A Hybrid Model for Hydroturbine Generating Unit Trend Analysis

This paper addresses processing of spectrophotometric array signals based on genetic algorithms (GA) least square support vector machines (LS-SVM) regression to provide a powerful model for machine learning and data mining. The key to complete LS-SVM regression is to choose its optimal parameters. Due to their outstanding ability in solving global optimization problems in complex multidimensional search space, GA are used in this study to obtain the optimal parameter combination of the LS-SVM model. Experimental results showed the GA-LS-SVM method to be successful for simultaneous multicomponent determination even where severe overlap of spectra was present. KeywordsLeast squares support vector machines; Genetic algorithms; Spectrophotometric array signals; Overlapping spectra; Artificial intelligence Nowadays, with the application of photometric diode array detector and computers, rapid scanning commercial spectrophotometers are capable of quickly generating huge data consisting of hundreds and even thousands of absorbance values per spectrum. The array data named fullspectrum contain sufficient information to be able to determine the contents of various compounds. The main drawback of ultraviolet-visible (UV-VIS) is its poor selectivity because in many cases UV-VIS spectra display strong overlaps, especially some less specific and selective chromagenic reagents often give rise to strongly overlapped spectra in many cases. The combination of artificial intelligence methods with the computer-controlled spectrophotometers was proven to be effective in overcoming this difficulty [1-3]. Artificial neural network (ANN) is a form of artificial intelligence that mathematically simulates biological nervous system [4, 5]. However, ANN often has slow convergence, is prone to the existence of many local minima during training, and has a tendency of overfitting. Recently, a promising technology called support vector machines (SVM) has been used for classification and regression problems. SVM pioneered by Vapnik is a kind of machine learning method based on modern statistical learning theory and has notable properties including absence of local minima and high generalization ability [6, 7]. Suykens and his coworkers [8] introduced a modified version of SVM called least square SVM (LS-SVM) , which requires solving a set of linear equations instead of a quadratic programming problem and is much easier and computationally simpler than SVM. SVM and LS-SVM represent relatively recent artificial intelligence method and have found some applications in image analysis, classification and disease diagnosis etc. [9, 10]. It is worth mentioning that the success of LS-SVM model is highly dependent on the optimum choice of two parameters, the relative weight of regression error γ and the kernel width σ of radial basis function (RBF). Genetic algorithms (GA) [11, 12] introduced by John Holland are probabilistic optimization techniques based on natural evolution and genetics and Darwin’s theory of survival of the best. With their efficient and robust global search ability, GA are used to search two optimal parameters for the LS-SVM model simultaneously and automatically. The LS-SVM model then performs the regression task using these optimal parameters.

Improving the accuracy and speed has become a main concern of time-series prediction. Aiming at these problems existing in time-series prediction, three kinds of researches and improvements are made as follows. This paper proposes a prediction method of combining Empirical Mode Decomposition (EMD) with least squares support vector machines (LS-SVM), the experimental results show that under the same conditions, the testing error of EMD combining with LS-SVM method is 0.1943 which significantly better than any single method of LS-SVM or SVM or BP neural network (BPNN), thus it is better for non-stationary time series. The immune clonal memetic algorithm (ICMA) is employed for resolving the parameter optimization problem in LS-SVM model, by combining global optimization with local optimization, the experiments show that the testing error of this method is 0.0865, which is faster than the optimization with the genetic algorithm (GA) or grid search algorithm. To raise the prediction speed, an improved LS-SVM online prediction method is proposed, which combine selective pruning algorithm with fast incremental learning, the results of experiment show that the speed of this method is improved nearly double compared with the direct inverse LS-SVM's, and a quarter is raised than the recursive inversion LS-SVM, with higher real-time performance while ensuring the reasonable prediction accuracy.

The present investigation introduces a robust soft computing model by comparing twelve least square support vector machine (LSSVM), six long short-term memory (LSTM), and thirty-six artificial neural network (ANN) models to predict the unconfined compressive strength (UCS) of fine-grained soil. For that purpose, a database of fine content, dry unit weight, porosity, void ratio, degree of saturation, and specific gravity results of 85 soil specimens has been compiled from the literature. 75 and 10 soil specimens were trained and tested for each model. Six training databases have been prepared to analyze the effect of quality and quantity of training database by selecting 50%, 60%, 70%, 80%, 90%, and 100% of 75 soil specimens. The performance comparison demonstrated that the LSTM model (MD 113) requires fewer training datasets (50% of 75) than the LSSVM (MD 102 and MD 108) and ANN (MD 120, MD 127, MD 136, MD139, MD 148, and MD 150) models. Also, it was observed that the nonlinear LSSVM model (MD 108) is unaffected by multicollinearity in training datasets and predicted UCS better than the linear LSSVM model (MD 102). Furthermore, the Levenberg-Marquardt neural network model (MD 120) has outperformed the other ANN models with the root mean square error (RMSE) of 5.1214 N/cm2, the mean absolute error (MAE) of 4.1379 N/cm2, and correlation (R) of 0.9836. The overall performance comparison revealed that the LSTM model is more potent than the LSSVM and ANN models. The LSTM model predicted the UCS of fine-grained soil with the RMSE of 4.7539 N/cm2, the MAE of 4.2461 N/cm2, and R of 0.9880. Conversely, cosine amplitude sensitivity analysis demonstrated that the fine content and dry unit weight influence the prediction of virgin UCS of fine-grained soils.

Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution

The objective of this paper was to determine soluble solids content (SSC) of intact Gannan navel orange by a portable near-infrared (NIR) spectrometer with the optical fiber in the wavelength range of 551~950nm. The effective wavelength regions (EWs) were chosen from the spectra pro-processed by second derivative by interval partial least square (iPLS) and backward interval partial least square (Bipls). Then the partial least square (PLS) and least square support vector machine (LS-SVM) models were developed with EWs. 60 unknown samples were used to evaluate the performance of them. The LS-SVM model was better than others with EWs chosen by Bilps. The correlation coefficient (R) and root mean square error of prediction (RMSEP) for LS-SVM (Bipls) were 0.86 and 0.55°Brix. The results showed that the portable NIR combination with LS-SVM was a feasible method to determine SSC of intact Gannan navel orange nondestructively.

Utilization of SVM, LSSVM and GP for Predicting the Medical Waste Generation

The prediction of wastes generated in the hospital will help their management for several activities like storage, transport and disposing. This chapter adopts Support Vector Machine (SVM), Least Square Support Vector Machine (LSSVM) and Genetic Programming (GP) in order to estimate the rate of medical waste generation. In the event of predicting the rate, type of hospital, capacity and bed occupancy has been used as inputs of SVM, LSSVM and GP. SVM is based on statistical learning theory, which provides an elegant tool for nonlinear system modeling. LSSVM is the re-formulation to the general SVM. GP, a best part of evolutionary algorithm and also the specification of Genetic Algorithm (GA). These SVM, LSSVM and GP have been used as the regression techniques. The results show the performance of the developed SVM, LSSVM and GP models were elegant and outstanding.

The prediction of wastes generated in the hospital will help their management for several activities like storage, transport and disposing. This chapter adopts Support Vector Machine (SVM), Least Square Support Vector Machine (LSSVM) and Genetic Programming (GP) in order to estimate the rate of medical waste generation. In the event of predicting the rate, type of hospital, capacity and bed occupancy has been used as inputs of SVM, LSSVM and GP. SVM is based on statistical learning theory, which provides an elegant tool for nonlinear system modeling. LSSVM is the re-formulation to the general SVM. GP, a best part of evolutionary algorithm and also the specification of Genetic Algorithm (GA). These SVM, LSSVM and GP have been used as the regression techniques. The results show the performance of the developed SVM, LSSVM and GP models were elegant and outstanding.

In nuclear power plant's peripheral environmental radiation monitoring wireless sensor network, the γ dose rate data collected in sensor node may be missed due to various factors, which will influence the validity of environmental radiation monitoring. To solve the problem, a missing data imputation algorithm based on least squares support vector machine(LSSVM) is proposed and particle swarm optimization is adopted to search the optimal set of the LSSVM model parameters. This LSSVM model imputes missing data utilizing node's previous monitoring data and neighbor node's current monitoring data jointly. The experimental results using the real radiation monitoring data around a nuclear power plant demonstrate that the proposed algorithm can achieve higher imputation accuracy than neural network model as well as direct LSSVM model, which has the non-optimized parameters.

This article adopts three soft computing techniques including support vector machine (SVM), least square support vector machine (LSSVM) and relevance vector machine (RVM) for prediction of status of epimetemorphic rock slope. The input variables of SVM, LSSVM and RVM are bulk density, height, inclination, cohesion and internal friction angle. There are 53 datasets which have been used to develop the SVM, LSSVM and RVM models. The developed SVM, LSSVM and RVM give equations for prediction of status of epimetemorphic rock slope. The performance of SVM, LSSVM and RVM is 100%. A comparative study has been presented between the developed SVM, LSSVM and RVM. The results confirm that the developed SVM, LSSVM and RVM are effective tools for prediction of status of epimetemorphic rock slope.

In this paper, based on the Discrete Wavelet Transform (DWT) and Least Square Support Vector Machine (LSSVM), the torque observer for hybrid electric vehicles (HEV) is established. Data from the benchmarking test is employed as the training sample, and the DWT-LSSVM based multi-layer observer was trained to observe the torque distribution results of hybrid electric vehicles. The DWT -LSSVM based multi-layer observer can accurately offer the control results of the original vehicle and solve the problem that it is difficult to reproduce the control results of the original vehicle completely. The main work is as follows: first, a multi-layer observation model based on DWT-LSSVM is established. Multiple LSSVM modules are used to observe the input signals with different frequency that are decomposed by wavelet method, and wavelet reconstruction method is used to integrate the observation results of different input signals to obtain the final observation result of vehicle torque distribution. Secondly, the cross-validation method is used to optimize the parameters in LSSVM model to ensure the accuracy of model prediction. Thirdly, taking the test data of a four-wheel drive hybrid electric vehicle (4WD-HEV)as an example, the observation model proposed in this paper is compared with the simply LSSVM observation model. The results show that the observation results of the torque observation model based on DWT-LSSVM are better than those by the simply LSSVM observation model. The compare results justify the proposed method can improve the accuracy of torque observation.

Wind speed is an important data in the research of the output power in wind farm, but the measured wind speed data have the problem of missing data, meanwhile, the wind speed data also have the characteristics of nonlinearity. Least squares support vector machines (LSSVM) model has strong ability of nonlinear fitting, so LSSVM model is used as the model of interpolating missing wind speed data in this paper, and optimal interpolation model of missing wind speed data is established by using comprehensive learning particle swarm optimization (CLPSO) that has good global search ability to optimize hyper-parameters of LSSVM model. The simulation results indicate: the precision of interpolating tested data by optimized LSSVM model is better, the results of interpolating missing wind speed data fit with the variation of wind speed data at adjacent level, the effectiveness of the interpolation model is verified.

IRIS flower data is a class of multi variable data set, which is widely applied in data classification. This paper aims at the parameter optimization problem of least squares support vector machine (LS-SVM) in data classification, an improved particle swarm optimization(IMPSO) algorithm is introduced into the LS-SVM model for improving the learning performance and generalization ability of LS-SVM model. A new data classification method based on IMPSO algorithm and LS-SVM (IMPSO-LS-SVM) model is proposed. First, the numbers of current iteration and population are added into the control strategy of adaptive adjustment inertia weight in order to improve the performance of inertia weight of PSO algorithm. Then the IMPSO algorithm is used to search the optimal combination values of the parameters of kernel function for obtaining the IMPSO-LS-SVM. Finally, the training samples are used to comprehensively train the IMPSO-LS-SVM, and the best large-scale data classification model is constructed. The IRIS flower data is used to validate the effectiveness of the IMPSO-LS-SVM model. The result indicates that the IMPSO algorithm can effectively search the optimal combination values of the parameters, and the proposed data classification model has better generalization performance, faster training speed and higher classification precision.

This article investigates the feasibility of multivariate adaptive regression spline (MARS) and least squares support vector machine (LSSVM) for the prediction of over consolidation ratio (OCR) of clay deposits based on Piezocone Penetration Tests (PCPT) data. MARS uses piece-wise linear segments to describe the non-linear relationships between input and output variables. LSSVM is firmly based on the theory of statistical learning, and uses regression technique. The input parameters of the models are corrected cone resistance (q t ), vertical total stress (σv), hydrostatic pore pressure (u 0), pore pressure at the cone tip (u 1), and the pore pressure just above the cone base (u 2). The developed LSSVM model gives error bar of predicted OCR. Equations have also been developed for prediction of OCR. The performance of MARS and LSSVM models has been compared with the traditional methods for OCR prediction. As the results reveal, the proposed MARS and LSSVM models are robust models for determination of OCR.

In the process of long-term storage, the equipment would happen storage environment contaminated corrosion, mechanical structure stress corrosion damage. Currently,the corrosion fatigue damage prediction accuracy of method was low. Different kernel functions were adopted by this paper to compare based on least squares support vector machine (LSSVM). Besides, comparison was made among the BP neural network method, Standard Support Vector Machines (SVM), Grey System Prediction model Method and the radial basis function kernel least squares support vector machine (RBF_LSSVM) method by the simulation experiment. The optimal results finally were applied to practical engineering. The results showed that high accuracy and performance could be gained by employing the RBF_LSSVM method for predicting the trends of the mechanical structure rivet corrosion.