Vibration amplitude prediction method for turbine rotor sliding bearing based on YOLOv8 optimized attention mechanism

LI Yachao; LIU Haoyu; XU Haokang; GUAN Yuhan; QI Zhantong; GU Yujiong

doi:10.19666/j.rlfd.202412263

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Vibration amplitude prediction method for turbine rotor sliding bearing based on YOLOv8 optimized attention mechanism

更新时间：2025-09-26

- Vibration amplitude prediction method for turbine rotor sliding bearing based on YOLOv8 optimized attention mechanism
- Thermal Power Generation Vol. 54, Issue 5, Pages: 122-131(2025)
- 作者机构：
  
  华北电力大学能源动力与机械工程学院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202412263
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
LI Yachao, LIU Haoyu, XU Haokang, et al. Vibration amplitude prediction method for turbine rotor sliding bearing based on YOLOv8 optimized attention mechanism[J]. Thermal power generation, 2025, 54(5): 122-131.
DOI：

LI Yachao, LIU Haoyu, XU Haokang, et al. Vibration amplitude prediction method for turbine rotor sliding bearing based on YOLOv8 optimized attention mechanism[J]. Thermal power generation, 2025, 54(5): 122-131. DOI： 10.19666/j.rlfd.202412263.

摘要

滑动轴承的早期故障具有隐秘性，为了准确预测其振动幅值，提出了一种结合YOLOv8优化的CBAM(convolutional block attention module)的深度学习模型，在Backbone和Neck之间嵌入CBAM模块以提升模型对重要振动特征的关注度，同时采用改进的完全交并比损失函数，提高目标检测精度。同时，考虑到振动数据的非线性、非稳态特性，在模型中添加经验模态分解（empirical mode decomposition

EMD）方法对振动状态数据进行预测，以提高预测的准确性。结果表明：该方法在600MW汽轮机运行数据集上相较于传统YOLOv8和YOLOv7，在目标检测准确率上分别提升2.85百分点和8.50百分点，均方根误差和平均绝对误差均有所减少；此外，在高噪声环境下，该模型的误差波动较传统方法降低30%，表现出更强的泛化能力和稳定性。

Abstract

The early faults of sliding bearings are highly concealed. To accurately predict their vibration amplitude

a deep learning model incorporating a YOLOv8-optimized CBAM attention mechanism is proposed.The CBAM module is embedded between the Backbone and Neck to enhance the model's focus on critical vibration features. Additionally

an improved complete intersection over union loss function is employed to enhance object detection accuracy. Considering the nonlinear and non-stationary characteristics of vibration data

the empirical mode decomposition(EMD) method is integrated into the model to improve the accuracy of vibration state prediction. The experimental results show that

on the 600 MW steam turbine operation dataset

this method improves the detection accuracy by 2.85 percentage points and 8.50 percentage points compared with that of the conventional YOLOv8 and YOLOv7

respectively. Moreover

the root mean square error(RMSE) is reduces

and the mean absolute error(MAE) decreases. Furthermore

in high-noise environments

the model's error fluctuation reduces by 30% compared with that of the conventional methods

demonstrating stronger generalization ability and stability.

关键词

Keywords

references

Views

1113

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

FILTRATION TREATMENT OF THERMODYNAMIC PARAMETERS CONCERNING THERMAL POWER UNIT BASED ON EMPIRICAL MODE DECOMPOSITION

Research on hybrid energy storage planning of isolated integrated energy system based on EMD decomposition

NO_x emission prediction of coal-gas hybrid combustion plant based on the combination of attention mechanism model

Online learning model of backpressure prediction for direct air-cooled unit under flexible peak regulation

Research on network intrusion detection method for industrial control system based on CNN-LSTM-Attention

Related Author

LAI Fei11.Xi'an Thermal Power Research Institute Co Lt

GE Xin1

YANG Dong1

WANG Zhi-wei1

LI Heng3

LI Yun2

JIANG Hao1

GAO Mingfei

Related Institution

西安热工研究院有限公司

贵州电力调度通信局

Guizhou Electric Power Dispatching and Communication Bureau

4:西安热工研究院有限公司

Department of Power Engineering

AI问答

⁰