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.

A Hybrid Optimization Approach of Single Point Incremental Sheet Forming of AISI 316L Stainless Steel Using Grey Relation Analysis Coupled with Principal Component Analysiss

We investigated the parametric optimization on incremental sheet forming of stainless steel using Grey Relational Analysis(GRA) coupled with Principal Component Analysis(PCA). AISI 316L stainless steel sheets were used to develop double wall angle pyramid with aid of tungsten carbide tool. GRA coupled with PCA was used to plan the experiment conditions. Control factors such as Tool Diameter(TD), Step Depth(SD), Bottom Wall Angle(BWA), Feed Rate(FR) and Spindle Speed(SS) on Top Wall Angle(TWA) and Top Wall Angle Surface Roughness(TWASR) have been studied. Wall angle increases with increasing tool diameter due to large contact area between tool and workpiece. As the step depth, feed rate and spindle speed increase,TWASR decreases with increasing tool diameter. As the step depth increasing, the hydrostatic stress is raised causing severe cracks in the deformed surface. Hence it was concluded that the proposed hybrid method was suitable for optimizing the factors and response.

A Modified Principal Component Analysis Method for Honeycomb Sandwich Panel Debonding Recognition Based on Distributed Optical Fiber Sensing Signals

The safety and integrity requirements of aerospace composite structures necessitate real-time health monitoring throughout their service life.To this end,distributed optical fiber sensors utilizing back Rayleigh scattering have been extensively deployed in structural health monitoring due to their advantages,such as lightweight and ease of embedding.However,identifying the precise location of damage from the optical fiber signals remains a critical challenge.In this paper,a novel approach which namely Modified Sliding Window Principal Component Analysis(MSWPCA)was proposed to facilitate automatic damage identification and localization via distributed optical fiber sensors.The proposed method is able to extract signal characteristics interfered by measurement noise to improve the accuracy of damage detection.Specifically,we applied the MSWPCA method to monitor and analyze the debonding propagation process in honeycomb sandwich panel structures.Our findings demonstrate that the training model exhibits high precision in detecting the location and size of honeycomb debonding,thereby facilitating reliable and efficient online assessment of the structural health state.

Comparative assessment of the frying efficiency of standard and low linolenic rapeseed oils: Principal Component Analysis (PCA)

In this research,the performance of regular rapeseed oil(RSO)and modified low-linolenic rapeseed oil(LLRO)during frying was assessed using a frying procedure that commonly found in fast-food restaurants.Key physicochemical attributes of these oils were investigated.RSO and LLRO differed for initial linolenic acid(12.21%vs.2.59%),linoleic acid(19.15%vs.24.73%).After 6 successive days frying period of French fries,the ratio of linoleic acid to palmitic acid dropped by 54.49%in RSO,higher than that in LLRO(51.54%).The increment in total oxidation value for LLRO(40.46 unit)was observed to be significantly lower than those of RSO(42.58 unit).The changes in carbonyl group value and iodine value throughout the frying trial were also lower in LLRO compared to RSO.The formation rate in total polar compounds for LLRO was 1.08%per frying day,lower than that of RSO(1.31%).In addition,the formation in color component and degradation in tocopherols were proportional to the frying time for two frying oils.Besides,a longer induction period was also observed in LLRO(8.87 h)compared to RSO(7.68 h)after frying period.Overall,LLRO exhibited the better frying stability,which was confirmed by principal component analysis(PCA).

Robust Principal Component Analysis Integrating Sparse and Low-Rank Priors

Principal Component Analysis (PCA) is a widely used technique for data analysis and dimensionality reduction, but its sensitivity to feature scale and outliers limits its applicability. Robust Principal Component Analysis (RPCA) addresses these limitations by decomposing data into a low-rank matrix capturing the underlying structure and a sparse matrix identifying outliers, enhancing robustness against noise and outliers. This paper introduces a novel RPCA variant, Robust PCA Integrating Sparse and Low-rank Priors (RPCA-SL). Each prior targets a specific aspect of the data’s underlying structure and their combination allows for a more nuanced and accurate separation of the main data components from outliers and noise. Then RPCA-SL is solved by employing a proximal gradient algorithm for improved anomaly detection and data decomposition. Experimental results on simulation and real data demonstrate significant advancements.

Predicting the alloying element yield in a ladle furnace using principal component analysis and deep neural network

The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal component analysis(PCA)and deep neural network(DNN).The PCA was used to eliminate collinearity and reduce the dimension of the input variables,and then the data processed by PCA were used to establish the DNN model.The prediction hit ratios for the Si element yield in the error ranges of±1%,±3%,and±5%are 54.0%,93.8%,and98.8%,respectively,whereas those of the Mn element yield in the error ranges of±1%,±2%,and±3%are 77.0%,96.3%,and 99.5%,respectively,in the PCA-DNN model.The results demonstrate that the PCA-DNN model performs better than the known models,such as the reference heat method,multiple linear regression,modified backpropagation,and DNN model.Meanwhile,the accurate prediction of the alloying element yield can greatly contribute to realizing a“narrow window”control of composition in molten steel.The construction of the prediction model for the element yield can also provide a reference for the development of an alloying control model in LF intelligent refining in the modern iron and steel industry.

A blast furnace fault monitoring algorithm with low false alarm rate:Ensemble of greedy dynamic principal component analysis-Gaussian mixture model

The large blast furnace is essential equipment in the process of iron and steel manufacturing. Due to the complex operation process and frequent fluctuations of variables, conventional monitoring methods often bring false alarms. To address the above problem, an ensemble of greedy dynamic principal component analysis-Gaussian mixture model(EGDPCA-GMM) is proposed in this paper. First, PCA-GMM is introduced to deal with the collinearity and the non-Gaussian distribution of blast furnace data.Second, in order to explain the dynamics of data, the greedy algorithm is used to determine the extended variables and their corresponding time lags, so as to avoid introducing unnecessary noise. Then the bagging ensemble is adopted to cooperate with greedy extension to eliminate the randomness brought by the greedy algorithm and further reduce the false alarm rate(FAR) of monitoring results. Finally, the algorithm is applied to the blast furnace of a large iron and steel group in South China to verify performance.Compared with the basic algorithms, the proposed method achieves lowest FAR, while keeping missed alarm rate(MAR) remain stable.

TOC estimation from logging data using principal component analysis

Total organic carbon(TOC)content is one of the most important parameters for characterizing the quality of source rocks and assessing the hydrocarbon-generating potential of shales.The Lucaogou Formation shale reservoirs in the Jimusaer Sag,Junggar Basin,NW China,is characterized by extremely complex lithology and a wide variety of mineral compositions with source rocks mainly consisting of carbonaceous mudstone and dolomitic mudstone.The logging responses of organic matter in the shale reservoirs is quite different from those in conventional reservoirs.Analyses show that the traditional△logR method is not suitable for evaluating the TOC content in the study area.Analysis of the sensitivity characteristics of TOC content to well logs reveals that the TOC content has good correlation with the separation degree of porosity logs.After a dimension reduction processing by the principal component analysis technology,the principal components are determined through correlation analysis of porosity logs.The results show that the TOC values obtained by the new method are in good agreement with that measured by core analysis.The average absolute error of the new method is only 0.555,much less when compared with 1.222 of using traditional△logR method.The proposed method can be used to produce more accurate TOC estimates,thus providing a reliable basis for source rock mapping.

Mantle sources of Cenozoic volcanoes around the South China Sea revealed by geochemical and isotopic data using the principal component analysis

Principal component analysis(PCA)was employed to determine the implications of geochemical and isotopic data from Cenozoic volcanic activities in the Southeast Asian region,including China(South China Sea(SCS),Hainan Island,Fujian-Zhejiang coast,Taiwan Island),and parts of Vietnam and Thailand.We analyzed 15 trace element indicators and 5 isotopic indicators for 623 volcanic rock samples collected from the study region.Two principal components(PCs)were extracted by PCA based on the trace elements and Sr-Nd-Pb isotopic ratios,which probably indicate an enriched oceanic island basalt-type mantle plume and a depleted mid-ocean ridge basalt-type spreading ridge.The results show that the influence of the Hainan mantle plume on younger volcanic activities(<13 Ma)is stronger than that on older ones(>13 Ma)at the same location in the Southeast Asian region.PCA was employed to verify the mantle-plume-ridge interaction model of volcanic activities beneath the expansion center of SCS and refute the hypothesis that the tension of SCS is triggered by the Hainan plume.This study reveals the efficiency and applicability of PCA in discussing mantle sources of volcanic activities;thus,PCA is a suitable research method for analyzing geochemical data.

Integrated classification method of tight sandstone reservoir based on principal component analysise simulated annealing genetic algorithmefuzzy cluster means

In this research,an integrated classification method based on principal component analysis-simulated annealing genetic algorithm-fuzzy cluster means(PCA-SAGA-FCM)was proposed for the unsupervised classification of tight sandstone reservoirs which lack the prior information and core experiments.A variety of evaluation parameters were selected,including lithology characteristic parameters,poro-permeability quality characteristic parameters,engineering quality characteristic parameters,and pore structure characteristic parameters.The PCA was used to reduce the dimension of the evaluation pa-rameters,and the low-dimensional data was used as input.The unsupervised reservoir classification of tight sandstone reservoir was carried out by the SAGA-FCM,the characteristics of reservoir at different categories were analyzed and compared with the lithological profiles.The analysis results of numerical simulation and actual logging data show that:1)compared with FCM algorithm,SAGA-FCM has stronger stability and higher accuracy;2)the proposed method can cluster the reservoir flexibly and effectively according to the degree of membership;3)the results of reservoir integrated classification match well with the lithologic profle,which demonstrates the reliability of the classification method.

Rail Surface Defect Detection Based on Improved UPerNet and Connected Component Analysis

To guarantee the safety of railway operations,the swift detection of rail surface defects becomes imperative.Traditional methods of manual inspection and conventional nondestructive testing prove inefficient,especially when scaling to extensive railway networks.Moreover,the unpredictable and intricate nature of defect edge shapes further complicates detection efforts.Addressing these challenges,this paper introduces an enhanced Unified Perceptual Parsing for Scene Understanding Network(UPerNet)tailored for rail surface defect detection.Notably,the Swin Transformer Tiny version(Swin-T)network,underpinned by the Transformer architecture,is employed for adept feature extraction.This approach capitalizes on the global information present in the image and sidesteps the issue of inductive preference.The model’s efficiency is further amplified by the windowbased self-attention,which minimizes the model’s parameter count.We implement the cross-GPU synchronized batch normalization(SyncBN)for gradient optimization and integrate the Lovász-hinge loss function to leverage pixel dependency relationships.Experimental evaluations underscore the efficacy of our improved UPerNet,with results demonstrating Pixel Accuracy(PA)scores of 91.39%and 93.35%,Intersection over Union(IoU)values of 83.69%and 87.58%,Dice Coefficients of 91.12%and 93.38%,and Precision metrics of 90.85%and 93.41%across two distinct datasets.An increment in detection accuracy was discernible.For further practical applicability,we deploy semantic segmentation of rail surface defects,leveraging connected component processing techniques to distinguish varied defects within the same frame.By computing the actual defect length and area,our deep learning methodology presents results that offer intuitive insights for railway maintenance professionals.

Wind turbine clutter mitigation using morphological component analysis with group sparsity

To address the problem that dynamic wind turbine clutter(WTC)significantly degrades the performance of weather radar,a WTC mitigation algorithm using morphological component analysis(MCA)with group sparsity is studied in this paper.The ground clutter is suppressed firstly to reduce the morphological compositions of radar echo.After that,the MCA algorithm is applied and the window used in the short-time Fourier transform(STFT)is optimized to lessen the spectrum leakage of WTC.Finally,the group sparsity structure of WTC in the STFT domain can be utilized to decrease the degrees of freedom in the solution,thus contributing to better estimation performance of weather signals.The effectiveness and feasibility of the proposed method are demonstrated by numerical simulations.

Wireless Sensor Network-based Detection of Poisonous Gases Using Principal Component Analysis

This work utilizes a statistical approach of Principal Component Ana-lysis(PCA)towards the detection of Methane(CH_(4))-Carbon Monoxide(CO)Poi-soning occurring in coal mines,forestfires,drainage systems etc.where the CH_(4) and CO emissions are very high in closed buildings or confined spaces during oxi-dation processes.Both methane and carbon monoxide are highly toxic,colorless and odorless gases.Both of the gases have their own toxic levels to be detected.But during their combined presence,the toxicity of the either one goes unidentified may be due to their low levels which may lead to an explosion.By using PCA,the correlation of CO and CH_(4) data is carried out and by identifying the areas of high correlation(along the principal component axis)the explosion suppression action can be triggered earlier thus avoiding adverse effects of massive explosions.Wire-less Sensor Network is deployed and simulations are carried with heterogeneous sensors(Carbon Monoxide and Methane sensors)in NS-2 Mannasim framework.The rise in the value of CO even when CH_(4) is below the toxic level may become hazardous to the people around.Thus our proposed methodology will detect the combined presence of both the gases(CH_(4) and CO)and provide an early warning in order to avoid any human losses or toxic effects.

Lung Cancer Prediction from Elvira Biomedical Dataset Using Ensemble Classifier with Principal Component Analysis

Machine learning algorithms (MLs) can potentially improve disease diagnostics, leading to early detection and treatment of these diseases. As a malignant tumor whose primary focus is located in the bronchial mucosal epithelium, lung cancer has the highest mortality and morbidity among cancer types, threatening health and life of patients suffering from the disease. Machine learning algorithms such as Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naïve Bayes (NB) have been used for lung cancer prediction. However they still face challenges such as high dimensionality of the feature space, over-fitting, high computational complexity, noise and missing data, low accuracies, low precision and high error rates. Ensemble learning, which combines classifiers, may be helpful to boost prediction on new data. However, current ensemble ML techniques rarely consider comprehensive evaluation metrics to evaluate the performance of individual classifiers. The main purpose of this study was to develop an ensemble classifier that improves lung cancer prediction. An ensemble machine learning algorithm is developed based on RF, SVM, NB, and KNN. Feature selection is done based on Principal Component Analysis (PCA) and Analysis of Variance (ANOVA). This algorithm is then executed on lung cancer data and evaluated using execution time, true positives (TP), true negatives (TN), false positives (FP), false negatives (FN), false positive rate (FPR), recall (R), precision (P) and F-measure (FM). Experimental results show that the proposed ensemble classifier has the best classification of 0.9825% with the lowest error rate of 0.0193. This is followed by SVM in which the probability of having the best classification is 0.9652% at an error rate of 0.0206. On the other hand, NB had the worst performance of 0.8475% classification at 0.0738 error rate.

Application of Principal Component Analysis as Properties and Sensory Assessment Tool for Legume Milk Chocolates

Principal component analysis (PCA) was employed to examine the effect of nutritional and bioactive compounds of legume milk chocolate as well as the sensory to document the extend of variations and their significance with plant sources. PCA identified eight significant principle components, that reduce the size of the variables into one principal component in physiochemical analysis interpreting 73.5% of the total variability with/and 78.6% of total variability explained in sensory evaluation. Score plot indicates that Double Bean milk chocolate in-corporated with MOL and CML in nutritional profile have high positive correlations. In nutritional evaluation, carbohydrates and fat content shows negative/minimal correlations whereas no negative correlations were found in sensory evaluation which implies every sensorial variable had high correlation with each other.

Independent component analysis approach for fault diagnosis of condenser system in thermal power plant

A statistical signal processing technique was proposed and verified as independent component analysis(ICA) for fault detection and diagnosis of industrial systems without exact and detailed model.Actually,the aim is to utilize system as a black box.The system studied is condenser system of one of MAPNA's power plants.At first,principal component analysis(PCA) approach was applied to reduce the dimensionality of the real acquired data set and to identify the essential and useful ones.Then,the fault sources were diagnosed by ICA technique.The results show that ICA approach is valid and effective for faults detection and diagnosis even in noisy states,and it can distinguish main factors of abnormality among many diverse parts of a power plant's condenser system.This selectivity problem is left unsolved in many plants,because the main factors often become unnoticed by fault expansion through other parts of the plants.

CNN-based segmentation frameworks for structural component and earthquake damage determinations using UAV images

Buildings undergo various kinds of structural damage during earthquakes,and damage detection and functional assessment of these structures in the aftermath of the events have been challenging issues.Under these circumstances,computer vision techniques offer a promising solution by automating the inspection process.This study presents an effective methodology for automatic structural components and damage detection using unmanned aerial vehicle(UAV)images of damaged buildings.Two types of neural network architectures are considered for appropriate feature extractions in different task detections.The feature pyramid network(FPN)is employed for crack,spall,rebar,and component damage segmentation,while the UNet++network is utilized for the damage state.For network training and validation,a total of 3805 original images of size 1920×1080 pixels are processed by the proposed method and reduced the image pixels.From the FPN,the achieved highest intersection over unions(IoUs)were 0.59,0.93,0.42,and 0.99 for crack,spall,rebar,and components,respectively.These predicted labels were found in close agreement with the labels.Similarly,the UNet++recognized the semantic information and damage state with an IoU of 0.72.This demonstrated the applicability of the proposed method for automated post-earthquake building inspection process accurately without information loss from the original images.

Kernel principal component analysis network for image classification

In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the data is mapped into a higher-dimensional space with kernel principal component analysis to make the data linearly separable. Then a two-layer KPCANet is built to obtain the principal components of the image. Finally, the principal components are classified with a linear classifier. Experimental results showthat the proposed KPCANet is effective in face recognition, object recognition and handwritten digit recognition. It also outperforms principal component analysis network（ PCANet） generally. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.

Construction of Anti-breaking Models of the Main Veins of Flue-cured Tobacco Leaves and Principal Component Analysis

[Objective] This study aimed to explore the related mechanisms of the breaking of flue-cured tobacco leaves. [Method] Anti-breaking models of the main veins of flue-cured tobacco leaves were constructed for principal component analysis on the anti-breaking index, leaf traits and cellulose contents. [Result] The results showed that the growth traits had certain relevance with the cellulose contents while the leaf weight assumed a significant negative correlation with the anti-breaking index, indicating that the heavier the leaf weight was, the weaker the anti-breaking capacity of flue-cured tobacco would be; the cross-sectional area of main veins and the cellulose contents had shown a positive correlation with the anti-breaking index, indicating that the thicker the main vein of flue-cured tobacco was, the higher the cellulose contents would be, and the stronger the anti-breaking capacity of flue-cured tobacco leaves would be. [Conclusion] This study provided theoretical basis and reference to improve tobacco production and enhance the quality of flue-cured tobacco.

Correlation and Principal Component Analysis on Main Agronomic Traits of New Waxy Corn Varieties

[Objective] This study was conducted to provide certain theoretical reference for the comprehensive evaluation and breeding of new fresh waxy corn vari- eties. [Method] With 5 good fresh waxy corn varieties as experimental materials, correlation analysis and principal component anatysis were performed on 13 agronomic traits, i.e., plant height, ear position, ear weight, ear diameter, axis diameter, ear length, bald tip length, ear row number, number of grains per row, 100-kernel weight, fresh ear yield, tassel length, and tassel branch number. [Result] The principal component analysis performed to the 13 agronomic traits showed that the first three principal components, i.e., the fresh ear yield factors, the tassel factors and the bald top factors, had an accumulative contribution rate over 87.2767%, and could basically represent the genetic information represented by the 13 traits. The first principal component is the main index for the selection and evaluation of good corn varieties which should have large ear, large ear diameter but small axis diameter, i.e., longer grains, larger number of grains per ear, higher, 100-grain weight and higher plant height. As to the second principal component, the plants of fresh corn varieties are best to have longer tassel and not too many branches, and under the premise of ensuring enough pollen for the female spike, the varieties with fewer tassel branches shoud be selected as far as possible. From the point of the third principal component, bald tip length affects the marketing quality of fresh corn, and during fariety evaluation and breeding, the bald top length should be control at the Iowest standard. [Conclusion] The fresh ear yield of corn is in close positive correlation with ear weight, 100-grain weight, ear diameter, number of grains per row and ear length, and plant height also affects fresh ear yield.