首页|高铁桥墩沉降的通用渐进分解长期预测网络模型

高铁桥墩沉降的通用渐进分解长期预测网络模型

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
高铁桥墩不均匀沉降是导致轨道不平顺的潜在原因之一,准确预测桥墩沉降对于确保铁路建设和运营的可靠性和安全性具有重要意义.目前,常规时间序列领域的多数预测模型仅在预处理良好且没有缺失的数据集上进行测试,而在高铁桥墩沉降的真实场景中,沉降数据相较于其他领域存在观测频次少且不等时距,以及沉降规律复杂多变的问题,造成长期预测困难.为此,本文提出一种高铁桥墩沉降的通用渐进分解长期预测网络(GPDLPnet),摒弃传统的预处理思想,将预处理过程嵌入网络结构,在网络训练过程中实现渐进预处理.首先,GPDLPnet在每轮迭代中利用改进对角掩码自注意力模块分析沉降数据中的缺失模式.然后,通过改进完全自适应噪声集合经验模态分解模块将沉降数据分解并重构为高频、低频和趋势子分量,将子分量作为BiLSTM-RSA-Resnet预测模块的特征输入.最后,输出递归预测结果,从而实现高铁桥墩沉降的长期预测.结合实际工程数据,将数据划分为高频观测和低频观测两类典型的观测模式进行试验,在3～4个月的预测中GPDLPnet均表现出良好的预测性能,并在精度指标上优于其他7种模型.
A general progressive decomposition long-term prediction network model for high-speed railway bridge pier settlement
Uneven settlement of high-speed railway bridge pier is one of the potential causes leading to track irregularities.Ac-curately predicting settlement of bridge pier is of significant importance for ensuring the reliability and safety of railway con-struction and operation.Most conventional time series prediction models are tested only on well-preprocessed datasets without missing values.However,in real-world scenarios of high-speed railway bridge pier settlement,the data are characterized by in-frequent and irregular observation intervals and complex,variable settlement patterns,posing challenges for long-term predic-tion.To address this,we introduce the general progressive decomposition long-term prediction network(GPDLPnet),which abandons traditional preprocessing concepts and embeds the preprocessing phase within the network structure,achieving pro-gressive preprocessing during training.In each iteration,GPDLPnet uses an improved diagonally-masked self-attention(IDM-SA)module to analyze missing patterns in the settlement data,then decomposes and reconstructs the data into high-frequency,low-frequency,and trend sub-components through an improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)module.These sub-components serve as feature inputs for the BiLSTM-RSA-Resnet prediction module,which outputs recursive predictions,thus enabling long-term prediction of high-speed railway bridge pier settlement.Utilizing real-world engineering data,experiments under two typical observation modes,high-frequency and low-frequency,are conduc-ted.GPDLPnet demonstrates excellent predictive performance over a 3-4 month,surpassing seven other models in accuracy in-dexes.

deep learninghigh-speed railway bridge piersettlement predictionresidual networkconvolutional neural net-work

龚循强、汪宏宇、鲁铁定、游为

展开 >

东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室,江西南昌 330013

东华理工大学测绘与空间信息工程学院,江西南昌 330013

西南交通大学高速铁路安全运营空间信息技术国家地方联合工程实验室,四川成都 611756

深度学习 高铁桥墩 沉降预测 残差网络 卷积神经网络

国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室开放基金重点项目

42101457423740404206107741974013MEMI-2023-01

2024

10.11947/j.AGCS.2024.20230387

测绘学报
中国测绘学会

测绘学报

CSTPCD北大核心
影响因子：1.602
ISSN：1001-1595
年,卷(期)：2024.53(6)
  • 17