Electrostatic Field Feature Selection Technique for Breakdown Voltage Prediction of Sphere Gaps Using Support Vector Regression

Qiu, Zhibin; Zhang, Louxing; Liu, Yan; Liu, Jianben; Hou, Huasheng; Zhu, Xiongjian

doi:10.1109/tmag.2021.3074035

Cited by 8 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, there is an imperious need to generate useful data to design insulation systems for these next generation aircrafts, which can also be useful for high-voltage systems operating at high altitude. This papers aims at generating useful experimental data for this purpose, so this end the sphere-to-plane geometry is analysed because it is a standard air gap in high-voltage applications [19][20][21][22]. To this end, the dependency of the corona extinction voltage (CEV) value on the environmental pressure and operating electrical frequency is studied by means of experimental data.…”

Section: Introductionmentioning

confidence: 99%

Measurement of Corona Discharges under Variable Geometry, Frequency and Pressure Environment

Bas-Calopa

Riba

Moreno-Eguilaz

2022

Sensors

View full text Add to dashboard Cite

Aeronautical industry is evolving towards more electric aircrafts (MEA), which will require much more electrical power compared to conventional models. To satisfy this increasing power demand and stringent weight requirements, distribution voltages must be raised, which jointly with the low-pressure environment and high operating frequencies increase the risk of electrical discharges occurrence. Therefore, it is important to generate data to design insulation systems for these demanding applications. To this end, in this work a sphere-to-plane electrode configuration is tested for several sphere geometries (diameters ranging from 2 mm to 10 mm), frequencies of 50 Hz, 400 Hz and 800 Hz and pressures in the 20–100 kPa range, to cover most aircraft applications. The corona extinction voltage is experimentally determined by using a gas-filled tube solar blind ultraviolet (UV) sensor. In addition, a CMOS imaging sensor is used to locate the discharge points. Next, to gain further insight to the discharge conditions, the electric field strength is calculated using finite element method (FEM) simulations and fitted to equations based on Peek’s law. The results presented in this paper could be especially valuable to design aircraft electrical insulations as well as for high-voltage hardware manufacturers, since the results allow determining the electric field values at which the components can operate free of surface discharges for a wide altitude range.

show abstract

Section: Introductionmentioning

confidence: 99%

Measurement of Corona Discharges under Variable Geometry, Frequency and Pressure Environment

Bas-Calopa

Riba

Moreno-Eguilaz

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, the data-driven models based on artificial intelligence algorithms provide a new possibility to realize dielectric strength prediction, which is an alternative way except for the physical models and empirical formulas. Some artificial intelligence or machine learning algorithms, such as artificial neural networks (ANN) [17][18][19][20], support vector machine (SVM) [21][22][23][24][25], fuzzy logic [26,27], Gaussian process regression (GPR) [28], least squares regression (LSR) [29], and extremely randomized trees [30], etc., have been applied for breakdown voltage prediction of air gaps, transformer oils, and solid dielectrics like insulation paper and nanocomposites. These data-driven models mainly focus on the mathematical correlations between the dielectric strength and various influencing factors, and do not directly consider the discharge evolution process full of randomness and uncertainty, which is not restricted by the complex and unclear physical process.…”

Section: Introductionmentioning

confidence: 99%

“…On this basis, Ding et al [22] conducted U 50 prediction of DC transmission tower gaps by AdaBoost-SVR model, with the inputs of atmospheric parameters, ring diameter and pipe dimeter of grading rings, tower widths, and gap distances. Qiu et al [23][24][25] proposed the idea to characterize gap structure by features extracted from electrostatic field calculation results, and used SVM model to establish the multi-dimensional non-linear relation of these features with air gap breakdown voltage. This idea has been validated by dielectric strength prediction of typical air gaps like rod-plane, rod-rod, sphere-sphere etc., and also applied to U 50 prediction of transmission line-tower gaps preliminarily [31,32], but a more reasonable electric field feature set that be appropriate to these engineering gap configurations is still a challenge that require further studies.…”

Section: Introductionmentioning

confidence: 99%

A machine learning‐based approach for dielectric strength prediction of long air gaps with engineering configurations

Qiu

Zhang

et al. 2022

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

It is a long‐term goal in external insulation studies to determine the discharge voltages of complicated engineering gaps by simulation methods. Based on the one‐to‐one correspondence between air gap structure and the static electric field (EF) distribution, this paper characterizes the transmission tower gap configuration by spatial EF features, which were used for machine learning to achieve switching impulse discharge voltage prediction. An interelectrode path and a conical zone between the energized sub‐conductor and the crossarm or the tower window were considered as EF regions strongly associated with gap breakdown, where 73 parameters were extracted to construct a feature set. Taking 15 extra‐high voltage (EHV) transmission tower gaps as training samples, with different gap distances and tower configurations, their EF features were input to a support vector machine (SVM) for model training to establish the relationships with discharge voltages. The trained SVM model was used to predict the impulse discharge voltages of 20 EHV and ultra‐high voltage (UHV) transmission tower gaps. The prediction results with different feature dimensions and various sizes of conical zones were compared to the experimental values, which demonstrate similar variation trends and acceptable errors. This study contributes to realize insulation strength calculation of engineering gaps.

show abstract

“…An idea to characterize air gap structure by electrostatic field distribution features was proposed in Ref. [12][13][14], and a data association model based on support vector machine (SVM) was constructed to learn the relationship between the electric field features and air gap breakdown voltages. This method offers an alternative way to realize breakdown voltage calculation by data association analysis rather than physical models.…”

Section: Introductionmentioning

confidence: 99%

Sphere Gap Breakdown Voltage Prediction Based on ISSA Optimized BP Neural Network and Effective Electric Field Feature Set

Qiu

Song

2022

IEEJ Transactions Elec Engng

Self Cite

View full text Add to dashboard Cite

Electric field distribution is a determinant factor of air gap breakdown voltage. This paper defined an effective electric field zone between the sphere gaps for feature extraction, and 29 parameters were extracted from this zone to reflect the electric field distribution. A data mining model was established by back propagation neural network (BPNN) for sphere gap breakdown voltage prediction, taking the electric field features as inputs. The maximum information coefficient (MIC) method was used to select features strongly correlated to the breakdown voltage, and a multi‐strategy improved salp swarm algorithm (ISSA) was applied to optimize the BPNN parameters to enhance the prediction performance. The standard sphere gaps provided in IEC 60052 were taken as training set and test set, which were divided according to the electric field nonuniform coefficients. The breakdown voltage prediction results of test sample sphere gaps demonstrate good agreements with the experimental values. With input features selected by the MIC method, the ISSA optimized BPNN model has a mean absolute percentage error of only 0.83% and a maximum relative error of 5.86%. By constructing the nonlinear mapping relationship between the effective electric field features and the insulation strength, this study provides a new approach to predict air gap breakdown voltage. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Electrostatic Field Feature Selection Technique for Breakdown Voltage Prediction of Sphere Gaps Using Support Vector Regression

Cited by 8 publications

References 10 publications

Measurement of Corona Discharges under Variable Geometry, Frequency and Pressure Environment

Measurement of Corona Discharges under Variable Geometry, Frequency and Pressure Environment

A machine learning‐based approach for dielectric strength prediction of long air gaps with engineering configurations

Sphere Gap Breakdown Voltage Prediction Based on ISSA Optimized BP Neural Network and Effective Electric Field Feature Set

Contact Info

Product

Resources

About