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

Phase pure ZrB_2-SiC composite powders were prepared after 1 450℃/3 h via carbothermal reduction route,by using ZrSiO_4,B_2O_3 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 ZrB_2-SiC was reduced to 1 400℃by the present conditions,and oxide additive(including CoSO_4·7H_2O,Y_2O_3 and TiO_2)was effective in enhancing the decomposition of raw ZrSiO_4,therefore accelerating the synthesis of ZrB_2-SiC.Moreover,microstructural observation showed that the as-prepared ZrB_2 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 ZrB_2-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.

A Method for Solving Computer-Aided Product Design Optimization Problem Based on Back Propagation Neural Network

Because of the powerful mapping ability, back propagation neural network (BP-NN) has been employed in computer-aided product design (CAPD) to establish the property prediction model. The backward problem in CAPD is to search for the appropriate structure or composition of the product with desired property, which is an optimization problem. In this paper, a global optimization method of using the a BB algorithm to solve the backward problem is presented. In particular, a convex lower bounding function is constructed for the objective function formulated with BP-NN model, and the calculation of the key parameter a is implemented by recurring to the interval Hessian matrix of the objective function. Two case studies involving the design of dopamine β-hydroxylase (DβH) inhibitors and linear low density polyethylene (LLDPE) nano composites are investigated using the proposed method.

一种LM-BP加速搜索的周跳探测与修复方法

针对传统三频周跳探测与修复方法中的不敏感、漏检以及效率较低等问题,提出一种基于莱文伯格-马夸特(LM)-反向传播(BP)神经网络加速搜索法的伪距相位组合与电离层残差组合联合周跳探测与修复方法:利用2个伪距相位组合以减少不敏感周跳数量,利用1个电离层残差组合以提高小周跳探测敏感度;在构成3个线性无关的组合观测值后,使用LM-BP加速搜索算法进行周跳探测与修复。实验结果表明,相对常规的伪距相位组合与电离层残差组合联合方法,该方法能够提高周跳探测与修复性能,可探测小至1个的周跳,探测与修复整体时效有较大提升。

基于GA-BP神经网络的风电功率预测方法研究

为了解决风电功率预测易受各种因素影响产生异常数据导致预测准确度不高的问题,提出了一种基于遗传算法-反向传播(GA-BP)神经网络的风电功率预测方法。首先,通过数学模型中的四分位算法对异常数据进行识别,并通过加入带通滤波器剔除异常数据。然后,在风电功率预测的方法上设计新型GA-BP神经网络算法,通过自检验及循环检测的方式获得准确的风电功率预测结果。试验结果表明,该方法不仅有很强的异常数据识别能力,而且在进行风电功率预测时可以保持90%以上的准确率,具有良好的数据处理稳定性。该研究大幅提升了风电功率预测的工作效率,为风电功率预测技术的进一步发展提供了技术参考。

PREDICTION OF FLOW STRESS OF HIGH-SPEED STEEL DURING HOT DEFORMATION BY USING BP ARTIFICIAL NEURAL NETWORK

The hot deformation behavior of TI (18W-4Cr-1V) high-speed steel was investigated by means of continuous compression tests performed on Gleeble 1500 thermomechan- ical simulator in a wide range of tempemtures (950℃-1150℃) with strain rotes of 0.001s-1-10s-1 and true strains of 0-0. 7. The flow stress at the above hot defor- mation conditions is predicted by using BP artificial neural network. The architecture of network includes there are three input parameters:strain rate,temperature T and true strain , and just one output parameter, the flow stress ,2 hidden layers are adopted, the first hidden layer includes 9 neurons and second 10 negroes. It has been verified that BP artificial neural network with 3-9-10-1 architecture can predict flow stress of high-speed steel during hot deformation very well. Compared with the prediction method of flow stress by using Zaped-Holloman parumeter and hyperbolic sine stress function, the prediction method by using BP artificial neurul network has higher efficiency and accuracy.

FORCE RIPPLE SUPPRESSION TECHNOLOGY FOR LINEAR MOTORS BASED ON BACK PROPAGATION NEURAL NETWORK

Various force disturbances influence the thrust force of linear motors when a linear motor (LM) is running.Among all of force disturbances,the force ripple is the dominant while a linear motor runs in low speed.In order to suppress the force ripple,back propagation(BP) neural network is proposed to learn the function of the force ripple of linear motors,and the acquisition method of training samples is proposed based on a disturbance observer.An off-line BP neural network is used mainly because of its high running efficiency and the real-time requirement of the servo control system of a linear motor.By using the function,the force ripple is on-line compensated according to the position of the LM.The experimental results show that the force ripple is effectively suppressed by the compensation of the BP neural network.

Surface Quality Evaluation of Fluff Fabric Based on Particle Swarm Optimization Back Propagation Neural Network

Aiming at the problem that back propagation(BP)neural network predicts the low accuracy rate of fluff fabric after fluffing process,a BP neural network model optimized by particle swarm optimization(PSO)algorithm is proposed.The sliced image is obtained by the principle of light-cutting imaging.The fluffy region of the adaptive image segmentation is extracted by the Freeman chain code principle.The upper edge coordinate information of the fabric is subjected to one-dimensional discrete wavelet decomposition to obtain high frequency information and low frequency information.After comparison and analysis,the BP neural network was trained by high frequency information,and the PSO algorithm was used to optimize the BP neural network.The optimized BP neural network has better weights and thresholds.The experimental results show that the accuracy of the optimized BP neural network after applying high-frequency information training is 97.96%,which is 3.79%higher than that of the unoptimized BP neural network,and has higher detection accuracy.

Combinatorial Optimization Based Analog Circuit Fault Diagnosis with Back Propagation Neural Network

Electronic components' reliability has become the key of the complex system mission execution. Analog circuit is an important part of electronic components. Its fault diagnosis is far more challenging than that of digital circuit. Simulations and applications have shown that the methods based on BP neural network are effective in analog circuit fault diagnosis. Aiming at the tolerance of analog circuit,a combinatorial optimization diagnosis scheme was proposed with back propagation( BP) neural network( BPNN).The main contributions of this scheme included two parts:( 1) the random tolerance samples were added into the nominal training samples to establish new training samples,which were used to train the BP neural network based diagnosis model;( 2) the initial weights of the BP neural network were optimized by genetic algorithm( GA) to avoid local minima,and the BP neural network was tuned with Levenberg-Marquardt algorithm( LMA) in the local solution space to look for the optimum solution or approximate optimal solutions. The experimental results show preliminarily that the scheme substantially improves the whole learning process approximation and generalization ability,and effectively promotes analog circuit fault diagnosis performance based on BPNN.

Parameter Self - Learning of Generalized Predictive Control Using BP Neural Network

This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.

Structural form selection of the high-rise buildingwith the improved BP neural network

As civil engineering technology development,the structural form selection is more and more critical in design of high-rise buildings.However,structural form selection involves expertise knowledge and changes with the environment which makes the task arduous.An approach utilizing improved back propagation(BP)neural network optimized by the Levenberg-Marquardt(L-M)algorithm is proposed to extract the main controlling factors of structural form selection.Then,an intelligent expert system with artificial neural network is constructed to design high-rise buildings structure effectively.The experiment tests the model in 15 well-known architecture samples and get the prediction accuracy of 93.33%.The results show that the method is feasible and can help designers select the appropriate structural form.

基于GA-BP神经网络的软土路基运营期沉降预测

为了实现高速公路软土路基沉降的准确预测,采用遗传算法(GA)优化BP神经网络,研究3种输入对预测结果精度的影响.选取时间t以及其15 d前的沉降量S_(t-15)和平均沉降速率v_(t-15)为影响因素,在t、t-S_(t-15)、t-S_(t-15)-v_(t-15)三种输入下,分别取某高速公路软土路基运营期实测沉降数据的前50%、80%为训练集,余下原始数据为测试集,重复训练10次后取平均值作为输出值.采用决定系数(R^(2))来判别模型拟合度,均方根误差(RMSE)和平均绝对百分比误差(MAPE)作为模型性能的评价指标.结果表明:3种输入的R^(2)均大于0.99;训练集占原始数据的比例为50%时,t-S_(t-15)输入的预测误差最小,RMSE为1.31 mm,MAPE为4.71%;训练集占原始数据的比例为80%时,t-S_(t-15)-v_(t-15)输入的预测误差最小,RMSE为0.29 mm,MAPE为1.00%.t、t-S_(t-15)、t-S_(t-15)-v_(t-15)三种输入都可对路基沉降进行预测,其中t-S_(t-15)-v_(t-15)输入下取实测沉降数据的80%作为训练集时预测结果最精确.

AGGREGATE VOLUMETRIC ESTIMATION BASED ON PCA AND MOMENTUM-ENHANCED BP NEURAL NETWORK

This paper proposes a Back Propagation (BP) neural network with momentum enhancement aiming to achieving the smooth convergence for aggregate volumetric estimation purpose. Network inputs are first selected by optically measuring the eight geometry-related parameters from the given particle image. To simplify the network structure, principal component analysis technique is applied to reduce the input dimension. The specific network structure is finalized based on both empirical expertise and analysis on selecting the appropriate number of neurons in hidden layer. The network is trained using the finite number of randomly-picked particles. The training and test results suggest that, compared to the generic BP network, the training duration of the proposed neural network is greatly attenuated, the complexity of the network structure is largely reduced, and the estimation precision is within 2%, being sufficiently up to technical satisfaction.

基于动量自适应学习率PSO-BP神经网络的钻速预测模型研究

机械钻速(rate of penetration,ROP)是钻井作业优化和减少成本的关键因素,钻井时有效地预测ROP是提升钻进效率的关键。由于井下钻进时复杂多变的情况和地层的非均质性,通过传统的ROP方程和回归分析方法来预测钻速受到了一定的限制。为了实现对钻速的高精度预测,对现有BP (back propagation)神经网络进行优化,提出了一种新的神经网络模型,即动态自适应学习率的粒子群优化BP神经网络,利用录井数据建立目标井预测模型来对钻速进行预测。在训练过程中对BP神经网络进行优化,利用启发式算法,即附加动量法和自适应学习率,将两种方法结合起来形成动态自适应学习率的BP改进算法,提高了BP神经网络的训练速度和拟合精度,获得了更好的泛化性能。将BP神经网络与遗传优化算法(genetic algorithm,GA)和粒子群优化算法(particle swarm optimization,PSO)结合,得到优化后的动态自适应学习率BP神经网络。研究利用XX8-1-2井的录井数据进行实验,对比BP神经网络、PSO-BP神经网络、GA-BP神经网络3种不同的改进后神经网络的预测结果。实验结果表明:优化后的PSO-BP神经网络的预测性能最好,具有更高的效率和可靠性,能够有效的利用工程数据,在有一定数据采集量的区域提供较为准确的ROP预测。

基于IPSO-BP神经网络的WSNs数据融合算法

针对无线传感器网络(WSNs)数据融合算法中反向传播(BP)神经网络存在对初值敏感、收敛速度慢、易陷入局部最优解等问题,提出基于改进粒子群优化BP(IPSO-BP)神经网络的WSNs数据融合算法。首先,用细菌觅食算法的趋化、迁徙算子对粒子群优化(PSO)算法进行改进;然后,用IPSO算法优化BP神经网络的权值和阈值,再引入到WSNs数据融合中,簇成员节点负责采集监测数据,在簇首节点通过优化后的BP神经网络对数据进行特征提取,并将融合结果发送至汇聚节点。仿真结果表明:IPSO-BP算法能有效提高融合精度和收敛速度,减少冗余数据传输,延长网络生命周期。

基于PSO-BP优化MPC的无人驾驶汽车路径跟踪控制研究

针对模型预测控制(MPC)路径跟踪控制器在不同路面附着系数及车速下跟踪误差大的问题,提出了基于粒子群寻优(PSO)-反向传播(BP)神经网络优化MPC的无人驾驶汽车路径跟踪控制策略。首先,设计了MPC路径跟踪控制器;其次,利用PSO-BP对MPC进行优化,以控制器精度和车辆稳定性作为评价函数,获得PSO离线最优时域参数;最后,选择4种工况进行双移线跟踪对比仿真验证。结果表明:所提出的控制策略在保证行驶稳定性的条件下,低路面附着系数低速、高路面附着系数低速、高路面附着系数高速及中路面附着系数中速工况下双移线跟踪横向控制精度分别提高了50%、55%、9%和20%。

基于GA-BP神经网络板材辊式矫直工艺预测模型

辊式矫直工艺是轧制生产线上必要精整工艺。为提升生产线的整体智能化生产需求,采用神经网络代替曲率积分矫直模型进行计算,解决其求解难、耗时长和不收敛的缺点。针对反向传播(Back Propagation,BP)神经网络易出现泛化能力弱、陷入局部最优等问题,引入遗传算法(Genetic Algorithm,GA),建立一种基于GA-BP神经网络算法的板材辊式矫直工艺神经网络多输入多输出计算模型。对比结果显示,选用trainscg函数可实现较好的预测结果,并通过贪婪策略对模型结构进行优化,实现了矫直工艺模型的快捷、高精度计算,首尾辊压下误差在0.2 mm以内,残余曲率比误差在5%以内,矫直力误差在7%以内。该神经网络模型对轧制生产线有较高的工程应用价值。

基于GA-BP神经网络的负氧离子浓度反演模型研究

针对负氧离子浓度监测过程中存在的手段单一,无法满足日常监测需求的问题,分析负氧离子浓度与环境参数之间的关系,以温度、湿度以及PM2.5浓度作为输入变量,通过建立遗传算法(GA)优化的反向传播(BP)神经网络模型(GA-BP),对负氧离子浓度进行反演分析。实验结果表明:基于BP神经网络的负氧离子浓度反演结果平均相对误差为11.12%。使用GA优化后的BP神经网络对负氧离子浓度的反演效果更好,平均相对误差(MRE)仅为6.51%。基于GA-BP神经网络的负氧离子浓度反演模型,可为负氧离子的深入研究提供可靠的理论依据,同时,该研究模型的应用将大幅降低负氧离子浓度的监测成本,推动负氧离子监测技术的进步。

运用GA-BP算法的BKlob模型优化分析

为了进一步提升北斗卫星导航系统(BDS)克洛步伽(Klobuchar)电离层模型(BKlob)在亚太以外区域的服务性能,提出利用遗传算法(GA)优化反向传播神经网络(BP)对BKlob模型进行改进:对BKlob模型残差进行相关性分析和周期性检测;然后采用遗传算法优化BP神经网络(GA-BP)算法对模型残差进行7、30和150 d的预测,以实现对BKlob模型的改进;最后,分别以全球电离层格网图(GIM)产品为参考和单频单点定位精度提升,评估改正精度。实验结果表明:BKlob模型残差不同格网点处具有较强的相关性,且受地理纬度影响较大,受地理经度影响较小;改进的BKlob模型改正性能有明显提升,在高纬度地区和全球范围,改正率可提升50.0%、30.0%以上;采用改进的BKlob模型进行伪距单点定位(SPP)解算,三维方向均方根误差(RMSE)可提升14.84%,北(N)、天(U)方向定位精度明显提升。

基于PCA-BP神经网络的输电线路工程投资概算模型研究

传统输电线路(TTL)工程投资概算预测模型存在与实际造价偏差较大、概算管理工作效率低等问题。基于此,研究了基于主成分分析(PCA)和反向(BP)神经网络相结合的新型输电线路工程投资概算预测模型。首先,以影响输电线路工程投资的关键参数为初始输入变量,借助PCA对变量进行降维处理以简化输入数据的复杂性。其次,应用相关性剪枝算法优化BP神经网络节点数,进一步提升算法的快速性和准确性。最后,以河北省电力公司2018年01月—2020年01月输电线路工程投资概算数据为样本进行实例研究。结果表明:所设计基于PCA-BP神经网络的概算预测模型的预测准确率相比于支持向量机法(SVM)和BP神经网络法分别提升了70%和29%,具有更快的收敛速度及显著的工程应用价值。

基于BP神经网络的谐波减速器柔轮疲劳寿命预测研究

柔轮是谐波减速器的易损零件,在波发生器的高转速带动下转动,其疲劳寿命一直是备受关注的研究重点。以某型号杯型谐波减速器柔轮为研究对象,建立有限元仿真模型,得到柔轮最大应力与筒长、筒体壁厚和不同过渡圆角半径等参数之间的关系。根据柔轮S-N曲线,计算得到柔轮疲劳寿命,利用反向传播(Back Propagation,BP)神经网络实现了柔轮疲劳寿命的预测。