Search Results (345)

Accurate evaluation of the operational status of smart meters, as the critical interface between the power grid and its users, is essential for ensuring fairness in power transactions. This highlights the importance of implementing rotation management practices based on meter status. However, the traditional expiration-based rotation method has become inadequate due to the extended service life of modern smart meters, necessitating a shift toward status-driven targeted management. Existing multifactor comprehensive assessment methods often face challenges in balancing accuracy and interpretability. To address these limitations, this study proposes a novel method for analyzing the status of smart meter groups using an interpretable random forest model. The approach incorporates an expert-knowledge-guided grouping assessment strategy, develops a multi-source heterogeneous feature set with strong correlations to meter status, and enhances the random forest model with the SHAP (SHapley Additive exPlanations) interpretability framework. Compared to conventional methods, the proposed approach demonstrates superior efficiency and reliability in predicting the failure rates of smart meter groups within distribution network areas, offering robust support for the maintenance and management of smart meters. Full article

The construction and maintenance of an ecological security pattern (ESP) are important for promoting the regional development of ecological civilizations, realizing sustainable and healthy development, and creating a harmonious and beautiful space for human beings and nature to thrive. Traditional construction methods have the limitations of a single dimension, a single method, and excessive human subjective intervention for source and corridor identification, without considering the multidimensional quality of the sources and the structural connectivity and resilience optimization of the corridors. Therefore, an ecological civilization demonstration area (Jiangxi Province) was used as the study area, a new research method for ESP was proposed, and an empirical study was conducted. To evaluate ecosystem service (ES) importance–disturbance–risk and extract sustainability sources through the deep embedded clustering–self-organizing map (DEC–SOM) deep unsupervised learning clustering algorithm, ecological networks (ENs) were constructed by applying the minimum cumulative resistance (MCR) gravity model and circuit theory. The ENs were then optimized to improve performance by combining the comparative advantages of the two approaches in terms of structural connectivity and resilience. A comparative analysis of EN performance was constructed among different functional control zones, and the ESP was constructed to include 42 ecological sources, 134 corridors, 210 restoration nodes, and 280 protection nodes. An ESP of ‘1 nucleus, 3 belts, 6 zones, and multiple corridors’ was constructed, and the key restoration components and protection functions were clarified. This study offers a valuable reference for ecological management, protection, and restoration and provides insights into the promotion of harmonious symbiosis between human beings and nature and sustainable regional development. Full article

With the continuous expansion and increasing operational complexity of high-speed railway networks, there is a growing need for more flexible and efficient EMU (Electric Multiple Unit) routing strategies. To address these challenges, in this paper, we propose a multi-day flexible circulation model that minimizes total connection time and deadheading mileage. A multi-commodity network flow model is formulated, incorporating constraints such as first-level maintenance intervals, storage capacity, train coupling/decoupling operations, and train types, with across-day consistency. To solve this complex model efficiently, a heuristic decomposition algorithm is designed to separate the problem into daily service chain generation and EMU assignment. A real-world case study in the Beijing–Baotou high-speed corridor demonstrates the effectiveness of the proposed approach. Compared to a fixed strategy, the flexible strategy reduces EMU usage by one unit, lowers deadheading mileage by up to 16.4%, and improves maintenance workload balance. These results highlight the practical value of flexible EMU deployment for large-scale, multi-day railway operations. Full article

Wear state prediction based on oil monitoring technology enables the early identification of potential wear and failure risks of friction pairs, facilitating optimized equipment maintenance and extended service life. However, the complexity of lubricating oil monitoring data often poses challenges in extracting discriminative features, limiting the accuracy of wear state prediction. To address this, a CNN–LSTM–Attention network is specially constructed for predicting wear state, which hierarchically integrates convolutional neural networks (CNNs) for spatial feature extraction, long short-term memory (LSTM) networks for temporal dynamics modeling, and self-attention mechanisms for adaptive feature refinement. The proposed architecture implements a three-stage computational pipeline. Initially, the CNN performs hierarchical extraction of localized patterns from multi-sensor tribological signals. Subsequently, the self-attention mechanism conducts adaptive recalibration of feature saliency, prioritizing diagnostically critical feature channels. Ultimately, bidirectional LSTM establishes cross-cyclic temporal dependencies, enabling cascaded fully connected layers with Gaussian activation to generate probabilistic wear state estimations. Experimental results demonstrate that the proposed model not only achieves superior predictive accuracy but also exhibits robust stability, offering a reliable solution for condition monitoring and predictive maintenance in industrial applications. Full article

Modern database systems require autonomous CPU scheduling frameworks that dynamically optimize resource allocation across heterogeneous workloads while maintaining strict performance guarantees. We present a novel hierarchical deep reinforcement learning framework augmented with graph neural networks to address CPU scheduling challenges in mixed database environments comprising Online Transaction Processing (OLTP), Online Analytical Processing (OLAP), vector processing, and background maintenance workloads. Our approach introduces three key innovations: first, a symmetric two-tier control architecture where a meta-controller allocates CPU budgets across workload categories using policy gradient methods while specialized sub-controllers optimize process-level resource allocation through continuous action spaces; second, graph neural network-based dependency modeling that captures complex inter-process relationships and communication patterns while preserving inherent symmetries in database architectures; and third, meta-learning integration with curiosity-driven exploration enabling rapid adaptation to previously unseen workload patterns without extensive retraining. The framework incorporates a multi-objective reward function balancing Service Level Objective (SLO) adherence, resource efficiency, symmetric fairness metrics, and system stability. Experimental evaluation through high-fidelity digital twin simulation and production deployment demonstrates substantial performance improvements: 43.5% reduction in p99 latency violations for OLTP workloads and 27.6% improvement in overall CPU utilization, with successful scaling to 10,000 concurrent processes maintaining sub-3% scheduling overhead. This work represents a significant advancement toward truly autonomous database resource management, establishing a foundation for next-generation self-optimizing database systems with implications extending to broader orchestration challenges in cloud-native architectures. Full article

Enhancing the seismic resilience of urban water distribution networks (WDNs) requires the improvement of both earthquake resistance and rapid recovery capabilities within the system. This paper proposes a multi-objective method to enhance the seismic resilience of the WDNs, focusing on system restoration capabilities while comprehensively considering the hydraulic recovery index, maintenance time, and maintenance cost. The method utilizes a random simulation approach to generate various damage scenarios for the WDN, considering pipe leakage, pipe bursts, and variations in node flow resulting from changes in water pressure. It characterizes the functions of the WDN through hydraulic service satisfaction and quantifies system resilience using a performance response function. Additionally, it determines the optimal dispatch strategy for emergency repair teams and the optimal emergency repair sequence for earthquake-damaged networks using a genetic algorithm. Furthermore, a comprehensive computational platform has been developed to systematically analyze and optimize seismic resilience strategies for WDNs. The feasibility of the proposed method is demonstrated through an example involving the WDN in Xi’an City. The results indicate that the single-objective seismic resilience improvement method based on the hydraulic recovery index is the most effective for enhancing the seismic resilience of the WDN. In contrast, the multi-objective method proposed in this article reduces repair time by 17.9% and repair costs by 3.4%, while only resulting in a 0.2% decrease in the seismic resilience of the WDN. This method demonstrates the most favorable comprehensive restoration effect, and the success of our method in achieving a symmetrically balanced restoration outcome demonstrates its value. The proposed methodology and software can provide both theoretical frameworks and technical support for urban WDN administrators. Full article

At present, the research on bridge structure health monitoring mainly focuses on discovering existing structural damage and less on predicting when the damage will occur in the future. This paper proposes a fatigue damage prognosis method for the main girders of cable-stayed bridges based on wavelet neural networks (WNNs). This method integrates WNN with multi-scale finite element modeling to predict fatigue damage progression. First, the theoretical foundation and implementation algorithms of the WNN are elaborated on and applied to forecast the future load environments of cable-stayed bridges. Subsequently, multi-scale finite element models are employed to derive stress influence lines for critical fatigue-prone regions in the main girder of the cable-stayed bridge. Finally, fatigue reliability methods are utilized to predict the fatigue reliability indices, service life, and failure probabilities of critical fatigue details. The proposed prognosis method in this paper can accurately predict the future operation conditions and remaining service life of bridge structures so as to provide a more reasonable maintenance strategy for bridge structures. Full article

Elevators are a vital part of urban infrastructure, playing a key role in smart cities where increasing population density has driven the rise in taller buildings. As an essential means of vertical transportation, elevators have become an integral part of daily life, making their design, construction, and maintenance crucial to ensuring safety and compliance with evolving industry standards. The safety of elevator systems depends on the continuous monitoring and fault-free operation of Permanent Magnet Synchronous Motor (PMSM) drives, which are critical to their performance. Furthermore, the fault-free operation of PMSM drives reduces operating costs, increases service life, and improves reliability. The PMSM drive components may be susceptible to electrical, mechanical, and thermal faults that, if undetected, can lead to operational disruptions or safety risks. The integration of artificial intelligence and Internet of Things (IoT) technologies can enhance fault prediction, reducing downtime and improving efficiency. Ongoing challenges such as managing machine thermal load and developing more durable materials for PMSMs require the development of suitable models that are adapted to existing drive systems. The proposed framework for fault prediction is validated on a real residential elevator equipped with a PMSM drive. Multimodal signal data is processed through a Generative Adversarial Network (GAN)-enhanced Positive Unlabeled (PU) classifier and a Reinforcement Learning (RL)-based adaptive decision engine, enabling robust and scalable fault prediction in a non-intrusive fashion. Full article

While digital transformation in e-commerce receives the most publicity, applications in energy and water utilities have been ongoing for decades. Using a methodology based on a systematic review, the paper offers a model of how it occurs in water utilities, reviews experiences from the field, and derives lessons learned to create a road map for future research and implementation. Innovation in water utilities occurs more in the field than through organized research, and utilities share their experiences globally through networks such as water associations, focus groups, and media outlets. Their digital transformation journeys are evident in business practices, operations, and asset management, including methods like decision support systems, SCADA systems, digital twins, and process optimization. Meanwhile, they operate traditional regulated services while being challenged by issues like aging infrastructure and workforce capacity. They operate complex and expensive distribution systems that require grafting of new controls onto older systems with vulnerable components. Digital transformation in utilities is driven by return on investment and regulatory and workforce constraints and leads to cautious adoption of innovative methods unless required by external pressures. Utility adoption occurs gradually as digital tools help utilities to leverage system data for maintenance management, system renewal, and water loss control. Digital twins offer the advantages of enterprise data, decision support, and simulation models and can support distribution system optimization by integrating advanced metering infrastructure devices and water loss control through more granular pressure control. Models to anticipate water main breaks can also be included. With such advances, concerns about cyber security will grow. The lessons learned from the review indicate that research and development for new digital tools will continue, but utility adoption will continue to evolve slowly, even as many utilities globally are too stressed with difficult issues to adopt them. Rather than rely on government and academics for research support, utilities will need help from their support community of regulators, consultants, vendors, and all researchers to navigate the pathways that lie ahead. Full article

Under the background of intensified global economic fluctuations, to prevent the systemic risk of real estate (e.g., the U.S. subprime crisis), this study constructs a linkage network of the real estate industry in the U.S. based on the complex network method, reveals the fluctuation diffusion mechanism, identifies the key pivotal industries through the network characteristic indicators, and analyses the characteristics of the fluctuation conduction paths by applying the industrial fundamental association trees. The study found that (1) the U.S. real estate industry is a ‘supply hub’ industry, with first-order and second-order weighted degrees of mean 6.78, 3.98, and significant asymmetry in the supply structure of the industrial network; (2) industries like architectural, engineering, and related services (541300), nonresidential maintenance and repair (230301), and electric power generation, transmission, and distribution (221100) show high degree centrality and betweenness centrality. Their strong propagation and control capabilities form real estate fluctuations’ core transmission mechanisms; (3) foundational association trees reveal long, broad propagation paths where financial investment and energy-supply sectors act as “traffic hubs,” decisively influencing risk diffusion depth and breadth. Targeted policy recommendations address four dimensions: optimizing industrial chain structures, strengthening financial risk isolation, improving housing supply systems, and enhancing policy coordination. This aims to help China avoid U.S.-style real-estate-bubble risks and achieve coordinated real estate macroeconomy development. Full article

Tree root intrusion can cause failures of underground sewer pipes and thus represent a major water asset management issue. If tree root intrusion is not detected early, this may lead to the interruption of wastewater services and high costs of repair to the pipeline. The objectives of this review are to assess the existing maintenance strategies, explore suitable strategies for Australia and similar settings around the world, and identify possible factors and predictive tools. Maintenance strategies can be divided into two categories: reactive and proactive approaches. The current reactive approaches are (1) mechanical techniques to clean the root mass in pipe networks and (2) chemical techniques to remove the root mass and control future growth. The literature suggests that the reactive approaches often provide only partial solutions. The proactive approaches, guided by a predictive model of tree root intrusion and its related factors, showed the potential to improve maintenance and limit the risk of the damage from re-occurring. Predictive models could help to evaluate the risk of planting trees in different conditions and minimise the damage of tree root intrusion after further multifactor investigations. Full article

Vehicle owners often use certified service centers throughout the warranty period, which usually extends for five years after buying. Nonetheless, after this timeframe concludes, a large number of owners turn to unapproved service providers, mainly motivated by financial factors. This change signifies a significant drop in income for automakers and their certified service networks. To tackle this issue, manufacturers utilize customer relationship management (CRM) strategies to enhance customer loyalty, usually depending on segmentation methods to pinpoint potential clients. However, conventional approaches frequently do not successfully forecast which clients are most likely to need or utilize maintenance services. This research introduces a machine learning-driven framework aimed at forecasting the probability of monthly maintenance attendance for customers by utilizing an extensive historical dataset that includes information about both customers and vehicles. Additionally, this predictive approach supports workforce planning and scheduling within after-sales service centers, aligning with AI-driven labor optimization frameworks such as those explored in the AI4LABOUR project. Four algorithms in machine learning—Decision Tree, Random Forest, LightGBM (LGBM), and Extreme Gradient Boosting (XGBoost)—were assessed for their forecasting capabilities. Of these, XGBoost showed greater accuracy and reliability in recognizing high-probability customers. In this study, we propose a machine learning framework to predict vehicle maintenance visits for after-sales services, leading to significant operational improvements. Furthermore, the integration of AI-driven workforce allocation strategies, as studied within the AI4LABOUR (reshaping labor force participation with artificial intelligence) project, has contributed to more efficient service personnel deployment, reducing idle time and improving customer experience. By implementing this approach, we achieved a 20% reduction in information delivery times during service operations. Additionally, survey completion times were reduced from 5 min to 4 min per survey, resulting in total time savings of approximately 5906 h by May 2024. The enhanced service appointment scheduling, combined with timely vehicle maintenance, also contributed to reducing potential accident risks. Moreover, the transition from a rule-based maintenance prediction system to a machine learning approach improved efficiency and accuracy. As a result of this transition, individual customer service visit rates increased by 30%, while corporate customer visits rose by 37%. This study contributes to ongoing research on AI-driven workforce planning and service optimization, particularly within the scope of the AI4LABOUR project. Full article

The rapid growth of urban metro systems requires novel strategies to guarantee operational dependability and energy efficiency. This article describes a new way to use deep reinforcement learning (DRL) to help metro networks with predictive maintenance that adapts to changing conditions and energy optimization. We used real-world transit data from the General Transit Feed Specification (GTFS) to model the maintenance scheduling and energy management problem as a Markov Decision Process. This included important operational metrics like peak-hour demand, train arrival times, and station stop densities. A custom reinforcement learning environment mimics the changing conditions of metro operations. Deep Q-Networks (DQNs) and Proximal Policy Optimization (PPO) sophisticated deep reinforcement learning techniques were used to identify the optimal policies for decreasing energy consumption and downtime. The PPO hyperparameters were additionally optimized using Bayesian optimization by implementing Optuna, which produces a far greater performance than baseline DQNs and basic PPO. Comparative tests showed that our improved DRL-based method improves the accuracy of predictive maintenance and the efficiency of energy use, which lowers operational costs and raises the dependability of the service. These results show that advanced learning and optimization techniques could be added to public transportation systems in cities. This could lead to more sustainable and smart transportation management in big cities. Full article

Progressive advancements in the global economy and technology have propelled human civilization forward; however, they have also inflicted significant harm on the global ecological environment. In the present era, electric vehicle (EV) technology is playing a vital role due to its environmentally friendly technological advances. However, widespread adoption of EVs has been hindered by their limited travel range, inadequate charging infrastructure, and high costs. This can be closely observed when we assess the adoption of electric vehicles (EVs) among motorcycle taxi drivers, commonly called ‘pilots,’ in Goa, India. Motorcycle taxis are crucial in Goa’s transportation network, providing affordable, efficient, and door-to-door services, especially in regions with limited public transport options. However, the rising costs of petrol and vehicle maintenance have adversely affected the income of these pilots, prompting concerns about their willingness to adopt EVs. This study aims to analyze the factors prompting the behavioral intention to adopt EVs by motorcycle taxi pilots in Goa, India, focusing on six key determinants: charging infrastructure, effort expectancy, performance expectancy, price value, social influence, and satisfaction with incentive policies. A quantitative approach was employed, utilizing stratified proportionate random sampling techniques to collect data from 242 motorcycle taxi pilots registered with the Goa State Government Transport Department. It was analyzed using partial least squares-structural equation modeling (PLS-SEM) through Smart-PLS 4.0 software. The research highlights that performance expectancy and price value are the potential motivators for the adoption of electric vehicles. These findings suggest that pilots are more likely to embrace EVs when they perceive tangible benefits in performance and find the cost reasonable in relation to the value offered. The results offer actionable insights for policymakers, manufacturers, and other stakeholders. These insights can guide strategic decisions and policy frameworks aimed at fostering a sustainable and user-centric transportation ecosystem. Full article

Modern data centers face increasing complexity with distributed microservice architectures, making anomaly detection and fault localization challenging yet critical. Traditional monitoring sensor tools struggle with heterogeneous metrics, temporal correlations, and precise root cause analysis in these environments. This paper proposes a dual-channel deep learning framework that integrates Temporal Convolutional Networks with Variational Autoencoders to address these challenges. Our approach employs contrastive learning to create unified representations of diverse service metrics and incorporates causal inference mechanisms to trace fault propagation paths. We evaluated our framework using a semi-supervised learning approach that leveraged both labeled anomalies and abundant normal data, achieving 95.4% detection accuracy, 93.8% F1-score, and 87.6% precision in fault component localization. The system reduced the average troubleshooting time by 43% and false localization rates by 31% compared to state-of-the-art methods, while maintaining a computational efficiency suitable for real-time monitoring. These results demonstrate the effectiveness of our approach in identifying and precisely localizing anomalies in complex microservice environments through intelligent sensing of system metrics, enabling proactive maintenance strategies that minimize service disruptions. Full article