–Kutta(RK)time integration.The methodology is implemented using the Tensorflow framework and it is tested on several numerical examples.Based on the results,the relative normalized error was observed to be less than 5%in all cases.

Forward prediction for tunnel geology and classification of surrounding rock based on seismic wave velocity layered tomography

Excavation under complex geological conditions requires effective and accurate geological forward-prospecting to detect the unfavorable geological structure and estimate the classification of surround-ing rock in front of the tunnel face.In this work,a forward-prediction method for tunnel geology and classification of surrounding rock is developed based on seismic wave velocity layered tomography.In particular,for the problem of strong multi-solution of wave velocity inversion caused by few ray paths in the narrow space of the tunnel,a layered inversion based on regularization is proposed.By reducing the inversion area of each iteration step and applying straight-line interface assumption,the convergence and accuracy of wave velocity inversion are effectively improved.Furthermore,a surrounding rock classification network based on autoencoder is constructed.The mapping relationship between wave velocity and classification of surrounding rock is established with density,Poisson’s ratio and elastic modulus as links.Two numerical examples with geological conditions similar to that in the field tunnel and a field case study in an urban subway tunnel verify the potential of the proposed method for practical application.

Simulation of Wave Forces on A Semi-Circular Breakwater Using Multilayer Feed Forward Network

In this paper, the Artificial Neural Network (ANN) is used to study the wave forces on a semi-circular breakwater. The process of establishing the network model for a specific physical problem is presented. Networks with double implicit layers have been studied by numerical experiments. 117 sets of experimental data are used to train and test the ANN. According to the results of ANN simulation, this method is proved to have good precision compared with experimental and numerical results.

HL-2A装置低频漂移波模数据库与机器学习初步研究

本文探索建立了HL-2A/3装置实验漂移波模数据库,并以此作为样本数据库,通过机器学习方法,利用人工神经网络预测托卡马克放电中漂移波模不稳定性的发生及其强度,为实现HL-2A/3等离子体实时参数控制提供参考。首先基于电子/离子温度梯度(η)、俘获电子份额(ε)、局域安全因子q和磁剪切s等4个基本参数构成的参数数据组(η,ε,q,s)作为变量,其他参数取有效的常数值,利用HD7代码计算相应模特征值数据,构建了一个低频漂移波模基本数据库。然后,基于BP神经网络与支持向量机(SVM)模型,分别进行了机器学习建模与编程实验,验证了对HL-2A装置离子温度梯度(ITG)\俘获电子模(TEM)不稳定性进行智能预测的可行性。研究结果表明,通过将参数集与数据集进一步扩充成完备数据库、并加快BP神经网络训练速度、或采用深度学习等更复杂模型,可以最终实现前述漂移波模预测目标。

基于BP神经网络的水中双爆源爆炸冲击波峰值压力预测模型研究

为了获得水中等质量两爆源同步爆炸时冲击波耦合中心的峰值压力计算模型,利用Autodyn计算得到不同药量和爆距下的峰值压力数据.一方面根据量纲分析确定的函数形式拟合数据从而获得峰值压力的计算公式;另一方面对药量、爆距及峰值压力三类数据进行对数变换和归一化,并将其分为训练集和测试集,然后将训练集代入BP神经网络进行训练,得到结构相对简单、均方误差最小的BP神经网络预测模型.结果表明:公式计算结果和BP神经网络模型计算得到的峰值压力与实际值吻合较好,公式计算值与实际值的平均相对误差为1.08%,BP神经网络预测值与实际值的平均相对误差为0.52%,与公式计算相比,BP神经网络能够以更少的数据样本容量实现更高的精度预测.

求解浅水波方程的并行物理信息神经网络算法

双曲守恒律方程是一类比较特殊的偏微分方程,其数值求解方法的研究一直是一个热点问题,一个显著特性是即使初始条件是光滑的,其解也可能会发展成间断。浅水波方程作为非线性双曲守恒律方程,由于间断解的存在,其精确求解存在很大困难。针对浅水波方程数值求解问题,本文基于PINN(Physics informed neural networks)反问题网络结构构造新的网络,构造的网络结构包括两个并行的神经网络,其中一个网络与已知状态数据(熵稳定格式加密求出)相关,另一个网络与方程本身相关。利用已知速度数据结合浅水波方程本身求解未知水深,最终通过一些数值算例验证网络的可行性。结果表明,新的网络结构可用于浅水波方程求解,利用速度数据可以较为精确地推算出水深。

基于U-net网络的频散曲线自动拾取方法研究

频散曲线拾取是面波勘探的关键环节,旨在通过频散曲线反演出地下横波速度结构。然而目前频散曲线拾取工作主要依靠人工拾取,耗时耗力。为此,本文通过将频散曲线拾取问题看成是图像分割问题,引入U-net网络,发展出一种频散曲线的自动拾取方法。该方法使用频散能量图并使其作为数据集,使用人工手动拾取的频散曲线作为标签集;通过卷积神经网络经由上采样、下采样和跳层链接等步骤学习图片特征,实现频散曲线的自动拾取。模型测试结果验证了利用U-net网络提取频散曲线的准确性。最后本文将训练好的网络模型应用于冰岛南部Ölfusá河岸的Arnarbæli周边试验场地的实际数据频散曲线提取,并将提取结果与手动拾取的频散曲线进行对比。结果表明,利用U-net网络提取频散曲线预测速度快,预测512×512×3大小的图片耗时为96 ms,预测准确度高。

基于人工神经网络的激光冲击复合强化残余压应力预测与分布调控

目的通过结合人工神经网络和激光冲击有限元仿真,以减少激光冲击强化最佳参数设计的迭代次数,提高参数优化效率。方法构建基于冲击波压力幅值的激光冲击强化Abaqus有限元模型。采用Vdload子程序与对应二次开发脚本形成光斑重叠区域残余应力的初始数据集。建立人工神经网络(ANN)算法模型,采用测试集对ANN模型进行测试,对超参数进行优化,对比分析不同机器学习算法的R2得分、MAE和RMSE。设计并优化镍铝青铜模型表面的残余应力大小与分布,对比分析经机器学习预测后的模型表面残余应力分布情况。结果经ANN预测整个面LSCP处理的模型表面形成了高达‒413 MPa的残余压应力,并且预测了均匀与非均匀的残余压应力分布;RMSE均方根误差仅为1.1891,既显示出较好的预测精度,又避免了模型的过拟合,保证了一定的泛化能力,模型综合性能远优于其他经典的ML算法回归模型。所预测的残余压应力分布模型均达到了较深的影响层深,且在1 Hz的脉冲重复频率下,最大效率达到了1.87 mm^(2)/s。结论激光冲击强化与机器学习的结合实现了易产生残余应力孔洞的镍铝青铜光斑重叠区域的最大残余压应力分布,且该方法优化出了整个表面的均匀与相对非均匀的残余压应力分布,为非均匀塑性应变引起镍铝青铜材料异质结构的形成开辟了新的设计途径。

基于人工神经网络的多源数据融合技术在浅层纵波速度调查中的应用

微测井是地震勘探中常用的一种近地表纵波速度调查方法,在场地条件和施工成本受限的情况下,该方法得到的速度解释剖面常存在横向分辨率不足的问题。利用静力触探法布设方便、成本低廉的优势,提出一种利用人工神经网络模型关联地层阻力和地层波速的方法,以期通过少量实测微测井实现大范围纵波速度结构的有效预测。该方法的实施流程如下:(1)两两配对静力触探和微测井数据以生成控制点位,以岩性变化为网络分裂条件,输入层神经元接收锥尖阻力、侧摩阻力和深度数据,输出层神经元接收纵波速度,在中间设置多个全连接隐藏层;(2)通过前馈训练机制更新隐藏层神经元参数;(3)将非控制点位的静力触探数据输入到训练好的神经网络模型以获取全区近地表纵波速度结构剖面。在苏北某场地进行方法测试和数据分析,结果证实岩性分层的精细度和训练样本量是决定模型表现的两个关键因素。人工神经网络法预测浅层纵波速度的准确率超过90%,在可靠性、分辨率以及鲁棒性方面都超越了现有的经验公式法,可以辅助判断地下虚反射界面和低降速带分布范围,是提高地震勘探浅层速度调查精度和效率的有益探索。

基于鱼群优化算法和Elman神经网络的短期电力负荷预测

精确的短期负荷预测允许用户选择合适的能源利用策略,并最大限度地降低电费支出。为实现更为精确且全局最优的短期负荷预测,提出一种基于鱼群优化算法和Elman神经网络的短期电力负荷预测方案。首先利用小波变换将时间序列分解成分量,并基于对立人工鱼群优化算法进行特征选择。接着基于Elman神经网络模型的水波优化算法进行短期负荷预测,从而显著提高了预测的精确度。最后应用逆小波变换得到每小时的负荷预测数据,借助武汉市电力负荷数据对所提方案进行验证评估。验证结果表明所提方案在冬季数据和夏季数据上的平均绝对百分比误差分别为1.43%和1.98%,明显优于支持向量机、混合网络和小波变换-神经进化算法。

Below the Data Range Prediction of Soft Computing Wave Reflection of Semicircular Breakwater

Coastal defenses such as the breakwaters are important structures to maintain the navigation conditions in a harbor.The estimation of their hydrodynamic characteristics is conventionally done using physical models,subjecting to higher costs and prolonged procedures.Soft computing methods prove to be useful tools,in cases where the data availability from physical models is limited.The present paper employs adaptive neuro-fuzzy inference system(ANFIS)and artificial neural network(ANN)models to the data obtained from physical model studies to develop a novel methodology to predict the reflection coefficient(Kr)of seaside perforated semicircular breakwaters under low wave heights,for which no physical model data is available.The prediction was done using the input parameters viz.,incident wave height(Hi),wave period(T),center-to-center spacing of perforations(S),diameter of perforations(D),radius of semicircular caisson(R),water depth(d),and semicircular breakwater structure height(hs).The study shows the prediction below the available data range of wave heights is possible by ANFIS and ANN models.However,the ANFIS performed better with R^2=0.9775 and the error reduced in comparison with the ANN model with R2=0.9751.Study includes conventional data segregation and prediction using ANN and ANFIS.

Application of Short-wave Near-infrared Reflectance Spectroscopy in Controlling Extract of Fructus Cnidii Using Supercritical Carbon Dioxide

Fructus cnidii （Chinese name shechuangzi） is the fruit produced by Cnidium monnieri （L.） Cusson （Umbelliferae）. It is a perennial herb that is used to treat skin-related diseases and gynecopathyell. Recent pharmacological studies have revealed crude extracts or components isolated from fructus cnidii possess antiallergic, antipruritic, antidermatophytic, antibacterial, antifungal, and antiosteoporotic activities. Osthole and imperatorin are the major compounds present in shechuangzi. They are often used as standards for the evaluation of the quality of shechuangzi products.

Synthesized Multi-Method to Detect and Classify Epileptic Waves in EEG

In order to sufficiently exploit the advantages of different signal processing methods, such as wavelet transformation (WT), artificial neural networks (ANN) and expert rules (ER),a synthesized multi-method was introduced to detect and classify the epileptic waves in the EEG data. Using this method, at first, the epileptic waves were detected from pre-processed EEG data at different scales by WT, then the characteristic parameters of the chosen candidates of epileptic waves were extracted and sent into the well-trained ANN to identify and classify the true epileptic waves,and at last, the detected epileptic waves were certificated by ER. The statistic results of detection and classification show that, the synthesized multi-method has a good capacity to extract signal features and to shield the signals from the random noise. This method is especially fit for the analysis of the biomedical signals in biomedical engineering which are usually non-placid and nonlinear.

基于ANN算法的海洋平台动力定位前馈-反馈控制方法

鉴于动力定位控制策略中的前馈控制与反馈控制方法具有不同的优缺点,提出一种基于人工神经网络(Artificial Neural Network,ANN)算法的二阶差频波浪力前馈控制与浮体位置反馈控制相结合的动力定位前馈-反馈控制方法,通过低频波浪载荷的超前预测提前做出反应,并对实时位置信息进行反馈控制以纠正前馈信息的误差及其累积效应,从而实现前馈、反馈两种控制模式的优势互补。对某半潜式平台动力定位模式进行数值仿真,验证所提出的前馈-反馈控制方法的可行性和有效性,与单一的前馈或反馈控制相比,平台动力定位的精度和稳定性得到显著提升。

面向高超声速飞行器的激波智能预测方法

高超声速飞行器激波位置的准确预测能够有效提升数值模拟的精度和效率。一方面,对高超声速飞行器激波附近网格进行正交和加密处理,可有效提升数值计算精度;另一方面,使用高超声速飞行器激波位置对计算网格进行修正,能够加速CFD计算收敛过程。提出了一种基于机器学习的高超声速飞行器激波智能预测方法,对典型高超声速飞行器外形进行激波位置的高效准确预测。首先,针对典型高超声速飞行器外形和典型飞行状态,使用数值模拟方法获得收敛的流场,并采用基于Mach数等值线的激波提取方法,从流场中判别激波面并提取构成激波面的关键点位置,形成训练数据;然后采用有监督学习算法,学习关键点位置,并利用二次曲线沿流向拟合关键点形成初步的激波线族;最后,基于剖面压力云图,构造基于投影压力图像的智能预测神经网络,对初步形成的激波线族进行修正,并获得三维激波面。大量的实验结果表明,激波预测模型能够对高超声速飞行器激波位置做出准确预测,预测的激波面与CFD数值计算结果中提取的激波面误差在10-4量级。