Parameters Of Least Squares Support Vector Machine Research Articles

Simulation research on breakdown diagnosis based on least squares support vector machine optimized by simulated annealing genetic algorithm

The application of support vector machine to the aircraft power supply system breakdown diagnosis is one of the research focuses in the tomorrow. Support vector machine (SVM) belongs a new type of machine learning technique, which uses structural hazard minimization rule to substitute for the conventional empirical hazard minimization according to great specimen. The powerful performance of the least squares support vector machine (LSSVM) needs to be reflected in the optimal selection of appropriate parameters, and the quality of parameters greatly affects the accuracy and efficiency of breakdown diagnosis. The traditional LSSVM parameters selection method is inefficient, the calculation is huge, and it takes expensive time to select the satisfactory solution. Aiming at the problem of parameters selection of LSSVM, the way of optimizing the parameters of LSSVM by apply simulated annealing genetic algorithm (SAGA) is proposed. SAGA uses the parallel sampling process of genetic algorithm to improve the time performance of optimization, and makes use of the simulated annealing algorithm to dominate the constriction of majorization to prevent precocity. On the one hand, genetic algorithm has strong ability to grasp the overall search process, on the other hand, simulated annealing algorithm is used to control the convergence of the algorithm to prevent premature phenomenon. The automatic optimal selection of LSSVM parameters is achieved. The Iris system classification and recognition in the UCI machine learning database and the breakdown diagnosis of the autopilot flight control box are used as experimental platforms to obtain data samples for simulation research. The simulation results show that LSSVM optimized by SAGA improves both the accuracy and efficiency of classification recognition. It not only effectively overcomes the problem of low efficiency caused by searching optimal parameters by experience, but also effectively improves the accuracy of classification recognition. The false alarm rate and redundant breakdowns are effectively reduced.

Abnormal Status Detection of Catenary Based on TSNE Dimensionality Reduction Method and IGWO-LSSVM Model

Background: Catenary is a crucial component of an electrified railroad's traction power supply system. There is a considerable incidence of abnormal status and failures due to prolonged outside exposure. Driving safety will be directly impacted if an abnormal status or failure occurs. Currently, catenary detection vehicles are the most often utilized technique for gathering data and identifying faults based on manual experience. However, this technology cannot meet the demands of prompt detection and correction of faults in railways engineering due to its extremely low work efficiency. Objective: Based on the above, an abnormal status detection method of catenary based on the improved gray wolf (IGWO) algorithm optimized the least squares support vector machine (LSSVM) with the t-distributed stochastic neighbor embedding (TSNE) is proposed in this paper. In order to improve the accuracy of catenary abnormal status detection and shorten the detection time. Methods: Firstly, the TSNE dimensionality reduction technology is used to reduce the original catenary data to three-dimensional space. Then, in order to address the issue that the parameters of the LSSVM detection model are hard to determine, the improved GWO algorithm is used to optimize the penalty factor and kernel parameter in the LSSVM and establish the TSNE-IGWO-LSSVM catenary abnormal status detection model. Finally, contrasting experimental results of different detection models. The T-distributed Stochastic Domain Embedding (TSNE) is an improved nonlinear dimensionality reduction method based on the Stochastic Neighbor Embedding (SNE). TSNE no longer adopts the distance invariance in linear dimensionality reduction methods such as ISOMAP. TSNE is much better than the linear dimensionality reduction method in the reduction degree of the original dimension. The GWO algorithm, which is frequently used in engineering research, has the advantages of a simple model, great generalization capability, and good optimization performance. The premature convergence is one of the remaining flaws. By applying a good point set to initialize the gray wolf population and the nonlinear control parameters, the gray wolf algorithm is improved in this research. The IGWO algorithm effectively makes up for the problem of balancing the local exploitation and global search capabilities of GWO. Additionally, this IGWO algorithm performs the Cauchy variation operation on the current generation optimal solution to improve population diversity, enlarge the search space, and increase the likelihood of the algorithm escaping the local optimal solution in order to prevent the algorithm from failing the local optimum. The Least Squares Support Vector Machine (LSSVM) is an improved version of the Support Vector Machine (SVM), which replaces the original inequality constraint with a linear least squares criterion for the loss function. The kernel parameters of the RBF function and the penalty factor, these two parameters directly determine the detection effect of LSSVM. In this paper, the IGWO is utilized to adjust and determine the LSSVM parameters in order to enhance the detection capacity of the LSSVM model. Results:: In this paper, in order to minimize the experiment's bias, the training data and the test data are allocated in a ratio of 4:1, the training data are set to 400 groups, and the test data are set to 100 groups. After training the five models, the test data is used to validate and compare the detection capacity of the models. After each of the five detection models was tested ten times, the TSNE-IGWO-LSSVM model is compared with the IGWO-LSSVM model, the TSNE-FA-LSSVM model, the GWO-LSSVM model, and the GWO-ELM model, the results show that the TSNE-IGWO-LSSVM model has the highest average detection accuracy of 97.1% and the shortest running time of 26.9s. For the root mean squared error (RMSE) and the root mean squared error (RMSE), the TSNE-IGWO-LSSVM model is 0.17320 and 2.51% respectively, which is the best among the five models, indicating that it not only has higher detection accuracy but also better convergence of detection accuracy than the other models. Conclusions: With the thousands of miles of catenary and the complexity of the data, it is crucial to shorten the running time in order to improve the efficiency and ease the burden of the processors. The experiments demonstrate that the TSNE-IGWO-LSSVM detection model can detect the abnormal status of catenary more accurately and quickly, providing a new method for the abnormal status detection of catenary, which has certain application value and engineering significance in the era of fully electrified railways.

Stock market prediction using Altruistic Dragonfly Algorithm.

Stock market prediction is the process of determining the value of a company's shares and other financial assets in the future. This paper proposes a new model where Altruistic Dragonfly Algorithm (ADA) is combined with Least Squares Support Vector Machine (LS-SVM) for stock market prediction. ADA is a meta-heuristic algorithm which optimizes the parameters of LS-SVM to avoid local minima and overfitting, resulting in better prediction performance. Experiments have been performed on 12 datasets and the obtained results are compared with other popular meta-heuristic algorithms. The results show that the proposed model provides a better predictive ability and demonstrate the effectiveness of ADA in optimizing the parameters of LS-SVM.

Prediction of the Yield Strength of RC Columns Using a PSO-LSSVM Model

Accuracy prediction of the yield strength and displacement of reinforced concrete (RC) columns for evaluating the seismic performance of structure plays an important role in engineering the structural design of RC columns. A new hybrid machine learning technique based on the least squares support vector machine (LSSVM) and the particle swarm optimization (PSO) algorithm is proposed to predict the yield strength and displacement of RC columns. In this PSO-LSSVM model, the LSSVM is applied to discover the mapping between the influencing factors and the yield strength and displacement, and the PSO algorithm is utilized to select the optimal parameters of LSSVM to facilitate the prediction performance of the proposed model. A dataset covering the PEER database and the available experimental data in relevant literature is established for model training and testing. The PSO algorithm is then evaluated and compared with other metaheuristic algorithms based on the experiment’s database. The results indicate the effectiveness of the PSO employed for improving the prediction performance of the LSSVM model according to the evaluation criteria such as the root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R2). Overall, the simulation demonstrates that the developed PSO-LSSVM model has ideal prediction accuracy in the yield properties of RC columns.

NEXT-HOUR ELECTRICITY PRICE FORECASTING USING LEAST SQUARES SUPPORT VECTOR MACHINE AND GENETIC ALGORITHM

Predicting the price of electricity is crucial for the operation of power systems. Short-term electricity price forecasting deals with forecasts from an hour to a day ahead. Hourly-ahead forecasts offer expected prices to market participants before operation hours. This is especially useful for effective bidding strategies where the bidding amount can be reviewed or changed before the operation hours. Nevertheless, many existing models have relatively low prediction accuracy. Furthermore, single prediction models are typically less accurate for different scenarios. Thus, a hybrid model comprising least squares support vector machine (LSSVM) and genetic algorithm (GA) was developed in this work to predict electricity prices with higher accuracy. This model was tested on the Ontario electricity market. The inputs, which were the hourly Ontario electricity price (HOEP) and demand for the previous seven days, as well as 1-h pre-dispatch price (PDP), were optimized by GA to prevent losing potentially important inputs. At the same time, the LSSVM parameters were optimized by GA to obtain accurate forecasts. The hybrid LSSVM-GA model was shown to produce an average mean absolute percentage error (MAPE) of 8.13% and the structure of this model is less complex compared with other models developed in previous studies. This is due to the fact that only two algorithms were used (LSSVM and GA), with the load and HOEP for the week preceding the forecasting hour as the inputs. Based on the results, it is concluded that the proposed hybrid algorithm is a promising alternative to produce good electricity price forecasts.

Modeling resilient modulus of subgrade soils using LSSVM optimized with swarm intelligence algorithms

Resilient modulus (Mr) of subgrade soils is one of the crucial inputs in pavement structural design methods. However, the spatial variability of soil properties and the nature of test protocols, the laboratory determination of Mr has become inexpedient. This paper aims to design an accurate soft computing technique for the prediction of Mr of subgrade soils using the hybrid least square support vector machine (LSSVM) approaches. Six swarm intelligence algorithms, namely particle swarm optimization (PSO), grey wolf optimizer (GWO), symbiotic organisms search (SOS), salp swarm algorithm (SSA), slime mould algorithm (SMA), and Harris hawks optimization (HHO) have been applied and compared to optimize the LSSVM parameters. For this purpose, a literature dataset (891 datasets) of different types of soils has been used to design and evaluate the proposed models. The input variables in all of the proposed models included confining stress, deviator stress, unconfined compressive strength, degree of soil saturation, soil moisture content, optimum moisture content, plasticity index, liquid limit, and percent of soil particles (P #200). The accuracy of the proposed models was assessed by comparing the predicted with the observed of Mr values with respect to different statistical analyses, i.e., root means square error (RMSE) and determination coefficient (R2). For modeling the Mr of subgrade soils, percent passing No. 200 sieve, optimum moisture content, and unconfined compressive strength were found to be the most significant variables. It is observed that the performance of LSSVM-GWO, LSSVM-SOS, and LSSVM-SSA outperforms other models in predicting accurate values of Mr. The (RMSE and R2) of the LSSVM-GWO, LSSVM-SSA, and LSSVM-SOS are (6.79 MPa and 0.940), (6.78 MPa and 0.940), and (6.72 MPa and 0.942), respectively, and hence, LSSVM-SOS can be used for high estimating accuracy of Mr of subgrade soils.

A hybrid variational mode decomposition and sparrow search algorithm-based least square support vector machine model for monthly runoff forecasting

Abstract Monthly runoff forecasting has always been a key problem in water resources management. As a data-driven method, the least square support vector machine (LSSVM) method has been investigated by numerous studies in runoff forecasting. However, selecting appropriate parameters for LSSVM is the key to obtaining satisfactory model performance. In this study, we propose a hybrid model for monthly runoff forecasting, VMD-SSA-LSSVM for short, which combines variational mode decomposition (VMD) with LSSVM and the parameters of LSSVM are optimized by a sparrow search algorithm (SSA). Firstly, VMD is utilized to decompose the original time series data into several subsequences. Secondly, LSSVM is employed to simulate each subsequence, for which the parameters are optimized by SSA. Finally, the simulated results for each subsequence are accumulated as the final results. The validity of the proposed model was verified by forecasting monthly runoff for two reservoirs located in China. Four frequently-used statistical indexes, namely the Nash efficiency coefficient, root mean squared error, correlation coefficient and mean absolute percentage error were used to evaluate model performance. The results demonstrate the superiority of VMD-SSA-LSSVM over the compared models in terms of all statistical indexes, indicating that it is beneficial for enhancing monthly runoff forecast accuracy.

Sensory evaluation and prediction of bulk wine by physicochemical indicators based on PCA‐PSO‐LSSVM method

It is difficult to implement the sensory quality evaluation of bulk wine before and after transportation due to geographical, time, cost, and personnel limitation. This study aimed to use the physicochemical indicators of bulk wine to construct an evaluation model of sensory quality. First, this paper designed and carried out the simulation experiment of bulk wine transportation and obtained experimental data on physicochemical and sensory indicators of wine. Afterwards, principal component analysis (PCA) was used to reduce the dimension and fuse features of the physicochemical index. Then, the extracted features were used as the input of the evaluation model, least square support vector machine (LSSVM) was constructed for sensory evaluation, and particle swarm optimization (PSO) algorithm was selected to optimize LSSVM parameters. Finally, the PCA-PSO-LSSVM model was practically applied in sampled winery. The results showed that comparing models’ accuracy the PCA-PSO-LSSVM model was superior to traditional models LSSVM and PSO-LSSVM, there is significant difference between PCA-PSO-LSSVM and LSSVM, and the predictive accuracy in appearance and taste attributes was high and the overall prediction accuracy was 86.6%. The application results revealed the changes of sensory quality for bulk wine after transportation. This research provides a set of simple and feasible methods for the sensory evaluation of bulk wine. Practical applications To study the method of using the basic physicochemical index of wine to intelligently evaluate the sensory attributes of bulk wine, so as to realize the accurate evaluation of the quality of bulk wine after transportation. By comparing the comprehensive and accurate quality evaluation before and after the bulk wine transportation, it is helpful for wine companies to understand the impact of the transportation link on the wine quality, further improve the transportation method of bulk wine, and ensure the quality of the wine has important practical significance.

A least square support vector machine approach based on bvRNA-GA for modeling photovoltaic systems

Accurate model plays an important role in designing, assessing, and controlling photovoltaic (PV) systems. In this work, the least-squares support vector machine (LSSVM) is adopted to model the current–voltage (V–I) characteristic curves of different PV systems. A novel RNA genetic algorithm (bvRNA-GA) is proposed to determine the parameters of LSSVM. The bvRNA-GA is featured by designing the bulge loop crossover operator and the virus-induced mutation operator, they are employed to balance the exploration and exploitation capacities. Different experiments with 10 benchmark functions are conducted to show that the search efficiency of bvRNA-GA is better than the other four state-of-art algorithms. The outputs of bvRNA-GA optimized LSSVM models can better agree with the real outputs of different PV systems, the modeling results demonstrate the effectiveness of bvRNA-GA in solving real-world problems.

Energy Loss Calculation of Low Voltage Distribution Area Based on Variational Mode Decomposition and Least Squares Support Vector Machine

In order to improve the accuracy of theoretical energy loss calculation in low voltage distribution area (LV-area), this paper proposes a new prediction method based on variational mode decomposition (VMD) and particle swarm optimization (PSO) least squares support vector machine (LSSVM). Firstly, the main influencing factors of energy loss calculation in LV-area are determined by the grey correlation method, which reflects the data-driven characteristic of the method and ensures the objectivity of the prediction results and the generalization of the calculation model. Secondly, the trend component and fluctuation component are obtained by VMD of daily energy loss series in the LV-area. The variable set of main influencing factors of energy losses is used as the input variable of LSSVM, and the VMD result of the energy loss sequence is used as the output. The theoretical energy loss training and calculation model of LV-area is established. Compared with the traditional calculation model, this model has more accurate calculation accuracy by taking into account the frequency characteristics of energy losses in different frequency bands. PSO is used to optimize the parameters of LSSVM for the purpose of improving the accuracy of LSSVM. Finally, an example of 252 LV-area in a city in northern China is given to verify the validity of the proposed method. The results indicate that the proposed method generates more accurate results.

Particle Swarm Optimization for Least Square Support Vector Machine in MediumTerm Electricity Price Prediction

Predicting electricity price has now become an important task for planning and maintenance of power system. In medium-term forecast, electricity price can be predicted for several weeks ahead, up to a few months or a year ahead. It is useful for resources reallocation where the market players have to manage the price risk on the expected market scenario. However, the research on medium-term price forecast have also exhibited low forecast accuracy due to the limited historical data for training and testing purposes. Therefore, an optimization technique using Particle Swarm Optimization (PSO) for Least Square Support Vector Machine (LSSVM) was developed in this study to provide an accurate electricity price forecast with optimized LSSVM parameters. After thorough database mining in English language, no literature has been found on parameter optimization using LSSVM-PSO for medium-term price prediction. The model was examined on the Ontario power market which was reported as among the most volatile market worldwide. Monthly average of Hourly Ontario Electricity Price (HOEP) for the past 12 months and month index were selected as the input. The developed LSSVM-PSO showed higher forecast accuracy with lower complexity than the existing models.

IDP: An Intelligent Data Prediction Scheme Based on Big Data and Smart Service for Soil Heavy Metal Content Prediction

In the application of regression prediction through big data technology, the error between the predicted value and the true value is often large. In order to reduce the error of data prediction, this paper proposes an Intelligent Data Prediction (IDP) scheme for Smart Service. It uses Least Squares Support Vector Machine (LSSVM) as the basic prediction model. Since there is no standard procedure for determining the main parameters of LSSVM, an improved Particle Swarm Optimization (MBPSO) algorithm is used to simultaneously optimize the parameters of LSSVM. The main disadvantage of PSO is precocity due to the disappearance of population diversity. Based on this, Improvement strategy of MBPSO aims to continuously generate “More” and “Better” particles. First, in order to avoid the early disappearance of particle diversity, MBPSO re-adjusted the inertia weight and learning factor. Secondly, a renewable access strategy is proposed to allow a part of the disappeared population to regenerate. Finally, the method of global optimal adjustment is introduced to help particles find the optimal flight direction. In order to verify the effectiveness of MBPSO, 9 test functions are used to test the algorithm performance. The results show that MBPSO’s optimization speed, best and mean all perform best. Taking the farmland soil heavy metal data sets of Dongxihu District and Hannan District of Wuhan City as examples of application, the content of heavy metals Cr and Pb in the soil was predicted. The results show that the predicted value of IDP is closer to the actual value, and the three error index values are significantly lower than other models. Especially in the prediction of Pb content, compared with the LSSVM model, the prediction errors of the two regions are reduced by 25.67% and 20.70% respectively. We can conclude that the proposed IDP scheme has practical significance in data prediction.

Prediction of Blood Glucose Concentration Based on CEEMD and Improved Particle Swarm Optimization LSSVM.

Aiming at the difficulty of accurate prediction due to the randomness and nonstationary nature of blood glucose concentration series, a blood glucose concentration prediction model based on complementary ensemble empirical mode decomposition (CEEMD) and least squares support vector machine (LSSVM) is proposed. Firstly, CEEMD is used to convert the blood glucose concentration sequence into a series of intrinsic mode functions (IMFs) to reduce the impact of randomness and nonstationary signals on prediction performance. Then, a LSSVM prediction model is established for each mode IMF. The comprehensive learning particle swarm optimization (CLPSO) algorithm is used to optimize the kernel parameters of LSSVM. Finally, the prediction results of all IMFs are superimposed to yield the final blood glucose concentration prediction value. The experimental results show that the proposed prediction model has higher prediction accuracy in short-term blood glucose concentration values.

Advanced Wide-Area Monitoring System Design for Electrical Power System

A monitoring system is an essential part of power system operation and planning. This system model is used to observe the system stability behaviour, to detect the unforeseen power system instabilities and to prevent the system from being collapsed. Since the power system scheme is a complex and non-linear system, employing the conventional method based on a mathematical model for designing a monitoring system is quite complicated. This paper proposes an advanced wide-area monitor design using a machine learning method called a multi-output least-square support vector machine to overcome the problem above. The application of the kernel approach in a multi-output least-square support vector machine provides higher accuracy in predicting result and flexibility. The kernel technique will transform the input data into a higher dimensional feature subspace as an input data of a multi-output least-square support vector machine. Then this non-linear pattern will be transformed into a linear pattern and intensive computing time can also be reduced. The major problem of multi-output least-square support vector machine parameters is on finding the best parameter. If the trial and error method is used to find the parameter of multi-output least-square support vector machine parameters, the machine is ineffective in obtaining good performance for a wide range of operating conditions and various load change scenarios in a multi-area power system. A quantum-inspired evolutionary algorithm is employed to achieve the machine’s appropriate parameters automatically and accurate output by minimizing the objective function. In order to measure the rigorousness of multi-output least-square support vector machine output, mean square error is used as an objective function in this study. The simulation results show that the amalgamation of the multi-output least-square support vector machine and quantum-inspired evolutionary algorithm provides a satisfactory result when compared to standard multi-output least-square support vector machine output. In addition, this proposed method can be considered as a promising technique in the future as a wide-area monitor model.

Long-term load forecasting using grey wolf optimizer -least-squares support vector machine

<p><span lang="EN-US">Long term load forecasting data is important for grid expansion and power system operation. Besides, it also important to ensure the generation capacity meet electricity demand at all times. In this paper, Least-Square Support Vector Machine (LSSVM) is used to predict the long-term load demand. Four inputs are considered which are peak load demand, ambient temperature, humidity and wind speed. Total load demand is set as the output of prediction in LSSVM. In order to improve the accuracy of the LSSVM, Grey Wolf Optimizer (GWO) is hybridized to obtain the optimal parameters of LSSVM namely GWO-LSSVM. Mean Absolute Percentage Error (MAPE) is used as the quantify measurement of the prediction model. The objective of the optimization is to minimize the value of MAPE. The performance of GWO-LSSVM is compared with other methods such as LSSVM and Ant Lion Optimizer – Least-Square Support Vector Machine (ALO-LSSVM). From the results obtained, it can be concluded that GWO-LSSVM provide lower MAPE value which is 0.13% as compared to other methods.</span></p>

A New Reliability Rock Mass Classification Method Based on Least Squares Support Vector Machine Optimized by Bacterial Foraging Optimization Algorithm

Classification of the surrounding rock is the basis of tunnel design and construction. However, conventional classification methods do not allow dynamic tunnel construction adjustments because they are time-consuming and do not consider the randomness of rock mass. This paper presents a new reliability rock mass classification method based on a least squares support vector machine (LSSVM) optimized by a bacterial foraging optimization algorithm (BFOA). The LSSVM is adopted to express the implicit relationship between classification indicators and rock mass grades, which is a response surface function for reliability evaluation. LSSVM parameters were optimized by the BFOA to form a hybrid BFOA-LSSVM algorithm. Using geological prediction and rock strength resilience results as classification indicators, samples were developed to train the LSSVM model using the hybrid algorithm. The Monte Carlo sampling method of reliability classification was implemented and applied to the Suqiao tunnel at the Puyan highway in the Fujian province of China; the influence of parameters on the performance of the algorithm is discussed. The results indicate that the new method is feasible for tunnel engineering; it can improve the classification accuracy of surrounding rock exhibiting randomness, to provide an effective means of classifying surrounding rock in the dynamic design of tunnel construction.

A Non-linear Model Predictive Control Based on Grey-Wolf Optimization Using Least-Square Support Vector Machine for Product Concentration Control in L-Lysine Fermentation.

l-Lysine is produced by a complex non-linear fermentation process. A non-linear model predictive control (NMPC) scheme is proposed to control product concentration in real time for enhancing production. However, product concentration cannot be directly measured in real time. Least-square support vector machine (LSSVM) is used to predict product concentration in real time. Grey-Wolf Optimization (GWO) algorithm is used to optimize the key model parameters (penalty factor and kernel width) of LSSVM for increasing its prediction accuracy (GWO-LSSVM). The proposed optimal prediction model is used as a process model in the non-linear model predictive control to predict product concentration. GWO is also used to solve the non-convex optimization problem in non-linear model predictive control (GWO-NMPC) for calculating optimal future inputs. The proposed GWO-based prediction model (GWO-LSSVM) and non-linear model predictive control (GWO-NMPC) are compared with the Particle Swarm Optimization (PSO)-based prediction model (PSO-LSSVM) and non-linear model predictive control (PSO-NMPC) to validate their effectiveness. The comparative results show that the prediction accuracy, adaptability, real-time tracking ability, overall error and control precision of GWO-based predictive control is better compared to PSO-based predictive control.

Adaptive Hybrid Soft-Sensor Model of Grinding Process Based on Regularized Extreme Learning Machine and Least Squares Support Vector Machine Optimized by Golden Sine Harris Hawk Optimization Algorithm

Soft-sensor technology plays a vital role in tracking and monitoring the key production indicators of the grinding and classifying process. Least squares support vector machine (LSSVM), as a soft-sensor model with strong generalization ability, can be used to predict key production indicators in complex grinding processes. The traditional crossvalidation method cannot obtain the ideal structure parameters of LSSVM. In order to improve the prediction accuracy of LSSVM, a golden sine Harris Hawk optimization (GSHHO) algorithm was proposed to optimize the structure parameters of LSSVM models with linear kernel, sigmoid kernel, polynomial kernel, and radial basis kernel, and the influences of GSHHO algorithm on the prediction accuracy under these LSSVM models were studied. In order to deal with the problem that the prediction accuracy of the model decreases due to changes of industrial status, this paper adopts moving window (MW) strategy to adaptively revise the LSSVM (MW-LSSVM), which greatly improves the prediction accuracy of the LSSVM. The prediction accuracy of the regularized extreme learning machine with MW strategy (MW-RELM) is higher than that of MW-LSSVM at some moments. Based on the training errors of LSSVM and RELM within the window, this paper proposes an adaptive hybrid soft-sensing model that switches between LSSVM and RELM. Compared with the previous MW-LSSVM, MW-neural network trained with extended Kalman filter(MW-KNN), and MW-RELM, the prediction accuracy of the hybrid model is further improved. Simulation results show that the proposed hybrid adaptive soft-sensor model has good generalization ability and prediction accuracy.

Study on evolution methods for the optimization of machine learning models based on FT-NIR spectroscopy

Least square support vector machine (LSSVM) is a prevalent machine learning method for near infrared calibration. The chemometric models were established by LSSVM for Fourier transform near infrared (FT-NIR) spectral analysis to determine the content of berberine in Coptidis Rhizoma samples. In order to improve the model prediction ability, LSSVM parameters need to be optimized by using some evolution methods. In this paper, genetic algorithm (GA) and differential evolution (DE) were applied for searching the optimal LSSVM parameters. In comparison with grid search, the GA- and DE-optimized models were validated to have appreciate enhancement for the FT-NIR calibrations. The model performance was systematically assessed by the correlation coefficient of test (RT), the root mean square error of test (RMSET), and the relative standard deviation of test (RSDT). For the GA-optimized LSSVM model, the RT, RMSET and RSDT were obtained as 0.900, 0.218 (%) and 9.112, respectively; while for the DE-optimized model, they were observed as 0.904, 0.215 (%) and 8.859, respectively. These results are more preferable than those of the grid searched LSSVM model. Furthermore, the experiments show that DE has fast convergence speed for parameter optimization. Thus we concluded that the evolutional methods (GA and DE) are feasible to optimize the LSSVM parameters in FT-NIR prediction on berberine content. It is expected that GA and DE can be utilized for model improvement in other near infrared applications.

Rotor Displacement Self-Sensing Modeling of Six-Pole Radial Hybrid Magnetic Bearing Using Improved Particle Swarm Optimization Support Vector Machine

An inverter-fed six-pole radial hybrid magnetic bearing (HMB) has the characteristics of compact structure, high support speed, long service life, and so on. However, using displacement sensors to detect rotor displacements leads to the problems of large volume, high cost, and low reliability. In this article, a self-sensing method using improved particle swarm optimization (IPSO) least square support vector machine (LS-SVM) is proposed, which eliminates the influences of displacement sensors fundamentally. The structure and working principle of six-pole radial HMB are introduced, and the mathematical model of its radial suspension force is deduced according to the equivalent magnetic circuit method. Based on the regression principle of the LS-SVM, the prediction model between the currents in control coils and the rotor displacements is established. Also, the performance parameters of LS-SVM are optimized by the IPSO algorithm, which realizes self-sensing modeling of rotor displacement. The simulation system for self-sensing modeling of rotor displacement for six-pole radial HMB is constructed, and floating experiment, static suspension experiment, dynamic suspension experiment, and disturbance experiment of the rotor are carried out, which verify the robustness and stability of the self-sensing method proposed.