Search

Microstrip filters are widely used in high-frequency circuit design for signal frequency selection. However, designing these filters often requires extensive trial and error to achieve the desired performance metrics, leading to significant time costs. In this work, we propose an automated design flow for hairpin filters, a specific type of microstrip filter. We employ artificial neural network (ANN) modeling techniques to predict the circuit performance of hairpin filters, and leverage the efficiency of low-cost models to deploy reinforcement learning agents. Specifically, we use the proximal policy optimization (PPO) reinforcement learning algorithm to learn abstract design actions for the filters, allowing us to achieve automated optimization design. Through simulation results, we demonstrate the effectiveness of the proposed approach. By optimizing the geometric dimensions, we significantly improve the performance metrics of hairpin filters, and the trained agent successfully meets our specified design goals within 5 to 15 design steps. This work serves as a conceptual validation attempt to apply reinforcement learning techniques and pre-trained ANN models to automate MMIC filter design. It exhibits clear advantages in terms of time-saving and performance efficiency when compared to other optimization algorithms.

The traditional rolling bearing diagnosis algorithms have problems such as insufficient information on time-frequency images and poor feature extraction ability of the diagnosis model. These problems limit the improvement of diagnosis performance. In this article, the input of the time-frequency image and intelligent diagnosis algorithms are optimized. Firstly, the characteristics of two advanced time-frequency analysis algorithms are deeply analyzed, i.e., multisynchrosqueezing transform (MSST) and time-reassigned multisynchrosqueezing transform (TMSST). Then, we propose time-frequency compression fusion (TFCF) and a residual time-frequency mixed attention network (RTFANet). Among them, TFCF superposes and splices two time-frequency images to form dual-channel images, which can fully play the characteristics of multi-channel feature fusion of the convolutional kernel in the convolutional neural network. RTFANet assigns attention weight to the channels, time and frequency of time-frequency images, making the model pay attention to crucial time-frequency information. Meanwhile, the residual connection is introduced in the process of attention weight distribution to reduce the information loss of feature mapping. Experimental results show that the method converges after seven epochs, with a fast convergence rate and a recognition rate of 99.86%. Compared with other methods, the proposed method has better robustness and precision.

The smart electricity meter (SEM) is an important part of smart power grid, and the accuracy of SEMs is the basis for power grid operation control and trade settlement between power supply and electricity consumption, but the evolution behaviors of metering error of SEMs under field operation conditions have not yet been identified. The SEMs were installed and operated on site, metering error data were collected under various temperature and current conditions. The influences of current, power coefficient, and temperature on metering error and consistency were analyzed separately with the help of quadratic polynomials, and then an integrated model elaborating the joint effects of multi-stress was developed based on a binary quadratic polynomial. We find that a lower temperature and a larger current result in a higher metering error of SEMs; however, the effects of current on metering error are determined by power coefficients. The results have reference value for remote metrological verification, error monitoring, and the optimization of the operation and maintenance scheme of SEMs.