Least Squares Support Vector Machine Research Articles

Temperature Compensation for Semiconductor Gas Sensors Based on Whale Optimization Algorithm–Least-Squares Support Vector Machine

Temperature Compensation for Semiconductor Gas Sensors Based on Whale Optimization Algorithm–Least-Squares Support Vector Machine

Rapid and Non-Invasive Assessment of Texture Profile Analysis of Common Carp (Cyprinus carpio L.) Using Hyperspectral Imaging and Machine Learning.

Hyperspectral imaging (HSI) has been applied to assess the texture profile analysis (TPA) of processed meat. However, whether the texture profiles of live fish muscle could be assessed using HSI has not been determined. In this study, we evaluated the texture profile of four muscle regions of live common carp by scanning the corresponding skin regions using HSI. We collected skin hyperspectral information from four regions of 387 scaled and live common carp. Eight texture indicators of the muscle corresponding to each skin region were measured. With the skin HSI of live common carp, six machine learning (ML) models were used to predict the muscle texture indicators. Backpropagation artificial neural network (BP-ANN), partial least-square regression (PLSR), and least-square support vector machine (LS-SVM) were identified as the optimal models for predicting the texture parameters of the dorsal (coefficients of determination for prediction (rp) ranged from 0.9191 to 0.9847, and the root-mean-square error for prediction ranged from 0.1070 to 0.3165), pectoral (rp ranged from 0.9033 to 0.9574, and RMSEP ranged from 0.2285 to 0.3930), abdominal (rp ranged from 0.9070 to 0.9776, and RMSEP ranged from 0.1649 to 0.3601), and gluteal (rp ranged from 0.8726 to 0.9768, and RMSEP ranged from 0.1804 to 0.3938) regions. The optimal ML models and skin HSI data were employed to generate visual prediction maps of TPA values in common carp muscles. These results demonstrated that skin HSI and the optimal models can be used to rapidly and accurately determine the texture qualities of different muscle regions in common carp.

Intelligent estimation on state of health of lithium-ion power batteries based on failure feature extraction

In order to provide an accurate and reliable effective state-of-health (SOH) estimation, a novel hybrid data-driven estimation method by failure feature extraction is proposed. Firstly, influencing factors which reflect the failure of lithium-ion power batteries are studied, and three failure features of lithium-ion power batteries used as inputs of the estimation model are extracted by fuzzy grey relational analysis (FGRA) method. Then, the improved Least Squares Support Vector Machine (LSSVM) model is employed to estimate the SOH under different ambient temperature conditions. The results show that CC charging time, CV charging capacity and CV charging average temperature are determined as the failure features of the SOH estimation model, whose correlation degree to the battery capacity are 0.8774, 0.8104 and 0.8771, respectively. Compared with SVM, the improved LSSVM model has higher SOH estimation accuracy for the lithium-ion power battery under different ambient temperature conditions. In addition, the SOH estimation curves basically matches the actual curves, where the SOH estimation errors are less than 0.02. Moreover, the mean square error accuracy of the prediction results is at the level of 0.00001, and the determination coefficient is between 0.92 and 0.997. This work provides reference for enhancing the SOH estimation performance and safety of lithium-ion power batteries.

Intelligent multiobjective optimization for high-performance concrete mix proportion design: A hybrid machine learning approach

The concrete mix proportion design process is complex but important, especially in cold, ocean, underground and other complex engineering environments. In this study, a hybrid intelligent optimization method based on the random forest (RF), recursive feature elimination (RFE), Bayesian optimization (BO), least squares support vector machine (LSSVM) and nondominated sorting genetic algorithm (NGSA)-III was proposed to optimize the concrete mix proportion and rapidly and accurately predict the frost resistance, chloride ion penetration resistance and concrete strength (CS). Adopting a key project in Jilin Province as an example, the RF-RFE-BO-LSSVM-NSGA-III algorithm achieved a significant optimization effect in terms of the chloride ion permeability coefficient (CIPC), relative dynamic elastic modulus (RDEM) and 28-day CS. After optimization, the chloride ion penetration resistance, frost resistance and CS increased by 34.6%, 4.1% and 3.7%, respectively, over the average levels of the sample data. This study can provide basis for concrete mix proportion design in complex environment.

基于可见/近红外高光谱成像无损预测猕猴桃可溶性固形物含量

Soluble solid content (SSC) is a major quality index of kiwifruits. Visible near-infrared (Vis/NIR) hyperspectral imaging with the genetic algorithm (GA) was adopted in this study to realize the non-destructive prediction of kiwifruit SSC. A laboratory Vis/NIR hyperspectral imaging system was established to collect the hyperspectral imaging of 120 kiwifruit samples at a range of 400–1100 nm. The average reflectance spectral data of the region of interest of the kiwifruit hyperspectral imaging were obtained after different preprocessing method, namely, Savitzky–Golay smoothing (SG), multiplicative scatter correction (MSC), and their combination method. The prediction models of partial least squares regression, multiple linear regression, and least squares support vector machine (LS-SVM) were built for determining kiwifruit SSC by using the average reflectance spectral data and effective feature wavelength variables selected by GA, respectively. The results show that SG+MSC is the best preprocessing method. The precisions of the prediction models built using the effective feature wavelength variables selected by GA are higher than that established using full average reflectance spectral data. The GA-LS-SVM prediction model has a best performance with correlation coefficient for prediction (R=0.932) and standard error of prediction (SEP=0.536° Bx) for predicting kiwifruit SSC. The prediction accuracy has been improved by 5.6% compared with that of the prediction models established by using the full-band reflectance spectral data. This study provides an effective method for non-destructive detection of kiwifruit SSC.

Non-destructive detection and recognition of pesticide residue levels on cauliflowers using visible/near-infrared spectroscopy combined with chemometrics.

In this study, two prediction models were developed using visible/near-infrared (Vis/NIR) spectroscopy combined with partial least squares discriminant analysis (PLS-DA) and least squares support vector machine (LS-SVM) for the detection of pesticide residues of avermectin, dichlorvos, and chlorothalonil at different concentration levels on the surface of cauliflowers. Five samples of each of the three different types of pesticide were prepared at different concentrations and sprayed in groups on the surface of the corresponding cauliflower samples. Utilizing the spectral data collected in the Vis/NIR as input values, comparison and analysis of preprocessed spectral data, and regression coefficient (RC), successive projections algorithm (SPA), and competitive adaptive reweighted sampling (CARS) were used in turn to downscale the data to select the main feature wavelengths, and PLS-DA and LS-SVM models were built for comparison. The results showed that the RC-LS-SVM was the best discriminant model for detecting avermectin residues concentration on the surface of cauliflowers, with a prediction set discriminant accuracy of 98.33%. For detecting different concentrations of dichlorvos, the SPA-LS-SVM had the best predictive accuracy of 95%. The accuracy of the model based on CARS-PLS-DA to identify chlorothalonil at different concentration levels on cauliflower surfaces reached 93.33%. The results demonstrated that the Vis/NIR spectroscopy combined with chemometrics could quickly and effectively identify pesticide residues on cauliflower surfaces, affording a certain reference for the rapid recognition of different pesticide residue concentrations on cauliflower surfaces. PRACTICAL APPLICATION: Vis/NIR spectroscopy can detect the concentration levels of pesticide residues on the surface of cauliflowers and help food regulators quickly and non-destructively detect traces of pesticides in food, providing a guarantee for food safety. The technique also provides a basis for determining pesticide residue concentrations on the surface of other vegetables.

基于高光谱成像技术的欧李果成熟度判别

In order to realize the rapid and accurate identification of different maturity of Cerasus humilis fruit, this study explored the nondestructive testing method of Cerasus Humilis fruit maturity based on hyperspectral imaging technology. The hyperspectral data of 320 samples of Cerasus humilis fruit were collected by using a hyperspectral imaging system in the range of 895~1700 nm. By comparing the prediction accuracy of the partial least squares (PLS) model established by four preprocessing methods, the competitive adaptive reweighted algorithm (CARS), successive projection algorithm (SPA), and random frog (RF) were used to extract characteristic wavelengths, and partial least squares-discriminant analysis (PLS-DA) and least squares-support vector machine (LS-SVM) discriminant models were established. The results showed that the SPA-LS-SVM model had the highest discrimination accuracy for the four types of maturity samples, and the discrimination accuracy of the correction set and prediction set were 85.00% and 87.50%, respectively. This study provides a theoretical reference for the rapid and nondestructive testing of the maturity of Cerasus Humilis fruit by hyperspectral imaging technology.

Detection of attention deficit hyperactivity disorder based on EEG signals using Least Square Support Vector Machine (LS-SVM)

ABSTRACT Attention Deficit Hyperactivity Disorder (ADHD) is a mental disorder affecting children in their early stages. Detection of ADHD is considered a challenging task for experts because there is no accurate test to determine whether a child has ADHD or not. Mainly, most of previous studies are used electroencephalography (EEG) signals to detect ADHD. In this study, a robust model for ADHD detection-integrated discrete wavelet transform (DWT), statistical features, and a least square support vector machine (LS-SVM) is proposed to detect ADHD from EEG signals. The EEG signals are decomposed into five bands and then, a set of statistical features are tested to find the optimal feature sets using K-means model. A public dataset is used to evaluate the proposed model. A total of 45 ADHD patients and 45 healthy are involved to evaluate the proposed model. Several metrics are used to evaluate the proposed model including 10-fold cross-validation precision, sensitivity, and specificity metrics. A channel selection is also investigated, and we found that the channels ‘P3, P7, Pz’ are more important and gave better prediction results than other channels. The proposed model obtained an average accuracy of 98.06% with LS-SVM, and 95.46% with the KNN classifier.

Prediction of interfacial wetting behavior of H2/mineral/brine; implications for H2 geo-storage

Underground hydrogen storage (UHS) is a suitable option for large-scale and long-term storing of hydrogen (H2), which is considered a highly promising energy carrier, offering an efficient solution to replace fossil fuels and achieve net-zero carbon emission targets. The successful storage and withdrawal of H2 are highly dependent on the wettability of the H2/mineral/brine system. Despite the importance of the interfacial wetting behavior of H2/mineral/brine in sedimentary formations, no accurate and generalized model has been developed yet for a fast and valid prediction of the contact angle. In the context, three intelligent models, namely multi-layer perceptron (MLP), radial basis function (RBF), and least square support vector machine (LSSVM) have been proposed to accurately predict the contact angle of H2/mineral/brine systems. Another primary objective is to thoroughly scrutinize the extent to which various parameters influence the contact angle. Results of models approved their capability in validly predicting the contact angle for a wide range of mineral types, considering the effects of thermodynamic conditions, brine salinity, cushion gases, surface coating, and surface roughness. The results also demonstrated that the LSSVM model outperforms the MLP and RBF models with coefficients of determination (R2), root mean square error (RMSE) and average absolute relative deviation (AARD) of 0.9942, 1.6133 and 1.6924 %, respectively, indicating higher accuracy and reliability. Moreover, sensitivity analysis confirmed that the rock mineralogies, in particular the percentage of quartz and calcite, followed by the presence or absence of cushion gas, as well as surface roughness/contamination exerted a greater influence on predicting the contact angle within the H2/mineral/brine system.

Rapid and nondestructive THz inspection of unsound kernel of sunflower seed based on SMOTE algorithm

Inspection of unsound kernel of sunflower seed do an important role to the safe storage of sun-flower seeds and the quality of its processed products. A rapid and nondestructive method based on terahertz (THZ) time-domain spectroscopy was studied here to detect unsound kernel of sunflower seed. To explore the feasibility, the THz spectra of 446 sunflower seed samples were obtained. The synthetic minority over-sampling technique (SMOTE) was applied to balance the number of normal and unsound samples in the training set. To test effectiveness of SMOTE, the proportion of normal and unsound samples was set 4:1, 2:1 and 1.5:1 respectively in the experiment, then, new unsound samples was created by SMOTE algorithm till the number of unsound same to the normal, finally, the least squares support vector machine (LS-SVM) was used to construct the discrimination model. Comparing the performance of the model used SMOTE before and after, the sensitivity in the test set was improved from 0 % to 91.04 %, from 34.52 % to 92.86 %, and from 51.85 % to 92.59 % respectively. Five independent experiments with new sets of sample were repeated to verify that the model is robust, and the accuracy fluctuation is not more than ±5 %. THz time-domain spectrum, combined with SMOTE algorithm can effectively solve the problem of sample imbalance, thereby improving model performance. It is expected to provide feasible reference for accurate, nondestructive and rapid inspection of sunflower seeds and other shell agricultural products.

Deep eutectic solvent viscosity prediction by hybrid machine learning and group contribution

In this study, hybrid machine learning nonlinear models were developed to predict the viscosity of DESs by combining the group contribution (GC) concept with the multilayer perceptron, a well-known feedforward artificial neural network, and the Least Squares Support Vector Machine (LSSVM) algorithm. Deep Eutectic Solvents (DESs) have come to the forefront in recent years as appealing substitutes for conventional solvents. It is imperative to have a thorough grasp of the essential properties of DESs to expand the employment of these compounds in new procedures. Most frequently, one of the crucial physical properties of a DES that must be precisely determined is its viscosity. To develop the models, a dataset of 2533 viscosity data points for 305 DESs at various temperatures (from 277.15 to 373.15 K) was gathered to build the models. By using temperature, molar ratios, and functional groups as inputs, the results indicate that the suggested models can determine the viscosity of DESs with high accuracy. The models yield average absolute relative deviations below 10% and squared correlation coefficients higher than 0.98.

Sparse solution of least-squares twin multi-class support vector machine using [formula omitted] and [formula omitted]-norm for classification and feature selection

In the realm of multi-class classification, the twin K-class support vector classification (Twin-KSVC) generates ternary outputs {−1,0,+1} by evaluating all training data in a “1-versus-1-versus-rest” structure. Recently, inspired by the least-squares version of Twin-KSVC and Twin-KSVC, a new multi-class classifier called improvements on least-squares twin multi-class classification support vector machine (ILSTKSVC) has been proposed. In this method, the concept of structural risk minimization is achieved by incorporating a regularization term in addition to the minimization of empirical risk. Twin-KSVC and its improvements have an influence on classification accuracy. Another aspect influencing classification accuracy is feature selection, which is a critical stage in machine learning, especially when working with high-dimensional datasets. However, most prior studies have not addressed this crucial aspect. In this study, motivated by ILSTKSVC and the cardinality-constrained optimization problem, we propose ℓp-norm least-squares twin multi-class support vector machine (PLSTKSVC) with 0<p<1 to perform classification and feature selection at the same time. The technique employed to solve the optimization problems associated with PLSTKSVC is user-friendly, as it involves solving systems of linear equations to obtain an approximate solution for the proposed model. Under certain assumptions, we investigate the properties of the optimum solutions to the related optimization problems. Several real-world datasets were tested using the suggested method. According to the results of our experiments, the proposed method outperforms all current strategies in most datasets in terms of classification accuracy while also reducing the number of features.

Experimental investigation and machine learning modeling of heat transfer characteristics for water based nanofluids containing magnetic Fe3O4 nanoparticles

The convective heat transfer coefficients of Fe3O4 magnetic nanofluids in both laminar and turbulent flow states inside a pipe were determined as base values and adequately simulated using machine learning techniques. Three selected machine learning methods for the simulations were Multiple Linear Regression Analysis (MLR), Radial Basis Function-Backpropagation (RBF-BP), and Least Squares-Support Vector Machines (LS-SVM). Initially, MLR was employed to fit the polynomial equation, followed by the selection of the best RBF-BP model with 6 hidden layer neurons using the grid search cross-validation method. For the LS-SVM model, a kernel function of 0.3 and a regularization parameter of 100 were used. By conducting a detailed comparison of the numerical patterns of the accuracy evaluation parameters, the RBF-BP and LS-SVM models were evaluated, with the LS-SVM model demonstrating superiority. The main parameters in the Reynolds number-mass fraction simulation were the mean square error (MSE) and regression coefficient (R2), which obtained specific values of MSE= 0.34 and R2 = 0.99994 under laminar flow conditions. Similarly, in the Reynolds number-magnetic field strength simplification, the best values for laminar flow conditions were MSE= 3.85 and R2 = 0.99993. The validity and accuracy of the model predictions were further demonstrated through visual comparisons of simulated and experimental values using Three-Dimensional smoothed surface plots. The groundbreaking discoveries hold the potential to catalyze advancements and foster significant progress in the fields of machine learning and nanotechnology. As a valuable resource, these results play a crucial role in propelling further research and development efforts, thus making noteworthy contributions to the continuous growth and innovation in these cutting-edge disciplines.

A self-error corrector integrating K-means clustering with Markov model for marine craft maneuvering prediction with experimental verification

A novel approach for maneuvering prediction of marine crafts in data-limited situations is presented in this study. The approach is a hybrid strategy that combines least square-support vector machines (LS-SVM) and a self-error corrector that integrates K-means clustering with Markov model. The strategy allows testing errors caused by LS-SVM to be compensated effectively by the dedicated self-error corrector. To classify the inputs of the Markov model-based error corrector rapidly and properly, the K-means clustering algorithm is resorted to classifying the training errors obtained from LS-SVM. Assuming that maneuvering prediction for marine crafts with a limited number of simulation or experiment data, a comparative analysis of the prediction performance between the proposed strategy and the conventional method based on LS-SVM is performed. The results of numerical simulations and experiments demonstrate the superiority of the proposed strategy, which reduces the root mean square error of surge speed by up to 86.2% in simulation tests and 54.5% in experiments.

Physical metallurgy guided machine learning to predict hot deformation mechanism of stainless steel

This study proposes a novel approach to address the limitations of traditional experimental and mathematical statistical methods in predicting the deformation mechanism of materials. Specifically, a physical metallurgy-guided machine learning method is proposed to achieve fast and accurate prediction of the thermal deformation mechanisms of antibacterial stainless steels with varying Cu contents. First, the Arrhenius and the dynamic recrystallization model were developed utilizing experimental data for the preliminary prediction of the effect of Cu content on the thermal deformation behavior of antibacterial stainless steel. Then, the calculated intermediate parameters were incorporated into the original data set as additional input features to construct a physical metallurgy (PM) guided least squares support vector machine (LSSVM) prediction model, and the optimization of the prediction model is performed through utilization of a particle swarm optimization (PSO) algorithm. The results indicate that the addition of Cu content influences the rheological stress of antibacterial stainless steel at low temperatures and high strain rates. Furthermore, the increase of Cu content reduces the thermal deformation activation energy, inhibiting the dynamic recrystallization of antibacterial stainless steel, while an increase in deformation temperature or a decrease in strain rate promotes recrystallization. The proposed PM-PSO-LSSVM model is in good agreement with experiments, providing theoretical guidance for optimizing the composition and process parameters of antibacterial stainless steel.

Near-Infrared spectroscopy combined with machine learning methods for distinguishment of the storage years of rice

Rice is one of the most important food crops that provide essential nutrients, micronutrients and daily energy for humans. The freshness of rice determines the quality and nutrition supply property, but the freshness decreases along with the storage time. A simple, nondestructive and rapid detection technology is needed to estimate the time of storage rice as for a fast evaluation of the rice quality. To accomplish this objective, near-infrared spectroscopy (NIRS) is employed in combination with three machine learning methods, including least square support vector machine (LSSVM), random forest (RF) and principal component-neural network (PC-NN). With specific design on grid search of the relevant parameters, the LSSVM model optimally performed classification with the highest accuracy of 95.7% in the distinguishment of three labeled storage years, the RF model and PC-NN models have close accuracies in model training and optimization processes. In comparison to the PLS method, which is the typical chemometric method in NIRS data analysis, the three presented machine learning methods all perform excellent over the PLS model for model training and for model testing. Especially the RF and PC-NN model were optimized by hyperparameter training, to obtain 90% of testing accuracy and reduced the error differences to ∼5.0% between model training and testing. This study indicated the potential of NIRS in combination with machine learning methods as practical chemometric tools for discrimination of the rice storage freshness by distinguishing their storage years. The design of adaptive tuning on hyperparameters provide a valuable approach to improve the model prediction abilities.

Crack identification of Yunnan walnuts based on acoustic vibration and feature fusion

AbstractCracks in walnuts during processing and storage can adversely affect their quality and cause economic losses. To achieve efficient identification of cracked walnuts, this study proposed a method of walnut crack identification based on acoustic vibration and feature fusion. First, the sound signals of intact and cracked walnuts were collected using an acoustic signal acquisition system, and 44 time‐domain features, 13 frequency‐domain features, and 768 Mel spectrogram features (the number of pixel frequencies corresponding to the gray‐scale values of R, G, and B channels) of the sound signals were extracted. Then, the classification models of support vector machines (SVM), least squares support vector machines (LSSVM), and extreme learning machines (ELM) were established based on single class features data and fusion of different feature groups data respectively. The results indicated that the LSSVM model with the fusion of the three feature sets was optimal, with an accuracy of 85% in the testing set. Next, three feature selection methods were employed to reduce the dimensionality of the best fused feature data. Subsequently, the LSSVM classification model was established based on the feature selection data. Finally, arithmetic optimization algorithm (AOA), particle swarm optimization (PSO), and gray wolf optimization (GWO) were introduced to optimize the parameters c and of the classification model. The results indicated that the best classification model was VISSA‐IRIV‐GWO‐LSSVM, with 95% accuracy in the testing set. This study provides theoretical support for the research and development of online detection equipment for walnut crack in Yunnan Yangbi.Practical applicationsCracks in walnut during harvesting, transportation and peeling may lead to economic losses and food safety problems. Aiming at the difficulty and low accuracy of crack identification in Yunnan walnut, this paper proposed a method for crack detection based on acoustic vibration identification combine with feature fusion. The features of time domain, frequency domain and Mel spectrogram were extracted from the effective sound signal, and the features were fused. The influence of three feature selection methods, three models and three optimization algorithms on walnut sound signal recognition was analyzed and compared. The results indicated that the best classification model was VISSA‐IRIV‐GWO‐LSSVM, and the method proposed in this study provides theoretical support for the research and development of online detection equipment for walnut crack in Yunnan Yangbi.

Enhancing the Performance of LSSVM Model in Predicting Rock Fragmentation Size Via Optimization Algorithms

The prediction of rock fragmentation is critical to improve the efficiency and economy of blasting excavation. In this study, an attempt is made to predict the entire fragmentation size distribution using a least square support vector machine (LSSVM) model. In addition, three optimization algorithms—the bacterial foraging algorithm (BFO), artificial fish swarm algorithm (AFSA), and adaptive particle swarm optimization (APSO)–were used to determine the appropriate parameters of the LSSVM model. In the constructed LSSVM-BFO, LSSVM-AFSA and LSSVM-APSO models, the hole spacing, row spacing, change per delay and stemming were used as the input parameters, while the statistical rock fragmentation size was assigned as the output. The LSSVM model was also employed as a control group for comparing with the optimized models. The above-mentioned models were trained and tested based on a database comprising of 10 datasets collected from in-site testing of Altashi Water Control Project in China. The performance of the proposed models was compared by several statistical criteria. The viability and efficiency of the LSSVM-BFO model were confirmed with an R2 of 0.9960 and an RMSE of 1.8044, which were better than those of the LSSVM-AFSA, LSSVM-APSO and LSSVM. Last but not least, sensitivity analysis was also executed. The result of sensitivity analysis demonstrated when the size of rock fragmentation of prediction is less 80mm, the most effective parameter will be stemming; otherwise the most effective parameter will be hole spacing.

Predicting uniaxial compressive strength from drilling variables aided by hybrid machine learning

Awareness of uniaxial compressive strength (UCS) as a key rock formation parameter for the design and development of gas and oil field plays. It plays an essential role in the selection of the drill bits and stability of the wellbore’s wall. Precise prediction of UCS before or during the drilling, especially in exploration wellbores, is necessary to improve the drilling speed and reduce the instability of the wellbore walls. UCS predictor machine-learning (ML) models are developed in this study using drilling parameters recorded during drilling using least-squares support-vector machine (LSSVM) and multi-layer extreme learning machine (MELM) algorithms hybridized with cuckoo optimization algorithm (COA), particle swarm optimization (PSO) and genetic algorithm (GA) optimizers. In addition, stand-alone LSSVM and convolutional neural network (CNN) models without optimizer enhancements are evaluated. Drilling and petrophysical data recorded for two wells (A and B) from the Rag-e-Safid oil field in southwest Iran were compiled to form the studied dataset. UCS was initially calculated numerically based on data from laboratory tests from petrophysical logs. The Well A dataset was pre-processed to remove outlying data records by applying the quantile regression algorithm. That analysis indicated that 9 data records should be removed from the Well A dataset. A decision tree model was employed for feature selection purposes to identify the more influential variables with respect to UCS. Depth, weight on the drill bit (WOB), drill-string rotation speed (RPM), rate of penetration (ROP), and torque (Trq) were the variables identified as being highly influential on UCS values. Application of the ML models on the training data subset (75% of Well A data records) revealed that the MELM-COA algorithm achieved the lowest root mean squared error (4.6945 MPa) and a higher coefficient of determination (0.9873) value than the other models when predicting UCS in the Well A training and validation data subsets. The Well-A-trained MELM-COA model confirmed its generalizability within the studied field by generating low UCS prediction errors when applied to the independent Well B testing dataset.

Machine learning-based single-phase ground fault identification strategy for AC-DC transmission lines

In this paper, an improved single-phase grounding fault (SPGF) nature identification strategy based on machine learning is proposed. To solve the problem of conventional single-phase automatic reclosure cannot distinguishing the nature of SPGF in AC-DC hybrid lines, the fault phase voltage characteristics of AC lines with DC feed are analyzed, and the voltage harmonic energy feature vector is extracted. The whale optimization algorithm (WOA) designed by orthogonal experiment design (OED) is used to select the model parameters of the least square support vector machine (LSSVM), and a discriminative model for the fault properties of the hybrid transmission line is obtained. The simulation experiments based on PSCAD/EMTDC 4.5.0 platform are conducted for model training and fault identification performance testing, and the results verifies the effectiveness and feasibility of the proposed method. Compared with LSSVM, the fault identification strategy based on OED-WOA-LSSVM has a higher accuracy in fault identification. In addition, the accuracy of the model identification strategy under different fault locations, parallel compensation degree, transition resistance, and power system noise effects is also verified.