Vibration Signal Trend Prediction Method for Straddle Monorail Train Gearbox Faults Under Multiple Operating Conditions

ZHAO Ling; WU Gang; WU Hangjun; ZHANG Na; TAN Jin

doi:10.7652/xjtuxb202511019

您当前的位置：

首页 >

文章列表页 >

Vibration Signal Trend Prediction Method for Straddle Monorail Train Gearbox Faults Under Multiple Operating Conditions

更新时间：2025-11-11

- Vibration Signal Trend Prediction Method for Straddle Monorail Train Gearbox Faults Under Multiple Operating Conditions
- Journal of Xi'an Jiaotong University Vol. 59, Issue 11, Pages: 198-208(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202511019
  CLC： TH165
- Received：12 March 2025，
  
  Published：10 November 2025
- 稿件说明：
移动端阅览
ZHAO Ling, WU Gang, WU Hangjun, et al. Vibration Signal Trend Prediction Method for Straddle Monorail Train Gearbox Faults Under Multiple Operating Conditions[J]. Journal of Xi'an Jiaotong University, 2025, 59(11): 198-208.
DOI：

ZHAO Ling, WU Gang, WU Hangjun, et al. Vibration Signal Trend Prediction Method for Straddle Monorail Train Gearbox Faults Under Multiple Operating Conditions[J]. Journal of Xi'an Jiaotong University, 2025, 59(11): 198-208. DOI： 10.7652/xjtuxb202511019.

摘要

针对低频调制干扰、非线性耦合谐波及工况依赖性特征导致跨座式单轨列车齿轮箱振动信号趋势预测精度低的问题，提出一种融合双向门控循环单元（BiGRU）与时序信息预测模型（Informer）的振动信号趋势预测模型。该模型利用BiGRU的门控机制抑制低频干扰，通过双向结构提取非线性耦合谐波特征，并借助自适应学习机制增强对不同运行工况的适应性；通过将Informer编码器中的多头注意力机制与空洞因果卷积结合扩大模型感受野，有效捕获时间序列的长期依赖特征，实现齿轮箱振动信号趋势预测。通过实验台采集的跨座式单轨列车齿轮箱故障数据集对模型进行了验证，在不同预测步长下，所提模型的平均绝对误差

MAE

、均方误差

MSE

以及均方根误差

RMSE

分别为0.2648、0.1160和0.3391，均低于自相关Transformer模型（Autoformer）、Informer和分解线性模型（Dlinear）；在正常工况、装配误差、内圈故障及疲劳磨损这4种工况条件下的预测精度稳定，绝对误差在0.21～0.35范围内。研究结果表明，所提模型在长短时间序列下的趋势预测精度均高于其他对比模型，多工况条件下的实验结果验证了所提模型的适应性和鲁棒性。

Abstract

To address the low prediction accuracy of vibration signal trends in straddle monorail train gearboxes caused by low-frequency modulation interference

nonlinear coupled harmonics

and condition-dependent characteristics

this study proposes a vibration signal trend prediction model that integrates a bidirectional gated recurrent unit (BiGRU) and a temporal information prediction model (Informer).This model utilizes the gating mechanism of BiGRU to suppress low-frequency interference

extracts nonlinear coupled harmonic features through its bidirectional structure

and enhances adaptability to various operating conditions through an adaptive learning mechanism. By combining the multi-head attention mechanism in the Informer encoder with dilated causal convolution

the model effectively expands its receptive field to capture long-term dependency features in time series data

thereby facilitating the trend prediction of gearbox vibration signals. Validation of the model is conducted using a dataset of gearbox fault data collected from a straddle monorail train gearbox test bench. The proposed model achieves average absolute error

mean square error

and root mean square error of 0.2648

0.1160

and 0.3391

respectively

across different prediction horizons

which are lower than those of the Autoformer

Informer

and Dlinear models. The prediction accuracy remains stable under four operating conditions：normal operation

assembly error

inner ring fault

and fatigue wear

with absolute errors ranging from 0.21 to 0.35.The results indicate that the proposed model demonstrates superior trend prediction accuracy for both short and long time series compared to other benchmark models

and the experimental outcomes under multiple operating conditions validate the model's adaptability and robustness.

关键词

Keywords

references

王国林 , 郑州 , 张松 , 等 . 跨座式单轨列车走行轮胎磨损控制方法研究 [J ] . 机械工程学报 , 2018 , 54 ( 6 ): 78 - 85 .

WANG Guolin , ZHENG Zhou , ZHANG Song , et al . Study on reducing wear of straddle-type monorail trains’running wheel tires [J ] . Journal of Mechanical Engineering , 2018 , 54 ( 6 ): 78 - 85 .

卞文彬 , 邓艾东 , 刘东川 , 等 . 基于改进深度残差收缩网络的风电机组滚动轴承故障诊断方法 [J ] . 机械工程学报 , 2023 , 59 ( 12 ): 202 - 214 .

BIAN Wenbin , DENG Aidong , LIU Dongchuan , et al . Fault diagnosis method of wind turbine rolling bearing based on improved deep residual shrinkage network [J ] . Journal of Mechanical Engineering , 2023 , 59 ( 12 ): 202 - 214 .

CHEN Yuejian , LI Zihan , JIANG Yuan , et al . Sparse LPV-ARMAmodel for non-stationary vibration representation and its application on gearbox tooth crack detection under variable speed conditions [J ] . Mechanical Systems and Signal Processing , 2025 , 224 : 112161 .

KHAN S , MUHAMMAD Y , JADOON I , et al . LeveragingLSTM-SMIand ARIMA architecture for robust wind power plant forecasting [J ] . Applied Soft Computing , 2025 , 170 : 112765 .

XU Feng , WANG Jinxin , SAKAI Yuka , et al . Graybox virtual sensor with constraints for predicting room temperature in cooling and heating modes [J ] . Building and Environment , 2025 , 273 : 112729 .

XU Xiaomin , GUAN Luoyun , WANG Zhiyi , et al . Short-term photovoltaic power intelligent forecasting based on XGBoost-GRU-informer-SVR model [J ] . Applied Soft Computing , 2025 , 7 : 112768 .

SAYEH K F , TAMALOUZT S , SAHRI Y , et al . Artificial intelligence-based direct power control for power quality improvement in a WT-DFIG system via neural networks:prediction and classification techniques [J ] . Journal of the Franklin Institute , 2025 , 362 ( 1 ): 107401 .

CAI Xiangjun , LI Dagang , ZHANG Jinglin , et al . MA-EMD:aligned empirical decomposition for multivariate time-series forecasting [J ] . Expert Systems with Applications , 2025 , 267 : 126080 .

GENG Donghan , ZHANG Yongkang , ZHANG Yunlong , et al . A hybrid model based on CapSA-VMD-ResNet-GRU-attention mechanism for ultra-short-term and short-term wind speed prediction [J ] . Renewable Energy , 2025 , 240 : 122191 .

WANG Dongsheng , ZHANG Congcong , LI Ao , et al . Spatio-temporal analysis and prediction for raw water quality of drinking water source by improved RNN algorithm [J ] . Journal of Water Process Engineering , 2025 , 71 : 107164 .

FU Fangze , AI Wei , YANG Fan , et al . SDR-GNN:spectral domain reconstruction graph neural network for incomplete multimodal learning in conversational emotion recognition [J ] . Knowledge-Based Systems , 2025 , 309 : 112825 .

HE Xin , ZHAO Wenlu , GAO Zhijun , et al . Shortterm load forecasting by GRU neural network and DDPG algorithm for adaptive optimization of hyperparameters [J ] . Electric Power Systems Research , 2025 , 238 : 111119 .

CHEN Yuejian , LIU Xuemei , RAO Meng , et al . Explicit speed-integrated LSTM network for non-stationary gearbox vibration representation and fault detection under varying speed conditions [J ] . Reliability Engineering & System Safety , 2025 , 254 ( Part A ): 110596 .

FERRI G G B , VELLOSO B P , AVILA S L , et al . Determining the trend behavior of the wind turbine powertrain using mechanical vibration and seasonal wind data [J ] . Energy Reports , 2025 , 13 : 353 - 362 .

LI Xilin , TENG Wei , WANG Luo , et al . Trend-constrained pairing based incremental transfer learning for remaining useful life prediction of bearings in wind turbines [J ] . Expert Systems with Applications , 2025 , 263 : 125731 .

JIN M J , KANG C G . Anomaly detection with transformer for a railway vehicle air compressor [J ] . International Journal of Control Automation and Systems , 2024 , 22 ( 8 ): 2644 - 2657 .

赵鑫 , 王东丽 , 彭泓 , 等 . 基于多策略改进蜣螂算法优化的变压器故障诊断 [J ] . 电力系统保护与控制 , 2024 , 52 ( 6 ): 120 - 130 .

ZHAO Xin , WANG Dongli , PENG Hong , et al . Transformer fault diagnosis based on a multi-strategy improved dung beetle optimizer [J ] . Power System Protection and Control , 2024 , 52 ( 6 ): 120 - 130 .

WU Haixu , XU Jiehui , WANG Jianmin , et al . Autoformer:decomposition transformers with auto-correlation for long-term series forecasting [C ] // Proceedings of the 35th International Conference on Neural Information Processing Systems . Red Hook,NY,USA : Curran Associates Inc ., 2021 : 22419 - 22430 .

ZHOU Haoyi , ZHANG Shanghang , PENG Jieqi , et al . Informer:beyond efficient transformer for long sequence time-series forecasting [C ] // Proceedings of the AAAI Conference on Artificial Intelligence . Palo Alto,CA,USA : AAAI Press , 2021 : 11106 - 11115 .

MENG Xin , LIU Xingyu , DUAN Hancong , et al . Research on yield prediction model driven by mechanism and data fusion [J ] . Sensors , 2025 , 25 ( 6 ): 1946 .

ŁAWRYNCZUK M , ZARZYCKI K . LSTMand GRU type recurrent neural networks in model predictive control:a review [J ] . Neurocomputing , 2025 , 632 : 129712 .

WANG Qiang , XU Feiyan , HE Jiahua , et al . A new fusion model for enhanced ultra-short-term offshore wind power forecasting [J ] . Renewable Energy , 2026 , 256 ( Part A ): 123876 .

TIAN Xiaoyi , HUANG Siyuan , XIAO Jinjie , et al . SDVS-Net:a spatial dilated convolution and variable self-attention network for multivariate long-term time series forecasting [J ] . Neurocomputing , 2025 , 619 : 129148 .

ZHAO Jingyuan , WANG Zhenghong , WU Yuyan , et al . Predictive pretrained transformer (PPT)for realtime battery health diagnostics [J ] . Applied Energy , 2025 , 377 ( Part D ): 124746 .

SHAMS M Y , TAREK Z , ELSHEWEY A M . Anovel RFE-GRU model for diabetes classification using PIMA Indian dataset [J ] . Scientific Reports , 2025 , 15 ( 1 ): 982 .

CAO Xianteng , NIU Huawei , CHEN Zhengqing . Real-time road surface unevenness recognition for ITS using BWO-BiGRU-transformer with adaptive CKF [J ] . IEEE Transactions on Intelligent Transportation Systems .( 2025-02-10 )[ 2025-02-13 ] . https://doi.org/10.1109/TITS.2025.3529921 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Mechanism and Optimal Control Strategy for Hysteresis in Rapid Dehumidification Response of Indirect Thermal Systems in Electric Vehicles

Knowledge Graph Representation Learning Driven by Semantic Discrimination and Subgraph Integration

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

I/O Performance Modeling and Prediction Method for Large-Scale Parallel Applications Using Machine Learning

Related Author

No data

Related Institution

No data

⁰