The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper discusses the application of least squares support vector machine (LS-SVM) in image inpainting. The data with strong correlation with the damaged area are selected to train the LS-SVM model, and then predict the damaged parts with the obtained model. In order to make full use of the correlation in the image, this paper employs the additive high order kernel function to improve the prediction...
Wind turbine data preprocessing is a key step in wind turbine equipment condition assessment, and it helps to improve data quality and data utilization. In this paper, a data preprocessing method has been proposed based on the neighbor model of least squares support vector machine, with the wind speed data as an example. There are strong similarities between the operating conditions of wind turbines...
In aerospace engineering, condition monitoring is an important reference for evaluating the performance of complex systems. Especially, effective anomaly detection, based on telemetry data, plays an important role for the system health management of a spacecraft. With the advantages of easy-to-use, high efficiency, and data-driven, the predicted model has been applied for anomalous point detection...
This paper proposes a wind power prediction method based on intrinsic time-scale decomposition (ITD) and least square support vector machine (LS-SVM) to improve the accuracy of wind power forecast. The proposed method employs ITD as a preprocessing method to decompose wind power data into a set of proper rotation components and a monotonous baseline signal. Afterwards, the backward difference of each...
Aiming at the difficult measurement problem of the extraction rate for plants and herbs with the ultrasonic wave technology, the influence of the various factors on the extraction rate in the ultrasonic extraction process is analyzed and the dynamic process variables which is easily measured and can affect the extraction rate is ensured in this paper. A soft sensor model between the easily measured...
The measurement of parameters of the crankshaft runout was implemented online. Then the runout data was processed by adopting the least square method and vector model transformation. The experiment shows that the tested result agrees with the real crankshaft deformation. The classifier for the crankshaft straightening position using LS-SVM was set up. The set classifying system is applied to the crankshaft...
Aiming at the characteristics of big inertia, pure lag, the nonlinear in the cement rotary kiln, A new model has been established using the least squares support vector machine intelligent algorithm. Also, the particle swarm optimization algorithm is introduced to carrying out the model analysis in the large amount of data that collected from the cement plant so as to determine optimal parameters...
In view of the corrosion of cooling water system, the dynamic simulation test was conducted with the cooling water dynamic simulation experiment device. In the test period the corrosion rate and the water quality factors were monitored. Based on the test data, an intelligent prediction model of cooling water corrosion rate based on least squares support vector machine (LS-SVM) is constructed, in which...
Very often important process variables which are concerned with the final product quality cannot be measured by a sensor or the measurements are too expensive and often not reliable. In order to enable continuous monitoring of process variables and efficient process control, soft-sensors are usually used to estimate these difficult-to-measure process variables. Soft-sensor is based upon mathematical...
To achieve the analysis of characteristic and forecasting of the mobile communication traffic, a mobile communication traffic modeling and forecasting method by Least Squares Support Vector Machine(LS-SVM) is proposed. With this method, an on-line forecasting scheme is designed to realize short-time forecasting of the mobile communication traffic. The traffic data is provided by China Mobile Communications...
Multi-layer perceptrons (MLP) have been employed to solve a variety of problems. The practical applications of MLP however suffer from different drawbacks such as local minima and over-fitting, such that good generalization may not be obtained. Least squares support vector machines (LS-SVM), a novel type of machine learning technique based on statistical learning theory, can be used for regression...
The polymerization rate of vinyl acetate is extremely important qualitative index and processing parameter, but it is inconvenient being measured directly and real-timely, therefor, in this paper, soft sensor modeling method based on Least Square SVM(LS-SVM)is proposed and cross validation method is used to select hyper-parameter of LS-SVM model. It is applied to the soft sensor of the vinyl acetate...
With regards to the petrochemical processes with various operating states and dynamic performance which will affect estimation precision for the static soft sensor, a time series soft sensor model which uses the time series of process variables to estimate the dynamic performance of quality variable was proposed. Meanwhile, the integrated Adaboost learning algorithm is introduced. With the help of...
Considering the strong non-linearity and large time delay of purification in zinc hydrometallurgy in purification process, a prediction model of cobalt concentration combining neural network (NN) and grey model (GM) are proposed. In the key part II of the purification, because of the harmful impurities cobalt ion concentration can not be on-line measured, and the testing results is two hours later...
The prediction of chaotic time series is performed by least square support vector machine (LS-SVM) based on particle swarm optimization (PSO). The main objective of this approach is to increase the accuracy of the chaotic time series prediction. For the generation performance of LS-SVM depending on a good setting of its parameters, PSO is adopted to choose the global optimum parameters of LS-SVM automatically...
The generator power have related with the wind turbine torque heavily. The wind speed, the rotor speed, the pitch angle and the inherent parameters of wind turbine can influence the wind turbine torque. Different torque curves in different operation can be simulated by Simulink software of Matlab. However, this method needs wind turbine's parameters which aren't usually obtained to construct the model...
In this paper, a LS-SVM model based RLG's scale factor temperature data modeling method is studied. Using traditional least square linear model to modeling nonlinear ring laser gyro scale factor test data has its intrinsic shortcoming, and sometimes it is difficult to meet the application requirements. Recently, nonlinear function approximation based modeling methods such as the BP networks are introduced...
In this paper, a novel modeling method based on least square support vector machines (LS-SVM) is proposed to deal with the rate-dependent hysteresis system. It is possible to construct a unique dynamic model in a given frequency range for a rate-dependent hysteresis system using the selected compound frequency as the training set of LS-SVM, which guarantees an outstanding generalization ability of...
Using least squares support vector machines (LS-SVM) technology, a new multi-sensor data fusion model for online predication of underwater flux-cored arc welding (FCAW) penetration depth is presented. In this model, welding speed, wire feed rate, arc voltage, contact-tube-to-work distance (CTWD), and weld pool width are used as inputs, while the depth of welding penetration as output. The radial basis...
Based on 66 capacitance values by 12-electrode capacitance sensor, combining Fast Independent Component Analysis (FastICA) with Least Squares Support Vector Machine (LS-SVM) algorithms, a new method for phase concentration measurement of two-phase flow was proposed. FastICA was used to extract the independent components from capacitance values. LS-SVM was used to establish the model for phase concentration...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.