Application of artificial neural networks in optimal tuning of tuned mass dampers implemented in high-rise buildings subjected to wind load

High-rise buildings are usually considered as flexible structures with low inherent damping. Therefore, these kinds of buildings are susceptible to wind-induced vibration. Tuned Mass Damper（TMD） can be used as an effective device to mitigate excessive vibrations. In this study, Artificial Neural Networks is used to find optimal mechanical properties of TMD for high-rise buildings subjected to wind load. The patterns obtained from structural analysis of different multi degree of freedom（MDF） systems are used for training neural networks. In order to obtain these patterns, structural models of some systems with 10 to 80 degrees-of-freedoms are built in MATLAB/SIMULINK program. Finally, the optimal properties of TMD are determined based on the objective of maximum displacement response reduction. The Auto-Regressive model is used to simulate the wind load. In this way, the uncertainties related to wind loading can be taken into account in neural network’s outputs. After training the neural network, it becomes possible to set the frequency and TMD mass ratio as inputs and get the optimal TMD frequency and damping ratio as outputs. As a case study, a benchmark 76-story office building is considered and the presented procedure is used to obtain optimal characteristics of the TMD for the building.

Fractional Order Environmental and Economic Model Investigations Using Artificial Neural Network

The motive of these investigations is to provide the importance and significance of the fractional order(FO)derivatives in the nonlinear environmental and economic(NEE)model,i.e.,FO-NEE model.The dynamics of the NEE model achieves more precise by using the form of the FO derivative.The investigations through the non-integer and nonlinear mathematical form to define the FO-NEE model are also provided in this study.The composition of the FO-NEEmodel is classified into three classes,execution cost of control,system competence of industrial elements and a new diagnostics technical exclusion cost.The mathematical FO-NEE system is numerically studied by using the artificial neural networks(ANNs)along with the Levenberg-Marquardt backpropagation method(ANNs-LMBM).Three different cases using the FO derivative have been examined to present the numerical performances of the FO-NEE model.The data is selected to solve the mathematical FO-NEE system is executed as 70%for training and 15%for both testing and certification.The exactness of the proposed ANNs-LMBM is observed through the comparison of the obtained and the Adams-Bashforth-Moulton database results.To ratify the aptitude,validity,constancy,exactness,and competence of the ANNs-LMBM,the numerical replications using the state transitions,regression,correlation,error histograms and mean square error are also described.

NONLINEAR MODELING AND CONTROLLING OF ARTIFICIAL MUSCLE SYSTEM USING NEURAL NETWORKS

The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is designed. The recursive prediction error (RPE)algorithm which yields faster convergence than back propagation (BP) algorithm is applied to trainthe neural networks. The realization of RPE algorithm is given. The difference of modeling ofartificial muscles using neural networks with different input nodes and different hidden layer nodesis discussed. On this basis the nonlinear control scheme using neural networks for artificialmuscle system has been introduced. The experimental results show that the nonlinear control schemeyields faster response and higher control accuracy than the traditional linear control scheme.

Design of a Computational Heuristic to Solve the Nonlinear Liénard Differential Model

In this study,the design of a computational heuristic based on the nonlinear Liénard model is presented using the efficiency of artificial neural networks(ANNs)along with the hybridization procedures of global and local search approaches.The global search genetic algorithm(GA)and local search sequential quadratic programming scheme(SQPS)are implemented to solve the nonlinear Liénard model.An objective function using the differential model and boundary conditions is designed and optimized by the hybrid computing strength of the GA-SQPS.The motivation of the ANN procedures along with GA-SQPS comes to present reliable,feasible and precise frameworks to tackle stiff and highly nonlinear differentialmodels.The designed procedures of ANNs along with GA-SQPS are applied for three highly nonlinear differential models.The achieved numerical outcomes on multiple trials using the designed procedures are compared to authenticate the correctness,viability and efficacy.Moreover,statistical performances based on different measures are also provided to check the reliability of the ANN along with GASQPS.

Neural Network Nonlinear Predictive Control Based on Tent-map Chaos Optimization

With the unique ergodicity,irregularity,and special ability to avoid being trapped in local optima,chaos optimization has been a novel global optimization technique and has attracted considerable attention for application in various fields,such as nonlinear programming problems.In this article,a novel neural network nonlinear predic- tive control(NNPC)strategy based on the new Tent-map chaos optimization algorithm(TCOA)is presented.The feedforward neural network is used as the multi-step predictive model.In addition,the TCOA is applied to perform the nonlinear rolling optimization to enhance the convergence and accuracy in the NNPC.Simulation on a labora- tory-scale liquid-level system is given to illustrate the effectiveness of the proposed method.

Numerical Computational Heuristic Through Morlet Wavelet Neural Network for Solving the Dynamics of Nonlinear SITR COVID-19

The present investigations are associated with designing Morlet wavelet neural network(MWNN)for solving a class of susceptible,infected,treatment and recovered(SITR)fractal systems of COVID-19 propagation and control.The structure of an error function is accessible using the SITR differential form and its initial conditions.The optimization is performed using the MWNN together with the global as well as local search heuristics of genetic algorithm(GA)and active-set algorithm(ASA),i.e.,MWNN-GA-ASA.The detail of each class of the SITR nonlinear COVID-19 system is also discussed.The obtained outcomes of the SITR system are compared with the Runge-Kutta results to check the perfection of the designed method.The statistical analysis is performed using different measures for 30 independent runs as well as 15 variables to authenticate the consistency of the proposed method.The plots of the absolute error,convergence analysis,histogram,performancemeasures,and boxplots are also provided to find the exactness,dependability and stability of the MWNN-GA-ASA.

Artificial neural network optimized by differential evolution for predicting diameters of jet grouted columns

A novel and effective artificial neural network(ANN) optimized using differential evolution(DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters.The proposed computational method adopts the DE algorithm to tackle the difficulties in the training and performance of neural networks and optimize the four quintessential hyper-parameters(i.e.the epoch size,the number of neurons in a hidden layer,the number of hidden layers,and the regularization parameter) that govern the neural network efficacy.This approach is further enhanced by a stochastic gradient optimization algorithm to allow ’expensive’ computation efforts.The ANN-DE is first trained using a prepared jet grouting dataset,then verified and compared with the prevalent machine learning tools,i.e.neural networks and support vector machine(SVM).The results show that,the ANN-DE outperforms the existing methods for predicting the diameter of jet grouting columns since it well balances training efficiency and model performance.Specifically,the ANN-DE achieved root mean square error(RMSE)values of 0.90603 and 0.92813 for the training and testing phases,respectively.The corresponding values were 0.8905 and 0.9006 for the optimized ANN,then,0.87569 and 0.89968 for the optimized SVM,respectively.The proposed paradigm is bound to be useful for solving various geotechnical engineering problems regardless of multi-dimension and nonlinearity.

Neural Network Based Thermal Analysis of Ultradeep Submicron Digital Circuit Design

With a reduction in transistor dimensions to the nanoscale regime of 45 nm or less, quantum mechanical effects begin to reveal themselves and have an impact on key device performance parameters. As a result, in order to develop simulation tools that can be used for the design of nanoscale transistors in the future, new theories and modelling methodologies must be developed that properly and effectively capture the physics of quantum transport. An artificial neural network(ANN) is used in this paper to examine nanoscale CMOS circuits and predict the performance parameters of CMOS-based digital inverters for a temperature range of 300 K to 400 K. The training algorithm included three hidden layers with sizes of 20, 10, and 8, as well as a function fitting ANN with Bayesian Backpropagation Regularization. Further, simulation through HSPICE using Predictive Technology Model(PTM) nominal parameters has been done to compare with ANN(trained using an analytical model) results. The obtained results lie within the acceptable range of 1%-10%. Moreover, it has also been demonstrated that the ANN simulation provides a speed improvement of around 85 % over the HSPICE simulation, and that it can be easily integrated into software tools for designing and simulating complicated CMOS logic circuits.

基于人工神经网络模型的碳排放预测研究进展

碳排放是一个受多因素交互作用的动态过程,准确预测碳排放量有利于碳减排措施的制定。由于碳排放本身模型具有动态变化性、非线性、社会性等特点,传统预测方法不能满足实际情况的需要。人工神经网络模型能够较好地描述碳排放时间系列数据的非线性特性,被广泛应用于预测国家、区域、行业等层面的碳排放量变化。其中,误差反向传播(Back Propagation,BP)神经网络模型和长短期记忆(Long Short-Term Memory,LSTM)神经网络模型备受关注。在模型预测过程中,通过识别目标模型的碳排放影响因素类型、提高输入层数据的准确性、构建适宜的线性—非线性耦合的组合模型等途径,进一步提高模型预测的准确性。研究结果对人工神经网络模型在碳排放预测中的应用情况进行梳理,为碳排放预测技术的进一步发展提供参考。

基于离散Hopfield模式识别样本的GRNN非线性组合短期风速预测模型

利用实时风速数据,建立基于离散Hopfield模式识别样本的广义回归神经网络(GRNN)非线性组合预测模型。在风速数据样本集经二维小波阈值去噪处理后,基于离散Hopfield识别历史数据中与待预测样本最相似的数据,并作为训练样本;将支持向量机、BP神经网络和Elman神经网络分别进行单项预测的结果作为输入向量,经GRNN进行非线性组合预测。采用某风电场的实际风速数据进行预测,结果验证了该预测模型的正确性和有效性。

基于实测数据融合的堆芯物理模型反演优化方法及工业验证研究

由于堆芯运行过程中的组件辐照生长、冷却剂高速冲击等因素,燃料组件不可避免地会出现弯曲现象。但机组运行期间无法直接测量燃料组件弯曲状态,导致数值模拟采用的堆芯物理模型与真实堆芯状态之间存在差异,直观上表现为堆芯功率分布的计算值与实测值存在显著误差。为了提高数值模拟精度,本文开展了基于实测数据融合的堆芯物理模型反演优化方法研究:采用人工神经网络算法,通过大量样本训练建立堆芯物理模型与实测数据物理场之间的显式函数关系;基于三维变分算法和实测数据物理场,建立物理模型反演优化代价函数,通过实测数据反演优化得到与真实状态更为接近的堆芯物理模型。为了实现方法验证,本文利用国内某商用压水堆核电厂的功率分布实测数据对堆芯燃料组件弯曲实现了反演优化。数值结果表明:采用反演优化得到的堆芯物理模型,可将堆芯功率分布计算误差的最大值由13.4%降至7.7%,显著提升了堆芯数值模拟结果的精度。因此,本文提出的基于实测数据融合的堆芯物理模型反演优化方法能够显著提高堆芯数值模拟的精度,在核反应堆数字孪生技术研发中具有重要的应用价值。

基于人工神经网络智能算法的9310钢本构模型优化

目的研究9310钢在变形温度为800~1200℃、应变速率为0.01~50s-1和高度压下量为70%条件下的热变形行为,建立预测效果相对较好的9310钢本构模型。方法使用Gleeble-3800热模拟机对9310钢进行等温恒应变速率热压缩实验,基于热压缩实验数据,分析了应变速率对9310钢流动软化效应的影响,建立了考虑应变补偿的Arrhenius本构模型与支持向量回归(SVR)本构模型,并进行了模型精度分析,之后引入人工神经网络(ANN)智能算法优化了Arrhenius本构模型。结果与变形温度相比,应变速率对9310钢流动软化效应的影响更为显著。相较于支持向量回归(SVR)本构模型,考虑应变补偿的Arrhenius本构模型精度更高,其相关系数R为0.9934,平均相对误差(AARE)和均方误差(MSE)分别为0.0556和89.362,它在预测高应变速率(1、10、50 s-1)流动应力时出现了较大偏差,经ANN智能算法优化后,相关系数R提高至0.9991,AARE和MSE分别降至0.0199和9.998,且绝对误差在±10MPa以内的预测流动应力占比为98.34%。结论在低应变速率(0.01 s-1)下软化效应更强,在高应变速率(10 s-1)下再结晶程度较低,软化效应较弱。ANN智能算法优化后的Arrhenius本构模型具有较高的精度,能较准确地预测9310钢的流动行为。

基于模拟退火的Hopfield网全局优化方法

为了改进Hopfield神经网络在多极点函数优化和组合优化中存在的某些缺陷,并影响着一些优化问题求解中的正确性和有效性的现实问题,将模拟退火智能优化算法与Hopfield神经网络有机结合,优势互补,提出了一种基于模拟退火的Hopfield神经网络混合全局优化算法(SA-HNN),新算法很大程度上避免了Hopfield神经网络优化陷入局部极小的缺陷,同时兼顾了算法的效率。通过典型的多极点函数优化和TSP组合优化问题求解,实验表明:SA-HNN混合优化算法具有帮助Hopfield网络摆脱局部极小点的能力并能得到较好的结果,有一定的工程实用价值。

推广的Hopfield神经网络模型

本文推广了Hopfield神经网络模型,对能量公式中的函数只要求一阶偏导数存在且连续即可,这就扩展了神经网络方法在求解组合优化问题中的应用。

格氏栲天然林灌木生物量模型研究

为探索适宜方法预测格氏栲天然林灌木生物量,以福建三明格氏栲自然保护区4种灌木的实测数据为基础,构建总生物量与各分量生物量的非线性独立模型。运用相容性模型解决生物量相容性问题,采用加权回归法消除模型的异方差。接着建立人工神经网络,与相容性模型进行精度对比,比较模型优劣。结果表明,1)4种灌木总量和各分量的生物量独立模型总体上受地径因子影响更大,二元模型在精度上要优于一元模型,决定系数(R^(2))基本提高了0.02以上。2)相容性模型与独立模型在精度上的差别不大,在某些分量模型的精度上甚至有所下降。3)人工神经网络预测灌木生物量在精度上相较相容性模型有明显提升,人工神经网络总量和各分量生物量模型较对应相容性模型R^(2)大部分可提高0.03以上,提高值最大可达0.21,且对相容性模型中精度较低的模型也有较好的预测效果,相容性模型中R^(2)<0.6的分量其人工神经网络模型R^(2)可提高0.08以上。总体来看,采用相容性模型可解决生物量不相容的问题;而人工神经网络预测精度较传统模型更高,当传统模型表现一般时更值得选择用于生物量预测。运用2种模型进行对比,旨在为准确预估格氏栲天然林灌木生物量提供理论参考。

Modeling and Optimizing of Deformed Steel Bars Hot Rolling

Based on experimental data, a nonlinear model about tensile strength and technical parameters such as Mn and St content, finishing rolling speed and finishing rolling temperature for deformed steel bars in the process of hot rolling was established by using artificial neural networks. The model can be optimized with a genetic algorithm. The optimum rolling parameters were obtained.

用Hopfield网络模型解决林种树种结构优化问题

叙述了Hopfield网络的优化原理,并采用Hopfield网络建立了林种树种结构优化模型,经计算机模拟,结果是可靠的;其目标函数可为非线性,与线性规划相比,其应用前景更广,为林业系统结构优化提供了一种新的方法.

基于DPSO-LSTM超参数调优的股市价格预测

长短期记忆网络(Long Short-Term Memory,LSTM)适合处理和预测时间序列中间隔和延迟较长的重要事件。由于其复杂的网络结构、不确定的超参数和耗时的网络训练,使得人工寻找高效的网络配置成为一项具有挑战性的工作。文中采用分布式粒子群算法(Distributed Particle Swarm Optimization,DPSO)来有效解决LSTM的超参数调优问题,研究LSTM中最优的隐藏元个数、激活函数以及学习率等超参数的选择,寻找高性能的LSTM。基于沪深300历史交易数据进行价格预测,实验结果表明该方法是有效的,这为超参数调优与股市价格预测提供了新的思路和方法。

Hopfield-Tank模型的收敛性证明

本文研究了Hopfield－Tank能量函数在Hopfield网络中的收敛性以及优化率方面的问题．虽然离散的Hopfield网络模型与连续的Hopfield网络模型都有严格的收敛性证明，但是HopfieldTank模型一直没有人给出严格的收敛性证明．本文指出连续的Hopfield网络模型与Hopfield－Tank模型是有区别的，所以需要另外给出Hopfield-Tank模型的收敛性证明．因此本文给出了Hopfield－Tank模型的收敛性证明，这一证明使Hopfield网络的优化计算理论更加完善．文中还讨论了网络参数1／τ对极小点的影响以及合适的取值范围．

辽宁省人口老龄化趋势预测——基于超参数优化的人工神经网络模型

为积极应对人口老龄化,依据辽宁省第七次全国人口普查数据,分析了人口老龄化的发展现状和特征。基于人工神经网络模型对辽宁省2022-2035年未来的65周岁以上人口所占比重发展趋势进行了预测分析,结果表明:选用5层神经网络结构模型,每层神经元数量为23,学习率为0.09462,训练得到的相对误差最小为0.0205。预测到2025年、2030年、2035年辽宁省65周岁及以上老年人口所占比重为21.23%、23.01%、23.77%,呈现稳定增长的趋势,老年人口规模不断增加,老龄化程度持续加深。根据模型的预测结果分析,提出了相应的对策建议:即发展老龄产业为老年人口服务;建立和完善以“社区为依托、养老机构为支撑、家庭为核心”的养老服务体系;开发利用老年人力资源,使之老有所用、老有所为。