With the increasing integration of emerging source-load types such as distributed photovoltaics,electric vehicles,and energy storage into distribution networks,the operational characteristics of these networks have ev...With the increasing integration of emerging source-load types such as distributed photovoltaics,electric vehicles,and energy storage into distribution networks,the operational characteristics of these networks have evolved from traditional single-load centers to complex multi-source,multi-load systems.This transition not only increases the difficulty of effectively classifying distribution networks due to their heightened complexity but also renders traditional energy management approaches-primarily focused on economic objectives-insufficient to meet the growing demands for flexible scheduling and dynamic response.To address these challenges,this paper proposes an adaptive multi-objective energy management strategy that accounts for the distinct operational requirements of distribution networks with a high penetration of new-type source-loads.The goal is to establish a comprehensive energy management framework that optimally balances energy efficiency,carbon reduction,and economic performance in modern distribution networks.To enhance classification accuracy,the strategy constructs amulti-dimensional scenario classification model that integrates environmental and climatic factors by analyzing the operational characteristics of new-type distribution networks and incorporating expert knowledge.An improved split-coupling K-means preclustering algorithm is employed to classify distribution networks effectively.Based on the classification results,fuzzy logic control is then utilized to dynamically optimize the weighting of each objective,allowing for an adaptive adjustment of priorities to achieve a flexible and responsivemulti-objective energy management strategy.The effectiveness of the proposed approach is validated through practical case studies.Simulation results indicate that the proposed method improves classification accuracy by 18.18%compared to traditional classification methods and enhances energy savings and carbon reduction by 4.34%and 20.94%,respectively,compared to the fixed-weight strategy.展开更多
Evolutionary algorithm is time-consuming because of the large number of evolutions and much times of finite element analysis, when it is used to optimize the wing structure of a certain high altitude long endurance un...Evolutionary algorithm is time-consuming because of the large number of evolutions and much times of finite element analysis, when it is used to optimize the wing structure of a certain high altitude long endurance unmanned aviation vehicle（UAV）. In order to improve efficiency it is proposed to construct a model management framework to perform the multi-objective optimization design of wing structure. The sufficient accurate approximation models of objective and constraint functions in the wing structure optimization model are built when using the model management framework, therefore in the evolutionary algorithm a number of finite element analyses can he avoided and the satisfactory multi-objective optimization results of the wing structure of the high altitude long endurance UAV are obtained.展开更多
Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based...Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.展开更多
Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may r...Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.展开更多
Arid and semi-arid ecosystems are prone to extensive fires due to specific climatic conditions,sparse vegetation cover,and high density of fine fuels.Understanding the flammability characteristics of land covers is es...Arid and semi-arid ecosystems are prone to extensive fires due to specific climatic conditions,sparse vegetation cover,and high density of fine fuels.Understanding the flammability characteristics of land covers is essential for fire management and designing land restoration programs in arid and semi-arid ecosystems.This study provided a new approach to evaluate the flammability of shrublands and woodlands using flammability indices(FIs)including time to ignition(TI),duration of combustion(DC),and flame height(FH)of plant species and their relative frequencies in the Dalfard Basin of southeastern Iran.The results showed that there was a significant difference in FIs between land covers.Shrublands had higher flammability potential compared with woodlands.Plant moisture content had a negative relationship with TI(P<0.010)and no significant relationship with DC and FH(P>0.050).Artemisia spp.,Astragalus gossypinus Fischer,Amygdalus scoparia Spach,and Cymbopogon jwarancusa(Jones)Schult.had the highest FI.Tree species such as Rhazya stricta Decne.,and Pistacia atlantica Desf.showed greater resistance to fire.Using principal component analysis,the relationship between species and FIs was examined,and TI of wet fuel was the most important FI in relation to species.Structural equation model showed that life form(P<0.001)was the most important flammability driver.Precipitation(P<0.010)and legume species(P<0.010)were significantly related to the flammability in arid land.This study emphasizes the importance of managing high-risk species and using resistant species in vegetation restoration and shows that combining species FIs with their abundance is an effective tool for assessing fire risk and fuel management at the plant community scale.展开更多
Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods...Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.展开更多
The integration of Artificial Intelligence(AI)and Machine Learning(ML)into groundwater exploration and water resources management has emerged as a transformative approach to addressing global water challenges.This rev...The integration of Artificial Intelligence(AI)and Machine Learning(ML)into groundwater exploration and water resources management has emerged as a transformative approach to addressing global water challenges.This review explores key AI and ML concepts,methodologies,and their applications in hydrology,focusing on groundwater potential mapping,water quality prediction,and groundwater level forecasting.It discusses various data acquisition techniques,including remote sensing,geospatial analysis,and geophysical surveys,alongside preprocessing methods that are essential for enhancing model accuracy.The study highlights AI-driven solutions in water distribution,allocation optimization,and realtime resource management.Despite their advantages,the application of AI and ML in water sciences faces several challenges,including data scarcity,model reliability,and the integration of these tools with traditional water management systems.Ethical and regulatory concerns also demand careful consideration.The paper also outlines future research directions,emphasizing the need for improved data collection,interpretable models,real-time monitoring capabilities,and interdisciplinary collaboration.By leveraging AI and ML advancements,the water sector can enhance decision-making,optimize resource distribution,and support the development of sustainable water management strategies.展开更多
The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management.Earlier approaches have often...The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management.Earlier approaches have often advanced one dimension—such as Internet of Things(IoT)-based data acquisition,Artificial Intelligence(AI)-driven analytics,or digital twin visualization—without fully integrating these strands into a single operational loop.As a result,many existing solutions encounter bottlenecks in responsiveness,interoperability,and scalability,while also leaving concerns about data privacy unresolved.This research introduces a hybrid AI–IoT–Digital Twin framework that combines continuous sensing,distributed intelligence,and simulation-based decision support.The design incorporates multi-source sensor data,lightweight edge inference through Convolutional Neural Networks(CNN)and Long ShortTerm Memory(LSTM)models,and federated learning enhanced with secure aggregation and differential privacy to maintain confidentiality.A digital twin layer extends these capabilities by simulating city assets such as traffic flows and water networks,generating what-if scenarios,and issuing actionable control signals.Complementary modules,including model compression and synchronization protocols,are embedded to ensure reliability in bandwidth-constrained and heterogeneous urban environments.The framework is validated in two urban domains:traffic management,where it adapts signal cycles based on real-time congestion patterns,and pipeline monitoring,where it anticipates leaks through pressure and vibration data.Experimental results show a 28%reduction in response time,a 35%decrease in maintenance costs,and a marked reduction in false positives relative to conventional baselines.The architecture also demonstrates stability across 50+edge devices under federated training and resilience to uneven node participation.The proposed system provides a scalable and privacy-aware foundation for predictive urban infrastructure management.By closing the loop between sensing,learning,and control,it reduces operator dependence,enhances resource efficiency,and supports transparent governance models for emerging smart cities.展开更多
Diabetes mellitus is an important chronic disease that affects the health of the population worldwide, causing a serious impact on patients’ quality of life and increasing the burden on the healthcare system. With th...Diabetes mellitus is an important chronic disease that affects the health of the population worldwide, causing a serious impact on patients’ quality of life and increasing the burden on the healthcare system. With the increasing number of diabetic patients, the traditional healthcare model is under tremendous pressure. In recent years, the nurse-led diabetes management model, as an innovative approach to nursing intervention, has gradually become an important part of comprehensive diabetes management. This article reviews the conceptual model, specific types of nurse-led diabetes management models, barriers faced by nurses during implementation, and corresponding strategies, with a view to providing a reference for the management of diabetic patients and the development of diabetes specialty nurses.展开更多
Cobalt phosphide has been successfully used as a catalyst in the production of ammonia from nitric acid.Substituting appropriate atoms is expected to further improve its catalytic performance.Owing to the diversity of...Cobalt phosphide has been successfully used as a catalyst in the production of ammonia from nitric acid.Substituting appropriate atoms is expected to further improve its catalytic performance.Owing to the diversity of substituting elements,substitution sites,adsorption sites,and adsorption configurations,extensive time-consuming simulation calculations are required for the high-throughput screening method.Additionally,multi-objective attributes should be considered simultaneously in catalytic design.To tackle this challenge,this paper suggests a multi-objective cobalt phosphide catalytic material design method based on surrogate models.And the effectiveness of the proposed method was validated through comparative experiments.The proposed method led to the discovery of fifteen promising cobalt phosphide catalyst configurations.This study provides a new avenue for expediting the design of catalyst,with the potential for application in other systems.展开更多
Hydrocracking is one of the most important petroleum refining processes that converts heavy oils into gases,naphtha,diesel,and other products through cracking reactions.Multi-objective optimization algorithms can help...Hydrocracking is one of the most important petroleum refining processes that converts heavy oils into gases,naphtha,diesel,and other products through cracking reactions.Multi-objective optimization algorithms can help refining enterprises determine the optimal operating parameters to maximize product quality while ensuring product yield,or to increase product yield while reducing energy consumption.This paper presents a multi-objective optimization scheme for hydrocracking based on an improved SPEA2-PE algorithm,which combines path evolution operator and adaptive step strategy to accelerate the convergence speed and improve the computational accuracy of the algorithm.The reactor model used in this article is simulated based on a twenty-five lumped kinetic model.Through model and test function verification,the proposed optimization scheme exhibits significant advantages in the multiobjective optimization process of hydrocracking.展开更多
This study proposes a multi-objective optimization framework for electric winches in fiber-reinforced plastic(FRP)fishing vessels to address critical limitations of conventional designs,including excessive weight,mate...This study proposes a multi-objective optimization framework for electric winches in fiber-reinforced plastic(FRP)fishing vessels to address critical limitations of conventional designs,including excessive weight,material inefficiency,and performance redundancy.By integrating surrogate modeling techniques with a multi-objective genetic algorithm(MOGA),we have developed a systematic approach that encompasses parametric modeling,finite element analysis under extreme operational conditions,and multi-fidelity performance evaluation.Through a 10-t electric winch case study,the methodology’s effectiveness is demonstrated via parametric characterization of structural integrity,stiffness behavior,and mass distribution.The comparative analysis identified optimal surrogate models for predicting key performance metrics,which enabled the construction of a robust multi-objective optimization model.The MOGA-derived Pareto solutions produced a design configuration achieving 7.86%mass reduction,2.01%safety factor improvement,and 23.97%deformation mitigation.Verification analysis confirmed the optimization scheme’s reliability in balancing conflicting design requirements.This research establishes a generalized framework for marine deck machinery modernization,particularly addressing the structural compatibility challenges in FRP vessel retrofitting.The proposed methodology demonstrates significant potential for facilitating sustainable upgrades of fishing vessel equipment through systematic performance optimization.展开更多
The rapid and increasing growth in the volume and number of cyber threats from malware is not a real danger;the real threat lies in the obfuscation of these cyberattacks,as they constantly change their behavior,making...The rapid and increasing growth in the volume and number of cyber threats from malware is not a real danger;the real threat lies in the obfuscation of these cyberattacks,as they constantly change their behavior,making detection more difficult.Numerous researchers and developers have devoted considerable attention to this topic;however,the research field has not yet been fully saturated with high-quality studies that address these problems.For this reason,this paper presents a novel multi-objective Markov-enhanced adaptive whale optimization(MOMEAWO)cybersecurity model to improve the classification of binary and multi-class malware threats through the proposed MOMEAWO approach.The proposed MOMEAWO cybersecurity model aims to provide an innovative solution for analyzing,detecting,and classifying the behavior of obfuscated malware within their respective families.The proposed model includes three classification types:Binary classification and multi-class classification(e.g.,four families and 16 malware families).To evaluate the performance of this model,we used a recently published dataset called the Canadian Institute for Cybersecurity Malware Memory Analysis(CIC-MalMem-2022)that contains balanced data.The results show near-perfect accuracy in binary classification and high accuracy in multi-class classification compared with related work using the same dataset.展开更多
Water is essential for agricultural production;however,climate change has exacerbated drought and water stress in arid and semi-arid areas such as Iran.Despite these challenges,irrigation water efficiency remains low,...Water is essential for agricultural production;however,climate change has exacerbated drought and water stress in arid and semi-arid areas such as Iran.Despite these challenges,irrigation water efficiency remains low,and current water management schemes are inadequate.Consequently,Iranian crops suffer from low water productivity,highlighting the urgent need for enhanced productivity and improved water management strategies.In this study,we investigated irrigation management conditions in the Hamidiyeh farm,Khuzestan Province,Iran and used the calibrated AquaCrop and WinSRFR(a surface irrigation simulation model)models to reflect these conditions.Subsequently,we examined different management scenarios using each model and evaluated the results from the second year.The findings demonstrated that combining simulation of the AquaCrop and WinSRFR models was highly effective and could be employed for irrigation management in the field.The AquaCrop model accurately simulated wheat yield in the first year,being 2.6 t/hm^(2),which closely aligned with the measured yield of 3.0 t/hm^(2).Additionally,using the WinSRFR model to adjust the length of existing borders from 200 to 180 m resulted in a 45.0%increase in efficiency during the second year.To enhance water use efficiency in the field,we recommended adopting borders with a length of 180 m,a width of 10 m,and a flow rate of 15 to 18 L/s.The AquaCrop and WinSRFR models accurately predicted border irrigation conditions,achieving the highest water use efficiency at a flow rate of 18 L/s.Combining these models increased farmers'average water consumption efficiency from 0.30 to 0.99 kg/m^(3)in the second year.Therefore,the results obtained from the AquaCrop and WinSRFR models are within a reasonable range and consistent with international recommendations.This adjustment is projected to improve the water use efficiency in the field by approximately 45.0%when utilizing the border irrigation method.Therefore,integrating these two models can provide comprehensive management solutions for regional farmers.展开更多
Objective:To explore the target management model for clinical pharmacists in primary hospitals facing current shortages of clinical pharmacists,in order to improve the work efficiency and service quality of clinical p...Objective:To explore the target management model for clinical pharmacists in primary hospitals facing current shortages of clinical pharmacists,in order to improve the work efficiency and service quality of clinical pharmacy,and promote the high-quality development of clinical pharmacy in primary hospitals.Methods:Developing a target management model,adopting a wide coverage work model of“1+1+N”(that is,1 clinical pharmacist,1 resident clinical department,and N contracted clinical departments).According to the SMART principle,various work assessment indicators were quantified.This involved setting clear work goals,diversifying work methods,personalizing work methods,standardizing workflows,and using numerical assessment indicators.Regular supervision,inspection,feedback,and improvement mechanisms were implemented.Results:The implementation of the target management model has made the work effectiveness of clinical pharmacists visualized.There were more than 200 annual consultations and multidisciplinary team(MDT)cases,with an opinion adoption rate of 90.2%and a patient improvement rate of 80.6%.More than 1500 rational drug use interventions were conducted,with a suggestion adoption rate of 83.5%.In terms of pharmaceutical indicators control.The intensity of antibacterial drug use in 2024(without CMI adjustment)was 30.07 DDDs,significantly lower than the 2023 value of 33.54 DDDs,and also significantly lower than the provincial average(32.87 DDDs)and the average for hospitals of the same level(32.49 DDDs).The daily usage of intravenous infusion per bed for hospitalized patients was 2.09,a decrease from 2.15 in 2023,significantly lower than the provincial average of 2.71 and the average of 2.56 in hospitals of the same level.The amount of the second batch of national key monitoring drugs accounts for the value was 6.48%,significantly lower than the provincial average of 8.27%and the same level hospital average of 8.82%.In terms of chronic disease pharmaceutical management,taking the pharmaceutical management of patients with chronic heart failure as an example,the usage rates of renin-aldosterone-angiotensin-system inhibitors(RAAS inhibitors)and beta-blockers for heart failure in the management group were 87.88%and 80.81%,respectively,significantly higher-1 than those in the control group(62.22%and 65.56%).Heart rate in the management group(69.54±10.68 times·min-1)was significantly lower than in the control group(80.04±17.68 times·min)(P<0.001).The low-density lipoprotein cholesterol(1.69±0.57 mmol·L-1)was significantly lower than the control group(1.95±0.77 mmol·L-1)(P<0.001),and the 1-year readmission rate was 47.47%,significantly lower than the control group 56.67%.The Minnesota Living with Heart Failure Questionnaire(MLHFQ)Score was(44.20±10.78),significantly lower than the control group(55.89±11.48)(P<0.001),indicating a significant improvement in the patient’s quality of life.Conclusions:The targeted management model for clinical pharmacists can effectively enhance communication and collaboration between clinical pharmacists and clinicians,improve the work efficiency and service quality of clinical pharmacists in primary hospitals,promote the work of clinical pharmacy towards standardization and scientificization,boost the high-quality development of pharmacy in primary hospitals,and also provide new ideas and methods for the management of clinical pharmacists in other primary hospitals.展开更多
This paper focuses on concrete technical management in construction engineering.It explains the core elements,including production mix ratio,analyzes problems of traditional models,presents innovative management model...This paper focuses on concrete technical management in construction engineering.It explains the core elements,including production mix ratio,analyzes problems of traditional models,presents innovative management models like BIM+GIS and their applications,and covers aspects such as job competence standards and prefabricated modular construction regulations,emphasizing the significance and development direction of innovative models.展开更多
The integration of Learning Management Systems(LMSs)into educational settings is becoming increasingly common,especially in the digital field.Understanding the factors influencing the acceptance and effective use of L...The integration of Learning Management Systems(LMSs)into educational settings is becoming increasingly common,especially in the digital field.Understanding the factors influencing the acceptance and effective use of LMS is essential to ensure successful implementation.The Technology Acceptance Model(TAM)has been widely used to check user acceptance of various technologies,including LMS.This study conducted a systematic literature review(SLR)to analyze existing research on the application of TAM in the context of LMS.A comprehensive search of the academic database was conducted to identify relevant studies published in 2010-2025.The review synthesizes findings related to the core constructs of TAM—Perceived Usability,Perceived Ease of Use,Behavioral Intent,and Actual Use—as well as extended factors such as system quality,self-efficacy,and social influence.The results reveal circumstantial evidence supporting the predictive power of TAM in LMS adoption,while also highlighting emerging trends and gaps in the literature.This review contributes to a deeper understanding of user acceptance in a digital learning environment and provides recommendations for future research and practical LMS implementation strategies.展开更多
Objective:To study the effectiveness of the PDCA cycle model in the nursing management of the disinfection supply room.Method:From March 2022 to February 2024,the hospital adopted the PDCA cycle model to manage the re...Objective:To study the effectiveness of the PDCA cycle model in the nursing management of the disinfection supply room.Method:From March 2022 to February 2024,the hospital adopted the PDCA cycle model to manage the related work of the disinfection supply room.In this study,40 nursing staff were selected as the research subjects.Sixty-five sets of data generated during the implementation of the PDCA model were selected,and 65 sets of similar data before the implementation were also selected.The relevant data information was compared and evaluated to understand the changes in work before and after the implementation of the PDCA cycle model management.Meanwhile,twenty departments in the hospital were selected to investigate the satisfaction before and after the implementation of the PDCA cycle model management.Result:After the implementation of the PDCA cycle model,the completion rates of various tasks were improved,and there was a significant difference compared with those before the implementation(P<0.05).The work quality of each working link has also been improved since the implementation.Compared with that before the implementation of the PDCA cycle model,there are significant changes(P<0.05).It can be learned from the comparison of satisfaction among various departments that the satisfaction of departments has improved after the implementation of PDCA,and there is a significant difference compared with that before the implementation(P<0.05).Conclusion:The application of the PDCA cycle model in the nursing management of the disinfection supply room can effectively improve the working conditions of the disinfection supply room and provide a basic guarantee for hospital treatment.Therefore,the PDCA cycle management model can be actively adopted in the actual work management.展开更多
The management of large-scale architectural engineering projects(e.g.,airports,hospitals)is plagued by information silos,cost overruns,and scheduling delays.While building information modeling(BIM)has improved 3D desi...The management of large-scale architectural engineering projects(e.g.,airports,hospitals)is plagued by information silos,cost overruns,and scheduling delays.While building information modeling(BIM)has improved 3D design coordination,its static nature limits its utility in real-time construction management and operational phases.This paper proposes a novel synergistic framework that integrates the static,deep data of BIM with the dynamic,real-time capabilities of digital twin(DT)technology.The framework establishes a closed-loop data flow from design(BIM)to construction(IoT,drones,BIM 360)to operation(DT platform).We detail the technological stack required,including IoT sensors,cloud computing,and AI-driven analytics.The application of this framework is illustrated through a simulated case study of a mega-terminal airport construction project,demonstrating potential reductions in rework by 15%,improvement in labor productivity by 10%,and enhanced predictive maintenance capabilities.This research contributes to the field of construction engineering by providing a practical model for achieving full lifecycle digitalization and intelligent project management.展开更多
With the rapid adoption of artificial intelligence(AI)in domains such as power,transportation,and finance,the number of machine learning and deep learning models has grown exponentially.However,challenges such as dela...With the rapid adoption of artificial intelligence(AI)in domains such as power,transportation,and finance,the number of machine learning and deep learning models has grown exponentially.However,challenges such as delayed retraining,inconsistent version management,insufficient drift monitoring,and limited data security still hinder efficient and reliable model operations.To address these issues,this paper proposes the Intelligent Model Lifecycle Management Algorithm(IMLMA).The algorithm employs a dual-trigger mechanism based on both data volume thresholds and time intervals to automate retraining,and applies Bayesian optimization for adaptive hyperparameter tuning to improve performance.A multi-metric replacement strategy,incorporating MSE,MAE,and R2,ensures that new models replace existing ones only when performance improvements are guaranteed.A versioning and traceability database supports comparison and visualization,while real-time monitoring with stability analysis enables early warnings of latency and drift.Finally,hash-based integrity checks secure both model files and datasets.Experimental validation in a power metering operation scenario demonstrates that IMLMA reduces model update delays,enhances predictive accuracy and stability,and maintains low latency under high concurrency.This work provides a practical,reusable,and scalable solution for intelligent model lifecycle management,with broad applicability to complex systems such as smart grids.展开更多
基金supported by the Science and Technology Project of the Headquarters of the State Grid Corporation(project code:5400-202323233A-1-1-ZN).
文摘With the increasing integration of emerging source-load types such as distributed photovoltaics,electric vehicles,and energy storage into distribution networks,the operational characteristics of these networks have evolved from traditional single-load centers to complex multi-source,multi-load systems.This transition not only increases the difficulty of effectively classifying distribution networks due to their heightened complexity but also renders traditional energy management approaches-primarily focused on economic objectives-insufficient to meet the growing demands for flexible scheduling and dynamic response.To address these challenges,this paper proposes an adaptive multi-objective energy management strategy that accounts for the distinct operational requirements of distribution networks with a high penetration of new-type source-loads.The goal is to establish a comprehensive energy management framework that optimally balances energy efficiency,carbon reduction,and economic performance in modern distribution networks.To enhance classification accuracy,the strategy constructs amulti-dimensional scenario classification model that integrates environmental and climatic factors by analyzing the operational characteristics of new-type distribution networks and incorporating expert knowledge.An improved split-coupling K-means preclustering algorithm is employed to classify distribution networks effectively.Based on the classification results,fuzzy logic control is then utilized to dynamically optimize the weighting of each objective,allowing for an adaptive adjustment of priorities to achieve a flexible and responsivemulti-objective energy management strategy.The effectiveness of the proposed approach is validated through practical case studies.Simulation results indicate that the proposed method improves classification accuracy by 18.18%compared to traditional classification methods and enhances energy savings and carbon reduction by 4.34%and 20.94%,respectively,compared to the fixed-weight strategy.
文摘Evolutionary algorithm is time-consuming because of the large number of evolutions and much times of finite element analysis, when it is used to optimize the wing structure of a certain high altitude long endurance unmanned aviation vehicle（UAV）. In order to improve efficiency it is proposed to construct a model management framework to perform the multi-objective optimization design of wing structure. The sufficient accurate approximation models of objective and constraint functions in the wing structure optimization model are built when using the model management framework, therefore in the evolutionary algorithm a number of finite element analyses can he avoided and the satisfactory multi-objective optimization results of the wing structure of the high altitude long endurance UAV are obtained.
基金the Hebei Province Science and Technology Plan Project(19221909D)rincess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R308),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.
文摘Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.
文摘Arid and semi-arid ecosystems are prone to extensive fires due to specific climatic conditions,sparse vegetation cover,and high density of fine fuels.Understanding the flammability characteristics of land covers is essential for fire management and designing land restoration programs in arid and semi-arid ecosystems.This study provided a new approach to evaluate the flammability of shrublands and woodlands using flammability indices(FIs)including time to ignition(TI),duration of combustion(DC),and flame height(FH)of plant species and their relative frequencies in the Dalfard Basin of southeastern Iran.The results showed that there was a significant difference in FIs between land covers.Shrublands had higher flammability potential compared with woodlands.Plant moisture content had a negative relationship with TI(P<0.010)and no significant relationship with DC and FH(P>0.050).Artemisia spp.,Astragalus gossypinus Fischer,Amygdalus scoparia Spach,and Cymbopogon jwarancusa(Jones)Schult.had the highest FI.Tree species such as Rhazya stricta Decne.,and Pistacia atlantica Desf.showed greater resistance to fire.Using principal component analysis,the relationship between species and FIs was examined,and TI of wet fuel was the most important FI in relation to species.Structural equation model showed that life form(P<0.001)was the most important flammability driver.Precipitation(P<0.010)and legume species(P<0.010)were significantly related to the flammability in arid land.This study emphasizes the importance of managing high-risk species and using resistant species in vegetation restoration and shows that combining species FIs with their abundance is an effective tool for assessing fire risk and fuel management at the plant community scale.
基金supported by the project“Romanian Hub for Artificial Intelligence-HRIA”,Smart Growth,Digitization and Financial Instruments Program,2021–2027,MySMIS No.334906.
文摘Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.
文摘The integration of Artificial Intelligence(AI)and Machine Learning(ML)into groundwater exploration and water resources management has emerged as a transformative approach to addressing global water challenges.This review explores key AI and ML concepts,methodologies,and their applications in hydrology,focusing on groundwater potential mapping,water quality prediction,and groundwater level forecasting.It discusses various data acquisition techniques,including remote sensing,geospatial analysis,and geophysical surveys,alongside preprocessing methods that are essential for enhancing model accuracy.The study highlights AI-driven solutions in water distribution,allocation optimization,and realtime resource management.Despite their advantages,the application of AI and ML in water sciences faces several challenges,including data scarcity,model reliability,and the integration of these tools with traditional water management systems.Ethical and regulatory concerns also demand careful consideration.The paper also outlines future research directions,emphasizing the need for improved data collection,interpretable models,real-time monitoring capabilities,and interdisciplinary collaboration.By leveraging AI and ML advancements,the water sector can enhance decision-making,optimize resource distribution,and support the development of sustainable water management strategies.
基金The researchers would like to thank the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025)。
文摘The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management.Earlier approaches have often advanced one dimension—such as Internet of Things(IoT)-based data acquisition,Artificial Intelligence(AI)-driven analytics,or digital twin visualization—without fully integrating these strands into a single operational loop.As a result,many existing solutions encounter bottlenecks in responsiveness,interoperability,and scalability,while also leaving concerns about data privacy unresolved.This research introduces a hybrid AI–IoT–Digital Twin framework that combines continuous sensing,distributed intelligence,and simulation-based decision support.The design incorporates multi-source sensor data,lightweight edge inference through Convolutional Neural Networks(CNN)and Long ShortTerm Memory(LSTM)models,and federated learning enhanced with secure aggregation and differential privacy to maintain confidentiality.A digital twin layer extends these capabilities by simulating city assets such as traffic flows and water networks,generating what-if scenarios,and issuing actionable control signals.Complementary modules,including model compression and synchronization protocols,are embedded to ensure reliability in bandwidth-constrained and heterogeneous urban environments.The framework is validated in two urban domains:traffic management,where it adapts signal cycles based on real-time congestion patterns,and pipeline monitoring,where it anticipates leaks through pressure and vibration data.Experimental results show a 28%reduction in response time,a 35%decrease in maintenance costs,and a marked reduction in false positives relative to conventional baselines.The architecture also demonstrates stability across 50+edge devices under federated training and resilience to uneven node participation.The proposed system provides a scalable and privacy-aware foundation for predictive urban infrastructure management.By closing the loop between sensing,learning,and control,it reduces operator dependence,enhances resource efficiency,and supports transparent governance models for emerging smart cities.
文摘Diabetes mellitus is an important chronic disease that affects the health of the population worldwide, causing a serious impact on patients’ quality of life and increasing the burden on the healthcare system. With the increasing number of diabetic patients, the traditional healthcare model is under tremendous pressure. In recent years, the nurse-led diabetes management model, as an innovative approach to nursing intervention, has gradually become an important part of comprehensive diabetes management. This article reviews the conceptual model, specific types of nurse-led diabetes management models, barriers faced by nurses during implementation, and corresponding strategies, with a view to providing a reference for the management of diabetic patients and the development of diabetes specialty nurses.
基金supported by the Jiangxi Provincial Natural Science Foundation(No.20224BAB212022)Science and Technology Project of Education Department of Jiangxi Province(No.GJJ211435)+3 种基金the National Key Research and Development Program of China(No.2021YFA1400204)the Project of China Postdoctoral Science Foundation(No.2022M712909)the Natural Science Foundation of China(No.21603109)the Henan Joint Fund of the National Natural Science Foundation of China(No.U1404216)。
文摘Cobalt phosphide has been successfully used as a catalyst in the production of ammonia from nitric acid.Substituting appropriate atoms is expected to further improve its catalytic performance.Owing to the diversity of substituting elements,substitution sites,adsorption sites,and adsorption configurations,extensive time-consuming simulation calculations are required for the high-throughput screening method.Additionally,multi-objective attributes should be considered simultaneously in catalytic design.To tackle this challenge,this paper suggests a multi-objective cobalt phosphide catalytic material design method based on surrogate models.And the effectiveness of the proposed method was validated through comparative experiments.The proposed method led to the discovery of fifteen promising cobalt phosphide catalyst configurations.This study provides a new avenue for expediting the design of catalyst,with the potential for application in other systems.
基金supported by National Key Research and Development Program of China (2023YFB3307800)National Natural Science Foundation of China (Key Program: 62136003, 62373155)+1 种基金Major Science and Technology Project of Xinjiang (No. 2022A01006-4)the Fundamental Research Funds for the Central Universities。
文摘Hydrocracking is one of the most important petroleum refining processes that converts heavy oils into gases,naphtha,diesel,and other products through cracking reactions.Multi-objective optimization algorithms can help refining enterprises determine the optimal operating parameters to maximize product quality while ensuring product yield,or to increase product yield while reducing energy consumption.This paper presents a multi-objective optimization scheme for hydrocracking based on an improved SPEA2-PE algorithm,which combines path evolution operator and adaptive step strategy to accelerate the convergence speed and improve the computational accuracy of the algorithm.The reactor model used in this article is simulated based on a twenty-five lumped kinetic model.Through model and test function verification,the proposed optimization scheme exhibits significant advantages in the multiobjective optimization process of hydrocracking.
基金supported by the Basic Public Welfare Research Program of Zhejiang Province(No.LGN22E050005).
文摘This study proposes a multi-objective optimization framework for electric winches in fiber-reinforced plastic(FRP)fishing vessels to address critical limitations of conventional designs,including excessive weight,material inefficiency,and performance redundancy.By integrating surrogate modeling techniques with a multi-objective genetic algorithm(MOGA),we have developed a systematic approach that encompasses parametric modeling,finite element analysis under extreme operational conditions,and multi-fidelity performance evaluation.Through a 10-t electric winch case study,the methodology’s effectiveness is demonstrated via parametric characterization of structural integrity,stiffness behavior,and mass distribution.The comparative analysis identified optimal surrogate models for predicting key performance metrics,which enabled the construction of a robust multi-objective optimization model.The MOGA-derived Pareto solutions produced a design configuration achieving 7.86%mass reduction,2.01%safety factor improvement,and 23.97%deformation mitigation.Verification analysis confirmed the optimization scheme’s reliability in balancing conflicting design requirements.This research establishes a generalized framework for marine deck machinery modernization,particularly addressing the structural compatibility challenges in FRP vessel retrofitting.The proposed methodology demonstrates significant potential for facilitating sustainable upgrades of fishing vessel equipment through systematic performance optimization.
文摘The rapid and increasing growth in the volume and number of cyber threats from malware is not a real danger;the real threat lies in the obfuscation of these cyberattacks,as they constantly change their behavior,making detection more difficult.Numerous researchers and developers have devoted considerable attention to this topic;however,the research field has not yet been fully saturated with high-quality studies that address these problems.For this reason,this paper presents a novel multi-objective Markov-enhanced adaptive whale optimization(MOMEAWO)cybersecurity model to improve the classification of binary and multi-class malware threats through the proposed MOMEAWO approach.The proposed MOMEAWO cybersecurity model aims to provide an innovative solution for analyzing,detecting,and classifying the behavior of obfuscated malware within their respective families.The proposed model includes three classification types:Binary classification and multi-class classification(e.g.,four families and 16 malware families).To evaluate the performance of this model,we used a recently published dataset called the Canadian Institute for Cybersecurity Malware Memory Analysis(CIC-MalMem-2022)that contains balanced data.The results show near-perfect accuracy in binary classification and high accuracy in multi-class classification compared with related work using the same dataset.
基金The study was funded by the Soil and Water Research Institute of Iran.
文摘Water is essential for agricultural production;however,climate change has exacerbated drought and water stress in arid and semi-arid areas such as Iran.Despite these challenges,irrigation water efficiency remains low,and current water management schemes are inadequate.Consequently,Iranian crops suffer from low water productivity,highlighting the urgent need for enhanced productivity and improved water management strategies.In this study,we investigated irrigation management conditions in the Hamidiyeh farm,Khuzestan Province,Iran and used the calibrated AquaCrop and WinSRFR(a surface irrigation simulation model)models to reflect these conditions.Subsequently,we examined different management scenarios using each model and evaluated the results from the second year.The findings demonstrated that combining simulation of the AquaCrop and WinSRFR models was highly effective and could be employed for irrigation management in the field.The AquaCrop model accurately simulated wheat yield in the first year,being 2.6 t/hm^(2),which closely aligned with the measured yield of 3.0 t/hm^(2).Additionally,using the WinSRFR model to adjust the length of existing borders from 200 to 180 m resulted in a 45.0%increase in efficiency during the second year.To enhance water use efficiency in the field,we recommended adopting borders with a length of 180 m,a width of 10 m,and a flow rate of 15 to 18 L/s.The AquaCrop and WinSRFR models accurately predicted border irrigation conditions,achieving the highest water use efficiency at a flow rate of 18 L/s.Combining these models increased farmers'average water consumption efficiency from 0.30 to 0.99 kg/m^(3)in the second year.Therefore,the results obtained from the AquaCrop and WinSRFR models are within a reasonable range and consistent with international recommendations.This adjustment is projected to improve the water use efficiency in the field by approximately 45.0%when utilizing the border irrigation method.Therefore,integrating these two models can provide comprehensive management solutions for regional farmers.
文摘Objective:To explore the target management model for clinical pharmacists in primary hospitals facing current shortages of clinical pharmacists,in order to improve the work efficiency and service quality of clinical pharmacy,and promote the high-quality development of clinical pharmacy in primary hospitals.Methods:Developing a target management model,adopting a wide coverage work model of“1+1+N”(that is,1 clinical pharmacist,1 resident clinical department,and N contracted clinical departments).According to the SMART principle,various work assessment indicators were quantified.This involved setting clear work goals,diversifying work methods,personalizing work methods,standardizing workflows,and using numerical assessment indicators.Regular supervision,inspection,feedback,and improvement mechanisms were implemented.Results:The implementation of the target management model has made the work effectiveness of clinical pharmacists visualized.There were more than 200 annual consultations and multidisciplinary team(MDT)cases,with an opinion adoption rate of 90.2%and a patient improvement rate of 80.6%.More than 1500 rational drug use interventions were conducted,with a suggestion adoption rate of 83.5%.In terms of pharmaceutical indicators control.The intensity of antibacterial drug use in 2024(without CMI adjustment)was 30.07 DDDs,significantly lower than the 2023 value of 33.54 DDDs,and also significantly lower than the provincial average(32.87 DDDs)and the average for hospitals of the same level(32.49 DDDs).The daily usage of intravenous infusion per bed for hospitalized patients was 2.09,a decrease from 2.15 in 2023,significantly lower than the provincial average of 2.71 and the average of 2.56 in hospitals of the same level.The amount of the second batch of national key monitoring drugs accounts for the value was 6.48%,significantly lower than the provincial average of 8.27%and the same level hospital average of 8.82%.In terms of chronic disease pharmaceutical management,taking the pharmaceutical management of patients with chronic heart failure as an example,the usage rates of renin-aldosterone-angiotensin-system inhibitors(RAAS inhibitors)and beta-blockers for heart failure in the management group were 87.88%and 80.81%,respectively,significantly higher-1 than those in the control group(62.22%and 65.56%).Heart rate in the management group(69.54±10.68 times·min-1)was significantly lower than in the control group(80.04±17.68 times·min)(P<0.001).The low-density lipoprotein cholesterol(1.69±0.57 mmol·L-1)was significantly lower than the control group(1.95±0.77 mmol·L-1)(P<0.001),and the 1-year readmission rate was 47.47%,significantly lower than the control group 56.67%.The Minnesota Living with Heart Failure Questionnaire(MLHFQ)Score was(44.20±10.78),significantly lower than the control group(55.89±11.48)(P<0.001),indicating a significant improvement in the patient’s quality of life.Conclusions:The targeted management model for clinical pharmacists can effectively enhance communication and collaboration between clinical pharmacists and clinicians,improve the work efficiency and service quality of clinical pharmacists in primary hospitals,promote the work of clinical pharmacy towards standardization and scientificization,boost the high-quality development of pharmacy in primary hospitals,and also provide new ideas and methods for the management of clinical pharmacists in other primary hospitals.
文摘This paper focuses on concrete technical management in construction engineering.It explains the core elements,including production mix ratio,analyzes problems of traditional models,presents innovative management models like BIM+GIS and their applications,and covers aspects such as job competence standards and prefabricated modular construction regulations,emphasizing the significance and development direction of innovative models.
文摘The integration of Learning Management Systems(LMSs)into educational settings is becoming increasingly common,especially in the digital field.Understanding the factors influencing the acceptance and effective use of LMS is essential to ensure successful implementation.The Technology Acceptance Model(TAM)has been widely used to check user acceptance of various technologies,including LMS.This study conducted a systematic literature review(SLR)to analyze existing research on the application of TAM in the context of LMS.A comprehensive search of the academic database was conducted to identify relevant studies published in 2010-2025.The review synthesizes findings related to the core constructs of TAM—Perceived Usability,Perceived Ease of Use,Behavioral Intent,and Actual Use—as well as extended factors such as system quality,self-efficacy,and social influence.The results reveal circumstantial evidence supporting the predictive power of TAM in LMS adoption,while also highlighting emerging trends and gaps in the literature.This review contributes to a deeper understanding of user acceptance in a digital learning environment and provides recommendations for future research and practical LMS implementation strategies.
文摘Objective:To study the effectiveness of the PDCA cycle model in the nursing management of the disinfection supply room.Method:From March 2022 to February 2024,the hospital adopted the PDCA cycle model to manage the related work of the disinfection supply room.In this study,40 nursing staff were selected as the research subjects.Sixty-five sets of data generated during the implementation of the PDCA model were selected,and 65 sets of similar data before the implementation were also selected.The relevant data information was compared and evaluated to understand the changes in work before and after the implementation of the PDCA cycle model management.Meanwhile,twenty departments in the hospital were selected to investigate the satisfaction before and after the implementation of the PDCA cycle model management.Result:After the implementation of the PDCA cycle model,the completion rates of various tasks were improved,and there was a significant difference compared with those before the implementation(P<0.05).The work quality of each working link has also been improved since the implementation.Compared with that before the implementation of the PDCA cycle model,there are significant changes(P<0.05).It can be learned from the comparison of satisfaction among various departments that the satisfaction of departments has improved after the implementation of PDCA,and there is a significant difference compared with that before the implementation(P<0.05).Conclusion:The application of the PDCA cycle model in the nursing management of the disinfection supply room can effectively improve the working conditions of the disinfection supply room and provide a basic guarantee for hospital treatment.Therefore,the PDCA cycle management model can be actively adopted in the actual work management.
文摘The management of large-scale architectural engineering projects(e.g.,airports,hospitals)is plagued by information silos,cost overruns,and scheduling delays.While building information modeling(BIM)has improved 3D design coordination,its static nature limits its utility in real-time construction management and operational phases.This paper proposes a novel synergistic framework that integrates the static,deep data of BIM with the dynamic,real-time capabilities of digital twin(DT)technology.The framework establishes a closed-loop data flow from design(BIM)to construction(IoT,drones,BIM 360)to operation(DT platform).We detail the technological stack required,including IoT sensors,cloud computing,and AI-driven analytics.The application of this framework is illustrated through a simulated case study of a mega-terminal airport construction project,demonstrating potential reductions in rework by 15%,improvement in labor productivity by 10%,and enhanced predictive maintenance capabilities.This research contributes to the field of construction engineering by providing a practical model for achieving full lifecycle digitalization and intelligent project management.
基金funded by Anhui NARI ZT Electric Co.,Ltd.,entitled“Research on the Shared Operation and Maintenance Service Model for Metering Equipment and Platform Development for the Modern Industrial Chain”(Grant No.524636250005).
文摘With the rapid adoption of artificial intelligence(AI)in domains such as power,transportation,and finance,the number of machine learning and deep learning models has grown exponentially.However,challenges such as delayed retraining,inconsistent version management,insufficient drift monitoring,and limited data security still hinder efficient and reliable model operations.To address these issues,this paper proposes the Intelligent Model Lifecycle Management Algorithm(IMLMA).The algorithm employs a dual-trigger mechanism based on both data volume thresholds and time intervals to automate retraining,and applies Bayesian optimization for adaptive hyperparameter tuning to improve performance.A multi-metric replacement strategy,incorporating MSE,MAE,and R2,ensures that new models replace existing ones only when performance improvements are guaranteed.A versioning and traceability database supports comparison and visualization,while real-time monitoring with stability analysis enables early warnings of latency and drift.Finally,hash-based integrity checks secure both model files and datasets.Experimental validation in a power metering operation scenario demonstrates that IMLMA reduces model update delays,enhances predictive accuracy and stability,and maintains low latency under high concurrency.This work provides a practical,reusable,and scalable solution for intelligent model lifecycle management,with broad applicability to complex systems such as smart grids.
