Recently, the Internet of Things (IoT) has an important role in the growth and development of digitalized electric power stations while offering ambitious opportunities, specifically real-time monitoring and cybersecurity In this regard, this paper introduces a novel IoT architecture for the online monitoring of the gas-insulated switchgear (GIS) status instead of the traditional observation methods The proposed IoT architecture is derived from the concept of the cyber-physic system (CPS) in Industry 40 However, the cyber-attacks and the classification of the GIS insulation defects represent the main challenges against the implementation of IoT topology for the online monitoring and tracking of the GIS status For this purpose, advanced machine learning techniques are utilized to detect cyber-attacks to conduct the paradigm and verification Different test scenarios on various defects in GIS are performed to demonstrate the effectiveness of the proposed IoT architecture Partial discharge pulse sequence features are extracted for each defect to represent the inputs for IoT architecture The results confirm that the proposed IoT architecture based on the machine learning technique, that is the extreme gradient boosting (XGBoost), can visualize all defects in the GIS with different alarms, besides showing the cyber-attacks on the networks effectively Furthermore, the defects of GIS and the fake data due to the cyber-attacks are recognized and presented on the dashboard of the proposed IoT platform with high accuracy and more clarified visualization to enhance the decision–making about the GIS status

/pdf/towards-secured-online-monitoring-for-digitalized-gis-12ghzs4y1e.pdf

Towards Secured Online Monitoring for Digitalized GIS Against Cyber-Attacks Based on IoT and Machine Learning

This paper investigates the impact factors of switching transient overvoltage (SOV) in an offshore wind farm (OWF) by analyzing multiple ignitions of a vacuum circuit breaker. The statistical features of transient overvoltages, which occur under real switching operation scenarios, are analyzed based on the measurements in a laboratory platform that is built according to the configuration of an actual OWF. Next, an OWF simulation transient model is established considering high-frequency characteristics of circuit breakers, which is verified to be able to calculate the SOV accurately. Based on the developed OWF simulation model, the occurrence mechanism of SOV is discussed in detail by studying characteristics of transient voltage and current during multiple ignitions within a vacuum circuit breaker when it is switched OFF. Then, the key impact factors of switching- OFF induced overvoltage are identified, which include the inter-phase capacitance of cable in a windmill tower, the actual operating capacity of a wind turbine generator, and the single-phase inlet capacitance in terminals of a wind turbine transformer. Finally, the recommended configurations are given for the transient mitigation in an OWF.

/pdf/impact-factor-identification-for-switching-overvoltage-in-an-b65b4nio9i.pdf

Impact Factor Identification for Switching Overvoltage in an Offshore Wind Farm by Analyzing Multiple Ignition Transients

This paper proposes a data-driven method-based fault diagnosis method using the deep convolutional neural network (DCNN). The DCNN is used to deal with sensor and actuator faults of robot joints, such as gain error, offset error, and malfunction for both sensors and actuators, and different fault types are diagnosed using the trained neural network. In order to achieve the above goal, the fused data of sensors and actuators are used, where both types of fault are described in one formulation. Then, the deep convolutional neural network is applied to learn characteristic features from the merged data to try to find discriminative information for each kind of fault. After that, the fully connected layer does prediction work based on learned features. In order to verify the effectiveness of the proposed deep convolutional neural network model, different fault diagnosis methods including support vector machine (SVM), artificial neural network (ANN), conventional neural network (CNN) using the LeNet-5 method, and long-term memory network (LTMN) are investigated and compared with DCNN method. The results show that the DCNN fault diagnosis method can realize high fault recognition accuracy while needing less model training time.

Sensor and Actuator Fault Diagnosis for Robot Joint Based on Deep CNN.

A novel autonomous strategy for multi-bolt looseness detection using smart glove and Siamese double-path CapsNet

Signal measurement and diagnosis of wind turbine gearbox are very important for equipment maintenance. Generative adversarial networks (GAN) are particularly outstanding in data generation due to its game mechanism. An improved gear fault diagnosis method based on GAN for unbalanced data sets is proposed in this paper. Firstly, the fault data is encoded by binary vectorization based on kurtosis perceptron. Secondly, the individuals that fit the fitness are selected by the deterministic selection and the macro factor code string is crossed by multiple points. Then, gaussian mutation is focused on searching for local fault points. Finally, the nonlinear decision boundary is established by the logistic regression auxiliary classifier. The effectiveness of the proposed method was verified by three groups of comparison experiments. Compared with the existing methods, the proposed method has a better ability for fault feature generation, classification, and diagnosis accuracy under unbalanced data sets.

Generative Adversarial Networks for Gearbox of Wind Turbine With Unbalanced Data Sets in Fault Diagnosis

As a kind of widely used switchgear in power system, the reliability of gas insulated switchgear (GIS) is very important for the safe operation of power systems. However, there is a lack of research on intelligent detection technology of mechanical state of GIS at present. A new method is urgently needed to improve the operability, effectiveness, and accuracy of fault detection in GIS. Aiming at the abnormal vibration signals generated by GIS faults, this article presents a fault diagnosis method (GA-DBSCAN) consisting of a feature selection method based on genetic algorithm (GA) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and a fault diagnosis method based on DBSCAN. First, this article analyzes the incentive force of GIS and discusses the characteristic frequency of response signal combining with the non-linear characteristics of a GIS system. Second, GA and DBSCAN are used to screen features for dimension reduction and get the optimized feature space, and DBSCAN-based classification is used to classify faults. Finally, optimized feature space is verified to be superior to the original feature space by typical classification method; the superiority and reliability of DBSCAN-based classification method under optimized feature space is verified by comparing with other classification methods. The proposed GA-DBSCAN approach can substantially increase the performance of the fault diagnosis method, which indicates that the method promotes development of intelligent detection technology of mechanical state in GIS.

Fault Diagnosis in Gas Insulated Switchgear Based on Genetic Algorithm and Density- Based Spatial Clustering of Applications With Noise

Intermediate frequency (IF) electric power supply system has been widely applied in airplanes. Reignition after interruption of 360–850 Hz vacuum arc in axial magnetic field (AMF) is studied in this paper. According to the experimental results, the current interruption ability decreases from 22.4 kA at 360 Hz to 14.0 kA at 850 Hz. With the increase of frequency, the rate of change of current, di/dt, at current zero (CZ) reaches the breaking threshold at a smaller current value. Based on the least squares solution of the Mayr model, the time of decay of arc energy is prolonged when interruption fails, which is disadvantageous to the breaking process. On the other hand, the eddy effect is enhanced by higher frequency, which increases the residual magnetic induction intensity and the hysteresis phase of AMF after CZ. As a result, the diffusion of plasma is blocked. In the experiments, we find that the position of arc reignition always appears at the margin of contacts. It is shown by calculation that the electric field at the marginal area is twice as strong as that inside the contact. The current density is high, where the electric field is strong, leading to the higher probability of field emission. Arc images are analyzed by frame differential method. The sputtering velocity of macroscopic particles is estimated to be 10–20 m/s. The dissipation time of the macroscopic particles is longer than the arc time of IF vacuum arc, and the presence of macroscopic particles leads to the arc reignition. The findings of this paper would be beneficial to the parameter design of IF vacuum circuit breakers, such as the magnetic flux density of AMF, the chamfering of contact margin, and contact materials.

Reignition After Interruption of Intermediate-Frequency Vacuum Arc in Aircraft Power System

Intermediate-frequency power technology is widely used in aircraft power-supply systems. This paper studies the appearance and motion of vacuum plasmas in an axial magnetic field (AMF) and butt contacts at 360–800 Hz. Under the influence of an AMF, electrons travel in a cylindrical spiral, which is advantageous for maintaining arc diffusion. The experimental results show that when the contact separation was 3 mm, the vacuum arcs were uniformly distributed and diffused in the AMF contacts. We found that the maximum magnetic pinch pressure in the arc column was approximately $10^{4}$ Pa. However, in butt contacts, the arc was intense and was clearly constricted. The order of magnitudes of the magnetic pinch pressure in the center reached $10^{5}$ Pa at the minimum radius of the arc column around the current peak, which formed a higher pressure gradient that caused the plasma and metal vapor to flow to the lower pressure region and form a plasma jet.

Appearance of Vacuum Arcs in Axial Magnetic Field and Butt Contacts at Intermediate Frequencies

With the development of new energy, DC system is widely applied in urban rail, ships and other fields. H 2 -N 2 mixed gas switch has been one of the effective methods to interrupt direct circuit current for its large breaking capacity and small volume. In order to study the arc characteristics of H 2 -N 2 mixed gas switch, a detachable interrupter is designed. The arc voltampere characteristics of H 2 -N 2 mixed gas switch are obtained by experiments. Then DC arc characteristics and evolution are studied through arc appearances obtained by high-speed camera. Besides, the influence of electromagnetic drive on arc appearance and the arc motion are analyzed. It is indicated that the application of electromagnetic drive is beneficial to the arc movement of DC H 2 mixed gas arc and shorten the arcing time, which is favorable to arc extinguish during interruption.

Arc motion characteristics of H 2 -N 2 mixed gas switch with magnetic field

In order to research the interruption process of vacuum circuit breaker in aviation intermediate-frequency (360Hz∼800Hz) power supply system, vacuum arc experiments are carried out in interrupter with the diameter being 41mm and with the contact material being CuCr50 alloy. It can be indicated from the results as follows: With the increase of frequency and peak value of the current, both the peak value and the rise rate of the intermediate-frequency vacuum arc voltage increase, and the interruption ability decreases. However, the erosion of contacts is weaker for a shorter arc time, comparing to the power frequency current in the same value. When the vacuum arc reignites0, metal droplets are emitted from the contacts. The drive force is from the center of the contact to edge. If the density of plasmas and metal vapors and the numbers of the metal droplets come to a certain level, the arc may be broken down, which cause the interruption failed.

Jia Bowen

Papers

Fault Diagnosis in Gas Insulated Switchgear Based on Genetic Algorithm and Density- Based Spatial Clustering of Applications With Noise

Reignition After Interruption of Intermediate-Frequency Vacuum Arc in Aircraft Power System

Appearance of Vacuum Arcs in Axial Magnetic Field and Butt Contacts at Intermediate Frequencies

Arc motion characteristics of H 2 -N 2 mixed gas switch with magnetic field

Interruption process and droplets emission in vacuum arc for aviation intermediate-frequency power supply system