A5071134888- Advanced Battery Technologies Research
- Advancements in Battery Materials
- Fault Detection and Control Systems
- Reliability and Maintenance Optimization
- Machine Fault Diagnosis Techniques
- Gear and Bearing Dynamics Analysis
- Industrial Vision Systems and Defect Detection
- Anomaly Detection Techniques and Applications
- Electric Vehicles and Infrastructure
- Engineering Diagnostics and Reliability
- Non-Destructive Testing Techniques
- Structural Health Monitoring Techniques
- Electrochemical Analysis and Applications
- Fatigue and fracture mechanics
- Control Systems and Identification
- Model Reduction and Neural Networks
- Advanced machining processes and optimization
- Advanced Control Systems Optimization
- Electrochemical sensors and biosensors
- Robot Manipulation and Learning
- Structural Integrity and Reliability Analysis
- Machine Learning and ELM
- Manufacturing Process and Optimization
- Advanced Nanomaterials in Catalysis
- Time Series Analysis and Forecasting
Qingdao University of Science and Technology
2024
Huazhong University of Science and Technology
2019-2023
State Key Laboratory of Digital Manufacturing Equipment and Technology
2020
Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing
2020
In industrial applications, nearly half the failures of motors are caused by degradation rolling element bearings (REBs). Therefore, accurately estimating remaining useful life (RUL) for REBs crucial importance to ensure reliability and safety mechanical systems. To tackle this challenge, model-based approaches often limited complexity mathematical modeling. Conventional data-driven approaches, on other hand, require massive efforts extract features construct health index. paper, a novel...
Real-time and personalized lithium-ion battery health management is conducive to safety improvement for end-users. However, prognostic of the status still challenging due diverse usage interests, dynamic operational patterns limited historical data. We generate a comprehensive dataset consisting 77 commercial cells (77 discharge protocols) with over 140 000 charge–discharge cycles—the largest our knowledge its kind, develop transfer learning framework realize real-time prediction unseen...
The manufacturing sector is envisioned to be heavily influenced by artificial-intelligence-based technologies with the extraordinary increases in computational power and data volumes. A central challenge lies requirement of a general framework ensure satisfied diagnosis monitoring performances different applications. Here, we propose data-driven, end-to-end for systems. This framework, derived from deep-learning techniques, evaluates fused sensory measurements detect even predict faults...
State of health (SOH) estimation lithium-ion batteries (LIBs) is critical importance for battery management systems (BMSs) electronic devices. An accurate SOH still a challenging problem limited by diverse usage conditions between training and testing LIBs. To tackle this problem, article proposes transfer learning-based method personalized new battery. More specifically, convolutional neural network (CNN) combined with an improved domain adaptation used to construct model, where the CNN...
The state of health (SOH) is a critical factor in evaluating the performance lithium-ion batteries (LIBs). Due to various end-user behaviors, LIBs exhibit different degradation modes, which makes it challenging estimate SOHs personalized way. In this article, we present novel particle swarm optimization-assisted deep domain adaptation (PSO-DDA) method SOH manner, where new strategy put forward reduce cross-domain distribution discrepancy. standard PSO algorithm exploited automatically adjust...
For the fault diagnosis problems of rotating machinery in real industrial practice, measurement data with imbalanced class distributions negatively affect diagnostic performance most conventional machine learning classification algorithms since equal cost weights are assigned to different classes. Meanwhile, widely used traditional generation methods for problem limited by dependencies over time continuity. To fill this research gap, paper develops a new framework based on adversarial neural...
Stochastic differential equations (SDEs) are mathematical models that widely used to describe complex processes or phenomena perturbed by random noise from different sources. The identification of SDEs governing a system is often challenge because the inherent strong stochasticity data and complexity system's dynamics. practical utility existing parametric approaches for identifying usually limited insufficient resources. This study presents novel framework leveraging sparse Bayesian...
Abstract The rising demands of more reliable and stable electrical systems attach importance to accurate Remaining Useful Life (RUL) prediction the lithium-ion batteries. As artificial intelligence machine learning techniques advance, data-driven methods especially deep algorithms have become star in RUL prediction. Recurrent Neural Networks (RNNs) their variants such as Long Short Term Memory proven effectiveness various sequential tasks. However, due its iterative nature along time axis,...
The state-of-health (SOH) is an important indicator in battery management system. In order to accurately estimate the SOH of lithium-ion batteries, improved Gaussian process regression (GPR) model named deep kernel learning (DKL), combining with dynamic time warping method proposed this paper. Use voltage curve during constant current charing procedure, two features are extracted as inputs DKL model. Particularly, feature by which makes full use information avoid a subjective extraction....
Fault diagnosis of rolling bearing plays an important role for the assessment system reliability. Meanwhile, number fault data tend to be much less than normal in real application. This imbalanced problem will greatly reduce accuracy most traditional methods. Especially multi-classification problem, some conventional methods can not have good performance on dealing with unbalanced data. In this paper, a method based generative adversarial network which generates compensation is proposed. use...
Early prediction of battery lifetime is crucial for manufacturers to sort and group lithium-ion batteries (LIBs). This article introduces a regressive multiple-source domain adaption (RMDA) method accurate early with multiple LIB datasets. First, common feature extractor used extract features from different domains. Then, the domain-specific extractors followed by maximum mean discrepancy loss are utilized reduce shift source Next, regressors adopted predict domains target domain. The...
Real-time fault diagnosis of rolling bearing is a challenging issue for industry. Although artificial intelligence-based technologies could be well used bearing, the factories may not take into account deployment algorithms. To tackle issue, this work proposes flexible system algorithm where required Convolutional Neural Network (CNN) model deployed on Field Programmable Gate Array (FPGA) to identify working conditions using vibration signals. The experimental results show that performs...