A5084856540- Advanced Algorithms and Applications
- Spectroscopy and Chemometric Analyses
- Fault Detection and Control Systems
- Mineral Processing and Grinding
- Water Quality Monitoring and Analysis
- Anomaly Detection Techniques and Applications
- Advanced Chemical Sensor Technologies
- Spectroscopy Techniques in Biomedical and Chemical Research
- Time Series Analysis and Forecasting
- Smart Grid and Power Systems
- Advanced Sensor and Control Systems
- Metaheuristic Optimization Algorithms Research
- Power Systems and Renewable Energy
- Power Systems and Technologies
- Advanced Control Systems Optimization
- Artificial Immune Systems Applications
- Smart Grid Energy Management
- Distributed and Parallel Computing Systems
- Industrial Technology and Control Systems
- Adaptive Control of Nonlinear Systems
- Industrial Vision Systems and Defect Detection
- Advanced Measurement and Detection Methods
- Machine Fault Diagnosis Techniques
- Distributed Control Multi-Agent Systems
- Neural Networks and Applications
Xi'an Jiaotong University
2016-2025
State Key Laboratory of Electrical Insulation and Power Equipment
2015-2025
Beijing University of Chemical Technology
2025
Fudan University
2012-2025
Hunan University
2025
Yangtze River Pharmaceutical Group (China)
2024
Shaanxi Normal University
2021-2024
Shenyang Aerospace University
2024
Anhui Business College
2024
Aviation Industry Corporation of China (China)
2024
With the prevalence of smart appliances, meters, and Internet Things (IoT) devices in grids, artificial intelligence (AI) built on rich IoT big data enables various energy analysis applications brings intelligent personalized services for users. In conventional AI (AIoT) paradigms, a wealth individual distributed across users' needs to be migrated central storage (e.g., cloud or edge device) knowledge extraction, which may impose severe privacy violation misuse risks. Federated learning, as...
Abstract We discuss an object-oriented, component-based architecture for a parallel reservoir simulator. The successfully balances the need extensibility, maintainability, and reuse with efficient computation. Parallelism is hidden from application developer via set of abstractions unifying framework that supports static dynamic load balancing on unstructured structured grids. explain how simulator black oil compositional models within general formulation, it achieves scalability all major...
This article proposes single-objective/multiobjective cat swarm optimization clustering algorithms for data partition. The proposed methods use the to search optimal. position of tightly associates with centers and is updated by two submodes: seeking mode tracing mode. uses simulated annealing strategy update at a probability. Inspired quantum theories, adopts model in whole solution space. First, single-objective method cohesion as objective function, which kernel applied. For considering...
Carbon nanotubes (CNTs) have been recently fabricated into macroscopic films to improve their practical applications in a wide variety of fields, e.g. electrode materials. In the current CNT electrodes however, CNTs are typically interconnected form networks or aligned as lots bundles, and resulting photovoltaic devices based on shown low energy conversion efficiencies. Here we report new general drying approach make well distributed film which exhibits rapid charge separation transport. As...
Based on the Lorenz chaotic system, this paper constructs a new four-dimensional hyperchaotic and studies basic dynamic behaviours of system. The Routh—Hurwitz theorem is applied to derive stability conditions proposed Furthermore, based Lyapunov theory, an adaptive controller designed system controlled at equilibrium point. Numerical simulation results are presented illustrate effectiveness method.
This paper establishes a short-term decision model, based on robust optimization, for an electricity retailer to determine the procurement and retail prices. The process includes purchasing from generation companies spot market. selling prices of customers are time-of-use (TOU) pricing which is widely employed in modern market as demand response program. objective model maximize expected profit through optimizing strategy scheme. A price elasticity matrix (PEM) adopted response. Also,...
The vehicle routing problem (VRP), as one of the classic combinatorial optimization problems, has garnered widespread attention in recent years. Existing deep reinforcement learning (DRL)-based methods predominantly focus on node information, neglecting edge information inherent graph structure. Moreover, solution trajectories produced by these tend to exhibit limited diversity, hindering a thorough exploration space. In this work, we propose novel Edge-Driven Multiple Trajectory Attention...
Abstract Due to sensor failures, interruptions data transmission, and other factors affecting industrial processes, whole segments may be missing from a dataset, which can reduce the accuracy of an established downstream data-driven model. Existing methods usually treat issues filling building model independently, do not fully consider requirements tasks, resulting in insufficient for data. In view this, fast gentle conditional diffusion is proposed this paper. The main contributions paper...
Highly flexible regions were targeted for successful modification to enhance enzyme stability. However, this approach could not cover all key sites. Residues in certain rigid are also crucial protein This study proposed a short-loop engineering strategy that explores "sensitive residues" and mutated them hydrophobic residues with large side chains fill the cavities, thereby improving thermal identified sensitive of three enzymes: lactate dehydrogenase from Pediococcus pentosaceus, urate...
Abstract Magnetic ordering modulation is essential for enhancing the functionality of materials and devices. However, achieving precise control over orientation positioning magnets within nanostructures through spatial manipulation remains a significant challenge due to magnetic self‐aggregation. Herein, strategy proposed quantitatively regulate viscous forces acting on particles spray stream under an applied electric field, modifying kinetic energy customize distribution. Notably, this...
Recently, the vehicle routing problem with pickup and delivery (VRP-PD) has attracted increasing interest due to its widespread applications in real-life logistics transportation. However, existing learning-based methods often fail fully exploit hierarchical graph structures, leading suboptimal performance. In this study, we propose a graph-driven deep reinforcement learning (GDRL) approach that employs an encoder–decoder framework address shortcoming. The encoder incorporates stacked...
In recent years, routing problems have attracted significant attention in the fields of operations research and computer science due to their fundamental importance logistics transportation. However, most existing learning-based methods employ simplistic context embeddings represent environment, which constrains capacity capture real-time visitation dynamics. To address this limitation, we propose a deep reinforcement decision-making framework (DRL-DM) built upon an encoder–decoder...
This article deals with the utterance-level modalities missing problem uncertain patterns on emotion recognition in conversation (ERC) task. Present models generally predict speaker's emotions by its current utterance and context, which is degraded modality considerably. Our work proposes a framework missing-modality robust (M2R2), trains model iterative data augmentation learned common representation. First, network called party attentive (PANet) designed to classify emotions, tracks all...
The wind turbine blades are the key part of converting energy into electrical energy. Currently fault diagnosis is mainly dependent on manual visual inspections. In this paper, an image based method for proposed. blade damage recognition realized by two-stage learning. first learning stage deep feature extractor stage. A convolutional neural network (ConvNet) built and trained ILSVRC dataset, owing to lack images. ConvNet without last two layer extracted as second pattern Deep features...
Abstract With the deterioration of ecological environment and improvement consumer environmental awareness, a number firms are actively engaging in product innovation to enhance greenness. In this paper, we develop differential game involving two competing firms, each which produces sells one green end consumers. The carry out investments improve customers' perceived greenness also determine their own retail prices. Each firm's demand is linearly dependent on its price investment, rival's...