Least Squares Support Vector Machine Research Articles

Displacement Self-Sensing Control of Permanent Magnet Assisted Bearingless Synchronous Reluctance Motor Based on Least Square Support Vector Machine Optimized by Improved NSGA-II

In order to solve the problems of low integration, low reliability, and high cost caused by mechanical sensors used in bearingless synchronous reluctance motor (PMa-BSynRM) control system, a novel displacement self-sensing control method using a least square support vector machine (LSSVM) left inverse system is proposed. Firstly, the working principle of the PMa-BSynRM is introduced and the mathematical model of the PMa-BSynRM is derived. Secondly, the observation principle of the left-inverse system of the PMa-BSynRM is explained and the left-invertibility of the displacement subsystem is proved. Thirdly, the improved NSGA-II algorithm is utilized to optimize the the regularization parameter and the bandwidth of LSSVM, and the displacement self-sensing control system is constructed. The simulations of speed variation and anti-interference are performed, which proves the dynamic tracking performance of the displacement. Finally, the static suspension, speed variation and anti-interference experiments are carried out. The feasibility and reliability of the proposed displacement self-sensing method are verified.

Prediction of the Harvest Time of Cabernet Sauvignon Grapes Using Near-Infrared Spectroscopy

Harvest time assessment during the grape-ripening process can provide meaningful information for vineyard harvest scheduling. The purpose of this study was to investigate the identification of the harvest time of grape clusters using near-infrared (NIR) spectroscopy. During the harvest season from September to October 2019, bunches of Cabernet Sauvignon grapes were examined. Before establishing two classification models, namely partial least-squares discriminant analysis (PLS-DA) and support vector machine (SVM) models, raw spectra were processed by different pre-processing methods, including multiplicative signal correction (MSC), mean-centering, the standard normal variable (SNV), and the Savitzky-Golay method. Competitive adaptive weighted sampling (CARS) and the successive projections algorithm (SPA) were employed to select the optimal wavenumbers. The results indicate that NIR spectroscopy is a potentially promising approach for the rapid identification of different harvest times of Cabernet Sauvignon grapes, and the proposed technique is helpful for the prediction of ripened and over-ripened Cabernet Sauvignon grapes during the harvest time.

Improved Least Squares Support Vector Machine Model Based on Grey Wolf Optimizer Algorithm for Predicting CO2–Crude Oil Minimum Miscibility Pressure

The minimum miscibility pressure (MMP) is an important reference parameter in the study of CO2 oil drive systems. In response to the problems of time‐consuming and costly prediction of MMP by conventional experimental methods, an improved least squares support vector machine (LSSVM) model based on grey wolf optimizer (GWO) algorithm is proposed to predict the CO2–crude oil MMP. Based on Pearson correlation analysis, reservoir temperature, C5+ molecular weight, intermediate component mole fraction, and volatile component mole fraction are selected as independent variables of the model, and MMP is the dependent variable. A total of 51 MMP experimental data are collected, of which 35 are used to fine‐tune the model's parameters and 16 are used to verify the model's reliability. The high leverage point method is used to detect anomalies in all experimental data to check the reliability of the model, and the abnormality of only one piece of experimental data is identified. Finally, a comparison of the model with other intelligent models is found. The absolute relative deviation of the GWO‐LSSVM model is 2.24% for the training data and 3.48% for the test data, which provides high adaptability and accuracy.

Detection and Analysis of Chili Pepper Root Rot by Hyperspectral Imaging Technology

The objective is to develop a portable device capable of promptly identifying root rot in the field. This study employs hyperspectral imaging technology to detect root rot by analyzing spectral variations in chili pepper leaves during times of health, incubation, and disease under the stress of root rot. Two types of chili pepper seeds (Manshanhong and Shanjiao No. 4) were cultured until they had grown two to three pairs of true leaves. Subsequently, robust young plants were infected with Fusarium root rot fungi by the root-irrigation technique. The effective wavelength for discriminating between distinct stages was determined using the successive projections algorithm (SPA) after capturing hyperspectral images. The optimal index related to root rot between each normalized difference spectral index (NDSI) was obtained using the Pearson correlation coefficient. The early detection of root rot illness can be modeled using spectral information at effective wavelengths and in NDSI, together with the application of partial least squares discriminant analysis (PLS-DA), least squares support vector machine (LSSVM), and back-propagation (BP) neural network technology. The SPA-BP model demonstrates outstanding predictive capabilities compared with other models, with a classification accuracy of 92.3% for the prediction set. However, employing SPA to acquire an excessive number of efficient wave-lengths is not advantageous for immediate detection in practical field scenarios. In contrast, the NDSI (R445, R433)-BP model uses only two wavelengths of spectral information, but the prediction accuracy can reach 89.7%, which is more suitable for rapid detection of root rot. This thesis can provide theoretical support for the early detection of chili root rot and technical support for the design of a portable root rot detector.

A gear fault diagnosis method based on variational mode decomposition and multi-scale discrete entropy

Aiming at monitoring of gearbox faults, a gear fault feature extraction method based on variational mode decomposition (VMD) and multi-scale discrete entropy (MDE) is proposed in this paper. Firstly, the gear fault signal is decomposed into a series of intrinsic modal function (IMF) by VMD with selected parameters; Secondly, the decomposed IMF are extracted by MDE feature extraction method to form a feature sample set; Finally, the least square support vector machine (LSSVM) is used to classify the data set after feature extraction. The experiment results show that the proposed method owns the higher fault diagnosis accuracy than the traditional multi-scale entropy methods.

Short-term PV power prediction based on VMD-CNN-IPSO-LSSVM hybrid model

Abstract This article discusses the significance and obstacles of short-term power prediction in photovoltaic systems and introduces a hybrid model for photovoltaic short-term power prediction technology based on variational mode decomposition (VMD), convolutional neural network (CNN), improved particle swarm optimization (IPSO) and least squares support vector machine (LSSVM). In the initial stage, the photovoltaic generation signal is decomposed into multiple Intrinsic mode functions (IMFs) using VMD to enhance the extraction of signal time–frequency characteristics. Subsequently, CNN is utilized for feature learning and extraction of each IMF, modeling the nonlinear and non-stationary features. Following this, the IPSO-LSSVM optimization algorithm is employed to establish and optimize multiple LSSVM models, predicting power fluctuations at different time scales. Finally, the predictions from each model are synthesized to obtain the final photovoltaic short-term power forecast. Through validation with actual photovoltaic generation data, this hybrid model demonstrates high accuracy and reliability in short-term power prediction, showing an average relative error and root mean square error reduction of 15.23 and 53.60%, respectively, compared to a certain comparative model. This proposed method based on VMD-CNN-IPSO-LSSVM hybrid model for photovoltaic power prediction holds promising prospects and practical value in the operation and scheduling of photovoltaic generation systems.

Short-term wind speed forecasting based on a hybrid model that integrates PSO-LSSVM and XGBoost

Abstract A groundbreaking method is proposed to mitigate the impact of unpredictable fluctuations in wind velocity on wind power generation. This innovative approach integrates the particle swarm optimization (PSO)-least squares support vector machine (LSSVM) and XGBoost models in a harmonious manner. Initially, the raw wind speed data is subjected to wavelet threshold denoising to reduce noise and volatility. For short-term wind speed prediction, a PSO-LSSVM-XGBoost model is introduced. After the initial wind speed sequence undergoes wavelet threshold denoising, the enhanced sequence is forecasted using the LSSVM model, with its hyperparameters optimized through the PSO algorithm. The errors, obtained by subtracting the predicted values from the original data, are compensated using XGBoost. The final forecast results combine the rectified error data with the initial projected results. Experimental findings demonstrate the model’s remarkable capability to enhance prediction performance and accuracy.

Machine Learning-Based Modeling and Predictive Control of Combustion Phasing and Load in a Dual-Fuel Low-Temperature Combustion Engine

<div>Reactivity-controlled compression ignition (RCCI) engine is an innovative dual-fuel strategy, which uses two fuels with different reactivity and physical properties to achieve low-temperature combustion, resulting in reduced emissions of oxides of nitrogen (NO<sub>x</sub>), particulate matter, and improved fuel efficiency at part-load engine operating conditions compared to conventional diesel engines. However, RCCI operation at high loads poses challenges due to the premixed nature of RCCI combustion. Furthermore, precise controls of indicated mean effective pressure (IMEP) and CA50 combustion phasing (crank angle corresponding to 50% of cumulative heat release) are crucial for drivability, fuel conversion efficiency, and combustion stability of an RCCI engine. Real-time manipulation of fuel injection timing and premix ratio (PR) can maintain optimal combustion conditions to track the desired load and combustion phasing while keeping maximum pressure rise rate (MPRR) within acceptable limits.</div> <div>In this study, a model-based controller was developed to track CA50 and IMEP accurately while limiting MPRR below a specified threshold in an RCCI engine. The research workflow involved development of an imitative dynamic RCCI engine model using a data-driven approach, which provided reliable measured state feedback during closed-loop simulations. The model exhibited high prediction accuracy, with an <i>R</i><sup>2</sup> score exceeding 0.91 for all the features of interest. A linear parameter-varying state space (LPV-SS) model based on least squares support vector machines (LS-SVM) was developed and integrated into the model predictive controller (MPC). The controller parameters were optimized using genetic algorithm and closed-loop simulations were performed to assess the MPC’s performance. The results demonstrated the controller’s effectiveness in tracking CA50 and IMEP, with mean average errors (MAE) of 0.89 crank angle degree (CAD) and 46 kPa and Mean absolute percentage error (MAPE) of 9.7% and 7.1%, respectively, while effectively limiting MPRR below of 10 bar/CAD. This comprehensive evaluation showcased the efficacy of the model-based control approach in tracking CA50 and IMEP while constraining MPRR in the dual-fuel engine.</div>

Remaining useful life prediction of lithium battery based on CEEMD-SE-IPSO-LSSVM hybrid model

Abstract In order to prevent accidents caused by battery aging, accurately predicting the remaining useful life (RUL) is a critical and highly challenging task in battery management systems. This article describes a lithium-ion battery RUL prediction method based on a hybrid model of CEEMD-SE-IPSO-LSSVM. This method integrates various technologies and algorithms, enhancing the accuracy and practicality of predictions. Initially, the complete ensemble empirical mode decomposition (CEEMD) is utilized to decompose the raw data into multiple intrinsic mode functions, aiding in denoising and feature extraction. Subsequently, the sample entropy (SE) is used to assess the complexity and irregularity of the data, merging intrinsic mode function components with similar SE values into a new component. Building upon this, the advanced iterative particle swarm optimization (IPSO) algorithm refines the parameters of the least squares support vector machine (LSSVM) model, improving the predictive performance of the model. Finally, through iterative training and refinement of the LSSVM model, accurate prediction of the remaining life of lithium-ion batteries is achieved. This hybrid model approach integrates data processing, feature extraction, and model refinement, resulting in a significant improvement over the baseline model with a 69.5% increase in mean absolute percentage error and a 49.4% decrease in root mean squared error, providing a robust solution for predicting the remaining life of lithium-ion batteries.

Research on Demagnetization Fault Diagnosis Method of Mine Cutting Permanent Magnet Synchronous Motor

To give timely and accurate diagnosis in the early stage of demagnetization failure for effective control and treatment, based on wavelet packet analysis, principal component analysis (PCA) dimensionality reduction, and least squares support vector machine(LSSVM), the extraction of features and the classification of demagnetization faults are completed. Since it is difficult to collect real data sets of demagnetization faults in practice, a two-dimensional finite element simulation model of permanent magnet synchronous motor (PMSM) under uniform demagnetization and partial demagnetization faults is established based on the Maxwell simulation platform. The wavelet packet analysis is used to extract the demagnetization feature of the A-phase current of the PMSM. Based on PCA dimensionality reduction, the dimensionality reduction of fault features is realized. The LSSVM is used to identify the fault and complete the fault classification. The simulation results show that the method has a high classification accuracy rate for demagnetization faults.

Research on the method of identifying upper and lower limb coordinated movement intentions based on surface EMG signals.

Rehabilitation robots have gained considerable focus in recent years, aiming to assist immobilized patients in regaining motor capabilities in their limbs. However, most current rehabilitation robots are designed specifically for either upper or lower limbs. This limits their ability to facilitate coordinated movement between upper and lower limbs and poses challenges in accurately identifying patients' intentions for multi-limbs coordinated movement. This research presents a multi-postures upper and lower limb cooperative rehabilitation robot (U-LLCRR) to address this gap. Additionally, the study proposes a method that can be adjusted to accommodate multi-channel surface electromyographic (sEMG) signals. This method aims to accurately identify upper and lower limb coordinated movement intentions during rehabilitation training. By using genetic algorithms and dissimilarity evaluation, various features are optimized. The Sine-BWOA-LSSVM (SBL) classification model is developed using the improved Black Widow Optimization Algorithm (BWOA) to enhance the performance of the Least Squares Support Vector Machine (LSSVM) classifier. Discrete movement recognition studies are conducted to validate the exceptional precision of the SBL classification model in limb movement recognition, achieving an average accuracy of 92.87%. Ultimately, the U-LLCRR undergoes online testing to evaluate continuous motion, specifically the movements of "Marching in place with arm swinging". The results show that the SBL classification model maintains high accuracy in recognizing continuous motion intentions, with an average identification rate of 89.25%. This indicates its potential usefulness in future rehabilitation robot-active training methods, which will be a promising tool for a wide range of applications in the fields of healthcare, sports, and beyond.

A dual-scale hybrid prediction model for UAV demand power: Based on VMD and SSA optimization algorithm

The prediction of power demand for unmanned aerial vehicles (UAV) is an essential basis to ensure the rational distribution of the energy system and stable economic flight. In order to accurately predict the demand power of oil-electric hybrid UAV, a method based on variational mode decomposition (VMD) and Sparrow Search Algorithm (SSA) is proposed to optimize the hybrid prediction model composed of long-short term memory (LSTM) and Least Squares Support Vector Machine (LSSVM). Firstly, perform VMD decomposition on the raw demand power data and use the sample entropy method to classify the feature-distinct mode components into high-frequency and low-frequency categories. Then, each modality component was separately input into the mixed model for rolling prediction. The LSSVM model and LSTM model were used to process low-frequency and high-frequency components, respectively. Finally, the predicted values for each modal component are linearly combined to obtain the final predicted value for power demand. Compared with the current models, the prediction model constructed in this paper stands out for its superior ability to track the changing trends of power demand and achieve the highest level of prediction accuracy.

Evaluation of Emission Reduction Performance of Power Enterprises Based on Least Squares Support Vector Machine

In response to the increasingly severe environmental pollution problem at present, many traditional power companies are facing the promotion of environmental protection work. The promotion of Energy Conservation and Emission Reduction (ECER) work needs sufficient theory and data support. Therefore, this study proposes a performance evaluation model for ECER in power enterprises based on the improved lion swarm algorithm optimized Least Squares Support Vector Machine (LSSVM). The evaluation index system has been reconstructed according to the current environment and era characteristics. The LSSVM has been used to evaluate the ECER work of power enterprises, and the training efficiency of Lion Swarm Optimization (LSO) algorithm has been solved using chaos theory. An improved LSO algorithm is utilized to improve the parameter selection problem of the LSSVM model, to achieve a scientific and objective evaluation of the ECER performance of power enterprises. The research findings denote that the algorithm put forward in this study has better training efficiency, higher accuracy and stability, as well as better response time. It also exhibits minimal errors in simulation experiments. In summary, the ECER performance evaluation model proposed by this research institute can effectively output correct scoring results, providing data support for the promotion of environmental protection work.

An information theory approach for recursive LPV-ARX model identification via LS-SVM

When modeling a dynamical system, linear models are always the first choice due to their simplicity. However, many times the system is too complex so that employing linear models results in poor performances. In this context, Linear Parameter Varying (LPV) models allow to represent non-linear input/output relationships while preserving the simple structure of linear models. The method of Least Squares Support Vector Machines (LS-SVM) is one of the most common approaches to identify a LPV model in an ARX formulation (LPV-ARX). However, due to its computational cost, it is difficult to identify a LPV-ARX model using LS-SVM in online applications, where the model must be updated every time new data are collected. An efficient update algorithm has been presented for online identification of such models, where the idea is to update the model only upon certain data that are considered informative. However, this approach requires the tuning of some hyperparameters and in certain conditions can stop updating the model even when data are informative. This paper proposes an information-based algorithm to overcome these drawbacks. Evaluation on simulated and experimental data show the effectiveness of the proposed approach on both identification and computational sides.

Multistep Wind Speed Prediction Based on the Fractional‐Order Longicorn Swarm Algorithm and the Two‐Stage Modal Decomposition Strategy

Least squares support vector machine (LSSVM) and variational mode decomposition are common research methods for wind speed time series prediction. Addressing the challenge of selecting relevant parameters of LSSVM and VMD, a fractional‐order Beetle swarm optimization algorithm is proposed to optimize the relevant parameters. To weaken the negative impact of wind speed volatility on the accuracy of the prediction model, a two‐stage modal decomposition strategy based on extreme‐point symmetric mode decomposition, FO‐BSO algorithm, and VMD is proposed. ESMD is used to decompose the original wind speed time series. The diversity entropy is introduced as the criterion, and the FO‐BSO‐VMD secondary decomposition is applied for the high‐entropy modal components to further weaken the volatility of wind speed. Simulation results show that compared with the original LSSVM model, the ESMD‐FO‐BSO‐VMD‐LSSVM model presented in this study exhibits an average 44.10% increase in the fitting degree of wind speed prediction over three steps, which verifies the superior performance of the model in short‐term multistep wind speed prediction.

ITTCA-MVL: A multi-view learning model based on physicochemical information and sequence statistical information for tumor T cell antigens identification

Immunotherapy is an emerging treatment method aimed at activating the human immune system and relying on its own immune function to kill cancer cells and tumor tissues. It has the advantages of wide applicability and minimal side effects. Effective identification of tumor T cell antigens (TTCAs) will help researchers understand their functions and mechanisms and carry out research on anti-tumor vaccine development. Considering that using biological experimental technology to identify TTCAs can be costly and time-consuming, it is necessary to develop a robust bioinformatics computing tool. At present, different machine learning models have been proposed for identifying TTCAs, but there is still room for further improvement in their performance. To establish a TTCA predictor with better prediction performance, we propose a prediction model called iTTCA-MVL in this paper. We extracted three sets of features from the views of physicochemical information and sequence statistics, namely the distribution descriptor of composition, transition, and distribution (CTDD), TF-IDF, and LSA topic. Then, we used least squares support vector machines (LSSVMs) as submodels and Hilbert‒Schmidt independence criteria (HSIC) as constraints to establish an independent and complementary multi-view learning model. The prediction accuracy of iTTCA-MVL on the independent test set is 0.873, and Matthew's correlation coefficient is 0.747, which is significantly better than those of existing methods. Therefore, iTTCA-MVL is an excellent prediction tool that researchers can use to accurately identify TTCAs.

Prediction of the effluent chemical oxygen demand and volatile fatty acids for anaerobic treatment based on different feature selections machine-learning methods from lab-scale to pilot-scale

The effluent chemical oxygen demand (COD) and volatile fatty acids (VFA) are important indicators for measuring wastewater anaerobic treatment systems. Through lab and pilot experiments on the anaerobic treatment process of high-salt wastewater, combined with different prediction requirements, the feature variables are classified. The effluent-COD and VFA prediction models of five different Machine-learning methods (i.e., back propagation neural network (BPNN), Genetic algorithm optimizes BPNN(GA-BP), support vector machine (SVM), Least squares support vector machine (LSSVM), and random forest (RF)) were established. The modeling results on different dataset (i.e., lab dataset, pilot dataset and mixed dataset) showed that the SVM and LSSVM methods based on statistical learning had the best model prediction performance in lab and pilot datasets, and the RF method performed well in mixed dataset. Furthermore, the genetic algorithm was adopted to optimize the RF model. After optimization of mixed dataset, the effluent-COD prediction (i.e., R2 = 0.966, RMSE/MAE are 61.227/48.584 mg/L) and VFA prediction (i.e., R2 = 0.639, RMSE/MAE are 26.838/21.831 mg/L) have been improved compared with the original RF model (i.e., R2 = 0.918, RMSE/MAE are 86.232/65.03 mg/L of effluent-COD, and R2 = 0.539, RMSE/MAE are 35.489/26.726 mg/L of VFA). This research can provide a reference for the prediction of the anaerobic treatment of actual large-scale industrial wastewater.

Optimisation Analysis of Enterprise Environmental Cost Accounting Based on Support Vector Machine Model

Abstract Environmental cost accounting, as a developing field, has been implemented in enterprises for only a brief duration, revealing several areas necessitating enhancements. This paper presents an environmental cost accounting method based on Support Vector Machines (SVM) to address the challenges posed by large and complex data sets in enterprise ecological cost accounting. The technique employs the Radial Basis Function (RBF) kernel to optimize the SVM model, derives the linear regression equation for the Least Squares SVM (LS-SVM) model, and preprocesses enterprise environmental cost data. It integrates Material Flow Cost Accounting (MFCA) to extract essential environmental cost-related data for enterprises. In the empirical application within a tested enterprise, the total cost attributed to resource loss amounted to 1,423,002.55 yuan, representing 4.89% of total expenses, with material costs accounting for the highest share at 86.35%. The analysis suggests that enterprises should prioritize monitoring and managing material costs to minimize resource wastage. Regarding the accounting for external environmental damage, sulfur dioxide and fluoride emissions from material quantity center 1 were identified as the predominant pollutants, exceeding 90% of emissions. This highlights the need for targeted energy-saving and emission-reduction measures for these pollutants to mitigate their environmental impact.

Exploring the variability and heterogeneity of apple firmness using visible and near-infrared hyperspectral imaging

In this work, the variability and heterogeneity of apple firmness and their effects on the prediction performances of developed models based on hyperspectral imaging (HSI) at 380–1010 nm were explored. Both the inter-variability of cultivars and the intra-variability of single apples presented intensive changes of firmness. A large heterogeneity of firmness inside single apples was located at the equator of ‘Red Fuji’, the calyx of ‘Cream Fuji’ and the stem of ‘Huaniu’, with the variation coefficient of 15.6%, 15.4% and 17.5%, respectively. Besides, the least square support vector machines (LS-SVM) models based on the HSI spectra from different cultivars and spatial regions had the best prediction performances of firmness, with the Rc2, Rp2 of 0.85 and 0.81, respectively. This study indicated the modelling calibration of apple firmness should particularly consider both apple variability and heterogeneity at the stem, equator and calyx regions to obtain accurate HSI determinations of firmness. Furthermore, the development of a multi-cultivar model for apple fruit is significant, for improving the performance of the firmness model.

Integrative analysis of multi machine learning models for tetracycline photocatalytic degradation with MOFs in wastewater treatment

This study focuses on the utilization of connectionist models, specifically Independent Component Analysis (ICA), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Genetic Algorithm-Particle Swarm Optimization (GAPSO) integrated with a least-squares support vector machine (LSSVM) to forecast the degradation of tetracycline (TC) through photocatalysis using Metal-Organic Frameworks (MOFs). The primary objective of this study was to evaluate the viability and precision of these connectionist models in estimating the efficiency of TC degradation, particularly within the context of wastewater treatment. The input parameters for these models cover essential MOF characteristics, such as pore size and surface area, along with critical operational factors, such as pH, TC concentration, catalyst dosage, and illumination duration, all of which are linked to the photocatalytic performance of MOFs. Sensitivity analysis revealed that the illumination duration is the primary influencer of TC photodegradation with MOF photocatalysts, while the MOFs’ surface area is the second crucial parameter shaping the efficiency and dynamics of the TC-MOF photocatalytic system. The developed LSSVM models display impressive predictive capabilities, effectively forecasting the experimental degradation of TC with high accuracy. Among these models, the GAPSO-LSSVM model excels as the top performer, achieving notable evaluation metrics, including STD, RMSE, MSE, MRE, and R2 at values of 3.09, 3.42, 11.71, 5.95, and 0.986, respectively. In comparison, the PSO-LSSVM, ICA-LSSVM, and GA-LSSVM models yield mean relative errors of 6.18%, 7.57%, and 11.37%, respectively. These outcomes highlight the exceptional predictive capabilities of the GAPSO-LSSVM model, solidifying its position as the most accurate and dependable model for predicting TC photodegradation in this study. This study contributes to advancing photocatalytic research and effectively reinforces the importance of leveraging machine learning methodologies for tackling environmental challenges.