Using deep neural networks coupled with principal component analysis for ore production forecasting at open-pit mines

Ore production is usually affected by multiple influencing inputs at open-pit mines.Nevertheless,the complex nonlinear relationships between these inputs and ore production remain unclear.This becomes even more challenging when training data(e.g.truck haulage information and weather conditions)are massive.In machine learning(ML)algorithms,deep neural network(DNN)is a superior method for processing nonlinear and massive data by adjusting the amount of neurons and hidden layers.This study adopted DNN to forecast ore production using truck haulage information and weather conditions at open-pit mines as training data.Before the prediction models were built,principal component analysis(PCA)was employed to reduce the data dimensionality and eliminate the multicollinearity among highly correlated input variables.To verify the superiority of DNN,three ANNs containing only one hidden layer and six traditional ML models were established as benchmark models.The DNN model with multiple hidden layers performed better than the ANN models with a single hidden layer.The DNN model outperformed the extensively applied benchmark models in predicting ore production.This can provide engineers and researchers with an accurate method to forecast ore production,which helps make sound budgetary decisions and mine planning at open-pit mines.

基于PCA和EEMD的柔性直流配电网故障选线算法

柔性直流故障选线技术的发展对直流配电网有着至关重要的作用。本文针对现有柔性直流故障存在的可利用的故障信息较少等问题,提出了一种新算法,该算法有效利用了集合经验模态分解EEMD(ensemble empirical mode decomposition)算法、主成分分析PCA(principal component analysis)和相关系数各自的优势。首先,提取暂态电流样本信号,采用EEMD得到以正交基函数表示的数据矩阵;接着,基于PCA进行该矩阵元素特征向量到主成分的转换,将样本信号投影到主元空间实现坐标变换,从而得到对样本数据的聚类和识别结果;最后,基于相关系数进行故障线路判别。本文算法的EEMD揭露了原始历史数据的内在变化规律,PCA能够有效选择故障有效特征。大量实验表明,该新算法准确有效,与现有其他方法相比,在故障信息不明显、不同过渡电阻方面具有优势。

Tool Health Condition Recognition Method for High Speed Milling of Titanium Alloy Based on Principal Component Analysis (PCA) and Long Short Term Memory (LSTM)

The healthy condition of the milling tool has a very high impact on the machining quality of the titanium components.Therefore,it is important to recognize the healthy condition of the tool and replace the damaged cutter at the right time.In order to recognize the health condition of the milling cutter,a method based on the long short term memory(LSTM)was proposed to recognize tool health state in this paper.The various signals collected in the tool wear experiments were analyzed by time-domain statistics,and then the extracted data were generated by principal component analysis(PCA)method.The preprocessed data extracted by PCA is transmitted to the LSTM model for recognition.Compared with back propagation neural network(BPNN)and support vector machine(SVM),the proposed method can effectively utilize the time-domain regulation in the data to achieve higher recognition speed and accuracy.

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PCA-PSO-ELM模型预测地震死亡人数研究

筛选42个历史地震震例,对地震震级、震源深度、震中烈度、抗震设防烈度、震中烈度与抗震设防烈度之差(ΔL)、人口密度以及发震时刻7个影响指标进行主成分分析(principal components analysis,PCA),构建粒子群优化(particle swarm optimization,PSO)极限学习机(extreme learning machine,ELM)地震死亡人数预测模型。将37个震例数据进行预处理和训练,并使用5个震例数据来检验模型的预测精度。实验结果表明,该PCA-PSO-ELM组合模型的平均误差率为10.87%,相比于PCA-ELM模型和ELM模型,其平均误差率分别降低8.70个百分点和18.38个百分点。因此,采用PCA-PSO-ELM组合模型预测地震死亡人数具有一定的可行性。

基于PCA-LDA-SVM算法的茶小绿叶蝉识别

为提高茶小绿叶蝉病虫害的识别效率和精度,提出一种基于PCA-LDA-SVM的茶小绿叶蝉病虫害识别方法。首先,对采集的茶叶图像进行预处理,得到缩放后的图像;然后,利用主成分分析(PCA)对预处理后的图像提取全局特征,降低特征数据的维度,从而减少后续的计算时间;再利用线性判别分析(LDA)寻找特征数据的最优投影空间,使类内散布距离最小,类间散布距离最大,进一步提高识别的准确率和精确度;最后,利用支持向量机(SVM)分类器进行分类识别。试验结果表明,PCA-LDA-SVM模型识别准确率达96%,精确度达100%,召回率达92%,整体识别性能优于SVM,BP,KNN,PCA-SVM模型,具备一定的理论价值和参考意义。

基于PCA和ICA模式融合的非高斯特征检测识别

针对无人船(Unmanned surface vehicle,USV)航行位姿观测数据的非高斯性/高斯性判别问题,提出一种基于主成分分析(Principal component analysis,PCA)和独立成分分析(Independent component analysis,ICA)模式融合的非高斯特征检测识别方法.首先,采用基于标准化加权平均和信息熵的数据预处理方法.其次,引入混合加权核函数并使用灰狼优化(Grey wolf optimization,GWO)算法进行参数优化,以提高PCA方法的准确性.同时,该算法采用一种新的非线性控制因子策略,提高全局和局部搜索能力.最后,建立了一种基于ICA和PCA联合的相关性分析方法来实现多维数据的降维,在降维数据的基础上综合T型多维偏度峰度检验法和KS(Kolmogorov-Smirnov)检验法进行非高斯性/高斯性特征检测识别.该方法考虑了非线性非高斯的噪声对降维结果精确度的影响,有效降低了多维数据非高斯检测的复杂度,同时也为后续在实际USV位姿估计等应用中提供了保障.实验表明,该方法具有较高的准确性和稳定性,可为USV航行位姿观测数据处理提供支持.

基于PCA-SBM的轨道交通站点接驳评价体系——以厦门市轨道交通站点为例

以慢行交通规划为指导,搭建基于PCA-SBM(主成分分析-基于松弛值测算)的效率评价模型,从管理者视角对厦门市轨道交通单车接驳现状作出评价。研究发现:厦门市站点接驳效率整体偏低,多呈现高投入、中回报的数据表现,需加强高峰日的引导轮次;电子围栏使用率低,应加强政企联动,做好及时的高峰时期车辆调度与用户前端引导,提升用户对电子围栏的感知,推动落实智能化管理。

基于PCA的汉中市中心城区空气质量影响因素研究

根据2022年汉中市中心城区环境空气质量监测数据和气象数据,运用主成分分析法(PCA)研究了影响空气质量的主要因素和重要因素,并对比分析了气象指标和各污染物浓度之间的关系。结果表明:主成分分析法提取的3个主成分方差贡献率为79.388%,达到了预期效果。主成分1的方差贡献率为51.745%,其中PM_(2.5)、CO、NO_(2)、PM_(10)权重较高,说明PM_(2.5)、CO、NO_(2)、PM_(10)是影响空气质量的主要因素,且它们高度正相关,相关系数最高为0.905(PM_(2.5)-CO),最低为0.751(PM_(10)-CO),分析表明加强对工业源、移动源CO、NOx以及颗粒物排放管控是改善空气质量的有效途径。主成分2、主成分3的方差贡献率合计为27.643%,主要包含了风向、O_(3)、风级、气温等信息,是影响空气质量的重要因素。气温对各污染物浓度影响最明显,与O_(3)显著正相关,与其他污染物负相关,影响程度大小依次为CO>O_(3)>NO_(2)>PM_(2.5)>PM_(10)>SO_(2),在7℃时,PM_(2.5)、PM_(10)、NO_(2)、CO、SO_(2)浓度相对较高;在偏东北风时PM_(2.5)、PM_(10)、CO平均浓度较高,O_(3)平均浓度较低,偏西南风时具有相反特征;风级增大污染物浓度降低,但O_(3)浓度在1级~2级风时较高。

基于PCA-FCE的成都市水资源承载力评价研究

为研究成都市各地区水资源承载力,采用主成分分析法PCA与模糊综合评判法FCE相结合的方式对成都市水资源承载力进行科学评价,首先根据2019年成都市水资源信息系统和评价标准对原始数据进行离散化处理,然后利用主成分分析法按照累计方差占比大于85%的原则,最终选择前4个主成分,同时依据特征值确定各属性的权重。再利用模糊综合评价法确定各地区的隶属度矩阵,将隶属度矩阵与权重向量的向量积作为各个地区的评价结果。结果表明成都市周边地区如邛崃县、大邑县、简阳市等地区水资源承载力最强,主城五区及新都区的水资源承载力偏弱。承载力空间分布上表现为西强东弱,外强内弱。评价结果符合成都市水资源现行状况,同时也能为政府部门制定科学合理的用水标准提供一定的技术支撑。

基于PCA-BP神经网络的跨境农产品供应链数字化转型风险预测

数字经济正在成为重组全球农业要素资源、重塑全球农业经济结构、改变全球农业竞争格局的关键力量。对于跨境农产品供应链(Cross-border Agri-food Supply Chains,CASCs),由于农产品自身具有易损易耗、季节性和周期性等特点,使得跨境农产品的链式结构相比其他供应链存在更大的脆弱性。推动跨境农产品供应链数字化转型,关键是有效识别和预测数字化转型过程中的风险因素。基于TOE框架归纳了企业数字化转型风险中的3个表现层面,在对跨境农产品供应链核心企业及其成员企业调研基础上,运用主成分分析(PCA)减少原始数据的维度,在此基础上构建反向传播神经网络(BPNN)用于预测CASCs数字化转型中的风险。结果表明,所选择的4个主成分是合理的,评价指标体系是有价值的。研究结果为跨境农产品供应链发展提供了新的思路。

基于PCA和SVM的遥感影像水体提取方法及验证

针对内陆湖泊水质及光谱特性空间差异性大、支流水系结构复杂而导致的遥感影像水体提取精度低的问题,提出了结合光谱主成分分析(PCA)及支持向量机(SVM)的PCA-SVM水体提取算法。基于GF-1卫星遥感影像,对原始影像光谱波段特征进行PCA降维,从中优选熵、方差、差异性纹理特征向量,结合原始波段及归一化差分水体指数(NDWI),构建了8维特征向量,并基于SVM算法提取湖泊水体。以巢湖洪水期与非洪水期影像为研究实例,分别采用NDWI法、传统SVM算法及PCA-SVM算法对水体进行提取,并进一步基于PCA-SVM算法对2020年汛期巢湖洪水期淹没演变过程进行反演和跟踪,定量解析特征向量组合及SVM惩罚系数C对水体提取性能的影响。结果表明:PCA-SVM算法提取的湖泊完整、支流连续,显著改善了含蓝藻水体漏提、建筑物误提等问题;洪水期和非洪水期提取结果的F1分数分别为95.08%和97.95%,虚警率分别为5.43%和1.13%,提取精度显著高于NDWI法和SVM算法。

基于PCA-PSO-BP神经网络的高速公路EPC项目成本风险研究

高速公路EPC项目建设周期长,不确定性、复杂性高,总成本控制难度大。为系统分析高速公路EPC项目面临的成本风险,提出基于粒子群优化算法和BP神经网络的EPC成本风险分析模型。首先,在识别成本风险因素的基础上,利用主成分分析法进行变量降维,简化网络输入节点;其次,通过粒子群算法优化BP神经网络,预测分析项目成本风险。结果表明,PCA-PSO-BP神经网络成本风险模型预测精确度高,可为高速公路总承包方评价项目成本风险提供一定的参考。

基于PCA-SSA-BP神经网络的烟叶分级方法

基于机器视觉检测的烟叶分级方法,存在识别效率低、识别稳定性差等问题。针对这些问题,该文基于主成分分析(PCA)、麻雀搜索算法(SSA)、BP神经网络提出一种烟叶分级方法,首先对采集到的烟叶图像进行分析提取17个图像特征进行PCA降维处理,以消除冗余信息,结合烟叶分级标准并平衡烟叶分级的识别正确率和分级效率确定最佳降维的维数为七维;然后,将七维特征向量作为BP神经网络的输入,利用SSA对BP网络模型的权值和阈值进行优化,完成网络模型的训练。实验结果表明,PCA-SSA-BP模型的平均识别率达到96%以上,总运行时间为97.99 s,因此该方法能有效提高小样本烟叶分级的识别效率和识别稳定性。

Comprehensive multivariate grey incidence degree based on principal component analysis

To overcome the too fine-grained granularity problem of multivariate grey incidence analysis and to explore the comprehensive incidence analysis model, three multivariate grey incidences degree models based on principal component analysis （PCA） are proposed. Firstly, the PCA method is introduced to extract the feature sequences of a behavioral matrix. Then, the grey incidence analysis between two behavioral matrices is transformed into the similarity and nearness measure between their feature sequences. Based on the classic grey incidence analysis theory, absolute and relative incidence degree models for feature sequences are constructed, and a comprehensive grey incidence model is proposed. Furthermore, the properties of models are researched. It proves that the proposed models satisfy the properties of translation invariance, multiple transformation invariance, and axioms of the grey incidence analysis, respectively. Finally, a case is studied. The results illustrate that the model is effective than other multivariate grey incidence analysis models.

Laser-induced breakdown spectroscopy applied to the characterization of rock by support vector machine combined with principal component analysis

Laser-induced breakdown spectroscopy（LIBS） is a versatile tool for both qualitative and quantitative analysis.In this paper,LIBS combined with principal component analysis（PCA） and support vector machine（SVM） is applied to rock analysis.Fourteen emission lines including Fe,Mg,Ca,Al,Si,and Ti are selected as analysis lines.A good accuracy（91.38% for the real rock） is achieved by using SVM to analyze the spectroscopic peak area data which are processed by PCA.It can not only reduce the noise and dimensionality which contributes to improving the efficiency of the program,but also solve the problem of linear inseparability by combining PCA and SVM.By this method,the ability of LIBS to classify rock is validated.

A novel method for chemistry tabulation of strained premixed/stratified flames based on principal component analysis

The principal component analysis （PCA） is used to analyze the high dimen- sional chemistry data of laminar premixed/stratified flames under strain effects. The first few principal components （PCs） with larger contribution ratios axe chosen as the tabu- lated scalars to build the look-up chemistry table. Prior tests show that strained premixed flame structure can be well reconstructed. To highlight the physical meanings of the tabu- lated scalars in stratified flames, a modified PCA method is developed, where the mixture fraction is used to replace one of the PCs with the highest correlation coefficient. The other two tabulated scalars are then modified with the Schmidt orthogonalization. The modified tabulated scalars not only have clear physical meanings, but also contain passive scalars. The PCA method has good commonality, and can be extended for building the thermo-chemistry table including strain rate effects when different fuels are used.

Watermarking Based on Principal Component Analysis

A new watermarking scheme using principal component analysis (PCA) is described.The proposed method inserts highly robust watermarks into still images without degrading their visual quality. Experimental results are presented, showing that the PCA based watermarks can resist malicious attacks including lowpass filtering, re scaling, and compression coding.

Characterization of three-dimensional channel reservoirs using ensemble Kalman filter assisted by principal component analysis

Ensemble-based analyses are useful to compare equiprobable scenarios of the reservoir models.However,they require a large suite of reservoir models to cover high uncertainty in heterogeneous and complex reservoir models.For stable convergence in ensemble Kalman filter(EnKF),increasing ensemble size can be one of the solutions,but it causes high computational cost in large-scale reservoir systems.In this paper,we propose a preprocessing of good initial model selection to reduce the ensemble size,and then,EnKF is utilized to predict production performances stochastically.In the model selection scheme,representative models are chosen by using principal component analysis(PCA)and clustering analysis.The dimension of initial models is reduced using PCA,and the reduced models are grouped by clustering.Then,we choose and simulate representative models from the cluster groups to compare errors of production predictions with historical observation data.One representative model with the minimum error is considered as the best model,and we use the ensemble members near the best model in the cluster plane for applying EnKF.We demonstrate the proposed scheme for two 3D models that EnKF provides reliable assimilation results with much reduced computation time.

WEB SERVICE SELECTION ALGORITHM BASED ON PRINCIPAL COMPONENT ANALYSIS

Existing Web service selection approaches usually assume that preferences of users have been provided in a quantitative form by users. However, due to the subjectivity and vagueness of preferences, it may be impractical for users to specify quantitative and exact preferences. Moreover, due to that Quality of Service (QoS) attributes are often interrelated, existing Web service selection approaches which employ weighted summation of QoS attribute values to compute the overall QoS of Web services may produce inaccurate results, since they do not take correlations among QoS attributes into account. To resolve these problems, a Web service selection framework considering user's preference priority is proposed, which incorporates a searching mechanism with QoS range setting to identify services satisfying the user's QoS constraints. With the identified service candidates, based on the idea of Principal Component Analysis (PCA), an algorithm of Web service selection named PCA-WSS (Web Service Selection based on PCA) is proposed, which can eliminate the correlations among QoS attributes and compute the overall QoS of Web services accurately. After computing the overall QoS for each service, the algorithm ranks the Web service candidates based on their overall QoS and recommends services with top QoS values to users. Finally, the effectiveness and feasibility of our approach are validated by experiments, i.e. the selected Web service by our approach is given high average evaluation than other ones by users and the time cost of PCA-WSS algorithm is not affected acutely by the number of service candidates.