A5100723083- Fault Detection and Control Systems
- Software System Performance and Reliability
- Advanced Battery Technologies Research
- Automotive and Human Injury Biomechanics
- Product Development and Customization
- Service-Oriented Architecture and Web Services
- Supply Chain and Inventory Management
- Advancements in Battery Materials
- Manufacturing Process and Optimization
- Machine Fault Diagnosis Techniques
- Power Systems and Renewable Energy
- Mechanical Engineering and Vibrations Research
- Industrial Technology and Control Systems
- Advanced Battery Materials and Technologies
- Evaluation and Optimization Models
- Data Mining Algorithms and Applications
- Face recognition and analysis
- Power Systems and Technologies
- Quality Function Deployment in Product Design
- Risk and Safety Analysis
- Target Tracking and Data Fusion in Sensor Networks
- Data Stream Mining Techniques
- Musculoskeletal pain and rehabilitation
- Integrated Energy Systems Optimization
- Web Data Mining and Analysis
Beijing Forestry University
2012-2024
Second Hospital of Anhui Medical University
2021-2024
Anhui Medical University
2021-2024
Xiangtan University
2022-2023
Guangxi University
2023
China Power Engineering Consulting Group (China)
2017-2023
Shandong Electric Power Engineering Consulting Institute Corp
2023
Fuyang Normal University
2023
Guilin University of Technology
2023
Xi'an Siyuan University
2023
Modern computing systems generate large amounts of log data. System administrators or domain experts utilize the data to understand and optimize system behaviors. Most logs are raw textual unstructured. One main fundamental challenge in automated analysis is generation events from logs. Log messages relatively short text but may have a vocabulary, which often result poor performance when applying traditional clustering techniques Other related methods various limitations only work well for...
This paper presents a class of risk measures to be used as damage indicators within particle filtering (PF)-based real-time prognosis algorithms, with application the case state-of-charge prediction in lithium-ion batteries. The proposed measure not only incorporates battery failure but also is for confidence on algorithm itself. In addition, novel simplified PF-based prognostic method estimate discharge time, while providing computationally inexpensive solution. Computing times both routine...
Visual design plays an important role in online display advertising: changing the layout of ad can increase or decrease its effectiveness, measured terms click-through rate (CTR) total revenue. The decision which lay- out to use for involves a trade-off: using provides feedback about effectiveness (exploration), but collecting that requires sacrificing immediate reward we already know is effective (exploitation). To balance exploration with exploitation, pose automatic selection as...
The cold-start problem has attracted extensive attention among various online services that provide personalized recommendation. Many vendors employ contextual bandit strategies to tackle the so-called exploration/exploitation dilemma rooted from problem. However, due high-dimensional user/item features and underlying characteristics of policies, it is often difficult for service providers obtain deploy an appropriate algorithm achieve acceptable robust economic profit.
Personalized recommendation services have gained increasing popularity and attention in recent years as most useful information can be accessed online real-time. Most recommender systems try to address the needs of users by virtue both user content information. Despite extensive advances, problem personalized remains challenging for at least two reasons. First, item repositories undergo frequent changes, which makes traditional algorithms ineffective. Second, so-called cold-start is...
Metal polyphosphides are regarded as the ideal anode candidates for sodium storage because of their high theoretical capacity, reasonable potential, and abundant resource alternative. However, most them suffer from irreversibility problems, reflected by low reversible inferior Coulombic efficiency (CE), rate capability, poor cycling stability. In this work, we systematically compare electrochemical behavior a variety bulks, discovering that CuP2 bulks have higher initial capacity (416 mAh...
Effective uncertainty management processes are essential elements in the design of prognostic modules if they to be viable for Integrated Vehicle Health Management (IVHM) systems. Modeling uncertainty, measurement and estimation uncertainties, future load among other factors, all potentially contribute uncertainty. This paper analyzes source uncertainties typical IVHM systems presents a rigorous set algorithms that generic capable addressing variety sources. Specifically, model parameter is...
Modern computing systems are instrumented to generate huge amounts of system logs and these data can be utilized for understanding complex behaviors. One main fundamental challenge in automated log analysis is the generation events from raw textual logs. Recent works apply clustering techniques translate messages into using only word/term information. In this paper, we first illustrate drawbacks existing event We then propose Log Tree, a novel algorithm-independent framework messages. Tree...
Conversion-type cathodes such as metal fluorides, especially FeF2 and FeF3 , are potential candidates to replace intercalation for the next generation of lithium ion batteries. However, application iron fluorides is impeded by their poor electronic conductivity, iron/fluorine dissolution, unstable cathode electrolyte interfaces (CEIs). A facile route fabricate a mechanical strong electrode with hierarchical electron pathways nanoparticles reported here. The /Li cell demonstrates remarkable...
In recent years, IT Service Providers have been rapidly transforming to an automated service delivery model. This is due advances in technology and driven by the unrelenting market pressure reduce cost maintain quality. Tremendous progress has made date towards attainment of truly delivery; that is, ability deliver same automatically using process with However, automating Incident Problem Management continuous be a difficult problem, particularly growing complexity environments. Software...
The competitive business climate and the complexity of IT environments dictate efficient cost-effective service delivery support services. These are largely achieved by automating routine maintenance procedures, including problem detection, determination resolution. System monitoring provides an effective reliable means for detection. Coupled with automated ticket creation, it ensures that a degradation vital signs, defined acceptable thresholds or conditions, is flagged as candidate sent to...
In recent years, IT service providers have rapidly achieved an automated delivery model. Software monitoring systems are designed to actively collect and signal event occurrences and, when necessary, automatically generate incident tickets. Repeating events similar tickets, which in turn a vast number of repeated problem resolutions likely be found earlier this paper, we develop techniques recommend appropriate resolution for incoming by making use similarities between the historical events....
Most mission planning algorithms are designed for healthy systems. When faults occur in a system, it is advantageous to optimize the plan by taking system health condition into consideration. In this paper, scheme proposed integrate real-time prognostics receding horizon path framework accommodate fault. scheme, state-of-charge of battery monitored and predicted particle-filtering based prognostic algorithm. The remaining useful life used minimize failure risk. A series experiments presented...
Today's competitive business climate and the complexity of IT environments dictate efficient cost effective service delivery support services. This is largely achieved through automating routine maintenance procedures including problem detection, determination resolution. System monitoring provides reliable means for detection. Coupled with automated ticket creation, it ensures that a degradation vital signs, defined by acceptable thresholds or conditions, flagged as candidate sent to...
Advanced manufacturing such as aerospace, semi-conductor, and flat display device often involves complex production processes, generates large volume of data. In general, the data comes from products with different levels quality, assembly line flows equipments, processing craft massive controlling parameters. The scale complexity is beyond analytic power traditional IT infrastructures. To achieve better performance, it imperative to explore underlying dependencies exploit insights improve...
The traction control system (TCS) of an electric vehicle is the key to ensuring sufficient stability when starts with a large throttle opening. Therefore, novel method for TCS single-motor, non-fully driven proposed in this paper. First, obtain road type and optimal slip rate driving wheels, extended Kalman filter (EKF) used estimate gradient total mass vehicle, unscented (UKF) adhesion coefficient. Second, controller based on wheels established coordinated motor torque brake pressure,...
Managing and reducing prognostic uncertainty is of significant importance to the success PHM applications. The focus prognosis management identify manage reducible uncertainties by applying available data using appropriate algorithms. Particularly for dynamic model-based systems, opportunities exist apply nonlinear filtering provide a systematic way dealing with propagation system damage at some future time, whenever imprecise diagnostic information obtained. goal this paper present...