A review on convolutional neural network in rolling bearing fault diagnosis

Measurement Science and Technology, Год журнала: 2024, Номер 35(7), С. 072002 - 072002

Опубликована: Март 19, 2024

Abstract The health condition of rolling bearings has a direct impact on the safe operation rotating machinery. And their working environment is harsh and complex, which brings challenges to fault diagnosis. With development computer technology, deep learning been applied in field diagnosis rapidly developed. Among them, convolutional neural network (CNN) received great attention from researchers due its powerful data mining ability feature adaptive ability. Based recent research hotspots, history trend CNN summarized analyzed. Firstly, basic structure introduced important progress classical models for bearing years studied. problems with classic algorithm have pointed out. Secondly, solve above problems, combined achievements, various methods principles optimizing are compared perspectives extraction, hyperparameter optimization, optimization. Although significant made based CNN, there still room improvement addressing issues such as low accuracy imbalanced data, weak model generalization, poor interpretability. Therefore, future networks discussed finally. transfer improve generalization interpretable used increase interpretability networks.

Язык: Английский

---

Feature selection for chillers fault diagnosis from the perspectives of machine learning and field application

Energy and Buildings, Год журнала: 2024, Номер 307, С. 113937 - 113937

Опубликована: Фев. 1, 2024

Язык: Английский

---

A review on hybrid physics and data-driven modeling methods applied in air source heat pump systems for energy efficiency improvement

Renewable and Sustainable Energy Reviews, Год журнала: 2024, Номер 204, С. 114804 - 114804

Опубликована: Авг. 14, 2024

Язык: Английский

---

Improved convolutional neural network chiller early fault diagnosis by gradient-based feature-level model interpretation and feature learning

Applied Thermal Engineering, Год журнала: 2023, Номер 236, С. 121549 - 121549

Опубликована: Сен. 7, 2023

Язык: Английский

---

An interpretable graph convolutional neural network based fault diagnosis method for building energy systems

Building Simulation, Год журнала: 2024, Номер 17(7), С. 1113 - 1136

Опубликована: Июнь 20, 2024

Язык: Английский

---

A Hybrid Transfer Learning to Continual Learning Strategy for Improving Cross-building Energy Prediction in Data Increment Scenario

Journal of Building Engineering, Год журнала: 2024, Номер 95, С. 110093 - 110093

Опубликована: Июль 16, 2024

Язык: Английский

---

Interpretability assessment of convolutional neural network-based fault diagnosis for air handling units working in three seasons

Energy and Buildings, Год журнала: 2024, Номер unknown, С. 114876 - 114876

Опубликована: Окт. 1, 2024

Язык: Английский

---

A hybrid artificial intelligence algorithm for fault diagnosis of hot rolled strip crown imbalance

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 130, С. 107763 - 107763

Опубликована: Дек. 26, 2023

Язык: Английский

---

Examining the impact of common faults on chiller performance through experimental investigation and parameter sensitivity analysis

Energy and Buildings, Год журнала: 2024, Номер 317, С. 114389 - 114389

Опубликована: Июнь 7, 2024

Язык: Английский

---

Model Interpretation and Interpretability Performance Evaluation of Graph Convolutional Network Fault Diagnosis for Air Handling Units

Journal of Building Engineering, Год журнала: 2025, Номер unknown, С. 112048 - 112048

Опубликована: Фев. 1, 2025

Язык: Английский

---