Search

Full-scale discharge tests of transmission line–tower air gaps are costly and time-consuming, and they cannot exhaustively simulate all the gap configurations in practical engineering. In this paper, a machine learning model established by support vector machine is introduced to predict the switching impulse discharge voltages of the ultra-high-voltage (UHV) AC transmission line–tower air gaps. The three-dimensional finite element models of a UHV cup-type tower and a UHV compact transmission line were established for electric field calculation, and some features were extracted from the hypothetic discharge channel and the shortest path between the bundled conductor and the tower. These features under a given voltage were normalised and input to the SVM model, while the output is two binary values, respectively, representing gap withstanding or breakdown. Trained by experimental data of one type of the UHV transmission line–tower gaps, the SVM model is able to predict the discharge voltages of another gap type. The mean absolute percentage errors of the two engineering gap types, under different gap distances, are 8.31 and 4.86%, respectively, which are acceptable for engineering applications. The results provide a possible way to obtain the discharge voltages of complicated engineering gaps by mathematical calculations.

Electrostatic field distribution has a decisive influence on the strength of air insulation. To predict air-gap breakdown voltages according to electric field calculation results, a set of electrostatic field features is defined on the shortest interelectrode path of the rod–plane gap. These features are taken as the input parameters of a machine learning model established by support vector regression (SVR), thus to describe their relationships with the output breakdown voltage. Trained by small-sample data randomly selected according to the distribution ranges of the electric field non-uniform coefficient, the SVR model is applied to predict the breakdown voltages of rod–plane gaps with the rod diameter of 20, 25 and 30 mm, and the gap distance ranging from 1 to 9 cm. The predicted results agree well with the experimental data, while the mean absolute percentage errors of the six predictions are within 2.5%. Furthermore, the Φ27 mm rod–plane gap breakdown voltages are also predicted, and the results fall in the range between those of Φ25 and Φ30 mm rod–plane gaps, which conform to the actual law. The results validate the validity of the electrostatic field features and the generalisation performance of the SVR model.

Discharge voltage prediction of practical air gaps in transmission projects is a long-sought goal and also a great challenge in high-voltage (HV) engineering. An approach combined electric field simulation, feature extraction and machine learning algorithm is presented in this study to predict the switching impulse discharge voltages of extra-HV (EHV) and ultra-HV (UHV) transmission lines-tower air gaps. Some features extracted from the electrostatic field distribution are used to characterise the air-gap configuration and taken as input parameters of a prediction model established by a support vector classifier (SVC). Three kinds of actual gap configurations in EHV and UHV transmission lines are taken as test samples to validate the validity of the SVC model. Trained by experimental data of rod-plane gaps and one of the engineering gap configurations, this model is able to predict the discharge voltages of the other two conductor-tower gaps with acceptable accuracy. The mean absolute percentage errors of the three prediction results are 6.84, 4.19 and 3.46%. This research demonstrates the feasibility of discharge voltage prediction for complicated engineering gaps, which is useful to reduce the costly full-scale tests and helpful to guide the external insulation design.

The electric field calculations cannot effectively guide the insulation design of high voltage equipment since the insulation strengths of dielectrics cannot be predicted according to the electromagnetic analysis. In this paper, some features related to the electric field distribution such as the electric field strength, electric field gradient, path length, and the electric field integral are defined and extracted from finite element calculations of air gaps. The electric field features are taken as the input parameters of a grey correlative model established by support vector machine (SVM), so as to establish the multi-dimensional nonlinear relationships between these features and the discharge voltage of an air gap. The grid search (GS) method was used to search the optimal parameters of the SVM. This model was applied to predict the 50% discharge voltages of large sphere-plane air gaps in UHVDC valve halls. The predicted results were obtained after multiple iterative calculations, using the golden section search method. Compared to experimental data, the relative errors of the predicted results are within an acceptable range in view of engineering applications, which indicates the validity of the proposed method. This paper achieves the discharge voltage of air gaps by numerical computations instead of costly experiments.

The distribution of electric field (EF) has a strong correlation with air insulation strength. In order to obtain air gap breakdown voltage (BV) through simulating calculation instead of experimental measurement, various parameters related to the electrostatic field distribution are used to characterize the sphere gap structure, which are defined on the shortest path between two sphere electrodes. These features of different sphere gaps are extracted from EF simulation results and input to a support vector machine (SVM) model optimized by the grid search algorithm, so as to establish their correlations with the output BVs. The golden section search method is used to predict the BV iteratively. Taking 9 sphere gaps, with the diameter in the range of 15 to 50 cm, as training samples, the SVM model is employed for BV prediction of 107 quasi-uniform sphere gaps with different diameters ranging from 75 to 150 cm and gap distances from 2 to 75 cm. For the predicted results, the average relative error is only 0.97% compared with the test values presented in IEC 60052. The results demonstrate the effectiveness of the EF features and the prediction model. This research offers a reference for air gap BV calculation by numerical approaches.

The hybrid high voltage direct current (HVDC) breaker is a key equipment of the DC grid. The high speed mechanical switch is a key component of the hybrid HVDC breaker and has a number of serially connected switch units. The serially connected units should divide the voltage uniformly. The static voltage distributions and distributed capacitances of a 500 kV hybrid HVDC breaker mechanical switch are studied in this paper. A three dimensional finite element model, considering the actual dimension parameters of six 110 kV high speed mechanical units in serially vertical arrangement, is established to study the static voltage distribution characteristics and capacitance parameters of a 500 kV multi-break high-speed mechanical switch, with six 110 kV high speed mechanical switches in serially vertical arrangement. The calculated results indicate that, under vertical arrangement, from the point of capacitive voltage distribution, the static voltage distributions of the six mechanical switch units are non-uniform, and the high voltage unit is more than 75% of the whole voltage.