Fault diagnosis of the bushing infrared images based on mask R‐CNN and improved PCNN joint algorithm

Bushings are served as an important component of the power transformers;it's of great significance to keep the bushings in good insulation condition.The infrared images of the bushing are proposed to diagnose the fault with the combination of image segmentation and deep learning,including object detection,fault region extraction,and fault diagnosis.By building an object detection system with the frame of Mask Region convolutional neural network(CNN),the bushing frame can be exactly extracted.To distinguish the fault region of bushings and the background,a simple linear iterative clustering‐based pulse coupled neural network is proposed to improve the fault region segmentation performance.Then,two infrared image feature parameters,the relative position and area,are explored to classify fault type effectively based on the K‐means cluster technique.With the proposed joint algorithm on bushing infrared images,the accuracy reaches 98%,compared with 44%by the conventional CNN classification method.The integrated algorithm provides a feasible and advantageous solution for the field application of bushing image‐based diagnosis.

An efficient chemical reduction-induced assembly of Fe_(3)O_(4)@graphene fiber for wire-shaped supercapacitors with ultrahigh volumetric energy density

Benefiting from high flexibility and weavability,the wire-shaped supercapacitors(SCs)arouse tremendous interests for the applications in wearable/portable electronics.Graphene fiber(GF)is considered as a promising linear electrode for wire-shaped SCs.However,the bottleneck is how to develop the GF-based linear electrode with facile fabrication process while wellmaintaining satisfactory electrochemical performance.Herein,a novel Fe_(3)O_(4)@GF composite linear electrode is proposed via a chemical reduction-induced assembly approach,in which the GO and Fe_(3)O_(4) nanoparticles(NPs)realize the efficient selfassembly owing to the electrostatic and van der Waals interactions,as well as the sufficient reduction of GO during the preparation process.The resultant fiber-shaped architecture shows boosted charge-transfer kinetics,high flexibility and structural integrity.Such Fe_(3)O_(4)@GF linear electrode exhibits excellent electrochemical behaviors including a large volumetric specific capacitance(~250.75 F cm^(−3)),remarkable rate capability and favorable electrochemical kinetics in aqueous electrolyte,superior than previously reported GF-based linear electrodes.For real application,a high-performance wire-shaped SC with excellent flexibility and weavability is fabricated based on such Fe_(3)O_(4)@GF linear electrode and gel electrolyte,demonstrating ultrahigh volumetric energy density(18.8 mWh cm^(−3)),power density(4000 mW cm^(−3))and strong durability(~93.5%retention after 10000 cycles).Prospectively,the fabricated wire-shaped SC can maintain reliable electrochemical behaviors in various deformation states,showing its potentials in future portable and wearable devices.

Propagation and localisation of partial discharge in transformer bushing based on ultra-high frequency technique

As an essential component of power transformers,the detection and diagnosis of incipient partial discharge(PD)activities of bushings are of great significance.A 35-kV oil-impregnated paper(OIP)bushing is investigated.The bushing is modelled by coaxial theory and electromagnetic(EM)simulation.As the paths of PD-induced ultra-high frequency(UHF)signal propagating in the bushing are OIPs and oil gap,small attenuation during signal propagation is seen.Since OIP is composed of het-erogeneous media compared with pure oil,there will be relatively less UHF signal leakage from OIPs,whereas more leakage from the oil gap.This leakage provides the possibility of non-contact detection outside the bushing by UHF method.PD mea-surements with UHF method are carried out on the bushing.Then,the minimum energy method is used to extract time-difference-of-arrival(TDOA),and Chan al-gorithm is adopted to locate points of UHF signal radiation.High accuracy locating with a small error of 15 cm has been achieved.The contactless UHF method-based tests have demonstrated the effectiveness of online monitoring and locating of bushing PD.