Wyniki wyszukiwania - BazTech

1

Prediction of Kaplan turbine coordination tests based on least squares support vector machine with an improved grey wolf optimization algorithm

Kong Fannie, Xia Jiahui, Yang Daliang, Luo Ming

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e137124

EN

The optimum combination of blade angle of the runner and guide vane opening with Kaplan turbine can improve the hydroelectric generating the set operation efficiency and the suppression capability of oscillations. Due to time and cost limitations and the complex operation mechanism of the Kaplan turbine, the coordination test data is insufficient, making it challenging to obtain the whole curves at each head under the optimum coordination operation by field tests. The field test data is employed to propose a least-squares support vector machine (LSSVM)-based prediction model for Kaplan turbine coordination tests. Considering the small sample characteristics of the test data of Kaplan turbine coordination, the LSSVM parameters are optimized by an improved grey wolf optimization (IGWO) algorithm with mixed non-linear factors and static weights. The grey wolf optimization (GWO) algorithm has some deficiencies, such as the linear convergence factor, which inaccurately simulates the actual situation, and updating the position indeterminately reflects the absolute leadership of the leader wolf. The IGWO algorithm is employed to overcome the aforementioned problems. The prediction model is simulated to verify the effectiveness of the proposed IGWO-LSSVM. The results show high accuracy with small samples, a 2.59% relative error in coordination tests, and less than 1.85% relative error in non-coordination tests under different heads.

2

A Novel Approach To Diagnosis Of Analog Circuit Incipient Faults Based On KECA And OAO LSSVM

Zhang C., He Y., Zuo L., Wang J., He W.

Metrology and Measurement Systems

|

2015

|

Vol. 22, nr 2

251--262

EN

Correct incipient identification of an analog circuit fault is conducive to the health of the analog circuit, yet very difficult. In this paper, a novel approach to analog circuit incipient fault identification is presented. Time responses are acquired by sampling outputs of the circuits under test, and then the responses are decomposed by the wavelet transform in order to generate energy features. Afterwards, lower-dimensional features are produced through the kernel entropy component analysis as samples for training and testing a one-against-one least squares support vector machine. Simulations of the incipient fault diagnosis for a Sallen-Key band-pass filter and a two-stage four-op-amp bi-quad low-pass filter demonstrate the diagnosing procedure of the proposed approach, and also reveal that the proposed approach has higher diagnosis accuracy than the referenced methods.

3

Rotor Displacement Estimation for MB Sensorless Control

Zhu Z., Sun Y., Huang Y., Ji X.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 1b

141-145

EN

This paper presents an on-line recursive least squares support vector machine(O-RLS-SVM)-based displacement estimator for magnetic bearings (MBs). The basic premise of the method is that an O-RLS-SVM forms an efficient mapping structure for a nonlinear MB. Through the measurement of phase flux linkages and currents, the O-RLS-SVM is able to estimate the rotor displacement; thereby it facilitates the elimination of the rotor displacement sensor. Simulation results show that the estimator has high estimation precision and favourable operation efficiency.

PL

W artykule przedstawiono system estymacji położenia wirniku w maszynach z poduszką magnetyczną. System nie wymaga czujników – miarą położenia wirnika są przesunięcia fazowe prądu i strumienia magnetycznego.

4

Displacement Self-sensing of Bearingless Switched Reluctance Motors Based on LS-SVM

Zhu Z., Sun Y., Huang Y., Ji X.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 12a

310-313

EN

To achieve the rotor radial displacement self-sensing for a bearingless switched reluctance motor (BSRM), a new displacement estimation method using least squares support vector machine (LS-SVM) was proposed. Firstly, the working principle and mathematic of a 3-phase 12/8 pole BSRM was introduced in brief. Then taking advantage of LS-SVM with better solution for small-sample learning problem and strong generalization ability, two LS-SVMs were trained off-line to obtain two efficient nonlinear mapping structures to express the dynamic behavior of BSRM. The LSSVM training data set is comprised of representative experimental data with current {i | i = (isa1, isa2, ima)} and rotor position θ as inputs and the corresponding displacements {D | D=(α , β )}as outputs. As well as giving a detailed explanation of the new method, simulation and experimental results were presented. It shows that the proposed LS-SVM-based displacement self-sensing method has high precision and operation efficiency.

PL

W artykule przedstawiono uczący się estymator przesunięcia dla bezłożyskowego silnika o przełączanej reluktancji (BSRM), wykorzystujący metodę LS-SVM (ang. Least Square Support Vector Machines). Opisano zasadę działania i model matematyczny silnika BSRM 3- fazowego 12/8 biegunowego. W celu uzyskania efektywnej struktury mapowania nieliniowego do określenia stanów dynamicznych, zastosowano dwa algorytmy, które zostały nauczone offline. Estymator poddano weryfikacji symulacyjnej i eksperymentalnej.