DAMAGE DETECTION IN STRUCTURES USING MODIFIED BACK-PROPAGATION NEURAL NETWORKS

A nonparametric structural damage detection methodology based on neuralnetworks method is presented for health monitoring of structure-unknown systems. In this approachappropriate neural networks are trained by use of the modal test data from a 'healthy' structure.The trained networks which are subsequently fed with vibration measurements from the same structurein different stages have the capability of recognizing the location and the content of structuraldamage and thereby can monitor the health of the structure. A modified back-propagation neuralnetwork is proposed to solve the two practical problems encountered by the traditionalback-propagation method, i.e., slow learning progress and convergence to a false local minimum.Various training algorithms, types of the input layer and numbers of the nodes in the input layerare considered. Numerical example results from a 5-degree-of-freedom spring-mass structure andanalyses on the experimental data of an actual 5-storey-steel-frame demonstrate thatneural-networks-based method is a robust procedure and a practical tool for the detection ofstructural damage, and that the modified back-propagation algorithm could improve the computationalefficiency as well as the accuracy of detection.

Optimization of processing parameters for microwave drying of selenium-rich slag using incremental improved back-propagation neural network and response surface methodology

In the non-linear microwave drying process, the incremental improved back-propagation （BP） neural network and response surface methodology （RSM） were used to build a predictive model of the combined effects of independent variables （the microwave power, the acting time and the rotational frequency） for microwave drying of selenium-rich slag. The optimum operating conditions obtained from the quadratic form of the RSM are： the microwave power of 14.97 kW, the acting time of 89.58 min, the rotational frequency of 10.94 Hz, and the temperature of 136.407 ℃. The relative dehydration rate of 97.1895% is obtained. Under the optimum operating conditions, the incremental improved BP neural network prediction model can predict the drying process results and different effects on the results of the independent variables. The verification experiments demonstrate the prediction accuracy of the network, and the mean squared error is 0.16. The optimized results indicate that RSM can optimize the experimental conditions within much more broad range by considering the combination of factors and the neural network model can predict the results effectively and provide the theoretical guidance for the follow-up production process.

Modeling water and carbon fluxes above summer maize field in North China Plain with back-propagation neural networks

In this work, datasets of water and carbon fluxes measured with eddy covariance technique above a summer maize field in the North China Plain were simulated with artificial neural networks (ANNs) to explore the fluxes responses to local environmental variables. The results showed that photosynthetically active radiation (PAR), vapor pressure deficit (VPD), air temperature (T) and leaf area index (LAI) were primary factors regulating both water vapor and carbon dioxide fluxes. Three-layer back-propagation neural networks (BP) could be applied to model fluxes exchange between cropland surface and atmosphere without using detailed physiological information or specific parameters of the plant.

A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis

Rainstorms are one of the most important types of natural disaster in China.In order to enhance the ability to forecast rainstorms in the short term,this paper explores how to combine a back-propagation neural network(BPNN)with synoptic diagnosis for predicting rainstorms,and analyzes the hit rates of rainstorms for the above two methods using the county of Tianquan as a case study.Results showed that the traditional synoptic diagnosis method still has an important referential meaning for most rainstorm types through synoptic typing and statistics of physical quantities based on historical cases,and the threat score(TS)of rainstorms was more than 0.75.However,the accuracy for two rainstorm types influenced by low-level easterly inverted troughs was less than 40%.The BPNN method efficiently forecasted these two rainstorm types;the TS and equitable threat score(ETS)of rainstorms were 0.80 and 0.79,respectively.The TS and ETS of the hybrid model that combined the BPNN and synoptic diagnosis methods exceeded the forecast score of multi-numerical simulations over the Sichuan Basin without exception.This kind of hybrid model enhanced the forecasting accuracy of rainstorms.The findings of this study provide certain reference value for the future development of refined forecast models with local features.

Predict typhoon-induced storm surge deviation in a principal component back-propagation neural network model

To reduce typhoon-caused damages, numerical and empirical methods are often used to forecast typhoon storm surge. However, typhoon surge is a complex nonlinear process that is difficult to forecast accurately. We applied a principal component back-propagation neural network (PCBPNN) to predict the deviation in typhoon storm surge, in which data of the typhoon, upstream flood, and historical case studies were involved. With principal component analysis, 15 input factors were reduced to five principal components, and the application of the model was improved. Observation data from Huangpu Park in Shanghai, China were used to test the feasibility of the model. The results indicate that the model is capable of predicting a 12-hour warning before a typhoon surge.

Preparation of ZrB_2-SiC Powders via Carbothermal Reduction of Zircon and Prediction of Product Composition by Back-Propagation Artificial Neural Network

Phase pure ZrB2-SiC composite powders were prepared after 1 450℃/3 h via carbothermal reduction route,by using ZrSiO4,B2O3 and carbon as the raw materials.The influences of firing temperature as well as the type and amount of additive on the phase composition of final products were detailedly investigated.The results indicated that the onset formation temperature of ZrB2-SiC was reduced to 1 400℃by the present conditions,and oxide additive（including CoSO4·7H2O,Y2O3 and TiO2）was effective in enhancing the decomposition of raw ZrSiO4,therefore accelerating the synthesis of ZrB2-SiC.Moreover,microstructural observation showed that the as-prepared ZrB2 and SiC respectively had well-defined hexagonal columnar and fibrous morphology.Furthermore,the methodology of back-propagation artificial neural networks（BP-ANNs）was adopted to establish a model for predicting the reaction extent（e g,the content of ZrB2-SiC in final product）in terms of various processing conditions.The results predicted by the as-established BP-ANNs model matched well with that of testing experiment（with a mean square error in 10^（-3） degree）,verifying good effectiveness of the proposed strategy.

Sound Quality Prediction of Vehicle Interior Noise under Multiple Working Conditions Using Back-Propagation Neural Network Model

This paper presents a back-propagation neural network model for sound quality prediction (BPNN-SQP) of multiple working conditions’ vehicle interior noise. According to the standards and regulations, four kinds of vehicle interior noises under operating conditions, including idle, constant speed, accelerating and braking, are acquired. The objective psychoacoustic parameters and subjective annoyance results are respectively used as the input and output of the BPNN-SQP model. With correlation analysis and significance test, some psychoacoustic parameters, such as loudness, A-weighted sound pressure level, roughness, articulation index and sharpness, are selected for modeling. The annoyance values of unknown noise samples estimated by the BPNN-SQP model are highly correlated with the subjective annoyances. Conclusion can be drawn that the proposed BPNN-SQP model has good generalization ability and can be applied in sound quality prediction of vehicle interior noise under multiple working conditions.

A back-propagation neural-network-based displacement back analysis for the identification of the geomechanical parameters of the Yonglang landslide in China

Xigeda formation is a type of hundredmeter-thick lacustrine sediments of being prone to triggering landslides along the trunk channel and tributaries of the upper Yangtze River in China. The Yonglang landslide located near Yonglang Town of Dechang County in Sichuan Province of China, which was a typical Xigeda formation landslide, was stabilized by anti-slide piles. Loading tests on a loading-test pile were conducted to measure the displacements and moments. The uncertainty of the tested geomechanical parameters of the Yonglang landslide over certain ranges would be problematic during the evaluation of the landslide. Thus, uniform design was introduced in the experimental design,and by which, numerical analyses of the loading-test pile were performed using Fast Lagrangian Analysis of Continua(FLAC3D) to acquire a database of the geomechanical parameters of the Yonglang landslide and the corresponding displacements of the loadingtest pile. A three-layer back-propagation neural network was established and trained with the database, and then tested and verified for its accuracy and reliability in numerical simulations. Displacement back analysis was conducted by substituting the displacements of the loading-test pile to the well-trained three-layer back-propagation neural network so as to identify the geomechanical parameters of the Yonglang landslide. The neuralnetwork-based displacement back analysis method with the proposed methodology is verified to be accurate and reliable for the identification of the uncertain geomechanical parameters of landslides.

Temperature prediction model for a high-speed motorized spindle based on back-propagation neural network optimized by adaptive particle swarm optimization

To predict the temperature of a motorized spindle more accurately,a novel temperature prediction model based on the back-propagation neural network optimized by adaptive particle swarm optimization(APSO-BPNN)is proposed.First,on the basis of the PSO-BPNN algorithm,the adaptive inertia weight is introduced to make the weight change with the fitness of the particle,the adaptive learning factor is used to obtain different search abilities in the early and later stages of the algorithm,the mutation operator is incorporated to increase the diversity of the population and avoid premature convergence,and the APSO-BPNN model is constructed.Then,the temperature of different measurement points of the motorized spindle is forecasted by the BPNN,PSO-BPNN,and APSO-BPNN models.The experimental results demonstrate that the APSO-BPNN model has a significant advantage over the other two methods regarding prediction precision and robustness.The presented algorithm can provide a theoretical basis for intelligently controlling temperature and developing an early warning system for high-speed motorized spindles and machine tools.

Simulation and optimization for synthetic technology of 2-chloro-4,6-dinitroresorcinol based on back-propagation neural network

Back-propagation neural network was applied to predict and optimize the synthetic technology of 2-chloro-4,6-dinitroresorcinol. A model was established based on back-propagation neural network using the experimental data of homogeneous design as the training sample set and the technological parameters were optimized by it. The optimal technological parameters are as follows： the reaction time is 4h, the reaction temperature is 80℃, the molar ratio of NaOH to 4,6-dinitro-1,2,3-trichlorobenzene is 5.5：1, the molar ratio of methanol to 4,6-dinitro-1,2,3- trichlorobenzene is 11：1, and the molar ratio of water to 4,6-dinitro-1,2,3-trichlorobenzene is 70：1. Under the optimal conditions, three groups of experiments were performed and the average yield of 2-chloro-4,6-dinitroresorcinol is 96.64%, the absolute error of it with the predicted value is -1.07%.

基于CSSA-BPNN模型的胶结充填体动态抗压强度预测

充填采矿法二步骤回采时胶结充填体稳定性受爆破扰动而降低。为快速准确地获得充填体动态抗压强度,利用分离式霍普金森压杆(SHPB)进行了40组不同应变率的单轴冲击实验,以灰砂比、充填体密度、养护龄期和平均应变率作为输入参数,充填体动态抗压强度作为输出参数,建立了一种基于Logistic混沌麻雀搜索算法(CSSA)优化BP神经网络(BPNN)的预测模型,并与传统BPNN和麻雀搜索算法优化的BPNN进行了对比分析。结果表明:CSSA-BPNN模型的平均相对误差为4.11%,预测值与实测值之间拟合的相关系数均在0.96以上,模型预测精度高。CSSA-BPNN模型的均方根误差为0.395 0 MPa,平均绝对误差为0.359 2 MPa,决定系数为0.995 2,均优于另外两种预测模型。实现了对充填体动态抗压强度的准确预测,可大幅减小物理实验量,为矿山胶结充填体的强度设计提供了一种新方法。

基于改进麻雀搜索算法优化BPNN的电阻点焊质量预测

电阻点焊技术由于具有高效、自动化程度高等焊接特点,被广泛应用于汽车、航空航天和公共交通等制造领域,由于焊点在封闭状态下进行,焊接过程存在诸多影响因素且无法直接检测,因此,准确预测电阻点焊质量是生产过程中必不可少的环节.本文以2219/5A06铝合金为研究对象,在3种不同的装配条件(包括间隙和间距)下进行电阻点焊工艺信号的分析,并进行人工智能建模.为了提高电阻点焊质量评价的性能和效率,本文采用Logistic-Tent(LT)复合映射改进麻雀搜索算法(SSA)对反向传播神经网络(LT-SSA-BPNN)模型进行优化,模型的输入和输出分别为多信号融合后的变量和熔核直径.实验结果表明,与传统的标准反向传播神经网络(BPNN)模型相比,经过LT-SSA-BP模型优化后,预测结果的平均绝对误差(MAE)、均方误差(MSE)和均方根误差(RMSE)分别降低了36.17%、17.55%和51.75%.同时,LT-SSA-BP神经网络在添加了不同间隙和间距条件作为训练集后,其预测稳定性明显提高,可以成功预测电阻点焊质量.

基于BPNN和MOOGA的高速联轴器多目标优化方法

针对高转速、复合工况下膜盘联轴器难以保证其强度特性问题,对已有膜盘联轴器强度及动力学特性进行了研究,提出了一种基于反向传播神经网络(BPNN)和多目标优化遗传算法(MOOGA)的高速联轴器多目标优化方法。首先,为了得到优化所需的关键参数,采用了正交实验结合多因素方差分析的方法,选取了联轴器优化参数;然后,基于已选取的关键参数,采用BPNN方法构建了截面应力和弯曲刚度的目标函数,并将其与多项式拟合方法进行了对比,对BPNN方法的精确性进行了验证;最后,采用MOOGA方法对目标函数进行了多目标优化,并将优化前后结果进行了对比分析。研究结果表明:采用BPNN结合MOOGA的方法对联轴器设计参数进行优化,在满足联轴器刚度需求的情况下,可有效降低联轴器膜盘的危险截面应力;优化后,联轴器危险应力减小了18.2%,弯曲刚度降低了5.05%,联轴器角向补偿能力增加了0.1°,从而证明了仿真的有效性。该结果可以为挠性联轴器参数优化设计提供参考。

基于MFO-BPNN的螺旋钻机钻速预测研究

针对利用现有经验公式所建立的螺旋钻机钻速预测模型存在准确度不足的问题,提出了一种基于飞蛾扑火算法(MFO)的反向传播神经网络(BPNN)钻速预测模型。首先,对MFO算法的基本原理进行了研究,构建了MFO算法优化BPNN的具体流程;接着,采集了江苏无锡某施工现场钻探数据,并分析了钻速影响因素,运用小波阈值降噪、归一化和灰色关联度分析等系列方法对采集数据进行了预处理,得到了训练和测试集;然后,将MFO算法运用于神经网络的权值和阈值训练,以代替原有梯度下降法,建立了MFO-BPNN钻速预测模型;最后,对上述预测模型与BPNN模型、遗传算法优化反向传播神经网络(GA-BPNN)模型以及粒子群优化算法优化反向传播神经网络(PSO-BPNN)模型的预测结果和评价指标进行了详细的对比分析。研究结果表明:运用MFO-BPNN建立的钻速预测模型,其可靠性达到了91.65%,其决定系数(R 2)优于其他3种预测模型,3项误差指标也是其中最低的,说明该模型的预测精度良好,适合于桩基础工程的实际应用,可为复杂因素影响下的钻速预测提供一种新思路。

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.

基于MCDM-BPNN的城市内涝风险评价及调蓄池选址

为建立一套较为完善的城市内涝风险评价体系,并据此确定调蓄池位置,首先,从积水风险、超载风险和边侧进流量3个维度构建评价指标,设计一种包括改进层次分析法(IAHP)、反熵权法(AEW)和优劣解距离法(TOPSIS)的混合多准则决策框架(MCDM);然后,将IAHP-AEW-TOPSIS模型分别与IAHP-TOPSIS、AEW-TOPSIS模型对比,通过斯皮尔曼排序相关系数验证排序一致性,通过计算变异系数、相对极差和灵敏度证实IAHP-AEW-TOPSIS模型的性能;最后,结合反向传播神经网络(BPNN),建立MCDM-BPNN模型,并以山西省某一内涝易发区域为例进行验证。结果表明:积水风险对城市内涝风险评价体系的影响最为显著,所占权重为0.46,其次为超载风险,所占权重为0.36;节点位置与连接管道数量很大程度上对该节点的内涝风险产生影响,在管道汇接处或汇流面积较大处内涝出现更为频繁;IAHP-AEW-TOPSIS模型在样本判别方面具有更好的性能;在5年与10年重现期下,MCDM-BPNN模型验证集准确率分别为93.3%和100%,能够准确快速模拟和预测城市洪水;应用案例设置调蓄池后,高、中、低风险节点数量分别为7、9、30和6、19、21,内涝溢流削减效果显著。

基于SSA-BPNN的锂离子电池SOH估算

锂离子电池已被广泛应用于储能系统与电动汽车中,精确地估算锂离子电池健康状态SOH(state-of-health)是保证系统安全可靠运行的必要条件。从容量的角度分析SOH,在恒流-恒压CC-CV(constant current-constant voltage)充电电压和温度曲线中提取了7个健康特征HI(health indicator)作为输入,基于数据驱动法提出了麻雀搜索算法-反向传播神经网络SSA-BPNN(sparrow search algorithm-back propagation neural network)的锂离子电池SOH估算方法,并应用数据增强进一步提高模型的鲁棒性,最终在NASA锂离子电池随机使用数据集上进行验证。通过与未采取数据增强的传统BP神经网络相比,获得SOH估算精度有明显提升,测试集SOH估算的最大绝对误差和均方根误差分别小于3%和1.32%,实验结果表明该方法兼顾误差小,收敛快,全局搜索能力且能够适应电池老化差异特性。

基于ADASYN数据平衡化的PSO-BPNN变压器套管故障诊断

变压器套管作为设备重要的绝缘部件,其绝缘性能直接影响着设备的安全运行。为诊断变压器套管绝缘状态,改善变压器套管油中溶解气体的小样本不平衡数据对变压器套管故障诊断结果的影响,使用粒子群优化结合反向传播神经网络(particle swarm optimization combined with back propagation neural network,PSO-BPNN)和自适应综合过采样(adaptive synthetic sampling,ADASYN)算法对变压器套管进行故障诊断。首先收集变压器套管的历史故障数据,建立具有明确故障类别的变压器套管油中溶解气体样本集,并通过ADASYN算法对原始数据中的少数类样本进行合成,得到平衡后的故障数据,然后将平衡后的油中溶解气体作为模型输入,故障状态作为标签输出,通过PSO-BPNN模型对变压器套管进行诊断,最后在原始样本集下使用反向传播神经网络(back propagation neural network,BPNN)、遗传结合反向传播神经网络(genetic combined with back propagation neural network,G-BPNN)算法、布谷鸟搜索结合反向传播神经网络(cuckoo search combined with back propagation neural network,CS-BPNN)算法以及PSO-BPNN模型对套管进行诊断。结果表明,针对变压器油纸套管绝缘状态进行故障诊断的多个模型中,基于ADASYN平衡数据后的PSO-BPNN模型和其他模型相比准确度最高,能有效减小小样本不平衡数据对诊断结果的影响,为判断变压器油纸套管绝缘性能提供了有效方法。

基于SBAS-InSAR和BPNN的铀尾矿坝形变智能监测与预测

为提高铀尾矿库退役治理的监测工作效率,提出一个基于小基线合成孔径雷达干涉测量(SBAS-InSAR)技术和反向传播神经网络(BPNN)的铀尾矿库形变智能监测与预测模型。首先,利用SBAS-InSAR技术得到铀尾矿库2020年12月—2022年12月的累计形变量与年均形变速率,并用第一拦水坝的7个全球导航卫星系统(GNSS)监测站验证InSAR监测值的精度;然后,选取铀尾矿库中的雷公塘坝、南坡横坝、战斗坝和松林坝4个坝段的累计沉降量并结合降雨量进行沉降分析;最后,随机提取铀尾矿坝100个沉降点的累积沉降数据,通过BPNN预测铀尾矿坝的形变。结果表明:2年间铀尾矿库的形变速率在-60.06~34.94 mm/a,铀尾矿坝整体处于下沉状态,累计沉降量最大为-46.67 mm。BPNN预测值与实际监测值的平均绝对误差为0.586 mm,均方误差为0.624 mm。

基于改进BPNN的5G通信网络流量预测

为提高5G网络流量预测结果的准确性,提出一种基于改进反向传播神经网络(Back Propagation Neural Network,BPNN)的5G通信网络流量预测方法,采用阿基米德优化算法(Arithmetic Optimization Algorithm,AOA)优化BPNN的权系数和阈值,建立基于AOA-BPNN的5G通信网络流量预测模型。采用某5G基站的网络通信流量监测数据进行仿真分析,并与其他方法的预测效果进行对比,结果表明,AOA-BPNN模型预测结果的平均相对误差和均方根误差分别为4.25%和0.522 GB,预测精度高于其他方法,验证了所提方法的实用性和优越性。