Abnormal Action Recognition with Lightweight Pose Estimation Network in Electric Power Training Scene

Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.

Intelligent Power Grid Load Transferring Based on Safe Action-Correction Reinforcement Learning

When a line failure occurs in a power grid, a load transfer is implemented to reconfigure the network by changingthe states of tie-switches and load demands. Computation speed is one of the major performance indicators inpower grid load transfer, as a fast load transfer model can greatly reduce the economic loss of post-fault powergrids. In this study, a reinforcement learning method is developed based on a deep deterministic policy gradient.The tedious training process of the reinforcement learning model can be conducted offline, so the model showssatisfactory performance in real-time operation, indicating that it is suitable for fast load transfer. Consideringthat the reinforcement learning model performs poorly in satisfying safety constraints, a safe action-correctionframework is proposed to modify the learning model. In the framework, the action of load shedding is correctedaccording to sensitivity analysis results under a small discrete increment so as to match the constraints of line flowlimits. The results of case studies indicate that the proposed method is practical for fast and safe power grid loadtransfer.

Optimizing Average Electric Power During the Charging of Lithium-Ion Batteries Through the Taguchi Method

In recent times, lithium-ion batteries have been widely used owing to their high energy density, extended cycle lifespan, and minimal self-discharge rate. The design of high-speed rechargeable lithium-ion batteries faces a significant challenge owing to the need to increase average electric power during charging. This challenge results from the direct influence of the power level on the rate of chemical reactions occurring in the battery electrodes. In this study, the Taguchi optimization method was used to enhance the average electric power during the charging process of lithium-ion batteries. The Taguchi technique is a statistical strategy that facilitates the systematic and efficient evaluation of numerous experimental variables. The proposed method involved varying seven input factors, including positive electrode thickness, positive electrode material, positive electrode active material volume fraction, negative electrode active material volume fraction, separator thickness, positive current collector thickness, and negative current collector thickness. Three levels were assigned to each control factor to identify the optimal conditions and maximize the average electric power during charging. Moreover, a variance assessment analysis was conducted to validate the results obtained from the Taguchi analysis. The results revealed that the Taguchi method was an eff ective approach for optimizing the average electric power during the charging of lithium-ion batteries. This indicates that the positive electrode material, followed by the separator thickness and the negative electrode active material volume fraction, was key factors significantly infl uencing the average electric power during the charging of lithium-ion batteries response. The identification of optimal conditions resulted in the improved performance of lithium-ion batteries, extending their potential in various applications. Particularly, lithium-ion batteries with average electric power of 16 W and 17 W during charging were designed and simulated in the range of 0-12000 s using COMSOL Multiphysics software. This study efficiently employs the Taguchi optimization technique to develop lithium-ion batteries capable of storing a predetermined average electric power during the charging phase. Therefore, this method enables the battery to achieve complete charging within a specific timeframe tailored to a specificapplication. The implementation of this method can save costs, time, and materials compared with other alternative methods, such as the trial-and-error approach.

Identification of Key Links in Electric Power Operation Based-Spatiotemporal Mixing Convolution Neural Network

As the scale of the power system continues to expand,the environment for power operations becomes more and more complex.Existing risk management and control methods for power operations can only set the same risk detection standard and conduct the risk detection for any scenario indiscriminately.Therefore,more reliable and accurate security control methods are urgently needed.In order to improve the accuracy and reliability of the operation risk management and control method,this paper proposes a method for identifying the key links in the whole process of electric power operation based on the spatiotemporal hybrid convolutional neural network.To provide early warning and control of targeted risks,first,the video stream is framed adaptively according to the pixel changes in the video stream.Then,the optimized MobileNet is used to extract the feature map of the video stream,which contains both time-series and static spatial scene information.The feature maps are combined and non-linearly mapped to realize the identification of dynamic operating scenes.Finally,training samples and test samples are produced by using the whole process image of a power company in Xinjiang as a case study,and the proposed algorithm is compared with the unimproved MobileNet.The experimental results demonstrated that the method proposed in this paper can accurately identify the type and start and end time of each operation link in the whole process of electric power operation,and has good real-time performance.The average accuracy of the algorithm can reach 87.8%,and the frame rate is 61 frames/s,which is of great significance for improving the reliability and accuracy of security control methods.

NOVEL AIRCRAFT ELECTRICAL POWER DISTRIBUTION SYSTEM BASED ON DISTRIBUTED COMPUTER

As a matured technique used in many fields,the distributed computer system is still a new management method for the aeronautical electrical power distribution system in our country. In this paper, a novel aircraft electrical power distribution system based on the distributed computer system is proposed. The principles, features and structure of the aircraft electrical power distribution system and the distributed computer system named electrical load management system (ELMS) are studied. The ELMS composed of four electrical load management centers (ELMCs) and two power source processors (PSPs) operates in the 1553B buses. Principles of the ELMCs and the PSPs are introduced. With the application of the distributed computer system, the aircraft electrical power distribution system is simple, adaptable and flexible.

PARAMETER OPTIMIZATION OF ELECTRIC POWER STEERING INTEGRATED WITH ACTIVE FRONT STEERING FUNCTION

The dynanaic model of a novel electric power steering（EPS） system integrated with active front steer- ing function and the three-freedom steering model are built. Based on these models, the concepts and the quanti- tative expressions of road feel, sensitivity, and operation stability of the steering are introduced. Then, according to constrained optimization features of multi-variable function, a genetic algorithm is designed. Making the road feel of the steering as optimization objective, and operation stability and sensitivity of the steering as constraints, the system parameters are optimized by the genetic and the coordinate rotation algorithms. Simulation results show that the optimization of the novel EPS system by the genetic algorithm can effectively improve the road feel, thus providing a theoretical basis for the design and optimization of the novel EPS system.

Integrated Automation of Power Plant Electrical System

Aiming at the comparatively laggard level of power plant electrical system automation, this paper analyzes the feasibility,necessity and some key points of the application of integrated automation technology to power plant electrical system. New idea using fieldbus control system technology is presented. This paper also gives the outline and detailed schemes.

The Research and Application of the Anti-Interference Techniques of Electronic Device in Power System

This paper presents the study and application of the electronic device anti-interference techniques underhigh voltage and/or heavy current electro-magnetic circumstance in power system.[

POWER GENERATION POTENTIAL OF BIPV APPLICATION IN CHINA

This paper discusses the potential and prospect of building-integrated photovoltaics (BIPV) for solar electrical power generation in China.The BIPV technology has been identified as the most economical renewable energy resource to contribute to world electrical energy demand for protecting environment from reduced fossil fuel consumption.The available solar energy resource of 14 cities and the potential power generation from PV claddings in buildings in China were estimated.The economical analysis of BIPV application is discussed.It is found that the potential is significant and the government should play an important role in its development.

Technical Efficiency Analysis of Electric Power Industry with Stochastic Frontier Model

A kind of algorithm was provided to resolve the calculating problem of stochastic frontier model and applied to electric power industry.By Matlab,maximum likelihood estimation is adopted to evaluate σ and λ of stochastic frontier model in this paper, then the technical efficiency of electric power companies is calculated. The calculated and analyzed results reflect the situation of the management of electric power industry on the whole,that is ,the electric power companies with high technical efficiency are those which have developed their modern enterprise system successfully.

Design and Application of a Novel Wire Stripper

With the rapid development of the power industry,the work of the power electrician is becoming increasingly heavy,and the demand for improving work efficiency and reducing work intensity is becoming increasingly prominent.As one of the common tools of electric power,the design and application of wire stripper has an important influence on the efficiency and safety of electric power.This paper briefly analyzes the design and application of ceramic wire for electric power and electricians to provide a reference for the development of related fields.

Key Technical Problems to be Solved in theCurrent Power Industy Development——Excerpted from the speech on the Seminar on Analysis Forecast of Economic Situation and Enterprise Reform

This paper briefs the development policies and focal construction points of powerindustry in China in 10th Five-year Plan period, and in accordance with the developmentaltrends of international power technology, puts forward the key technological problems tobe studies in China power industry currently.[

Tracking Performance of Electric Power Steering System Based on the Mixed H_2/H_∞ Strategy

The tracking performance of motor current is an important factor that affects the assistance torque of electric power steering （EPS） system. Bad tracking performance will cause assistant torque delay, and make road feeling bad, and is influenced by the input steering torque and system measuring noise. However the existing methods have some shortages on system＇s robust dynamic performance and robust stability. The mixed H2/H∞ strategy for recirculating ball-type EPS system in a pure electric bus is proposed, and vehicle dynamic model of the system is established. Due to the existence of system model uncertainty, disturbance signals, sensor noises and the demand of system dynamic performance, the indexes of robust performance and road feeling for drivers are defined as the appraisal control objectives. The H∞ method is introduced to design the H∞ controller, and the H2 method is applied to optimize the H∞ controller, thus the mixed H2/H∞ controller is designed. The response of EPS system to the motor current command with amplitude of 20 A, the road disturbance with amplitude of 500 N and the sensor random noise with the amplitude of 1 A is simulated. The simulation results show that the recirculating ball-type EPS system with the mixed H2/H∞ controller can attenuate the random noises and disturbances and track the boost curve well, so the mixed H2/H∞ controller can improve the system＇s robust performance and dynamic performance. For the purpose of verifying the performance of the designed control strategy, the motor current tracking performance ground tests are conducted with step response input of the steering wheel, double-lane steering test and lemniscate steering test, respectively. The tests show that the mixed H2/H∞ controller for the recirculating ball-type EPS system of pure electric bus is feasible. The designed controller can solve the robust performance and robust stability of the system, thus improve the tracking performance of the EPS system and provide satisfied road feeling for the drivers.

H∞ control of novel active steering integrated with electric power steering function

Based on the traditional active steering system, a novel active steering system integrated with electric power steering function was introduced, which can achieve the functions of both active steering and electric power steering. In view of the interference from road random signal and sensor noise in the novel active steering system, the H∞ control model of the novel active steering system was built. With satisfying steering feel, good robust performance and steering stability being the control objectives, the H∞ controller for the novel active front steering (AFS) system was designed. The simulation results show that the novel AFS system with H∞ control strategy can attenuate the road interference quickly, and there is no resonance peak in the bode diagram. It can make the driver obtain more useful information in the low frequency range, and attenuate the road interference better in the high frequency range, thus the driver can get more satisfying road feeling. Therefore, the designed H∞ controller can synthesize the advantages of both robust performance and robust stability, and has certain contribution to the design of novel AFS system.

Integration optimization of novel electric power steering system based on quality engineering theory

The dynamic model of a novel electric power steering （EPS） system integrated with active front steering function （the novel EPS system） is built. The concepts and quantitative expressions of the steering road feel, steering sensibility, and steering operation stability are introduced. Based on quality engineering theory, the optimization algorithm is proposed by integrating the Monte Carlo descriptive sampling, elitist non-dominated sorting genetic algorithm （NSGA-II） and 6-sigma design method. With the steering road feel and the steering portability as optimization targets, the system parameters are optimized by the proposed optimization algorithm. The simulation results show that the system optimized based on quality engineering theory can improve the steering road feel, guarantee steering stability and steering portability and thus provide a theoretical basis for the design and optimization of the novel electric power steering system.

Distributed Secondary Control and Optimal Power Sharing in Microgrids

We address the control problem of microgrids and present a fully distributed control system which consists of primary controller, secondary controller, and optimal active power sharing controller. Different from the existing control structure in microgrids, all these controllers are implemented as local controllers at each distributed generator. Thus, the requirement for a central controller is obviated. The performance analysis of the proposed control systems is provided, and the finite-time convergence properties for distributed secondary frequency and voltage controllers are achieved. Moreover, the distributed control system possesses the optimal active power sharing property. In the end, a microgrid test system is investigated to validate the effectiveness of the proposed control strategies. © 2014 Chinese Association of Automation.

Estimate of China's energy carbon emissions peak and analysis on electric power carbon emissions

China＇s energy carbon emissions are projected to peak in 2030 with approximately 110% of its 2020 level under the following conditions： 1） China＇s gross primary energy consumption is 5 Gtce in 2020 and 6 Gtce in 2030; 2） coal＇s share of the energy consumption is 61% in 2020 and 55% in 2030; 3） non-fossil energy＇s share increases from 15% in 2020 to 20% in 2030; 4） through 2030, China＇s GDP grows at an average annual rate of 6%; 5） the annual energy consumption elasticity coefficient is 0.30 in average; and 6） the annual growth rate of energy consumption steadily reduces to within 1%. China＇s electricity generating capacity would be 1,990 GW, with 8,600 TW h of power generation output in 2020. Of that output 66% would be from coal, 5% from gas, and 29% from non-fossil energy. By 2030, electricity generating capacity would reach 3,170 GW with 11,900 TW h of power generation output. Of that output, 56% would be from coal, 6% from gas, and 37% from non-fossil energy. From 2020 to 2030, CO2 emissions from electric power would relatively fall by 0.2 Gt due to lower coal consumption, and rela- tively fall by nearly 0.3 Gt with the installation of more coal-fired cogeneration units. During 2020--2030, the portion of carbon emissions from electric power in China＇s energy consumption is projected to increase by 3.4 percentage points. Although the carbon emissions from electric power would keep increasing to 118% of the 2020 level in 2030, the electric power industry would continue to play a decisive role in achieving the goal of increase in non-fossil energy use. This study proposes countermeasures and recommendations to control carbon emissions peak, including energy system optimization, green-coal-fired electricity generation, and demand side management.

Distributed Model Predictive Load Frequency Control of Multi-area Power System with DFIGs

Reliable load frequency control LFC is crucial to the operation and design of modern electric power systems. Considering the LFC problem of a four-Area interconnected power system with wind turbines, this paper presents a distributed model predictive control DMPC based on coordination scheme. The proposed algorithm solves a series of local optimization problems to minimize a performance objective for each control area. The generation rate constraints GRCs, load disturbance changes, and the wind speed constraints are considered. Furthermore, the DMPC algorithm may reduce the impact of the randomness and intermittence of wind turbine effectively. A performance comparison between the proposed controller with and without the participation of the wind turbines is carried out. Analysis and simulation results show possible improvements on closed-loop performance, and computational burden with the physical constraints. © 2014 Chinese Association of Automation.

Study on Transformer Magnetic Biasing Control Method for AC Power Supplies

This paper presents a novel transformer magnetic biasing control method for high-power high-performance AC power supplies. Serious consequences due to magnetic biasing and several methods to overcome magnetic biasing are first discussed. The causes of the transformer magnetic biasing are then analyzed in detail. The proposed method is based on a high-pass filter inserted in the forward path and the feedforward control. Without testing magnetic biasing of transformer, this method can eliminate magnetic biasing of transformer completely in real-time waveform feedback control systems though the zero error of the Hall effect sensors varies with time and temperature. The method has already been employed in a 90KVA AC power supply. It is shown that it offers improved performance over existing ones. In this method, no sensors are used such that the zero error of the Hall effect sensors has not any influence on the system. It is simple to design and implement. Furthermore, the method is suitable for various power applications.

Security Risk Assessment of Cyber Physical Power System Based on Rough Set and Gene Expression Programming

Risk assessment is essential for the safe and reliable operation of cyber physical power system. Traditional security risk assessment methods do not take integration of cyber system and physical system of power grid into account. In order to solve this problem, security risk assessment algorithm of cyber physical power system based on rough set and gene expression programming is proposed. Firstly, fast attribution reduction based on binary search algorithm is presented. Secondly, security risk assessment function for cyber physical power system is mined based on gene expression programming. Lastly, security risk levels of cyber physical power system are predicted and analyzed by the above function model. Experimental results show that security risk assessment function model based on the proposed algorithm has high efficiency of function mining, accuracy of security risk level prediction and strong practicality. © 2014 Chinese Association of Automation.