Electric Operation Research Articles

Work Domain Analysis of Electric Transmission Networks and Operation

Work Domain Analysis of Electric Transmission Networks and Operation

Renewable Energy Use for Buildings Decarbonization Causes Inequity in Consumers? Comparative Analysis of Spain, Mexico, and Colombia

Building decarbonization strategy with Distributed renewable energy sources (DRES) is applied and extended worldwide for its climate change mitigation benefits, however, it generates debate regarding equity in sharing electric system operation costs. To analyze DRES effects on equity, it is conducted a case study, in which same residential consumer is evaluated in three different markets (Spain, Mexico, Colombia). We analyze not only electrical system technical variables, but we also include society’s economic, social, technological, and environmental characteristics. Next, energy, economic, and environmental benefits are obtained in each the three case studies, analyzing the impact of using DERS on equity to recover electric system operating costs. We also evaluate whether tariff mechanisms are equitable to motivate all consumers participation, as well as whether all consumers have equal opportunity for using DERS. We conclude that tariff mechanisms in Mexico and Colombia lead to inequity to recover market operating costs, favoring large consumers with high incomes. Furthermore, tariff mechanisms discourage the use of DERS by small and medium consumers due to economic, social, and technological aspects. In Spain, inequity arises due to increased difficulty for some consumers to use DERS, i.e., consumers in apartment buildings.

Electric flight operations for interisland mobility

Several studies have shown that flying electric between the so-called ABC-islands in the Caribbean (i.e., Aruba, Bonaire and Curaçao) is feasible with the upcoming first generation of battery-electric aircraft. This paper presents a real-world case study that deals with the technical and operational characteristics of electric flight in that region. With that purpose, the Aruba Airport Authority (AAA) commissioned this investigation, which involved numerous local stakeholders, such as airlines, energy providers and navigation services. This study involves two commuter electric aircraft under development, aiming to investigate how they fit in the current operational scheme of three local airlines and three conventional aircraft types in terms of technology, capacity, schedule, performance, CO2 emissions and fuel costs. Conclusions indicate that a transition to batter-electric aircraft is feasible with regards to the aforementioned criteria and with the current technology and energy density of batteries.

Reducing the effect of engine failure on the aerodynamic performance of the light transport aircraft model

Recently, aircraft engine manufacturers have shown increased interest in developing hybrid powerplants, which are a combination of gas turbine engines (GTE) with electric motor-generators. The use of the hybrid powerplant makes it possible to increase the fuel efficiency of an airplane, as well as to create new configurations with improved aerodynamic and thrust characteristics. The fuel efficiency improvement is achieved as a result of optimizing the powerplant operation mode to meet the cruising flight requirements, compensating insufficient power during the takeoff and go-around procedures by activating battery-powered electric motors. The creation of new configurations with improved performance can be ensured due to the synergetic effect of the propeller-airframe interaction. Successful flight tests of the hybrid powerplant prototypes in light aircraft configurations allow us to rely on their possible application in the future regarding the projects of new propeller-driven aircraft. The potential benefits of using new powerplants on local airlines can lead to both fuel savings and carbon emission reduction. Short-term maintaining a safe flight mode is also practical in case of one engine failure when using multiple power sources. The power, generated by an electric generator connected to the running engine, can be used both for the electric motor drive of the tip propellers and for rotating the thrust producer of the failed engine. The paper presents the study results of the critical engine failure effect on the aerodynamic performance of the light transport aircraft model obtained as under available electrical transmission as under non-available one between a running and a failed engine. Experimental studies were carried out in a low-speed wind tunnel T-102 TsAGI. The simulation of the electric transmission operation was carried out by setting the operation mode of two power-plant simulators corresponding to the half value of the load factor of one engine propeller Bo in the take-off mode.

A comprehensive survey of low‐carbon planning and operation of electricity, hydrogen fuel, and transportation networks

AbstractThe trend of global energy systems towards carbon neutrality has led to an escalating interdependency between electricity, hydrogen fuel, and transportation networks. However, the means of surmounting the many challenges confronting the optimal coupling and coordination of electric power, hydrogen fuel, and transportation systems are not sufficiently understood to guide modern infrastructure planning operations. The present work addresses this issue by surveying the extant literature, relevant government policies, and future development trends to evaluate the present state of technology available for coordinating these systems and then determine the most pressing issues that remain to be addressed to facilitate future trends. On the one hand, the users of transportation networks represent flexible consumers of electric power and hydrogen fuel for those connected via devices such as electric vehicles and hydrogen fuel cell vehicles through charging stations and hydrogen refuelling stations. On the other hand, power grids can mitigate the negative effect of random charging behaviours on grid security through time‐of‐use electricity pricing, while excess renewable energy outputs can be applied to generate hydrogen fuel. The findings of this overview offer support for infrastructure planning and operations. Finally, the most urgent issues requiring further research are summarised.

Influence of Pressure, Temperature and Discharge Rate on the Electrical Performances of a Commercial Pouch Li-Ion Battery

In this study, the performances of a pouch Li-ion battery (LIB) with respect to temperature, pressure and discharge-rate variation are measured. A sensitivity study has been conducted with three temperatures (5 °C, 25 °C, 45 °C), four pressures (0.2 MPa, 0.5 MPa, 0.8 MPa, 1.2 MPa) and three electrical discharge rates (0.5 C, 1.5 C, 3.0 C). Electrochemical processes and overall efficiency are significantly affected by temperature and pressure, influencing capacity and charge–discharge rates. In previous studies, temperature and pressure were not controlled simultaneously due to technological limitations. A novel test bench was developed to investigate these influences by controlling the surface temperature and mechanical pressure on a pouch LIB during electrical charging and discharging. This test rig permits an accurate assessment of mechanical, thermal and electrical parameters, while decoupling thermal and mechanical influences during electrical operation. The results of the study confirm what has been found in the literature: an increase in pressure leads to a decrease in performance, while an increase in temperature leads to an increase in performance. However, the extent to which the pressure impacts performance is determined by the temperature and the applied electrical discharge rate. At 5 °C and 0.5 C, an increase in pressure from 0.2 MPa to 1.2 MPa results in a 5.84% decrease in discharged capacity. At 45 °C the discharge capacity decreases by 2.17%. Regarding the impact of the temperature, at discharge rate of 0.5 C, with an applied pressure of 0.2 MPa, an increase in temperature from 25 °C to 45 °C results in an increase of 4.27% in discharged capacity. The impact on performance varies significantly at different C-rates. Under the same pressure (0.2 MPa) and temperature variation (from 25 °C to 45 °C), increasing the electrical discharge rate to 1.5 C results in a 43.04% increase in discharged capacity. The interplay between temperature, pressure and C-rate has a significant, non-linear impact on performance. This suggests that the characterisation of an LIB would require the active control of both temperature and pressure during electrical operation.

Electric Aircraft Operations: An Interisland Mobility Case Study

This study focuses on the feasibility of electric aircraft operations between the Caribbean islands of Aruba, Bonaire, and Curaçao. It explores the technical characteristics of two different future electric aircraft types (i.e., Alice and ES-19) and compares their operational requirements with those of three conventional types currently in operation in the region. Flight operations are investigated from the standpoint of battery performance, capacity, and consumption, while their operational viability is verified. In addition, the CO2 emissions of electric operations are calculated based on the present energy mix, revealing moderate improvements. The payload and capacity are also studied, revealing a feasible transition to the new types. The impact of the local climate is discussed for several critical components, while the required legislation for safe operations is explored. Moreover, the maintenance requirements and costs of electric aircraft are explored per component, while charging infrastructure in the hub airport of Aruba is proposed and discussed. Overall, this study offers a thorough overview of the opportunities and challenges that electric aircraft operations can offer within the context of this specific islandic topology.

Thin-film transistor for temporal self-adaptive reservoir computing with closed-loop architecture.

Reservoir computing is a powerful neural network-based computing paradigm for spatiotemporal signal processing. Recently, physical reservoirs have been explored based on various electronic devices with outstanding efficiency. However, the inflexible temporal dynamics of these reservoirs have posed fundamental restrictions in processing spatiotemporal signals with various timescales. Here, we fabricated thin-film transistors with controllable temporal dynamics, which can be easily tuned with electrical operation signals and showed excellent cycle-to-cycle uniformity. Based on this, we constructed a temporal adaptive reservoir capable of extracting temporal information of multiple timescales, thereby achieving improved accuracy in the human-activity-recognition task. Moreover, by leveraging the former computing output to modify the hyperparameters, we constructed a closed-loop architecture that equips the reservoir computing system with temporal self-adaptability according to the current input. The adaptability is demonstrated by accurate real-time recognition of objects moving at diverse speed levels. This work provides an approach for reservoir computing systems to achieve real-time processing of spatiotemporal signals with compound temporal characteristics.

Research on electric vehicle load forecasting considering regional special event characteristics

With the rise of electric vehicles and fast charging technology, electric vehicle load forecasting has become a concern for electric vehicle charging station planners and operators. Due to the non-stationary nature of traffic flow and the instability of the charging process, it is difficult to accurately predict the charging load of electric vehicles, especially in sudden major events. In this article, We proposes a high-precision EV charging load forecasting model based on mRMR and IPSO-LSTM, which can quickly respond to the epidemic (or similar emergencies). Firstly, the missing data in the original EV charging load data are supplemented, and the abnormal data are corrected. Based on this, a factor set is established, which included five epidemic factors, including new confirmed cases, the number of moderate risk areas, the number of high risk areas, epidemic situation and epidemic prevention policies of the city, and other factors such as temperature. Secondly, the processed load data and other data in the influencing factor set are normalized, and the typical characteristic curve is established for personalized processing of the relevant data of epidemic factors, so as to improve the sensitivity of load response to epidemic changes and the ability to capture special data (peak and valley values and turning points of load). Then the maximum relevant minimum redundancy (mRMR) is used to select the optimal feature set from the set of influencing factors. Then, the processed load data and its corresponding optimal selection are input into the IPSO-LSTM model to obtain the final prediction result. Finally, taking the relevant data of EV charging load in a city in China from November 2021 to April 2022 (the city experienced two local epidemics in December 2021 and March 2022 respectively) as an example, the model is evaluated and compared with other models under the forecast period of 1 h. Meanwhile, the performance of the model under different foresight periods (2 h, 4 h, 6 h) is compared and analyzed. The results show that the model has good stability and representativeness, and can be used for EV charging load prediction under the COVID-19 pandemic.

Identifying topology of distribution substation in power Internet of Things using dynamic voltage load fluctuation flow analysis.

At present, the reconfiguration, maintenance, and review of power lines play a pivotal role in maintaining the stability of electrical grid operations and ensuring the accuracy of electrical energy measurements. These essential tasks not only guarantee the uninterrupted functioning of the power system, thereby improving the reliability of the electricity supply but also facilitate precise electricity consumption measurement. In view of these considerations, this article endeavors to address the challenges posed by power line restructuring, maintenance, and inspections on the stability of power grid operations and the accuracy of energy metering. To accomplish this goal, this article introduces an enhanced methodology based on the hidden Markov model (HMM) for identifying the topology of distribution substations. This approach involves a thorough analysis of the characteristic topology structures found in low-voltage distribution network (LVDN) substations. A topology identification model is also developed for LVDN substations by leveraging time series data of electricity consumption measurements and adhering to the principles of energy conservation. The HMM is employed to streamline the dimensionality of the electricity consumption data matrix, thereby transforming the topology identification challenge of LVDN substations into a solvable convex optimization problem. Experimental results substantiate the effectiveness of the proposed model, with convergence to minimal error achieved after a mere 50 iterations for long time series data. Notably, the method attains an impressive discriminative accuracy of 0.9 while incurring only a modest increase in computational time, requiring a mere 35.1 milliseconds. By comparison, the full-day data analysis method exhibits the shortest computational time at 16.1 milliseconds but falls short of achieving the desired accuracy level of 0.9. Meanwhile, the sliding time window analysis method achieves the highest accuracy of 0.95 but at the cost of a 50-fold increase in computational time compared to the proposed method. Furthermore, the algorithm reported here excels in terms of energy efficiency (0.89) and load balancing (0.85). In summary, the proposed methodology outperforms alternative approaches across a spectrum of performance metrics. This article delivers valuable insights to the industry by fortifying the stability of power grid operations and elevating the precision of energy metering. The proposed approach serves as an effective solution to the challenges entailed by power line restructuring, maintenance, and inspections.

Research on vision control methods based on multi-sensor fusion

This paper focuses on the application scenarios of electric power live line working robots, addressing tasks such as live wire stripping and live wire connection/disconnection. It utilizes Mixed Reality (MR) technology for rapid environment modeling and visual signal acquisition. Through the research on robot contact force sensing, real-time force feedback, and obstacle avoidance through the fusion of robot motion paths and environmental data, it establishes a novel electric power live line working robot system centered around dexterous dual arms at the operation end, force feedback teleoperation controllers, multi-sensor fusion acquisition systems, and robot motion planning and control technology. Through prototyping, a demonstration application is realized, showcasing a semi-autonomous electric power live line working robot system that employs remote operation combined with sensor-based MR for task execution. This teleoperation and Mixed Reality-based semi-autonomous electrified operation approach is poised to play a significant role in advancing and demonstrating the use of robots in the field of electrical grid operations.

Towards fully electrically controlled domain-wall logic

Utilizing magnetic tunnel junctions (MTJs) for write/read and fast spin-orbit-torque (SOT)-driven domain-wall (DW) motion for propagation, enables non-volatile logic and majority operations, representing a breakthrough in the implementation of nanoscale DW logic devices. Recently, current-driven DW logic gates have been demonstrated via magnetic imaging, where the Dzyaloshinskii-Moriya interaction (DMI) induces chiral coupling between perpendicular magnetic anisotropy (PMA) regions via an in-plane (IP) oriented region. However, full electrical operation of nanoscale DW logic requires electrical write/read operations and a method to pattern PMA and IP regions compatible with the fabrication of PMA MTJs. Here, we study the use of a Hybrid Free Layer (HFL) concept to combine an MTJ stack with DW motion materials, and He+ ion irradiation to convert the stack from PMA to IP. First, we investigate the free layer thickness dependence of 100-nm diameter HFL-MTJ devices and find an optimal CoFeB thickness, from 7 to 10 Å, providing high tunneling magnetoresistance (TMR) readout and efficient spin-transfer torque (STT) writing. We then show that high DMI materials, like Pt/Co, can be integrated into an MTJ stack via interlayer exchange coupling with the CoFeB free layer. In this design, DMI values suitable for SOT-driven DW motion are measured by asymmetric bubble expansion. Finally, we demonstrate that He+ irradiation reliably converts the coupled free layers from PMA to IP. These findings offer a path toward the integration of fully electrically controlled DW logic circuits.

Arrangement for reliable power supply to emergency commercial customers with techno-economic performance improvement of PV enhanced distribution systems

Accelerating engagement of distributed energy resources unleashed the dependency on traditional electric power generation. To reduce the craving for traditional power dependency and unplanned outages the power distribution sectors are gradually adopting cleaner and reliable electrification. However, the unscheduled and unorganized engagement of stochastic generation from renewable energy sources (RES) makes the distribution system operation more vulnerable. For reliable and continuous power supply with RES, scheduled operation of BSSs and power capacitor (CAP) units can be integrated to provide emergency power supply support to consumers. In this paper, the supply of continuous and reliable power to commercial and emergency customers has been investigated subject to complete reliability (CR). The benefit-to-cost ratio (BCR) has been maximized to give reliable power to consumers by the minimum investment cost by utility, which can benefit both electric customers and power distribution operators in a single platform. The maximization of BCR has been evaluated by optimal S-CDS of the BSSs and S-S of CAP units’ operation through the PSO technique in the considered 28-bus active distribution network in different seasons. The techno-economic benefit of integrating only BSSs and BSSs with CAP units in the prospective locations has been analyzed. The improvement in battery life and decrease in SAENS, SADPL, and SADD have been obtained, which shows the efficacy of the proposed work.

Metoda Sederhana untuk Memperbaiki Kinerja Motor Listrik 3 Fasa berdasarkan Insulation Resistance Test

In the electrical energy conversion laboratory, the stable operation of the induction motor is one of the most important factors. Failure of induction motor operation can be fatal in research activities in energy conversion laboratories. Prevention is needed so that the performance of induction motors remains optimal. this paper was created as an alternative for laboratory users of electrical energy conversion in maintaining the performance of induction motors. Based on a survey conducted by the Institute of Electrical and Electronics Engineers (IEEE), the main cause of electric motor operation failure is generally caused by insulation failure, so electric motor testing is generally dominated by insulation testing. Many insulation testing methods such as Insulation Resistance (IR) testing, Polarization Index (PI), Delta tangent, and other tests. In this paper, IR-based testing is proposed, because it is relatively cheap and easy to implement. The IR testing process is carried out using direct voltage from the Insulation Tester to the sample to be tested using the IEEE 43TM-2013 Standard. The test results show the IR value of the sample motor is good. This condition is categorized as safe to operate, so research activities that use induction motors can run well and safely.

Bibliometric and visual analysis of neurological damage caused by electrical welding operations

Objective: To analyze and summarize the trends and hot spots in the field of neurological damage caused by electric welding operations, and to provide ideas for new researches by searching the domestic and international literature. Methods: In December 2022, using Web of Science Citation Index (Web of Science), China Journal Full-Text Database (CNKI) and Wanfang Database as search databases, literature search was conducted on the Chinese and English search terms related to eletrical welding operations and neurological damage. The bibliometric analysis software VOSviewer 1.6.18 and CiteSpace 6.1.6 were used to visualize the publication year, publication quantity, country, research institution and key words of the literature. Results: A total of 309 articles (112 in Chinese and 197 in English) were included in this study. The first domestic and international papers were published in 1976 and 1994 respectively, and the number of papers reached the peak in 2006 and 2018, and then showed a downward trend to varying degrees. In China, Shandong First Medical University (including Shandong Institute of Occupational Health and Occupational Disease Prevention and Shandong Academy of Medical Sciences) and Wuhan University of Science and Technology had the largest number of publications. The 309 articles were from 52 Chinese journals and 86 English journals. The co-occurrence analysis of key words showed that the domestic research mainly focused on eletrical welding operation, welding workers, neurobehavioral function and manganese, and the nervous system damage caused by manganese in welding smoke was the field of international attention. Long term exposure, risk, and performance were key buzzwords in the field. Conclusion: The research focus in the field of nervous system damage caused by electric welding operation has an obvious trend of time evolution, gradually transiting from clinical manifestations to its toxic mechanism and early biomarkers.

State of charge estimation for electric vehicles using random forest

This paper introduces an innovative approach to addressing a critical challenge in the electric vehicle (EV) industry—the accurate estimation of the state of charge (SOC) of EV batteries under real-world operating conditions. The electric mobility landscape is rapidly evolving, demanding more precise SOC estimation methods to improve range prediction accuracy and battery management. This study applies a Random Forest (RF) machine learning algorithm to improve SOC estimation. Traditionally, SOC estimation has posed a formidable challenge, particularly in capturing the complex dependencies between various parameters and SOC values during dynamic driving conditions. Previous methods, including the Extreme Learning Machine (ELM), have exhibited limitations in providing the accuracy and robustness required for practical EV applications. In contrast, this research introduces the RF model, for SOC estimation approach that excels in real-world scenarios. By leveraging decision trees and ensemble learning, the RF model forms resilient relationships between input parameters, such as voltage, current, ambient temperature, and battery temperatures, and SOC values. This unique approach empowers the model to deliver precise and consistent SOC estimates across diverse driving conditions. Comprehensive comparative analyses showcase the superiority of the RF over ELM. The RF model not only outperforms in accuracy but also demonstrates exceptional robustness and reliability, addressing the pressing needs of the EV industry. The results of this study not only underscore the potential of RF in advancing electric mobility but also suggest a promising integration of the SOC estimation approach into the battery management system of BMW i3. This integration holds the key to more efficient and dependable electric vehicle operations, marking a significant milestone in the ongoing evolution of EV technology. Importantly, the RF model demonstrates a lower Root Mean Squared Error (RMSE) of 5.902,8% compared to 6.312,7% for ELM, and a lower Mean Absolute Error (MAE) of 4.432,1% versus 5.111,2% for ELM across rigorous k-fold cross-validation testing, reaffirming its superiority in quantitative SOC estimation.

Broken symmetry and fractionalized flux strings in a staggered U(1) pure gauge theory

Inspired by self-adjoint extensions of the electric field operator in the Hamiltonian formalism, we extend the Wilsonian framework of Abelian lattice gauge theory by introducing a modified action parametrized by an angle α, where the ordinary Wilson theory corresponds to α=0. Choosing instead α=π (the “staggered” case) gives the only other theory in the family which preserves all symmetries of the original model at the microscopic level. We study the case of 3D U(1) pure gauge theory, simulating the staggered case of this model numerically in its dual formulation. We find evidence of a continuum limit with a spontaneously broken Z2 single-site translational symmetry, in contrast to the ordinary theory. Moreover, the confining string fractionalizes into multiple strands which separate spatial regions in distinct ground states of the broken symmetry. Published by the American Physical Society 2024

Towards Efficient Battery Electric Bus Operations: A Novel Energy Forecasting Framework

As the adoption of battery electric buses (BEBs) in public transportation systems grows, the need for precise energy consumption forecasting becomes increasingly important. Accurate predictions are essential for optimizing routes, charging schedules, and ensuring adequate operational range. This paper introduces an innovative forecasting methodology that combines a propulsion and auxiliary energy model with a novel concept, the environment generator. This approach addresses the primary challenge in electric bus energy forecasting: estimating future environmental conditions, such as weather, passenger load, and traffic patterns, which significantly impact energy demand. The environment generator plays a crucial role by providing the energy models with realistic input data. This study validates various models with different levels of model complexity against real-world operational data from a case study of over one year with 16 electric buses in Göttingen, Germany. Our analysis thoroughly examines influencing factors on energy consumption, like altitude, temperature, passenger load, and driving patterns. In order to comprehensively understand energy demands under varying operational conditions, the methodology integrates data-driven models and physical simulations into a modular and highly accurate energy predictor. The results demonstrate the effectiveness of our approach in providing more accurate energy consumption forecasts, which is essential for efficient electric bus fleet management. This research contributes to the growing body of knowledge in electric vehicle energy prediction and offers practical insights for transit authorities and operators in optimizing electric bus operations.

Emission characteristics and removal of heavy metals in flue gas: a case study in waste incineration and coal-fired power plants.

Heavy metal pollutants such as Hg, As, Pb, Cr, and Cd emitted from coal and waste combustion have received widespread attention. In this study, we systematically investigated the emission characteristics of heavy metals in waste incineration and coal-fired flue gases, focused on testing the removal effect of self-made cold electrode electrostatic precipitator (CE-ESP) on heavy metals in flue gas, and made a comparative analysis with the existing air pollution control devices (APCDs). Test results from waste incineration power plant showed that each APCD showed a certain effect on the removal of heavy metals in condensable particulate matter (CPM), with an average removal efficiency of bag filter was 86%, but its effect on Hg removal was slightly worse. Under the coupled field with electrified cold electrode plate operation mode, the average removal efficiency of CE-ESP on heavy metals in CPM was as high as 93%, including 76% for Hg. The removal efficiency of heavy metals (especially Hg) in CPM increased with the increase of flue gas temperature difference between inlet and outlet of CE-ESP. Test results from this coal-fired power plant showed that heavy metals were enriched in fly ash to a higher degree than in slag, the synergistic control of heavy metals in submicron particulate matter by the dust remover was not obvious, and there was a significant correlation between each heavy metal emission factor and its content in coal. Under the temperature field with non-electric cold electrode plate operation mode, the overall effect of CE-ESP on the removal of gaseous heavy metals was better than that of particulate heavy metals. Under the conventional electric field operation mode, CE-ESP was less effective in removing particulate Cr and gaseous Hg0. Under the coupled field with electrified cold electrode plate operation mode, the average removal efficiencies of CE-ESP for particulate and gaseous heavy metals were 82.37% and 76.16%, respectively.

Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology

Abstract This paper builds a power operation target detection model based on the YOLOv4 algorithm in intelligent image recognition, and optimizes the YOLOv4 algorithm by combining with the loss function to improve the accuracy of power target operation detection. The kmeans++ algorithm was used to cluster the electric power operation behaviors to obtain a more accurate electric power operation behavior dataset. Three sets of tests were conducted after the model was constructed, targeting the behavioral set of electric power workers in a certain place and the behavior in VOC format, followed by the multi-target tracking effect test. The analysis based on the obtained data showed that the helmet placement detection confidence, fatigue detection confidence, smoking detection confidence, and fall detection confidence reached 0.97, 0.93, 0.89, and 0.93, respectively. The transmission speed got 53.58 fps, and the recall and precision of the multi-target tracking were also above 93%. The YOLOv4 detection model based on keans++ clustering algorithm can effectively detect and identify the variable power operation behavior images.