An Improved Solov2 Based on Attention Mechanism and Weighted Loss Function for Electrical Equipment Instance Segmentation

The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.

Operation and Management of Electrical Equipment in Iron and Steel Enterprises

How to ensure the reliable operation of the complex and huge electrical system composed of a large number of electrical equipment in iron and steel enterprises?Combined with working experience,the author introduces four main factors affecting the normal operation of equipment,analyzes five main problems existing in the operation and management of electrical equipment,and puts forward corresponding improvement measures,so as to improve the management level of electrical equipment in iron and steel enterprises.

Real-time localization for underwater equipment using an extremely low frequency electric field

A new real-time underwater equipment location method adopting an electric field induced by a standard current source is proposed.Our goals were real-time tracking and location of stationary or moving underwater equipment both in shallow and deep seas,under noisy conditions.The main features of this method are as follows:(1)a standard current source on the water surface,which can be towed by a vehicle,consisting of two electrodes,a signal generator,and a GPS unit;(2)measurement of the extremely low frequency(ELF)electric field emitted by the current source,made possible by electric field sensors on the underwater equipment;(3)position of the underwater equipment is estimated in real time based on a progressive update extended Kalman filter(PUEKF),which is carried out using the propagation model of an ELF electric field because the electric field at the position of the underwater equipment and the current source position are known.We verified the accuracy of our method and confirmed real-time location feasibility through numerical,physical scale,and real-time sea experiments.Through numerical experiments,we verified that our method works for underwater equipment location in real-world conditions,and the location error can be less than 0.2 m.Next,real-time location experiments for stationary underwater measuring equipment in water tank were conducted.The result shows that the location error can be less than 0.1 m.We also confirmed real-time location feasibility through the use of offshore experiment.We expect that our method will complement conventional underwater acoustic location methods for underwater equipment in acoustically noisy environments.

Experimental and analytical studies on multiple tuned mass dampers for seismic protection of porcelain electrical equipment

Porcelain electrical equipment （PEE）, such as current transformers, is critical to power supply systems, but its seismic performance during past earthquakes has not been satisfactory. This paper studies the seismic performance of two typical types of PEE and proposes a damping method for PEE based on multiple tuned mass dampers （MTMD）. An MTMD damping device involving three mass units, named a triple tuned mass damper （TTMD）, is designed and manufactured. Through shake table tests and finite element analysis, the dynamic characteristics of the PEE are studied and the effectiveness of the MTMD damping method is verified. The adverse influence of MTMD redundant mass to damping efficiency is studied and relevant equations are derived. MTMD robustness is verified through adjusting TTMD control frequencies. The damping effectiveness of TTMD, when the peak ground acceleration far exceeds the design value, is studied. Both shake table tests and finite element analysis indicate that MTMD is effective and robust in attenuating PEE seismic responses. TTMD remains effective when the PGA far exceeds the design value and when control deviations are considered.

A REPLACEMENT MODEL FOR QUEUEING SYSTEM WITH REPAIRABLE ELECTRICAL EQUIPMENT OF AUTOMATIC STEEL ROLLING

The optimal replacement model for the repairable queueing system con-sisting of single electrical equipment of automatic steel rolling is studied. Assumingthat the equipment after repair is not “as goed as new” , by using geometric pro-cess, we take the n

An Improved Biometric Fuzzy Signature with Timestamp of Blockchain Technology for Electrical Equipment Maintenance

The power infrastructure of the power system is massive in size and dispersed throughout the system.Therefore,how to protect the information security in the operation and maintenance of power equipment is a difficult problem.This paper proposes an improved time-stamped blockchain technology biometric fuzzy feature for electrical equipment maintenance.Compared with previous blockchain transactions,the time-stamped fuzzy biometric signature proposed in this paper overcomes the difficulty that the key is easy to be stolen by hackers and can protect the security of information during operation and maintenance.Finally,the effectiveness of the proposed method is verified by experiments.

New “Intellectual Networks” (Smart Grid) for Detecting Electrical Equipment Faults, Defects and Weaknesses

The most important elements of “intellectual networks” (Smart Grid) are the systems of monitoring the parameters of electrical equipment. Information-measuring systems (IMS), which described in this paper, were proposed to use together with rapid digital protection against short-circuit regimes in transformer windings. This paper presents an application’s experience of LVI-testing, some results of the use of Frequency Response Analysis (FRA) to check the condition of transformer windings and infra-red control results of electrical equipment. The LVI method and short-circuit inductive reactance measurements are sensitive for detecting such faults as radial, axial winding deformations, a twisting of low-voltage or regulating winding, a losing of winding’s pressing and others.

Hardware,Machines & Electrical Equipment From Wenzhou

Scissors and locks are famous products from Wenzhou. Now scissors from the city including multi-purpose, tailoring, tourist and special-purpose ones and exquisite fruit and artistic knives have entered the world market. At the

Japanese National Safety Standards for Electrical Equipment

I am working in Japan electrical safety & environment technology laboratory,which is called JET for short. In JET, we are carrying out the safety test of electrical equipmentaccording to Japanese domestic standards or IEC standards. And in my section, our stuff is draftingsome national safety standards harmonized with IEC in cooperation with the government. The standardsare applied for the mandatory regulation and other schemes.

A Comparison of Domestic and Foreign Seismic Fortification Standards for Electrical Equipment

It is of great significance to make comparative analyses of seismic fortification criteria at home and abroad for improving the anti-seismic capability of electrical equipment and revising the relevant national standards.A brief overview of American,Japanese,IEC standards and Chinese seismic design codes for electrical equipment is presented.Differences between these seismic fortification standards of electrical equipment are compared and analyzed in respect of the goal and level of seismic fortification and the seismic design spectrum.The advantages and disadvantages of Chinese standards are pointed out.Through learning from foreign experience on the determination of seismic fortification standards,recommendations are made for the improvement and revision of Chinese seismic fortification standards for electrical equipment.

Analysis on Economic Performance of Electrical Equipment Industry in 2010

In this paper the analysis is presented on the economic performance of the electrical equipment industry in 2010.Substantial increase was seen in both the economic aggregate indices such as production and sales,and economic efficiency indices such as profits.Increase of indices that reflect foreign trade situation of the industry,such as import volume,export volume,gross import and export volume,and export delivery volume were prominent in particular.The industry has completely stepped out of the "negative growth" predicament in 2009,comprehensively outperformed the level in 2008,and recovered true growth.The economic situation of the electrical equipment industry in 2011 is also predicted in this paper.

Simulation of seafloor electrical resistivity measuring equipment based on 3D finite element method

In order to explore the mineral resources buried in sea mud,it is necessary to use seabed resistivity measuring equipment,which works closer to the sediments than ordinary ship-based geophysical measuring equipment. Because of the harsh environment of seafloor,high pressure and highly conductive seawater,marine magnetotelluric method developed slowly. The sea floor environment is similar to the environment of logging, According to the design of dual lateral logging equipment,a new equipment for seafloor electrical resistivity measurement is designed. Four 3D FEM models that contain resistivity abnormal targets are built to test the ability of this equipment to locate different shape of shallow buried resistivity abnormal targets in sea mud. The authors propose the method to correct the response curve while the bottom surface of this equipment is suspended or not parallel to the seafloor. The resistivity of targets can be calculated accurately.

Characteristic Period Value of the Seismic Design Response Spectrum of UHV Electrical Equipment

Characteristic period is an important parameter of the seismic design response spectrum. There is important theoretical significance and engineering application value to the study of the characteristic period of seismic design response spectrum of ultra high voltage （UHV） electrical equipment. In this paper, 1448 horizontal earthquake records within the world scope including the United States and Japan for Site Class m were analyzed. Results show that both magnitude and epicentral distance have great influence on the characteristic period. About 80 % of characteristic periods of strong earthquake records are about 0. 9s. Statistical analysis was conducted on the seismic hazard assessment results of 312 projects of China in recent years, and it is found that about 70 % of characteristic periods are about 0. 9s. Combined with the related code comparison and analysis, it is suggested that the characteristic period of the seismic design response spectrmn of UHV electrical equipment should select 0. 9s in order to effectively guarantee the seismic safety of UHV electrical equipment.

Fault diagnosis for on-board equipment of train control system based on CNN and PSO-SVM hybrid model

Rapid and precise location of the faults of on-board equipment of train control system is a significant factor to ensure reliable train operation.Text data of the fault tracking table of on-board equipment are taken as samples,and an on-board equipment fault diagnosis model is designed based on the combination of convolutional neural network(CNN)and particle swarm optimization-support vector machines(PSO-SVM).Due to the characteristics of high dimensionality and sparseness of fault text data,CNN is used to achieve feature extraction.In order to decrease the influence of the imbalance of the fault sample data category on the classification accuracy,the PSO-SVM algorithm is introduced.The fully connected classification part of CNN is replaced by PSO-SVM,the extracted features are classified precisely,and the intelligent diagnosis of on-board equipment fault is implemented.According to the test analysis of the fault text data of on-board equipment recorded by a railway bureau and comparison with other models,the experimental results indicate that this model can obviously upgrade the evaluation indexes and can be used as an effective model for fault diagnosis for on-board equipment.

Zibo Sangde Machinery Equipment Co., Ltd The Most Professional Manufacturer of Refractory Electric Screw Press in China

Zibo Sangde Machinery Equipment Co., Ltd. is the first Manufacturer of Refractory Electric Screw Press in China, in the year of 2008, our company produced the first set 315T Refractory Electric Program-controlled Screw Press in China, which is no friction discs, simple structure, with PLC controlling the brick forming process, no need special operator. Once upon the Press was on the market, it achieved a strong interests and reputations from many Refractory Factories because of its Highefficient, Energy-saving（can save by 40-50% electricity comparing to the Friction Press）, manpower reduction and improving the quality of bricks.

Shanghai Electric (Group) Corp.- The pioneer of Power Equipment Manufacturing in China

Shanghai Electric (Group) Corporation (SEC) is a large-scale industrial enterprise group in China engaged in design and manufacturing of power generation equipment, power transmission and distribution equipment and heavy machinery equipment. SEC is separately catalogued in the program of the State Planning Commission. Based on its main economic norms, SEC is listed as one of the 500

Study on Negative Impact of Harmonic Components on Sensitive Electric Equipment

Distribution systems operators are often confronted with declined power quality, which can cause substantial economical losses. The problem analyzed in paper concerns thyristor controlled direct current motor used for ski-lift in ski resort as a source of disturbances with negative impact on sensitive electric equipment, which is then unable to operate correctly. To solve mentioned problems, series of measurements of voltage quality parameters were carried out according to the respective valid standards. Crucial power quality parameters necessary for parallel power active filter design were then analyzed. Power active filter compensates power factor and filters characteristic current harmonics. After power active filter was put into operation, power quality problems were eliminated. Payback period is estimated up to four years.

NINGBO TENDERING CENTER OF MACHINERY AND ELECTRIC EQUIPMENT

Ningbo TenderingCenter of Machinery andElectric Equipment wasestablished with the ap-proval by the CompetantState Department andNingbo Municipal Gov-ernment.It is a legal en-tity subordinated to Ning-bo Municipal EconomicCommittee,specializingin tendering service un-der the supervision,in-spection and guidance ofthe China National Ten-dering Center of Machin-ery and Electric Equip-ment.

基于双对数正态分布的电瓷型电气设备地震易损性研究

总结了110 kV和220 kV典型电气设备的地震易损性曲线研究成果,考虑不同研究成果的离散性,基于双对数正态分布给出了抗震能力中值、随机性和不确定性建议值。进一步开展220 kV变电站系统的抗震性能分析,定量评价了变电站的功能性。研究结果表明:双对数正态分布可以较好地反映电气设备地震易损性的离散性,尤其是模型、方法等原因导致的不确定性。变电站系统的抗震能力低于电气设备的抗震能力,设计中应采取措施提高变电站的冗余性。变电站系统抗震性能与电气设备抗震能力中值正相关,与随机性和不确定性呈负相关。

基于卷积神经网络的电气设备故障诊断研究

电气设备在工业生产中具有重要作用。由于长期运行和环境因素的影响,电气设备难免会出现故障,因此,快速准确地进行电气设备故障诊断尤为重要。文章通过总结探讨将卷积神经网络应用于电气设备故障诊断的技术原理、关键操作流程、故障诊断程序及应用难点后认为,可通过优化网络结构、改进数据预处理方法、模型迁移应用以及与其他故障诊断方法融合,来提高电气设备故障诊断的效率和准确性。