Intelligent direct analysis of physical and mechanical parameters of tunnel surrounding rock based on adaptive immunity algorithm and BP neural network

Because of complexity and non-predictability of the tunnel surrounding rock, the problem with the determination of the physical and mechanical parameters of the surrounding rock has become a main obstacle to theoretical research and numerical analysis in tunnel engineering. During design, it is a frequent practice, therefore, to give recommended values by analog based on experience. It is a key point in current research to make use of the displacement back analytic method to comparatively accurately determine the parameters of the surrounding rock whereas artificial intelligence possesses an exceptionally strong capability of identifying, expressing and coping with such complex non-linear relationships. The parameters can be verified by searching the optimal network structure, using back analysis on measured data to search optimal parameters and performing direct computation of the obtained results. In the current paper, the direct analysis is performed with the biological emulation system and the software of Fast Lagrangian Analysis of Continua (FLAC3D. The high non-linearity, network reasoning and coupling ability of the neural network are employed. The output vector required of the training of the neural network is obtained with the numerical analysis software. And the overall space search is conducted by employing the Adaptive Immunity Algorithm. As a result, we are able to avoid the shortcoming that multiple parameters and optimized parameters are easy to fall into a local extremum. At the same time, the computing speed and efficiency are increased as well. Further, in the paper satisfactory conclusions are arrived at through the intelligent direct-back analysis on the monitored and measured data at the Erdaoya tunneling project. The results show that the physical and mechanical parameters obtained by the intelligent direct-back analysis proposed in the current paper have effectively improved the recommended values in the original prospecting data. This is of practical significance to the appraisal of stability and informationization design of the surrounding rock.

Analysis and Prediction of Regional Electricity Consumption Based on BP Neural Network

Electricity consumption forecasting is one of the most important tasks for power system workers,and plays an important role in regional power systems.Due to the difference in the trend of power load and the past in the new normal,the influencing factors are more diversified,which makes it more difficult to predict the current electricity consumption.In this paper,the grey system theory and BP neural network are combined to predict the annual electricity consumption in Jiangsu.According to the historical data of annual electricity consumption and the six factors affecting electricity consumption,the gray correlation analysis method is used to screen the important factors,and three factors with large correlation degree are selected as the input parameters of BP neural network.The power forecasting model uses nearly 18 years of data to train and validate the model.The results show that the gray correlation analysis and BP neural network method have higher accuracy in power consumption prediction,and the calculation is more convenient than traditional methods.

Fault detection and diagnosis of permanent-magnetic DC motors based on current analysis and BP neural networks

In order to guarantee quality during mass serial production of motors, a convenient approach on how to detect and diagnose the faults of a permanent-magnetic DC motor based on armature current analysis and BP neural networks was presented in this paper. The fault feature vector was directly established by analyzing the armature current. Fault features were extracted from the current using various signal processing methods including Fourier analysis, wavelet analysis and statistical methods. Then an advanced BP neural network was used to finish decision-making and separate fault patterns. Finally, the accuracy of the method in this paper was verified by analyzing the mechanism of faults theoretically. The consistency between the experimental results and the theoretical analysis shows that four kinds of representative faults of low power permanent-magnetic DC motors can be diagnosed conveniently by this method. These four faults are brush fray, open circuit of components, open weld of components and short circuit between armature coils. This method needs fewer hardware instruments than the conventional method and whole procedures can be accomplished by several software packages developed in this paper.

Study on the Classification of Pulse Signal Based on the BP Neural Network

The objectification of the pulse signal analysis is a practical problem. The classification of the pulse signal is studied based on the BP neural network. It is first analyzed how to select the characteristic factors of the pulse signal. Then the method of nondimensionalization/normalization on the pulse signal is presented to preprocess the characteristic factors. The classification of the pulse signal and the effects of the selection of characteristic factors are studied by using the normalized data and BP neural network. It is shown that nondimensionalization/normalization of the data is in favor of the training and forecasting of the network. The selection of characteristic factors affects the accuracy of forecasting obviously. The results of forecasting by selection of 8, 6 and 4 factors respectively show that the less the factors are, the worse the effects are.

Research on Global Higher Education Quality Based on BP Neural Network and Analytic Hierarchy Process

Having a universal, fair, democratic and practical higher education system plays a particularly important role in the future development of the country. However, the higher education system in various countries is uneven. It is of great significance to establish a general evaluation system for the development of global education. In this paper, 23 indicators are preliminarily selected from the education data of Universitas 21 and Global Statistical Yearbook. After the gray correlation analysis, 12 indicators were selected. On the one hand, principal component analysis is used to reduce the dimension of these 12 indicators in 50 countries, and the first four principal components with cumulative contribution rate of 99% are finally selected as the input parameters of BP neural network. On the other hand, 12 indicators are divided into four aspects as the standard of scheme decision-making. Finally, a higher education quality evaluation and decision-making model based on BP neural network and analytic hierarchy process are established. Then eight countries are selected to use the model to evaluate their current higher education quality. Based on the input and evaluation results of the four aspects of higher education in various countries, the analytic hierarchy process is used to make program decision, and several improvement suggestions are put forward for the current education policies of various countries.

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.

基于改进BP神经网络的河北省碳排放预测

“双碳”目标背景下,针对河北省高碳经济发展模式难以改变、以往预测模型难以满足现实需求等问题。论文根据统计年鉴数据,研究河北省能源消费趋势和分行业碳排放特征,并借助脱钩指数探究河北省碳排放动态变化趋势,选取IPCC二氧化碳排放的计算方法,基于6项碳排放量影响因素建立遗传算法(GA)优化BP神经网络的河北省碳排放模型,对河北省2021—2030年碳排放量进行仿真预测。结果显示:河北省能源效率低于全国水平,河北省工业碳排放量最高;河北省的经济增长与碳排放之间主要呈弱脱钩态势;GA-BP模型预测结果比BP模型更加稳定,误差较小,更适合用于碳排放量的预测。预测结果显示,河北省未来碳排放量呈缓慢增长趋势,以期为政府决策提供理论依据,助力河北省“双碳”目标的实现。

基于PCA-BP神经网络的巷道通风摩擦阻力系数预测模型

根据实测巷道通风摩擦阻力系数数据的特点,建立了主成分分析PCA-BP神经网络预测模型。采用PCA法对影响巷道通风摩擦阻力系数的支护类型、断面形状、巷道宽、巷道高、支护部分周边长、巷道断面积和巷道长度7个因素进行降维。将降维后因素的贡献率进行排序筛选,得到3个主成分指标(F_(1)、F_(2)和F_(3)),作为BP神经网络输入层的神经元。利用实测数据对PCA-BP神经网络模型进行训练和测试,并将测试结果与支持向量机回归(SVM)模型和BP神经网络模型的测试结果进行对比,结果显示:全因素的BP神经网络预测模型和SVM预测模型的平均精度分别为92.9420%、93.0235%,而PCA-BP预测模型的平均精度达到了96.4325%。PCA-BP神经网络模型不但简化了网络结构,更提高了网络的泛化能力,使预测误差更小、精度更高,为更准确地获得巷道通风摩擦阻力系数提供了一种有效的方法。

交通荷载下煤矸石路基填料累积变形PSO-BP神经网络预测模型

基于煤矸石路基填料大型动三轴试验结果,采用灰色关联分析法分析累积变形影响因子,确定了围压、压实度、级配参数、循环荷载振动次数4个特征参数。引入PSO算法对BP神经网络的权重、阈值进行全局寻优并赋值,提出了一种煤矸石路基填料累积变形PSO-BP神经网络预测模型。与传统BP神经网络模型对比结果验证了该预测模型的可行性和优越性,并通过不同学习程度下模型的预测效果分析了模型的泛化能力,证明了模型的预测潜力。

基于5参数GA-BP模型的出水水质预测——以宁夏某水厂为例

为解决饮用水处理过程中关键水质参数浊度取样检测时滞性大和精度低的问题,提出了基于遗传算法优化BP神经网络(GA-BP)的出水浊度预测模型。利用2019—2021年银川市某水厂的实测出水浊度及相关水质数据,采用灰色关联度分析对影响出水浊度的输入指标进行筛选,结合Q型聚类分析将样本数据划分为具有不同特征的3类,构建了基于GA-BP神经网络的机器学习模型对出水浊度进行预测,并与传统BP和未分类的预测结果进行对比。结果表明:与未分类相比,利用Q型聚类分析后预测模型的误差评价指标决定系数(R2)和均方根误差(RMSE)分别优化了2.9%和22%;与传统BP神经网络相比,经遗传算法优化后的预测模型误差评价指标R2和RMSE分别优化了2.4%和12%。研究表明,Q型聚类分析和遗传算法均能提高BP神经网络预测模型的泛化能力,减小误差。

基于回归分析和GA-BP神经网络算法的3D打印件弯曲性能预测

为进一步探究熔融沉积成型(FDM)3D打印参数和制件弯曲性能之间的关系,创建合理的FDM 3D打印制件弯曲强度预测模型。根据正交试验L_(16)(4^(5))的设计原则和神经网络算法模型的构建要求,按照不同分层高度、填充密度、打印温度、打印速度以及外壳厚度五种因素,制备25组试验试样,并进行弯曲性能检测。随后通过建立GA-BP神经网络模型、传统BP神经网络模型以及多元回归方程模型,分别对FDM 3D打印制件弯曲性能进行预测,并将预测数据与试验测试数据进行对比。通过对比发现,GA-BP神经网络模型预测数据与试验测试数据更为接近,其平均误差为3.71%,且误差值整体波动最小,BP神经网络模型与多元回归方程模型预测精度相差不大,BP神经网络模型预测平均误差为8.05%,多元回归方程模型预测平均误差为9.07%,但多元回归方程误差值整体波动最大。因此,采用GA遗传算法优化后的BP神经网络模型在进行FDM 3D打印制件弯曲性能预测方面具有更高的精度和更良好的稳定性。

地表沉陷预测的改进BP神经网络模型

为了更加准确地预测地表沉陷变形,基于Adaboost算法采用多网络共同计算策略改进了BP神经网络,通过实际沉降数据对Adaboost算法改进后的神经网络进行训练,预测地表最大下沉量、影响角正切和拐点偏移距,将预测的3个参数代入概率积分法中,建立了地表沉陷公式,对改进效果和地表沉陷公式分别进行了验证。结果表明:(1)通过对比改进前后BP神经网络的计算精度,未经过Adaboost算法改进的BP神经网络误差明显大于改进后的BP神经网络,说明基于Adaboost修正后的BP神经网络计算精度得到了有效提升;(2)基于BP神经网络对最大下沉量、影响角正切和拐点偏移距3个参数进行预测,结合概率分析法,能够实现稳沉后采空区主断面上方地表沉降规律的准确描述。以鲁西南地区某矿3301采空区地表为例,利用改进BP神经网络预测了地表最大下沉量、影响角正切和拐点偏移距,进而给出了地表沉陷曲线,与现场实测结果对比显示:改进BP神经网络的最大误差小于0.105 m,最大相对误差为4.3%,证明了所提计算方法的可靠性。

基于GA-BP-Garson模型的市政污泥干燥过程含水率预测

市政污泥干燥过程中内部水分检测困难,为准确预测市政污泥热风干燥过程中内部水分的变化规律,将干燥时间、干燥温度、泥层厚度、流量压差作为输入变量,含水率作为输出变量,采用BP神经网络以及GA-BP神经网络分别建立市政污泥热风干燥过程的水分预测模型;对GA-BP神经网络进行敏感性分析,研究了4个输入变量对预测结果的影响。结果表明,BP和GA-BP 2种水分预测模型测试集的决定系数(R^(2))分别为0.99955和0.99964,均方根误差(RMSE)分别为0.51317和0.45523,即GA-BP预测模型的预测效果更佳,能更准确地预测市政污泥干燥过程中含水率的动态变化。敏感性分析表明,干燥时间对GA-BP含水率预测模型的影响最为显著。研究结果可为污泥干燥工艺和过程的优化提供理论依据,为污泥资源化利用提供参考。

基于GA-BP神经网络的微磨具磨损预测研究

为提高硬脆材料微结构的加工效率和精度,需要预测微磨具的不确定性磨损。基于微磨具在位视觉磨损检测和聚类分析,提出基于遗传算法的反向神经网络(genetic algorithm back propagation,GA-BP)模型。选取微磨具磨头截面面积损失量为指标,以表征微磨具不确定性磨损特征。利用K-均值聚类算法划分微磨具磨损状态阶段。最后构建以主轴转速、进给率、微槽深度、磨削长度和微磨具初始截面面积为输入层神经元,以磨头截面面积损失量预测值为输出层的GA-BP神经网络模型。设计不同工艺参数条件下的单晶硅微槽微细磨削实验,基于自搭建的机器视觉系统在位测量微磨具的磨头截面面积磨损量。将实验测得的微磨具磨损量作为训练数据,与传统高斯过程回归预测模型对比,验证GA-BP神经网络模型的有效性和准确性。结果表明,GA-BP神经网络模型能够实现不同工艺参数和不同磨削长度下的微磨具磨损预测,比传统高斯过程回归预测模型具有更高预测精度,平均误差精度达到5%,可以实现微磨具磨损阶段状态预测。

基于改进PCA-BP神经网络模型的海宁市需水预测

需水预测是地区水资源规划中的重要部分,对于实现水资源合理有序开发,保障社会经济的可持续发展有重要的指导意义。采用改进PCA-BP神经网络模型对影响需水量的9个影响因子进行降维处理,并分别以海宁市2001~2014、2015~2020年数据作为训练样本和检验样本完成模型训练,其中,综合灰色预测模型GM(1,1)对降维后的影响因子独立预测,从而预测海宁市规划年需水量,并与传统定额法的需水预测结果进行对比分析。结果表明,人口、GDP、居民生活用水量、城镇公共用水量为影响海宁市需水量的主要因子;通过构建改进PCA-BP神经网络模型得到的2025、2030、2035年需水结果,比传统定额法更为真实、合理,进一步证实了预测模型的合理性,可为海宁市未来水资源规划提供指导。

基于GPT3和PSO-BPNN的欧洲地区天顶对流层延迟模型

利用粒子群优化算法(PSO)优化反向传播神经网络(BPNN),建立优化的GPT3模型(MGPT3)。以欧洲地区30个IGS测站2020年连续366 d的天顶对流层延迟(ZTD)数据为例进行实验,对比MGPT3、UNB3m和GPT3模型预测ZTD的精度。结果表明,MGPT3模型的RMSE为18.49 mm,相较于UNB3m和GPT3模型,其精度分别提高55.0%和47.7%。

基于相关性分析和SSA-BP神经网络的铝合金电阻点焊质量预测

基于电阻点焊过程中工艺信号特征,在不同间距、不同间隙和不同间距与间隙3种条件下,引入相关性分析方法分析工艺信号与熔核直径之间的相关性,并建立基于麻雀搜索算法-BP神经网络(sparrow search algorithmback propagation neural network,SSA-BP)的电阻点焊质量预测模型,将功率、焊接电流、焊接电压和动态电阻作为预测模型输入特征.结果表明,经麻雀搜索算法优化后的BP神经网络在测试集上的决定系数R2、均方误差(meansquare error,MSE)、均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)分别为0.95,1.55,1.24和0.90,均优于BP模型.获得了功率、焊接电流、焊接电压和动态电阻与熔核直径的映射关系,可为焊接的工艺参数设计提供依据.

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。

基于MD-PCA-BP模型的露天矿山爆破振动速度预测

为解决露天矿山爆破复杂场地地质条件的爆破振动预测问题,提出了一种基于马氏距离判别(MD)和主成分分析(PCA)的改进BP神经网络预测模型,即MD-PCA-BP模型。结合内蒙古长滩露天矿爆破振动监测数结果,利用马氏距离判别法剔除监测数据的离群值,并采用主成分分析法对爆破振动影响因素进行降维处理得到3个主成分因子,计算各主成分因子的得分,最终通过BP神经网络构建爆破振动与主成分得分的非线性关系,建立了基于MD-PCA-BP的爆破振动预测模型。结果表明:基于MD-PCA-BP模型建立的爆破振动速度预测模型预测结果与实测值的拟合度达到0.94,预测模型具有较高的预测精度;将预测结果与萨道夫斯基经验公式、2个改进的高程经验公式、MD-BP模型、PCA-BP模型以及BP模型进行比较,MD-PCA-BP模型的预测误差大部分在10%以内,相较于经验公式和未改进的BP预测模型具有更高的可靠度和准确度。基于MD-PCA-BP的爆破振动预测模型在复杂地形的爆破振动速度预测方面表现出了良好的预测效果,对复杂地形的爆破振动预测具有一定的参考作用。