A5027785791- Multi-Criteria Decision Making
- Bayesian Modeling and Causal Inference
- Rough Sets and Fuzzy Logic
- Fault Detection and Control Systems
- Risk and Safety Analysis
- Infrastructure Maintenance and Monitoring
- Advanced Decision-Making Techniques
- Software Reliability and Analysis Research
- Technology Assessment and Management
- Fuzzy Logic and Control Systems
- Systems Engineering Methodologies and Applications
- Military Defense Systems Analysis
- Machine Learning and Data Classification
- Data Mining Algorithms and Applications
- Metaheuristic Optimization Algorithms Research
- Biomedical Text Mining and Ontologies
- Evaluation and Optimization Models
- Fire Detection and Safety Systems
- Occupational Health and Safety Research
- Neural Networks and Applications
- Topic Modeling
- Anomaly Detection Techniques and Applications
- Software Engineering Research
- Natural Language Processing Techniques
- Infrastructure Resilience and Vulnerability Analysis
Hangzhou Dianzi University
2018-2025
Shenzhen Institute of Information Technology
2018-2024
National University of Defense Technology
2010-2024
Gansu Agricultural University
2024
Huazhong University of Science and Technology
2023
Hefei University of Technology
2020-2022
State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System
2022
Soochow University
2022
First Affiliated Hospital of Soochow University
2022
Nanyang Technological University
2006-2021
A transparent digital twin (DT) is designed for output control using the belief rule base (BRB), namely, DT-BRB. The goal of DT-BRB not only to model complex relationships between system inputs and but also conduct by identifying optimizing key parameters in inputs. proposed approach composed three major steps. First, BRB adopted physical system. Second, an analytical procedure identify with highest contribution output. Being consistent inferencing, integration, unification procedures BRB,...
The belief rule-base (BRB) model is a new intelligent expert system with the characteristics of both and data-driven model. In BRB there are many if-then rules which use degrees to express various types uncertain information, including fuzziness, randomness, ignorance. As semi-quantitative modeling tool for complex systems, has superiorities dealing numerical quantitative data linguistic qualitative knowledge that derived from heterogeneous sources. Moreover, it also white box approach can...
In current studies of the belief rule base (BRB) model, attributes are assumed to be fully reliable and observation data directly used as input. However, in engineering practice, may affected by some disturbance factors, including quality sensors noise environment. Then, reliability modeling accuracy BRB is therefore influenced. As such, a new model with attribute (BRB-r) proposed this paper. particular, calculation method given based on statistical method. Moreover, integrate into BRB-r,...
It is vital to online assess the safety of a complex dynamic system by taking into account current state, degradation trend, and historical records together. This paper proposes new assessment model with an algorithm based on evidential reasoning (ER) approach. does not only take relative importance each indicator, but also consider reliability indicator. To obtain integrated level, multiple indicators are fused at first "history," "current," "future" states then integrated. First,...
It is vital to assess the lives of newly developed products by using failure data from various testing environments. In current methods, two steps are generally included. The first step transforming under one environment into actual working environment, and second integrating all a unified result. However, most available methods cannot use information that includes part expert knowledge simultaneously. To resolve above issue, based on belief rule base (BRB) evidential reasoning (ER)...
Nonlinear complex system modeling has drawn attention from diverse fields and many approaches have been developed. Among those approaches, the advantages of belief rule base (BRB) expert shown for managing multiple types information under uncertainty nonlinearity present in theoretical practical systems. However, two challenges still need to be addressed. First, BRB needs downsized conserve computational effort. For this challenge, a new disjunctive assumption is applied, which can...
The combinatorial explosion problem is a great challenge for belief rule base (BRB) when complex system has overnumbered attributes and/or referenced values the attributes. This because BRB conventionally constructed under conjunctive assumption, BRB, which requires covering each possible combination of all To solve this challenge, study proposes generic modeling, inferencing, and optimization approach disjunctive that can significantly reduce its size. First, defined based on mathematical...
Extended belief-rule-based (EBRB) system is a representative rule-based and has attracted much attention due to its capability of solving the problems combinatorial explosion time-consuming optimization incurred by system. Despite their advantages, development EBRB suffers from some shortcomings, such as unreasonable calculation similarity between input antecedent belief distributions (BDs), inaccurate individual matching degrees rule weights, inefficient determination activation rules. To...
The performance of vector-controlled sensorless induction motor drives is generally poor at very low speeds, especially zero speed due to offset and drift components in the acquired feedback signals, increased sensitivity dynamic model parameter mismatch resulting from stator resistance variations. estimation adversely affected by variations temperature frequency changes. This particularly significant speeds where calculated flux deviates its set values. Therefore, it necessary compensate...