Idiopathic pulmonary fibrosis (IPF) is a progressive fibrotic disease with pathophysiological characteristics of transforming growth factor-β (TGF-β), and reactive oxygen species (ROS)-induced excessive fibroblast-to-myofibroblast transition extracellular matrix deposition. Macrophages are closely involved in the development fibrosis. Nuclear factor erythroid 2 related (Nrf2) key molecule regulating ROS TGF-β expression. Therefore, Nrf2 signaling modulation might be promising therapy for The...

Automatic registration for infrared, and visible images of power equipment has become a challenging work in intelligent diagnosis system the grid. Existing methods usually fail accurately aligning because resolutions, spectrums, viewpoints differences. To solve this problem, we propose novel main orientation feature points named contour angle (CAO), describe an automatic image method CAO-Coarse to Fine (CAO-C2F). CAO is based on images, invariant viewpoints, scales C2F matching obtain...

Faulted line detection is a key step of intelligent fault diagnosis distribution systems, laying the foundation for further location and service restoration. A novel single line-to-ground (SLG) faulted method based on feature fusion framework proposed. In proposed framework, one-dimensional convolutional neural network employed as powerful tool to extract more effective features. addition, there an imbalance phenomenon between data healthy lines when data-driven model used in detection. The...

The reliability of distribution systems is often challenged under unfavorable weather conditions, where weather-related failures occur with high probability. Predicting the number in can provide guiding information for operation and maintenance decisions, improving risk management capability utility companies. This article proposes a novel Bayesian Neural Network (BNN) based model to predict caused by wind, rain lightning. Superior prediction performance BNN verified contrast experiments...

Maize is one of the main grain reserve crops, which directly affects food security country. It extremely important to evaluate growth status maize in a timely and accurate manner. Canopy Chlorophyll Density (CCD) closely related crop health status. A estimation CCD helpful for managers take measures avoid yield loss. Thus, many methods have been developed estimate with remote sensing data. However, relationship between features used these at different stages unclear. In addition, was...

Ultra-high frequency (UHF) technique is chosen for partial discharge (PD) detection due to its excellent anti-interference and stability. The existing UHF PD localisation methods are mainly based on time-difference technique, that suffer high hardware cost the sampling rate requirement. wireless sensors together with scene analysis methods, i.e. received signal strength indicator (RSSI) fingerprint, provide us a low environmental adaptability solution in substation. proposed method here...

Accurate fault‐cause identification is highly important to the fault analysis of overhead transmission lines (OTLs). In order improve efficiency and accuracy identification, this study proposes a method based on ADBN (adaptive deep belief network) model time–frequency characteristics travelling wave. According mechanisms different OTL faults, appropriate characteristic parameters current wave were selected as input model, fault‐type labels output. The introduces idea adaptive learning rate...

The single-line-to-ground faults with line breaks (SLGFs-LBs) occur more and frequently in distribution networks can cause major safety accidents. It is difficult to distinguish the (SLGFs) resonant grounding systems ungrounding due same electrical characteristics on source side uncertain operation conditions of networks. This paper proposes a method for distinguishing SLGFs-LBs SLGFs. First, source-side load-side voltage SLGFs are analyzed, phase difference between voltages fault non-fault...

Faults with line breaks occur more and frequently are difficult to detect by relay protection device in small-current grounding distribution networks. However, faults likely cause security accidents such as fires, overvoltages electric shocks. Considering the low cost high reliability of collecting data on low-voltage (LV) side networks, this paper proposes a method for distinguishing between short-circuit medium-voltage (MV) side. Voltage amplitude phase LV transformer (DT) analyzed through...

Weather-related failures significantly challenge the reliability of distribution systems. To enhance risk management weather-related failures, an interpretable extra-trees based prediction model is proposed in this study. In model, interpretability successfully introduced to by analyzing and processing paths decision trees extra-trees. As a result, reflected following three respects: it can output importance, contribution, threshold weather variables at high risk. The importance help...

Root-cause identification of faults in a distribution network is conducive to fault inspection as well reducing injuries and damage. In this article, novel method based on correlation dimension average resistance proposed identify the root cause permanent single line-to-ground urban small current grounding systems. First, reliability whether occurred dry or wet surface can be identified by dimension. Then, used classify specific cause, including land, concrete, water. Experimental results...

The porcelain insulator incipient fault (PIIF) is a self-clearing discharge process caused by water entering the crack of insulator. It will not result in tripping operation but may evolve into permanent grounding after multiple occurrences, leading to various types accidents, such as wire breaks, power outages, fires, and personal electric shocks. This paper uncovered mechanisms behind initiation evolution PIIF. Unique characteristics PIIF are analyzed from aspects starting time,...

Fault feature extraction is critical for fault line detection, but difficult to be effective and robust. Unbalanced characteristics of the signal sample will make more difficult. A novel method using Choi- Williams time-frequency distribution based convolutional neural network task decomposition framework was proposed. analysis applied generate image signal. Then, (CNN) trained by a lot images generated under different conditions. CNN can extract features adaptively select line. The first...

Motivated by the increasing frequency and intensity of extreme weather events, this article aims to effectively assess scope zones damaged natural disasters in distribution systems, which can help for rapid restoration power supply. Multiple-branch faults uncertainty monitoring information pose huge challenges Disaster Damage Assessment (DDA). This paper proposes a multiple hypothesis based DDA method solve problem. In proposed method, novel external environment is used updating objective...

Abstract It is important to estimate the cumulative distribution function (CDF) of a failure mode in geotechnical system, because often characterized by some empirical and/or semi‐empirical thresholds and engineers sometimes might be interested probability associated with various thresholds. The systems also generally contain multiple modes. This requires an efficient estimation functions (CDFs) modes, which poses significant challenge application conventional reliability analysis methods....