An advanced method of modeling radio-frequency (RF) devices based on a deep learning technique is proposed for accurate prediction of S parameters. The S parameters of RF devices calculated by full-wave electromagnetic solvers along with the metallic geometry of the structure, permittivity and thickness of the dielectric layers of the RF devices are used partly as the training and partly as testing data for the deep learning structure. To implement the training procedure efficiently, a novel selection method of training data considering critical points is introduced. In order to rapidly and accurately map the geometrical parameters of the RF devices to the S parameters, deep neural networks are used to establish the multiple non-linear transforms. The hidden-layers of the neural networks are adaptively chosen based on the frequency response of the RF devices to guarantee the accuracy of generated model. The Adam optimization algorithm is utilized for the acceleration of training. With the established deep learning model of a parameterized device, the S parameters can efficiently be obtained when the device geometrical parameters change. Comparing with the traditional modeling method that uses shallow neural networks, the proposed method can achieve better accuracy, especially when the training data are non-uniform. Three RF devices, including a rectangular inductor, an interdigital capacitor, and two coupled transmission lines, are used for building and verifying the deep neural network. It is shown that the deep neural network has good robustness and excellent generalization ability. Even for very wide frequency band (0–100 GHz), the maximum relative error of the coupled transmission lines using the proposed method is below 3%.

One major difficulty of parameter extraction for an equivalent circuit lies in applying an optimization algorithm to efficiently approach the global minimum. Traditional genetic algorithm (GA) is able to find the global minimum but it has very low convergence rate. On the other hand, direct search method may be easily trapped in local minima. In this work, an improved parameter extraction method which is capable of effectively performing the global minimum search is proposed. This method combines GA and Powell’s method to efficiently determine circuit elements of an equivalent circuit model. A spiral inductor and an interdigital capacitor are used as design examples to illustrate the extraction procedure and validate the proposed hybrid method.

In the transmission and distribution of energy, circuit breaker plays a very important role. In order to fulfill the current market/user demands, they must be capable of promptly identifying the problem and isolating the problematic areas. According to the extinguishing medium used, circuit breakers are divided into the following categories: air blast, SF6, vacuum, and oil. Among others, permanent magnet (PM) based vacuum circuit breaker is also gaining popularity with each passing day and has become a crucial control and protection equipment in the modern power systems. This study proposes the pulse width modulation (PWM) intelligent control strategy for PM vacuum circuit breaker closing/opening capacitance, group charging, and movement process. For the practical implementation of this idea, dual CPUs are utilized for PM vacuum circuit breaker intelligent control components, by taking STM32F103RBT6 as the core and combining peripheral hardware circuit. PWM pulse output drives IGBT to fulfill the closing/opening capacitance group intelligent charging. On the other hand, PM circuit breaker closing/opening motion displacement signals and coil current feedback achieve closed-loop for PWM intelligent control. The experimental results show that the proposed intelligent control component and PWM intelligent control strategy effectively improve the PM circuit breaker intelligent charging and motion dynamic characteristics.