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-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。

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.

Water Quality Evaluation of Chapurson Valley in Hunza Nagar, Gilgit Baltistan, Pakistan, Based on Statistical Analysis and Water Quality Index

Water borne ailments are of serious public health concern in Gilgit Baltistan’s (GB) region of Pakistan. The pollution load on the glacio-fluvial streams and surface water resources of the Chapurson Valley in the Hunza Nagar area of the GB is increasing as a result of anthropogenic activities and tourism. The present study focuses on the public health quality of drinking water of Chapurson valley. The study addressed the fundamental drinking water quality criteria in order to understand the state of the public health in the valley. To ascertain the current status of physico-chemical, metals, and bacteriological parameters, 25 water samples were collected through deterministic sampling strategy and examined accordingly. The physico-chemical parameters of the water samples collected from the valley were found to meet the World Health Organization (WHO) guidelines of drinking water. The water samples showed a pattern of mean metal concentrations in order of Arsenic (As) > Lead (Pb) > Iron (Fe) > Zinc (Zn) > Copper (Cu) > Magnesium (Mg) > Calcium (Ca). As, Cu, Zn, Ca and Mg concentration were under the WHO guidelines range. However, results showed that Pb and Fe are present at much higher concentrations than recommended WHO guidelines. Similarly, the results of the bacteriological analysis indicate that the water samples are heavily contaminated with the organisms of public health importance (including total coliforms (TCC), total faecal coliforms (TFC) and total fecal streptococci (TFS) are more than 3 MPN/100mL). Three principal components, accounting for 48.44% of the total variance, were revealed using principal component analysis (PCA). Bacteriological parameters were shown to be the main determinants of the water quality as depicted by the PCA analysis. The dendrogram of Cluster analysis using the Ward’s method validated the same traits of the sampling locations that were found to be contaminated during geospatial analysis using the Inverse Distance Weight (IDW) method. Based on these findings, it is most likely that those anthropogenic activities and essentially the tourism results in pollution load from upstream channels. Metals may be released into surface and groundwater from a few underlying sources as a result of weathering and erosion. This study suggests that the valley water resources are more susceptible to bacteriological contamination and as such no water treatment facilities or protective measure have been taken to encounter the pollution load. People are drinking the contaminated water without questioning about the quality. It is recommended that the water resources of the valley should be monitored using standard protocol so as to protect not only the public health but to safe guard sustainable tourism in the valley.

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。

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。

Study on Complete Analysis of LRE Test Samples Based on PCA

Incomplete data samples have a serious impact on the effectiveness of data mining.Aiming at the LRE historical test samples,based on correlation analysis of condition parameter,this paper introduced principle component analysis(PCA)and proposed a complete analysis method based on PCA for incomplete samples.At first,the covariance matrix of complete data set was calculated;Then,according to corresponding eigenvalues which were in descending,a principle matrix composed of eigen-vectors of covariance matrix was made;Finally,the vacant data was estimated based on the principle matrix and the known data.Compared with traditional method validated the method proposed in this paper has a better effect on complete test samples.An application example shows that the method suggested in this paper can update the value in use of historical test data.

VARIABILITY OF DAILY PRECIPITATION IN CHINA(1980-1993): PCA AND WAVELET ANALYSIS OF OBSERVATION AND ECMWF REANALYSIS DATA

In this study, principal component analysis(PCA) and complex Morlet wavelet transform were used with daily rainfall in China for the period 1980-1993(1 May-31 Dec.) from observation and ECMWF reanalysis to study its variability and evaluate the validation of reanalyzed precipitation. The results showed that northward movement of the summer rain belt was a wavelike propagation, which was always accompanied by rainfall breaks and could be treated as one event under time scale of about 1 month only. The first 4 EOFs accounted for 28% and 35% of total variance from observation and reanalysis, respectively, and were roughly consistent with each other. The first and third EOFs for observation mainly represented interweekly, interseasonal and interannual variations and contained some summer intraseasonal fluctuations also. The second and fourth ones mainly represented some rather strong summer intraseasonal fluctuations for a paticular year and contained interweekly, interseasonal and interannual variations also. Although there is still room for improvement, the ECMWF reanalysis is the best available dataset with global coverage and daily variability.

QAMS多组分定量联合PCA、OPLS-DA及GRA分析法评价白花蛇舌草的质量

目的:采用高效液相-一测多评(HPLC-QAMS)法联合化学计量学及灰色关联度分析法评价白花蛇舌草质量。方法:采用Alltima C_(18)色谱柱(5.0μm,250.0 mm×4.6 mm),0.2%磷酸-乙腈为流动相梯度洗脱;以芦丁为参照物,建立其与京尼平苷酸、京尼平苷、车叶草苷酸、车叶草苷、2-羟基-3-甲基蒽醌、1,2-二羟基-3-甲基蒽醌、槲皮素、山柰酚、齐墩果酸、熊果酸、豆甾醇和β-谷甾醇的相对校正因子并进行校正因子耐用性考察。同时采用ESM和QAMS法测定收集到的16批白花蛇舌草中该13种成分的含量,再运用统计软件进行化学计量学及灰色关联度分析。结果:13种成分方法学验证均符合2020年版《中华人民共和国药典》要求。京尼平苷酸、京尼平苷、车叶草苷酸、车叶草苷、2-羟基-3-甲基蒽醌、1,2-二羟基-3-甲基蒽醌、槲皮素、山柰酚、齐墩果酸、熊果酸、豆甾醇、β-谷甾醇与芦丁的平均相对校正因子分别为0.9489、0.7033、0.7824、1.1359、0.5845、0.8005、0.8933、1.0683、0.7406、0.8640、0.6745、0.5424。两种方法测定结果比较,差异无统计学意义(P>0.05)。化学计量学方法显示16批白花蛇舌草聚为3类,呈现一定的产区差异。芦丁、车叶草苷酸、京尼平苷和齐墩果酸是影响白花蛇舌草产品质量的主要潜在标志物。GRA法分析结果显示7个省中浙江和江西地区所得白花蛇舌草质量最优。结论:本试验所建立的方法操作便捷、结果准确,结合化学计量学及GRA方法可用于白花蛇舌草质量的综合评价。

Analysis of PCA Method in Image Recognition with MATALAB

The growing need for effective biometric identification is widely acknowledged.Human face recognition is an important area in the field of biometrics.It has been an active area of research for several decades,but still remains a challenging problem because of the complexity of the human face.The Principal Component Analysis(PCA),or the eigenface method,is a de-facto standard in human face recognition.In this paper,the principle of PCA is introduced and the compressing and rebuilding of the image is accomplished with matlab program.

Discrete wavelet and modified PCA decompositions for postural stability analysis in biometric applications

The aim of this study is to compare the Discrete wavelet decomposition and the modified Principal Analysis Component (PCA) decomposition to analyze the stabilogram for the purpose to provide a new insight about human postural stability. Discrete wavelet analysis is used to decompose the stabilogram into several timescale components (i.e. detail wavelet coefficients and approximation wavelet coefficients). Whereas, the modified PCA decomposition is applied to decompose the stabilogram into three components, namely: trend, rambling and trembling. Based on the modified PCA analysis, the trace of analytic trembling and rambling in the complex plan highlights a unique rotation center. The same property is found when considering the detail wavelet coefficients. Based on this property, the area of the circle in which 95% of the trace’s data points are located, is extracted to provide important information about the postural equilibrium status of healthy subjects (average age 31 ± 11 years). Based on experimental results, this parameter seems to be a valuable parameter in order to highlight the effect of visual entries, stabilogram direction, gender and age on the postural stability. Obtained results show also that wavelets and the modified PCA decomposition can discriminate the subjects by gender which is particularly interesting in biometric applications and human stability simulation. Moreover, both techniques highlight the fact that male are less stable than female and the fact that there is no correlation between human stability and his age (under 60).

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-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。

Study on the Key Influence Factors of Environmental Mass Incidents by Delphi-PCA-Frequency Analysis Composite Method

In order to prevent and control environmental mass incidents,by comprehensively using literature research,case analysis and logical reasoning method,27 factors influencing environmental mass incidents were selected. Among them,15 key influencing factors were screened by Delphi-PCA-frequency analysis composite method. The key influencing factors were analyzed,and corresponding countermeasures were put forward.

基于DBSCAN-PCA和改进自注意力机制的光伏功率预测

光伏电站功率数据存在随机性和波动性的特征,研究精准的光伏电站功率预测模型成为未来电力发展中灵活的电力调度和管理的必要条件。对此提出一种基于混合DBSCAN聚类、PCA主成分分析和改进自注意力机制的光伏功率预测模型。首先采用DBSCAN聚类将分布较为分散和密集的历史数据进行分类,得到波动数据集和平稳数据集;其次利用PCA提取波动数据的主要成分序列,得到便于模型获得关键信息的时间序列;最后提取关键气象参数与具有感知上下文信息的改进自注意力机制模型进行互助式的动态建模。实验运用RMSE和MAE两个指标说明本文所提模型在每个季节下的平稳数据和波动数据都有较高的预测精度。

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。