Zhibin Qiu

A prediction method for breakdown voltage of typical air gaps based on electric field features and support vector machine

Breakdown voltage of the air gap is of vital importance for the design of the external insulation in high-voltage transmission and transformation projects. In this paper, a new prediction method for the breakdown voltages of typical air gaps based on the electric field features and support vector machine (SVM) was proposed. According to the finite element calculation results of static electric field distribution, the electric field values in the whole region, discharge channel, surface of the electrode and the shortest path were extracted and post-processed, which constituted the electric field features characterizing the gap structure. Then, the breakdown voltage prediction model of the air gap was established by using electric field features as the input parameters to SVM, and whether the gap breakdown would happen as the output parameters of SVM, which changing the regression problem to a binary classification problem. This model was applied to predict the power frequency breakdown voltages of different short air gaps including sphere-sphere gaps, rod-plane gaps, sphere-plane gaps and sphereplane- sphere gaps. The power frequency breakdown voltages of longer air gaps which are affected by corona, and the 50% positive switching impulse breakdown voltages of long sphere-plane gaps and rod-plane gaps were predicted as well. The predicted results agree well with experimental values and simulated results of the published models, which validate the effectiveness of the proposed model. This method supplies a new possible way to obtain the breakdown voltage of air gaps.

Hybrid prediction of the power frequency breakdown voltage of short air gaps based on orthogonal design and support vector machine

This paper attempts to establish the grey correlation between the breakdown voltage of air gap and its energy storage status before discharge inception. A new method is presented for the breakdown voltage prediction of short air gaps. This method is based on an orthogonal design array and support vector machine (SVM). A hybrid model is established to predict the power frequency breakdown voltage of three typical air gaps including sphere-sphere, rod-plane, and rod-rod gaps. The input data are fifty parameters extracted from the static electric field distribution of the air gap, and the output of the model is whether the gap will breakdown under a given voltage. This model is trained by 9 samples selected by L9(33) orthogonal array and applied to predict the breakdown voltage of 90 test samples. With effective feature dimension reduction and parameter optimization of the SVM model, the predicted results coincide well with the experimental data, and the mean absolute percentage error (MAPE) is only 3.9%. The SVM model is also applied to predict the breakdown voltage of some atypical short air gaps including sphere-plane gaps, rod-sphere gaps, sphere-sphere gaps with different diameters, and rod-plane-sphere gaps. The MAPEs are respectively 4.3, 3.2, 4.2, and 6.4%, which verifies the validity and generalization performance of the proposed method. This model provides a new way to gain the critical breakdown voltage of air gaps, and therefore contributes to reducing the required test work.

Energy storage features and a predictive model for switching impulse flashover voltages of long air gaps

It has been a long sought goal to determine the critical flashover voltages of long air gaps by mathematical calculations instead of experiments. In this paper, a predictive model is proposed for 50% discharge voltage (U50) prediction of long air gaps subjected to switching impulses. This model is developed on the basis of the physical thought that air breakdown can be viewed as out-of-limit of the capacitive energy stored in the electric field. Two groups of features are defined to characterize the energy storage status of an air gap, from the perspective of electric field distribution and impulse voltage waveform, respectively representing the space distribution and time accumulation of the energy. The predictive model is established by support vector machine (SVM), and the input data are the energy storage features. Giving an estimated applied voltage range, the predicted result of the critical flashover voltage is searched by the golden section method. Trained by 6 known experimental data, this model is used to predict the U50 of rod-plane, rod-rod and rod-conductor long air gaps subjected to negative switching impulse voltages. The mean absolute percentage errors of 5 groups of test samples are respectively 6.0%, 5.8%, 6.3%, 3.2% and 1.7%, which are in an acceptable range in the view of engineering applications. The proposed method might be useful to predict the U50 of long air gaps with various geometries and under different voltage waveshapes, therefore reducing the required test work for insulation design of high voltage equipments.

A method for breakdown voltage prediction of short air gaps with atypical electrodes

The most determinant factor for the dielectric strength of an air gap is the inhomogeneity of the electric field. This paper attempts to establish the internal relation between the electric field distributions of air gaps with different electrode geometries, and so as to predict the breakdown voltage of the air gap with atypical electrodes. A classification model is established based on support vector machine (SVM), which considers that the breakdown or withstand of an air gap under an applied voltage can be viewed as 1 or -1. 28 features are defined and applied to characterize the electric field distribution of an inter-electrode air gap. Taking these features as input parameters of the SVM model, the grey correlation between the air gap breakdown voltage and its electric field distribution can be trained by some training samples, which are selected from typical air gaps like sphere-sphere and rodplane gaps according to the electric field distribution similarity along the shortest discharge path. The SVM model is applied to predict the breakdown voltages of atypical air gaps including the serial gaps, the ring gaps and the stranded conductor gaps. The predicted results are in good agreement with the experimental data, and the mean absolute percentage errors of these gap arrangements are within 5.4%. This method provides an alternative for the breakdown voltage prediction of air gaps with complex geometries, and therefore helps minimizing the required test work.

Corona onset and breakdown voltage prediction of rod-plane air gaps based on SVM algorithm

Corona onset voltage and breakdown voltage of the air gap are the basis for the external insulation design of high-voltage transmission projects. A new prediction method for the discharge voltage of rod-plane air gaps is proposed in this paper. Support vector machine (SVM) is applied to establish the prediction model, and the improved grid search (GS) method is used for parameter optimization. The features extracted from the electric field distribution calculated by finite element model of the rod-plane air gap are taken as the input parameters to the SVM model, and whether corona will onset, or the gap will breakdown under a given voltage is taken as the output of the SVM model. Trained by the electric field features under several limited experimental values, the SVM model is effective to predict the corona onset or breakdown voltage. The proposed method is applied to predict the positive DC corona onset voltage and power frequency AC breakdown voltage of rod-plane air gaps. The predicted results are in accordance with the experimental values with small deviation, which preliminary validate the feasibility of predicting the discharge voltage of the air gap by machine learning algorithms.

Study on glaze electrical erosion characteristics of porcelain post insulator by using inclined plane and graphite-layer-based method

In order to study the effect of glaze erosion on the performance of porcelain post insulator, an inclined plane (IP) test similar to IEC 60587 standard was conducted on a cylindrical insulator sample under laboratory conditions for ac voltage, and a new test method, called graphite-layer-based glaze erosion test was proposed in this paper and performed on the sheds of a 40.5 kV post insulator. The experimental details of the graphite-layer-based glaze erosion test was introduced, the technical points of which are coating a graphite layer on the surface of the shed using a brush mold which contains multiple hollowed-out rhombic grids, and arranging high voltage electrode at shed root and grounded electrode at shed edge respectively at both ends of the graphite layer, so as to form continuous and stable surface arcing under ac voltage and therefore achieve desired glaze electrical erosion effect. The graphite layer is a uniform viscous mixture made up with flake graphite and liquid glue according to a quality ratio of 1:1.2. The arcing process, arc current characteristics, surface temperature, and glaze erosion appearance were analyzed. Leakage current under power frequency voltage and flashover voltage of the eroded cylindrical insulator by IP test were measured, while porosity test and scanning electron microscopy (SEM) tests were conducted on samples taken from the sheds after graphite-layer-based glaze erosion test. The results indicate that glaze erosion will decrease both electrical and mechanical performance of the porcelain post insulator. The new test method proposed in this paper has been proved to be effective for glaze erosion test and consumes much less time compared with IP test, which provides a new idea for accelerated tracking and erosion test of glaze and porcelain materials so as to study the aging characteristics of porcelain insulators.

Static voltage distribution of 126 kV modular multi-break vacuum circuit breaker prototype

In order to analyze the potential distributions of U-shaped arrangement 126 kV triple-break vacuum circuit breaker prototype, formed with fiber-controlled vacuum circuit breaker modules, and electric field distributions interior vacuum interrupters, three dimensional finite element models were established. The potential distributions and the electric field distributions interior vacuum interrupters of four models, including single pole prototype without supporting structure, single pole prototype with supporting structure, double poles prototype with supporting structure, three phases double poles prototype with supporting structure were analyzed with the established finite element models. The calculated results indicate that, under U-shaped arrangement, the static voltage distributions of the triple-break vacuum circuit breaker are non-uniform. The static voltage distribution of the high voltage break is more than 65%, and suitable voltage grading measures are needed. The supporting structure can be not installed in the circuit breaker in series prototype test.

Breakdown voltage calculation of sphere-planesphere air gap in slightly uneven electric field

The breakdown voltage of typical electrode structures is important for the design of external insulation, but little attention is paid to the analysis of floating metals, which is common in high voltage transmission and transformation projects. Thus, photoionization criterion was adopted in this paper to calculate the breakdown voltage of sphere-plane-sphere air gap in slightly uneven electric field with the consideration of floating metals, and the power-frequency withstand voltage tests were carried out for the comparison. The results indicate that the calculation results agreed well with the test ones, where the mean absolute percentage errors are less than 3%. The study verifies the validity and generalization values of photoionization criterion within a certain range, and contributes to explaining the discharge mechanism of complex air gap in slightly uneven electric field.

Breakdown voltage prediction of rod-plane gap in rain condition based on support vector machine

Air gap breakdown is the result of the synthetic effect of electric field distribution and atmospheric environment. The breakdown voltage prediction model of rod-plane air gaps under rain conditions was established by support vector machine (SVM). The electric field features and atmospheric parameters were taken as the input of the prediction model. Based on the idea of binary classification, the withstanding or breakdown of an air gap under applied voltage was characterized by −1 and 1, which was taken as the output of the prediction model. 9 training samples were selected based on the idea of orthogonal design, and the power frequency breakdown voltages of other 29 test samples were predicted by the proposed model. The predicted results coincide well with the experimental values, and the average error of the 29 test samples is only 0.74%. The influence rules of the atmospheric parameters on breakdown voltage obtained by analysing the predicted results are almost the same with those obtained by experiments, which validates the accuracy and rationality of the proposed method. The research results can provide reference for breakdown voltage prediction and discharge characteristic study of air gaps in complex atmospheric environment.

Breakdown voltage prediction of SF6 gaps based on electric field features and SVM algorithm

The breakdown voltages of SF6 gaps in uniform field and non-uniform field are predicted by a new method based on the electric field features and support vector machine (SVM). The finite element method (FEM) is used to calculate the electric field distribution of the SF6 gap. The parameters including the electric field strength, electric field energy, energy density, electric field gradient and scale parameters are used to characterize the electric field distribution of SF6 gaps. The breakdown voltage prediction model is established by SVM, the electric field features and the gas pressure are taken as the input to the SVM model. The output is whether the gap will breakdown under a given applied voltage and a certain gas pressure. Several experimental values of breakdown voltage are set as training samples and the corresponding electric field features are applied to train the SVM model. The improved grid search method is used to search optimal parameters including the penalty coefficient and kernel function parameter. The proposed method is applied to predict the breakdown voltages of coaxial cylinder gaps and rod-plane gaps in SF6. The predicted results coincide with the experimental values very well.