Investigation on the fault monitoring of high-voltage circuit breaker using improved deep learning.

Mechanical faults are the main causes of abnormal opening, refusal operation, or malfunction of high-voltage circuit breakers. Accurately assessing the operational condition of high-voltage circuit breakers and delivering fault evaluations is essential for the power grid's safety and reliability. This article develops a circuit breaker fault monitoring device, which diagnoses the mechanical faults of the circuit breaker by monitoring the vibration information data. At the same time, the article adopts an improved deep learning method to train vibration information of high-voltage circuit breakers, and based on this, a systematic research method is employed to identify circuit breaker faults. Firstly, vibration information data of high-voltage circuit breakers is obtained through monitoring devices, this vibration data is then trained using deep learning methods to extract features corresponding to various fault types. Secondly, using the extracted features, circuit breaker faults are classified and recognized with a systematic analysis of the progression traits across various fault categories. Finally, the circuit breaker's fault type is ascertained by comparing the test set's characteristics with those of the training set, using the vibration data. The experimental results show that for the same type of circuit breaker, the accuracy of this method is over 95%, providing a more efficient, intuitive, and practical method for online diagnosis and fault warning of high-voltage circuit breakers.

Modular Approach for Odometry Localization Method for Vehicles with Increased Maneuverability.

Localization and navigation not only serve to provide positioning and route guidance information for users, but also are important inputs for vehicle control. This paper investigates the possibility of using odometry to estimate the position and orientation of a vehicle with a wheel individual steering system in omnidirectional parking maneuvers. Vehicle models and sensors have been identified for this application. Several odometry versions are designed using a modular approach, which was developed in this paper to help users to design state estimators. Different odometry versions have been implemented and validated both in the simulation environment and in real driving tests. The evaluated results show that the versions using more models and using state variables in models provide both more accurate and more robust estimation.

Inhibition Effect of Graphene on Space Charge Injection and Accumulation in Low-Density Polyethylene.

Space charge injection and accumulation is attracting much attention in the field of dielectric insulation especially for electronic devices, power equipment and so on. This paper proposes using the inhibition effect of graphene for the injection and accumulation of space charge in low-density polyethylene (LDPE). Scanning electron microscope (SEM) and transmission electron microscopy (TEM) images were employed to observe the dispersion of graphene with a two-dimensional structure in LDPE. The time-dependent space charge dynamic behaviors of graphene/LDPE nanocomposites with the filler content of 0, 0.003, 0.005, 0.007 and 0.01 wt % were characterized by the pulsed electro-acoustic (PEA) test at 40, 60 and 80 °C, and the charge mobility was evaluated by its depolarization processes. The experimental results show that for the undoped LDPE film, large amounts of space charges were injected from the electrodes into samples, especially at 60 and 80 °C. The graphene/LDPE nanocomposites with a filler content of 0.005 wt % could markedly suppress the space charge injection and accumulation even at 80 °C, which is attributed to the large quantities of graphene-polymer in interface regions. These interface regions introduced numbers of deep trap sites within the forbidden band of nanocomposites, which can reduce the de-trapping rate of charges and suppress the space charge accumulation in the polymer bulks. The graphene/LDPE nanocomposites are suggested for dielectric applications, intending the inhibition of space charge injection and accumulation.

Trap Modulated Charge Carrier Transport in Polyethylene/Graphene Nanocomposites.

The role of trap characteristics in modulating charge transport properties is attracting much attentions in electrical and electronic engineering, which has an important effect on the electrical properties of dielectrics. This paper focuses on the electrical properties of Low-density Polyethylene (LDPE)/graphene nanocomposites (NCs), as well as the corresponding trap level characteristics. The dc conductivity, breakdown strength and space charge behaviors of NCs with the filler content of 0 wt%, 0.005 wt%, 0.01 wt%, 0.1 wt% and 0.5 wt% are studied, and their trap level distributions are characterized by isothermal discharge current (IDC) tests. The experimental results show that the 0.005 wt% LDPE/graphene NCs have a lower dc conductivity, a higher breakdown strength and a much smaller amount of space charge accumulation than the neat LDPE. It is indicated that the graphene addition with a filler content of 0.005 wt% introduces large quantities of deep carrier traps that reduce charge carrier mobility and result in the homocharge accumulation near the electrodes. The deep trap modulated charge carrier transport attributes to reduce the dc conductivity, suppress the injection of space charges into polymer bulks and enhance the breakdown strength, which is of great significance in improving electrical properties of polymer dielectrics.