An integrated energy service company in an industrial park or commercial building is responsible for managing all energy sources in their local region, including electricity, water, gas, heating, and cooling. To reduc...An integrated energy service company in an industrial park or commercial building is responsible for managing all energy sources in their local region, including electricity, water, gas, heating, and cooling. To reduce energy wastage and increase energy utilization, it is necessary to perform efficiency analyses and diagnoses on integrated energy systems(IESs). However, the integrated energy data necessary for energy efficiency analyses and diagnoses come from a wide variety of instruments, each of which uses different transmission protocols and data formats. This makes it challenging to handle energy-flow data in a unified manner. Thus, we have constructed a unified model for diagnosing energy usage abnormalities in IESs. Using this model, the data are divided into working days and non-working days, and benchmark values are calculated after the data have been weighted to enable unified analysis of several types of energy data. The energy-flow data may then be observed, managed, and compared in all aspects to monitor sudden changes in energy usage and energy wastage. The abnormal data identified and selected by the unified model are then subjected to big-data analysis using technical management tools, enabling the detection of user problems such as abnormalities pertaining to acquisition device, metering, and energy usage. This model facilitates accurate metering of energy data and improves energy efficiency. The study has significant implications in terms of fulfilling the energy saving.展开更多
In the current biomedical data movement, numerous efforts have been made to convert and normalize a large number of traditional structured and unstructured data (e.g., EHRs, reports) to semi-structured data (e.g., RDF...In the current biomedical data movement, numerous efforts have been made to convert and normalize a large number of traditional structured and unstructured data (e.g., EHRs, reports) to semi-structured data (e.g., RDF, OWL). With the increasing number of semi-structured data coming into the biomedical community, data integration and knowledge discovery from heterogeneous domains become important research problem. In the application level, detection of related concepts among medical ontologies is an important goal of life science research. It is more crucial to figure out how different concepts are related within a single ontology or across multiple ontologies by analysing predicates in different knowledge bases. However, the world today is one of information explosion, and it is extremely difficult for biomedical researchers to find existing or potential predicates to perform linking among cross domain concepts without any support from schema pattern analysis. Therefore, there is a need for a mechanism to do predicate oriented pattern analysis to partition heterogeneous ontologies into closer small topics and do query generation to discover cross domain knowledge from each topic. In this paper, we present such a model that predicates oriented pattern analysis based on their close relationship and generates a similarity matrix. Based on this similarity matrix, we apply an innovated unsupervised learning algorithm to partition large data sets into smaller and closer topics and generate meaningful queries to fully discover knowledge over a set of interlinked data sources. We have implemented a prototype system named BmQGen and evaluate the proposed model with colorectal surgical cohort from the Mayo Clinic.展开更多
The phenomenon of electrical potential differences along the plant apoplast has been reported for more than a century. Earlier works of harvesting energy from trees reported nW range of power with a few hundred-mV ope...The phenomenon of electrical potential differences along the plant apoplast has been reported for more than a century. Earlier works of harvesting energy from trees reported nW range of power with a few hundred-mV open circuit voltage and near uA range short circuit current. In this work, we show that if we cut a stem into pieces, each segment would maintain nearly the same open circuit voltage and short circuit current regardless of length. Using a pico-ampere meter, we also found that the living cells in the vascular cambial and secondary xylem and phloem tissues are the source of electricity. They provide a relatively constant voltage and current to external environment for reasons still under investigation. We demonstrate that by cascading separated stems we can accumulate up to 2 V of open circuit voltage. We also demonstrate by connecting them in parallel we can increase the short circuit current.展开更多
A review on thermal power plant automation development in China over 50 years is presented. The level of thermal power automation is introduced, especially for 200 MW and above units which are clarified into three cat...A review on thermal power plant automation development in China over 50 years is presented. The level of thermal power automation is introduced, especially for 200 MW and above units which are clarified into three categories by grade. The conditions, existing problems, relevant solutions and policies are summarized chronologically in aspects of centralized control, automatic regulation and controllability of main and auxiliary units, turbine control system, furnace security protection, and computer application in thermal power plants. This paper also points out the development tendency of thermal power plant automation and concepts of some vocabularies.展开更多
Lung cancer is a leading cause of global mortality rates.Early detection of pulmonary tumors can significantly enhance the survival rate of patients.Recently,various Computer-Aided Diagnostic(CAD)methods have been dev...Lung cancer is a leading cause of global mortality rates.Early detection of pulmonary tumors can significantly enhance the survival rate of patients.Recently,various Computer-Aided Diagnostic(CAD)methods have been developed to enhance the detection of pulmonary nodules with high accuracy.Nevertheless,the existing method-ologies cannot obtain a high level of specificity and sensitivity.The present study introduces a novel model for Lung Cancer Segmentation and Classification(LCSC),which incorporates two improved architectures,namely the improved U-Net architecture and the improved AlexNet architecture.The LCSC model comprises two distinct stages.The first stage involves the utilization of an improved U-Net architecture to segment candidate nodules extracted from the lung lobes.Subsequently,an improved AlexNet architecture is employed to classify lung cancer.During the first stage,the proposed model demonstrates a dice accuracy of 0.855,a precision of 0.933,and a recall of 0.789 for the segmentation of candidate nodules.The suggested improved AlexNet architecture attains 97.06%accuracy,a true positive rate of 96.36%,a true negative rate of 97.77%,a positive predictive value of 97.74%,and a negative predictive value of 96.41%for classifying pulmonary cancer as either benign or malignant.The proposed LCSC model is tested and evaluated employing the publically available dataset furnished by the Lung Image Database Consortium and Image Database Resource Initiative(LIDC-IDRI).This proposed technique exhibits remarkable performance compared to the existing methods by using various evaluation parameters.展开更多
Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive behaviors.Timely and precise ASD detection is crucial,particula...Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive behaviors.Timely and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like Pakistan.This study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local context.The research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate schedulers.In addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the tool.The findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation approach.Specifically,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test images.To validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD detection.This research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.展开更多
Windbelt generators have been proposed as small, green power sources for battery charging applications. Some of the reported results lack detailed information about how key parameters influence the output power of the...Windbelt generators have been proposed as small, green power sources for battery charging applications. Some of the reported results lack detailed information about how key parameters influence the output power of the generator. In this work, we built prototypes with different architectures to study the voltage generation and power delivery as functions of belt tension, length, and electrical load at various wind speeds. We also studied the maximum power delivery conditions before the breakdown of the belt oscillation occurs. Our results are obtained from windbelt generators with two types of architectures： a conventional design with an adjustable belt that uses weight for tension control, and a revised design with a belt oscillation perpendicular to the coil axis. We have concluded that the breakdown of the belt oscillation at lower output resistances is a primary bottleneck that will limit windbelt systems to only very low power applications.展开更多
Distributed generation(DG)systems with renewable energy are often connected to weak grids.However,there may be large background harmonics in weak grids,which can easily cause power quality issues at the point of commo...Distributed generation(DG)systems with renewable energy are often connected to weak grids.However,there may be large background harmonics in weak grids,which can easily cause power quality issues at the point of common coupling(PCC).For this reason,DG-grid interfacing inverters are expected to have the ability to suppress harmonics while achieving power transmission with the grid.To this end,a collaborative control method with feedforward multiple secondorder generalized integrator(FMSOGI)harmonic extraction and harmonic weighting control(HWC)are proposed in this paper to improve voltage quality at PCC.Compared with traditional control methods,the proposed collaborative control is simpler and has better harmonic suppression ability due to direct suppression.On the basis of the proposed collaborative control,system stability is analyzed for DG-grid interfacing inverters to set proper parameters.Finally,simulation and experimental results from Matlab and HIL StarSim,respectively,are presented to verify effectiveness of the proposed control method.展开更多
The complex working environment of distribution networks tends to cause impermanent single-phase-to-ground(SPG)fault,and high-temperature ground fault arc is prone to endanger lives and power equipment,resulting in la...The complex working environment of distribution networks tends to cause impermanent single-phase-to-ground(SPG)fault,and high-temperature ground fault arc is prone to endanger lives and power equipment,resulting in large-scale power outages and fire accidents.Thus,fault arc should be extinguished in time.Meanwhile,stable operation conditions of distribution networks and reliable load power supply should be guaranteed to provide high-quality customer service.This paper proposes an active mitigation strategy for SPG fault,and provide active and reactive power compensation at the same time by utilizing an improved flexible power electronic equipment(FPEE)with dc-link sources.These controls are decoupled from each other,so utilization of FPEE is maximized as much as possible.When a SPG fault occurs in distribution networks,FPEE can output,simultaneously,active power,reactive power,and SPG fault compensation current by controlling output current on the d,q,0 coordinate system,respectively.During normal operation of distribution networks,the FPEE can be used as a virtual synchronous generator to compensate load power and its fluctuation.The proposed simultaneous multi-function can also be applied in other cases.Simulation cases are implemented to verify principles and practicability.展开更多
More electricity utilities will participate in the investment and operation of private distributed generations(DGs)while the local power company is responsible for the reinforcement of lines and DGs,as well.How to ach...More electricity utilities will participate in the investment and operation of private distributed generations(DGs)while the local power company is responsible for the reinforcement of lines and DGs,as well.How to achieve the maximum benefits among various utilities,including the power company,is a task in the expansion planning of distribution networks.To solve the market-oriented planning problem,virtual peer to peer(P2P)trading is integrated and modeled in the new expansion planning of distribution networks.First,virtual market transaction optimization among prosumers is formulated.Second,the distributed regional marginal price(DLMP)is calculated by the optimal operation model,which contributed to the network usage charge(NUC)and then integrated in the expansion planning model.Case studies are performed and indicate the integrated P2P transaction strategy could improve local load consumption,while reducing the load rate of lines,as well as the electricity cost of users.Besides,the total planning cost paid by the power company could be saved via prosumers’investment and P2P transactions and the factors affecting power company’s profit are also classified in multi-investor planning of distribution networks.展开更多
Line-commutated-converter-based high-voltage direct current(LCC-HVDC)represents an important approach for transmitting large-scale integrated renewable power over long distances.However,coordination of various discret...Line-commutated-converter-based high-voltage direct current(LCC-HVDC)represents an important approach for transmitting large-scale integrated renewable power over long distances.However,coordination of various discrete and continuous adjustment devices,as well as the complex automatic voltage control problem bring great challenges for voltage control and var dispatch in converter stations(CSs).Besides,traditional approaches may suffer from frequent filter switching issues or conservativeness.To address these issues,this paper proposes a hierarchical robust voltage dispatching schedule consisting of a day-ahead schedulable period plan and an intraday model predictive control(MPC)-based rolling scheduling,which fully considers coordination of multifarious adjustment equipment with different response-time constants and control characteristics in CSs in multiple time dimensions.This method can implement adaptive adjustment of CS discrete/continuous regulating devices with sufficient dynamic var reserves under CS mutable operational conditions caused by renewable energy fluctuation.The day-ahead schedulable period plan ensures global allocation of discrete equipment action resources.MPC-based intraday rolling dispatch is used to overcome conservativeness of the traditional method and achieve automatic reactive power compensation,as well as voltage control of converter station.In a case study,a modified IEEE 9-bus system with wind farms is used to verify the proposed method.展开更多
Knowledge graph,which is a rapidly developing technology,provides strong support in business and engineering.Knowledge graph plays an important role in recommendations and decision-making,while in the electric power i...Knowledge graph,which is a rapidly developing technology,provides strong support in business and engineering.Knowledge graph plays an important role in recommendations and decision-making,while in the electric power industry,there would be more possibilities for knowledge graph to be utilized.However,as a complex cause-and-effect network,the electric power domain knowledge graph has massive nodes,heterogeneous edges,and sparse structures.Thus,it requires human effort to process data,while quality and accuracy cannot be guaranteed.We propose a novel graph computing-based knowledge reasoning method that takes into account the sparsity of the electric power domain knowledge graph to solve the aforementioned problems and achieve improved accuracy of graph classification and knowledge reasoning tasks.The Haar basis is constructed to realize fast calculation,while the multiscale network structure is introduced to assure classification accuracy and generalization.We evaluate the proposed algorithm on the NCI-1,CEPRI UHVP,and CEPRI EQUIP databases.Simulation results demonstrate its superior performance in terms of accuracy and loss.展开更多
A regional electricity-heating integrated energy system(REH-IES)can make extensive use of renewable energy sources,realize complementary and coordinated operation of multiple energy sources,reduce carbon emissions and...A regional electricity-heating integrated energy system(REH-IES)can make extensive use of renewable energy sources,realize complementary and coordinated operation of multiple energy sources,reduce carbon emissions and promote the development of zero/low carbon systems.This paper proposes a risk-averse stochastic optimal scheduling model for REHIES.An energy flow framework for the REH-IES is proposed considering energy interaction between the electric-heating microgrids(EHMs)and electricity distribution network and the heating network.Then,considering the uncertainties of power output of renewable energy sources,dynamic characteristics of pipelines in the heating network,and thermal inertia of smart buildings,a stochastic optimal scheduling model for the REH-IES is established.Uncertainties of renewable energy sources bring financial risks to optimal scheduling of the REH-IES.Therefore,conditional value-at-risk(CVaR)theory is adopted to measure the risk and to limit the risk within an acceptable range,to achieve minimum expected scheduling cost of the REH-IES.The stochastic programming-based problem is transformed into a second-order cone programming(SOCP)model through secondorder cone relaxation method.Case studies verify the stochastic optimal scheduling model can reduce expected scheduling cost of the REH-IES,promote consumption of renewable energy sources and reduce carbon emissions.展开更多
Accurate topology information is crucial to management and application in an active low-voltage distribution network(LVDN).Existing topology identification(TI)methods mostly lack a systematic framework to obtain preci...Accurate topology information is crucial to management and application in an active low-voltage distribution network(LVDN).Existing topology identification(TI)methods mostly lack a systematic framework to obtain precise hierarchical relations and consumers’segment locations.Their performances are usually deteriorated by introduction of incomplete and tampered smart meter data.To address the problem of TI with penetration of PV prosumers,non-consumption users,and electricity thieves,a data-driven algorithm is proposed via measurements of nodal voltage magnitude and active power,without any prior network information.Inspired by engineering applications of graph theory knowledge,we cast connection problems of LVDN into the solution of adjacency matrices.Up-down and parallel relations of branches are first identified using active power,based on feature extraction of frequency domain filtering and correlation.Correlation factor analysis is subsequently adopted to assign multiple consumers to specific subnetworks,and then consumers’segments are precisely located by combining regression analysis and association strategy.The proposed algorithm is successfully examined on in a complex LVDN,and results show higher robustness under different scenarios.展开更多
In a press-pack insulated gate bipolar transistor(IGBT),a compact packaging structure forms a strong electromagnetic coupling,thermal coupling,and stress coupling,threatening current sharing,temperature sharing,and st...In a press-pack insulated gate bipolar transistor(IGBT),a compact packaging structure forms a strong electromagnetic coupling,thermal coupling,and stress coupling,threatening current sharing,temperature sharing,and stress sharing of paralleled chips.Optimized layouts are proposed based on the inductance analytical model to improve the performance and reliability of Press-Pack IGBT devices.What’s more,transient and steady-state co-simulation using an improved behavioral model is performed to verify the proposed layout.In the test,the PCB Rogowski coil,direct thermocouple,and force-sensitive parameters fittings are used to measure the current distribution,temperature distribution,and stress distribution.The simulation and test results indicate that a rotationally symmetrical layout with IGBT surrounding the FRD mode can achieve uniform current,temperature,and stress.展开更多
Hydrogen storage and ice storage are promising,environmentally friendly energy storage technologies.However,there are few investigations on the optimal configuration of hybrid renewable energy systems(HRES)for remote ...Hydrogen storage and ice storage are promising,environmentally friendly energy storage technologies.However,there are few investigations on the optimal configuration of hybrid renewable energy systems(HRES)for remote off-grid areas with localized scenarios.This paper proposes a new optimal configuration of an off-grid PV/wind/hydrogen/cooling system.Given three performance indices for evaluating HRES,i.e.,the levelized cost of energy(LCOE),the loss of power supply possibility(LPSP),and the power curtailment rate(PCR),we use theε-constraint method that formulates LCOE as the objective,while LPSP and PCR serve as constraints.Furthermore,to solve the optimal size of HRES,an improved salp swarm algorithm(ISSA)is proposed.The simulation results show that for an off-grid remote community,the LCOE,LPSP,and PCR of the optimal HRES configuration can achieve$0.31/kWh,5.00%,and 7.23%,respectively.The comparison of different systems illustrates that adding ice storage in the HRES with hydrogen storage will decrease the LCOE by 27.12%.In addition,compared with other heuristic algorithms,such as SSA,ISSA offers the configuration with the minimum LCOE.The hydrogen-ice storage system is economically significant to off-grid areas with cooling load demand,and the proposed ISSA has excellent accuracy.展开更多
Recognition methods of electromagnetic transients(EMT)have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution.However,that assumption ...Recognition methods of electromagnetic transients(EMT)have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution.However,that assumption is hard to satisfy in industrial applications because the distribution of measured EMT testing data generally changes over time.The performance of these methods gradually deteriorates with the distribution shift.The phenomenon limits application of EMT recognition methods.Therefore,this paper proposes a transfer learning-based recognition network(TLRN)for EMT to break the limitation.It consists of a feature extractor,EMT recognizer,domain recognizer,and maximum mean discrepancy(MMD).The feature extractor is constructed to learn features of EMT automatically.The domain recognizer and MMD make features learned by the feature extractor domain invariant.Based on domain invariant features,the EMT recognizer achieves accurate EMT recognition,despite the distribution discrepancy between EMT training and testing data.TLRN maintains satisfactory EMT recognition performance by updating periodically with an unsupervised learning strategy.Using EMT datasets measured from different substations,scenario experiments,and experiment comparisons are conducted,and the recognition performance of the proposed TLRN is demonstrated.展开更多
This paper proposes a multi-agent cooperative operation optimization strategy for regional power grids considering the uncertainty of renewable energy output and flexibility of electric vehicle(EV)scheduling,which not...This paper proposes a multi-agent cooperative operation optimization strategy for regional power grids considering the uncertainty of renewable energy output and flexibility of electric vehicle(EV)scheduling,which not only improves the economy of networked microgrid(NMG)scheduling but also reduces the impact on active distribution network(ADN).EV condition matrix and model of the adjustable charge-anddischarge capacity of the EV may be built up by simulating the trip rule of an EV using the driving behavior of the vehicle model.In the day-ahead stage,by taking into account NMG operating cost,distribution network loss,and EV owners’payment cost,a multi-objective optimal scheduling model is developed,and the day-ahead scheduling contract for EV is obtained.Generative Adversarial Network(GAN)generates a significant number of intraday scenarios of photovoltaic(PV),load,and EV based on historical scheduling data as training data for the intra-day scheduling model multi-agent PPO(MAPPO).In the intra-day scheduling stage,intra-day ultra-short-term forecast data is input into the intra-day scheduling model,and the trained multi-agent model realizes NMG distributed real-time optimal scheduling.Finally,the economy and effectiveness of the proposed strategy are verified by Day-after optimal scheduling results.展开更多
基金supported by National Key Research and Development Program of China (No.2017YFB903304)the State Grid Science and Technology Program (Hybrid Simnlation Key Technology for Integrated Energy System and Platform Construction)
文摘An integrated energy service company in an industrial park or commercial building is responsible for managing all energy sources in their local region, including electricity, water, gas, heating, and cooling. To reduce energy wastage and increase energy utilization, it is necessary to perform efficiency analyses and diagnoses on integrated energy systems(IESs). However, the integrated energy data necessary for energy efficiency analyses and diagnoses come from a wide variety of instruments, each of which uses different transmission protocols and data formats. This makes it challenging to handle energy-flow data in a unified manner. Thus, we have constructed a unified model for diagnosing energy usage abnormalities in IESs. Using this model, the data are divided into working days and non-working days, and benchmark values are calculated after the data have been weighted to enable unified analysis of several types of energy data. The energy-flow data may then be observed, managed, and compared in all aspects to monitor sudden changes in energy usage and energy wastage. The abnormal data identified and selected by the unified model are then subjected to big-data analysis using technical management tools, enabling the detection of user problems such as abnormalities pertaining to acquisition device, metering, and energy usage. This model facilitates accurate metering of energy data and improves energy efficiency. The study has significant implications in terms of fulfilling the energy saving.
文摘In the current biomedical data movement, numerous efforts have been made to convert and normalize a large number of traditional structured and unstructured data (e.g., EHRs, reports) to semi-structured data (e.g., RDF, OWL). With the increasing number of semi-structured data coming into the biomedical community, data integration and knowledge discovery from heterogeneous domains become important research problem. In the application level, detection of related concepts among medical ontologies is an important goal of life science research. It is more crucial to figure out how different concepts are related within a single ontology or across multiple ontologies by analysing predicates in different knowledge bases. However, the world today is one of information explosion, and it is extremely difficult for biomedical researchers to find existing or potential predicates to perform linking among cross domain concepts without any support from schema pattern analysis. Therefore, there is a need for a mechanism to do predicate oriented pattern analysis to partition heterogeneous ontologies into closer small topics and do query generation to discover cross domain knowledge from each topic. In this paper, we present such a model that predicates oriented pattern analysis based on their close relationship and generates a similarity matrix. Based on this similarity matrix, we apply an innovated unsupervised learning algorithm to partition large data sets into smaller and closer topics and generate meaningful queries to fully discover knowledge over a set of interlinked data sources. We have implemented a prototype system named BmQGen and evaluate the proposed model with colorectal surgical cohort from the Mayo Clinic.
基金Acknowledgments This material is based upon work supported by the National Science Foundation under Grant No. EEC-0540832. The authors also wish to acknowledge the contributions to discussions on plant electrophysiology by Dr. Dan Kostov and Dr. Xing Chen.
文摘The phenomenon of electrical potential differences along the plant apoplast has been reported for more than a century. Earlier works of harvesting energy from trees reported nW range of power with a few hundred-mV open circuit voltage and near uA range short circuit current. In this work, we show that if we cut a stem into pieces, each segment would maintain nearly the same open circuit voltage and short circuit current regardless of length. Using a pico-ampere meter, we also found that the living cells in the vascular cambial and secondary xylem and phloem tissues are the source of electricity. They provide a relatively constant voltage and current to external environment for reasons still under investigation. We demonstrate that by cascading separated stems we can accumulate up to 2 V of open circuit voltage. We also demonstrate by connecting them in parallel we can increase the short circuit current.
文摘A review on thermal power plant automation development in China over 50 years is presented. The level of thermal power automation is introduced, especially for 200 MW and above units which are clarified into three categories by grade. The conditions, existing problems, relevant solutions and policies are summarized chronologically in aspects of centralized control, automatic regulation and controllability of main and auxiliary units, turbine control system, furnace security protection, and computer application in thermal power plants. This paper also points out the development tendency of thermal power plant automation and concepts of some vocabularies.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(Grant Number IMSIU-RP23044).
文摘Lung cancer is a leading cause of global mortality rates.Early detection of pulmonary tumors can significantly enhance the survival rate of patients.Recently,various Computer-Aided Diagnostic(CAD)methods have been developed to enhance the detection of pulmonary nodules with high accuracy.Nevertheless,the existing method-ologies cannot obtain a high level of specificity and sensitivity.The present study introduces a novel model for Lung Cancer Segmentation and Classification(LCSC),which incorporates two improved architectures,namely the improved U-Net architecture and the improved AlexNet architecture.The LCSC model comprises two distinct stages.The first stage involves the utilization of an improved U-Net architecture to segment candidate nodules extracted from the lung lobes.Subsequently,an improved AlexNet architecture is employed to classify lung cancer.During the first stage,the proposed model demonstrates a dice accuracy of 0.855,a precision of 0.933,and a recall of 0.789 for the segmentation of candidate nodules.The suggested improved AlexNet architecture attains 97.06%accuracy,a true positive rate of 96.36%,a true negative rate of 97.77%,a positive predictive value of 97.74%,and a negative predictive value of 96.41%for classifying pulmonary cancer as either benign or malignant.The proposed LCSC model is tested and evaluated employing the publically available dataset furnished by the Lung Image Database Consortium and Image Database Resource Initiative(LIDC-IDRI).This proposed technique exhibits remarkable performance compared to the existing methods by using various evaluation parameters.
文摘Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive behaviors.Timely and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like Pakistan.This study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local context.The research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate schedulers.In addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the tool.The findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation approach.Specifically,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test images.To validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD detection.This research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.
文摘Windbelt generators have been proposed as small, green power sources for battery charging applications. Some of the reported results lack detailed information about how key parameters influence the output power of the generator. In this work, we built prototypes with different architectures to study the voltage generation and power delivery as functions of belt tension, length, and electrical load at various wind speeds. We also studied the maximum power delivery conditions before the breakdown of the belt oscillation occurs. Our results are obtained from windbelt generators with two types of architectures： a conventional design with an adjustable belt that uses weight for tension control, and a revised design with a belt oscillation perpendicular to the coil axis. We have concluded that the breakdown of the belt oscillation at lower output resistances is a primary bottleneck that will limit windbelt systems to only very low power applications.
基金supported in part by the Natural Science Foundation of Hebei Province of China under Grant E2018203152in part by the National Natural Science Foundation of China under Grant 6200739.
文摘Distributed generation(DG)systems with renewable energy are often connected to weak grids.However,there may be large background harmonics in weak grids,which can easily cause power quality issues at the point of common coupling(PCC).For this reason,DG-grid interfacing inverters are expected to have the ability to suppress harmonics while achieving power transmission with the grid.To this end,a collaborative control method with feedforward multiple secondorder generalized integrator(FMSOGI)harmonic extraction and harmonic weighting control(HWC)are proposed in this paper to improve voltage quality at PCC.Compared with traditional control methods,the proposed collaborative control is simpler and has better harmonic suppression ability due to direct suppression.On the basis of the proposed collaborative control,system stability is analyzed for DG-grid interfacing inverters to set proper parameters.Finally,simulation and experimental results from Matlab and HIL StarSim,respectively,are presented to verify effectiveness of the proposed control method.
基金supported in part by the National Natural Science Foundation of China(No.51677030).
文摘The complex working environment of distribution networks tends to cause impermanent single-phase-to-ground(SPG)fault,and high-temperature ground fault arc is prone to endanger lives and power equipment,resulting in large-scale power outages and fire accidents.Thus,fault arc should be extinguished in time.Meanwhile,stable operation conditions of distribution networks and reliable load power supply should be guaranteed to provide high-quality customer service.This paper proposes an active mitigation strategy for SPG fault,and provide active and reactive power compensation at the same time by utilizing an improved flexible power electronic equipment(FPEE)with dc-link sources.These controls are decoupled from each other,so utilization of FPEE is maximized as much as possible.When a SPG fault occurs in distribution networks,FPEE can output,simultaneously,active power,reactive power,and SPG fault compensation current by controlling output current on the d,q,0 coordinate system,respectively.During normal operation of distribution networks,the FPEE can be used as a virtual synchronous generator to compensate load power and its fluctuation.The proposed simultaneous multi-function can also be applied in other cases.Simulation cases are implemented to verify principles and practicability.
基金supported by the National Natural Science Foundation of China(52177103).
文摘More electricity utilities will participate in the investment and operation of private distributed generations(DGs)while the local power company is responsible for the reinforcement of lines and DGs,as well.How to achieve the maximum benefits among various utilities,including the power company,is a task in the expansion planning of distribution networks.To solve the market-oriented planning problem,virtual peer to peer(P2P)trading is integrated and modeled in the new expansion planning of distribution networks.First,virtual market transaction optimization among prosumers is formulated.Second,the distributed regional marginal price(DLMP)is calculated by the optimal operation model,which contributed to the network usage charge(NUC)and then integrated in the expansion planning model.Case studies are performed and indicate the integrated P2P transaction strategy could improve local load consumption,while reducing the load rate of lines,as well as the electricity cost of users.Besides,the total planning cost paid by the power company could be saved via prosumers’investment and P2P transactions and the factors affecting power company’s profit are also classified in multi-investor planning of distribution networks.
基金supported by the Youth Program of National Natural Science Foundation of China(No.52007017)the National Science Fund for Outstanding Young Scholar of China(No.51725701).
文摘Line-commutated-converter-based high-voltage direct current(LCC-HVDC)represents an important approach for transmitting large-scale integrated renewable power over long distances.However,coordination of various discrete and continuous adjustment devices,as well as the complex automatic voltage control problem bring great challenges for voltage control and var dispatch in converter stations(CSs).Besides,traditional approaches may suffer from frequent filter switching issues or conservativeness.To address these issues,this paper proposes a hierarchical robust voltage dispatching schedule consisting of a day-ahead schedulable period plan and an intraday model predictive control(MPC)-based rolling scheduling,which fully considers coordination of multifarious adjustment equipment with different response-time constants and control characteristics in CSs in multiple time dimensions.This method can implement adaptive adjustment of CS discrete/continuous regulating devices with sufficient dynamic var reserves under CS mutable operational conditions caused by renewable energy fluctuation.The day-ahead schedulable period plan ensures global allocation of discrete equipment action resources.MPC-based intraday rolling dispatch is used to overcome conservativeness of the traditional method and achieve automatic reactive power compensation,as well as voltage control of converter station.In a case study,a modified IEEE 9-bus system with wind farms is used to verify the proposed method.
基金supported by National Key R&D Program of China(2020YFB0905900).
文摘Knowledge graph,which is a rapidly developing technology,provides strong support in business and engineering.Knowledge graph plays an important role in recommendations and decision-making,while in the electric power industry,there would be more possibilities for knowledge graph to be utilized.However,as a complex cause-and-effect network,the electric power domain knowledge graph has massive nodes,heterogeneous edges,and sparse structures.Thus,it requires human effort to process data,while quality and accuracy cannot be guaranteed.We propose a novel graph computing-based knowledge reasoning method that takes into account the sparsity of the electric power domain knowledge graph to solve the aforementioned problems and achieve improved accuracy of graph classification and knowledge reasoning tasks.The Haar basis is constructed to realize fast calculation,while the multiscale network structure is introduced to assure classification accuracy and generalization.We evaluate the proposed algorithm on the NCI-1,CEPRI UHVP,and CEPRI EQUIP databases.Simulation results demonstrate its superior performance in terms of accuracy and loss.
基金supported by the National Natural Science Foundation of China(52377080,U24B2078)the Department of Science and Technology of Jilin Province(20230101374JC).
文摘A regional electricity-heating integrated energy system(REH-IES)can make extensive use of renewable energy sources,realize complementary and coordinated operation of multiple energy sources,reduce carbon emissions and promote the development of zero/low carbon systems.This paper proposes a risk-averse stochastic optimal scheduling model for REHIES.An energy flow framework for the REH-IES is proposed considering energy interaction between the electric-heating microgrids(EHMs)and electricity distribution network and the heating network.Then,considering the uncertainties of power output of renewable energy sources,dynamic characteristics of pipelines in the heating network,and thermal inertia of smart buildings,a stochastic optimal scheduling model for the REH-IES is established.Uncertainties of renewable energy sources bring financial risks to optimal scheduling of the REH-IES.Therefore,conditional value-at-risk(CVaR)theory is adopted to measure the risk and to limit the risk within an acceptable range,to achieve minimum expected scheduling cost of the REH-IES.The stochastic programming-based problem is transformed into a second-order cone programming(SOCP)model through secondorder cone relaxation method.Case studies verify the stochastic optimal scheduling model can reduce expected scheduling cost of the REH-IES,promote consumption of renewable energy sources and reduce carbon emissions.
文摘Accurate topology information is crucial to management and application in an active low-voltage distribution network(LVDN).Existing topology identification(TI)methods mostly lack a systematic framework to obtain precise hierarchical relations and consumers’segment locations.Their performances are usually deteriorated by introduction of incomplete and tampered smart meter data.To address the problem of TI with penetration of PV prosumers,non-consumption users,and electricity thieves,a data-driven algorithm is proposed via measurements of nodal voltage magnitude and active power,without any prior network information.Inspired by engineering applications of graph theory knowledge,we cast connection problems of LVDN into the solution of adjacency matrices.Up-down and parallel relations of branches are first identified using active power,based on feature extraction of frequency domain filtering and correlation.Correlation factor analysis is subsequently adopted to assign multiple consumers to specific subnetworks,and then consumers’segments are precisely located by combining regression analysis and association strategy.The proposed algorithm is successfully examined on in a complex LVDN,and results show higher robustness under different scenarios.
基金supported by National Key R&D Program of China(2016YFB0901800).
文摘In a press-pack insulated gate bipolar transistor(IGBT),a compact packaging structure forms a strong electromagnetic coupling,thermal coupling,and stress coupling,threatening current sharing,temperature sharing,and stress sharing of paralleled chips.Optimized layouts are proposed based on the inductance analytical model to improve the performance and reliability of Press-Pack IGBT devices.What’s more,transient and steady-state co-simulation using an improved behavioral model is performed to verify the proposed layout.In the test,the PCB Rogowski coil,direct thermocouple,and force-sensitive parameters fittings are used to measure the current distribution,temperature distribution,and stress distribution.The simulation and test results indicate that a rotationally symmetrical layout with IGBT surrounding the FRD mode can achieve uniform current,temperature,and stress.
基金supported by National Key R&D Program of China(No.2018YFB1500800)National Natural Science Foundation of China(No.51807134)Science and Technology Project of State Grid Corporation,and State Key Laboratory of Power System and Generation Equipment(SKLD21KM10).
文摘Hydrogen storage and ice storage are promising,environmentally friendly energy storage technologies.However,there are few investigations on the optimal configuration of hybrid renewable energy systems(HRES)for remote off-grid areas with localized scenarios.This paper proposes a new optimal configuration of an off-grid PV/wind/hydrogen/cooling system.Given three performance indices for evaluating HRES,i.e.,the levelized cost of energy(LCOE),the loss of power supply possibility(LPSP),and the power curtailment rate(PCR),we use theε-constraint method that formulates LCOE as the objective,while LPSP and PCR serve as constraints.Furthermore,to solve the optimal size of HRES,an improved salp swarm algorithm(ISSA)is proposed.The simulation results show that for an off-grid remote community,the LCOE,LPSP,and PCR of the optimal HRES configuration can achieve$0.31/kWh,5.00%,and 7.23%,respectively.The comparison of different systems illustrates that adding ice storage in the HRES with hydrogen storage will decrease the LCOE by 27.12%.In addition,compared with other heuristic algorithms,such as SSA,ISSA offers the configuration with the minimum LCOE.The hydrogen-ice storage system is economically significant to off-grid areas with cooling load demand,and the proposed ISSA has excellent accuracy.
基金supported by National Natural Science Foundation of China(51837002).
文摘Recognition methods of electromagnetic transients(EMT)have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution.However,that assumption is hard to satisfy in industrial applications because the distribution of measured EMT testing data generally changes over time.The performance of these methods gradually deteriorates with the distribution shift.The phenomenon limits application of EMT recognition methods.Therefore,this paper proposes a transfer learning-based recognition network(TLRN)for EMT to break the limitation.It consists of a feature extractor,EMT recognizer,domain recognizer,and maximum mean discrepancy(MMD).The feature extractor is constructed to learn features of EMT automatically.The domain recognizer and MMD make features learned by the feature extractor domain invariant.Based on domain invariant features,the EMT recognizer achieves accurate EMT recognition,despite the distribution discrepancy between EMT training and testing data.TLRN maintains satisfactory EMT recognition performance by updating periodically with an unsupervised learning strategy.Using EMT datasets measured from different substations,scenario experiments,and experiment comparisons are conducted,and the recognition performance of the proposed TLRN is demonstrated.
基金supported by the Science and Technology Project of State Grid Corporation of China(5100-202155320A-0-0-00).
文摘This paper proposes a multi-agent cooperative operation optimization strategy for regional power grids considering the uncertainty of renewable energy output and flexibility of electric vehicle(EV)scheduling,which not only improves the economy of networked microgrid(NMG)scheduling but also reduces the impact on active distribution network(ADN).EV condition matrix and model of the adjustable charge-anddischarge capacity of the EV may be built up by simulating the trip rule of an EV using the driving behavior of the vehicle model.In the day-ahead stage,by taking into account NMG operating cost,distribution network loss,and EV owners’payment cost,a multi-objective optimal scheduling model is developed,and the day-ahead scheduling contract for EV is obtained.Generative Adversarial Network(GAN)generates a significant number of intraday scenarios of photovoltaic(PV),load,and EV based on historical scheduling data as training data for the intra-day scheduling model multi-agent PPO(MAPPO).In the intra-day scheduling stage,intra-day ultra-short-term forecast data is input into the intra-day scheduling model,and the trained multi-agent model realizes NMG distributed real-time optimal scheduling.Finally,the economy and effectiveness of the proposed strategy are verified by Day-after optimal scheduling results.
