WO2020048090A1 - 一种能够剔除车辆动力效应的桥梁影响线识别方法 - Google Patents
一种能够剔除车辆动力效应的桥梁影响线识别方法 Download PDFInfo
- Publication number
- WO2020048090A1 WO2020048090A1 PCT/CN2019/073826 CN2019073826W WO2020048090A1 WO 2020048090 A1 WO2020048090 A1 WO 2020048090A1 CN 2019073826 W CN2019073826 W CN 2019073826W WO 2020048090 A1 WO2020048090 A1 WO 2020048090A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- bridge
- imf
- response
- res
- influence line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0008—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings of bridges
Definitions
- the invention belongs to the technical field of structural safety detection, and particularly relates to a method for identifying a bridge influence line capable of eliminating vehicle dynamic effects.
- a bridge influence line is a response curve of a specific position of the bridge when a unit load passes through the bridge.
- the influence line contains a large amount of structural information.
- the influence line can directly reflect the stiffness and compliance information of the bridge.
- the influence line also contains the position information of the bridge, and the damage can be located through the change of the influence line.
- Railway bridges are particularly suitable for identifying their influence lines due to the single load trajectory.
- the dynamic effects caused by high-speed trains passing bridges can cause large deviations in bridge responses compared with the quasi-static bridge responses when low-speed trains cross bridges. A difficult question.
- OBerin For the quasi-static loading of low-speed loading trains across the bridge, there have been many research results on the method of line identification.
- OBerin first proposed a matrix method to identify influence lines from measured data. This method establishes a matrix related to train information and identifies the influence line of the bridge by inverting the matrix.
- Sio-Song Leng uses the maximum likelihood estimation method to derive an influence line identification formula. This method can consider the effects of multiple loaded vehicles at the same time, thereby giving a more accurate influence line estimation.
- Chen first adopted a regularization method to eliminate the fluctuations of the influence lines that are not consistent with the physical meaning. It is recognized that the bridge response can be expressed as a convolution of the influence line and the train information function, and the influence line is identified by a fast Fourier variation deconvolution method.
- the object of the present invention is a bridge influence line recognition method capable of eliminating vehicle dynamic effects.
- a bridge influence line identification method capable of excluding vehicle dynamic effects the steps are as follows:
- Step 1. Use empirical mode decomposition to preprocess bridge response information measured by sensors
- H (t) When H (t) satisfies the conditions of the eigenmode function, H (t) becomes an imf (t); otherwise, replace R (t) in step (1) with H (t) and remove from step ( 1) Start repeating the above process; an eigenmode function must satisfy 2 conditions: 1) the number of local extreme points and zero-crossing points is equal, or at most one difference, over the entire time range; 2) at any time point The average value of the envelope of the local maximum and the envelope of the local minimum must be 0;
- Step 2 Use quasi-static method to identify the influence line of the bridge response after pretreatment
- the dynamic response of the bridge is transformed into a bridge response under quasi-static conditions, which are identified using a classic quasi-static influence line identification model.
- the bridge influence line identification method can identify the bridge structure response when a high-speed train is loaded, and provides a theoretical basis for the identification of influence lines of high-speed railway bridges;
- the method for identifying the influence line of a bridge of the present invention has a strict theoretical basis. Based on the synchronous collection of bridge load and bridge response information, combined with an advanced optimization identification algorithm, it can ensure that the influence line identified by the system has high accuracy;
- the method for identifying the influence line of a bridge of the present invention is simple to use, and does not need to predict the structure information of the bridge, and can directly process the collected bridge dynamic response data to obtain the influence line.
- FIG. 1 is a flowchart of an algorithm used in the present invention
- FIG. 2 is a vibration model of a loaded vehicle crossing a bridge simulated in an embodiment of the method of the present invention
- 3 is a bridge dynamic response caused by a loading vehicle in an embodiment of the method of the present invention.
- the influence line recognition method of the present invention is divided into two steps: "pre-processing bridge response information measured by sensors using empirical mode decomposition” and "recognizing bridge response after pre-processing using a quasi-static method”. It has been given, and the following uses a calculation example to explain the use method and characteristics of the invention.
- a differential equation of motion of a four-degree-of-freedom vehicle and a simply supported beam with a distributed mass system is established.
- the time history of the mid-span response of the simply supported beam is obtained by solving ordinary differential equations, as shown in Figure 3.
- the bridge deflection response when a high-speed train crosses a bridge can be divided into two parts: quasi-static response and dynamic superposition term.
- the two parts can be decomposed by empirical mode decomposition. The decomposition results are shown in Figure 4.
- the quasi-static influence line identification method can be used to identify the influence lines.
- the comparison between the identified influence line and the real influence line is shown in Figure 5. It can be seen that the identified influence line is basically consistent with the real value.
- This method is an effective method for identifying bridge influence lines during dynamic loading.
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
一种能够剔除车辆动力效应的桥梁影响线识别方法,包括:(1)采用经验模式分解对传感器测得的桥梁响应数据进行预处理;(2)对经过预处理后的桥梁响应采用准静态方法进行识别。采用经验模式分解对桥梁响应进行预处理可以对桥梁响应的动力叠加项进行剔除,从而得到桥梁的准静态响应,进一步可用于影响线识别。同时该方法无需提前了解任何桥梁结构信息,可对各种桥型上由传感器测得的结构响应数据进行处理,具有良好的工程应用前景。
Description
本发明属于结构安全性检测技术领域,具体涉及一种能够剔除车辆动力效应的桥梁影响线识别方法。
近些年来,随着高速铁路技术的不断发展和人们对出行效率要求的提升,世界上已建成的高速铁路总里程数前所未有的提高了。由于高速铁路的绝大多数运营里程都在高架桥上,高铁桥梁的安全状况也越来越受到人们的关注。高铁桥梁由于不断的承受高速列车的动力加载,其受到的荷载效应要比普通的公路桥梁更加复杂,如何实时的监测高铁桥梁的服役性能成为了一个关乎乘客生命财产安全的重大问题。
同时值得注意的是,近些年来出现了一种基于影响线变化的损伤识别方法。桥梁影响线是单位荷载通过桥梁时桥梁某一特定位置的响应曲线,作为桥梁的一种静力特征,影响线包含了大量的结构信息。作为一个结构损伤的指标,影响线可以直接反应桥梁的刚度和柔度信息。除此之外,影响线还包含了桥梁的位置信息,可以通过影响线的变化对损伤进行定位。铁路桥梁由于荷载运行轨迹单一,特别适合对其影响线进行识别。但高速列车过桥时造成的动力效应会使桥梁响应和低速列车过桥时的准静态桥梁响应相比产生较大的偏差,如何从动力效应中识别得到影响线成为了高速铁路桥梁影响线识别的一个难点问题。
针对低速加载列车过桥的准静态加载情况,影响线识别的方法已经有了很多研究成果。OBerin最先提出了一种矩阵法来从实测数据中识别影响线。这种方法建立了一种和列车信息相关的矩阵,通过对矩阵求逆来识别桥梁影响线。Sio-Song Leng采用极大似然估计方法推导出了一种影响线识别公式,这种方法 可以同时考虑多个加载车辆的作用,从而给出了一种更加准确的影响线估计。Chen首先采用了正则化方法对识别得到的影响线不符合物理意义的波动进行了消除。
认识到桥梁响应可以表示成影响线和列车信息函数的卷积,通过快速傅立叶变化解卷积的方法识别影响线。这种方法能够大大提高影响线识别的效率,并且在识别精度上也有一定的保障。在考虑动力效应的情况下,王宁波等人通过多项式和正弦函数分别对静力效应和动力效应进行了拟合,识别得到了某些特定桥型的影响线。而对于其他更普遍的情况,有待于进一步的研究。
发明内容
本发明的目的是一种能够剔除车辆动力效应的桥梁影响线识别方法。
本发明的技术方案:
一种能够剔除车辆动力效应的桥梁影响线识别方法,步骤如下:
步骤1、采用经验模式分解对传感器测得的桥梁响应信息进行预处理
(1)找出桥梁响应信号R(t)的局部极大值和局部极小值;
(2)利用三次样条插值方法分别计算极小值插值和极大值插值函数,并得到对应信号包络e
min(t)和e
max(t);
(3)计算信号极大值与极小值包络的局部均值M(t)=(e
min(t)+e
max(t))/2。
(4)将原始输入信号减去局部均值得到震荡信号H(t)=R(t)-M(t);
(5)当H(t)满足本征模函数的条件,H(t)变成一个imf(t);否则,用H(t)替换步骤(1)中的R(t)并从步骤(1)开始重复上述过程;一个本征模函数必须满足2个条件:1)函数在整个时间范围内,局部极值点和过零点的数目相等,或最多差一个;2)在任一时间点上,局部最大值的包络线和局部最小值的包络线平均 值必须为0;
(6)令imf
1(t)=H(t),则imf
1(t)为第一个imf(t),对应的余量Res
1(t)=R(t)-imf
1(t),将Res
1(t)作为新的信号重复上述所有步骤,得到第二个imf(t)分量,以此类推,得到Res
1(t)-imf
2(t)=Res
2(t),…Res
n-1(t)-imf
n(t)=Res
n(t);当本征模函数无法再继续提取时,停止筛分过程;
步骤2、对经过预处理后的桥梁响应采用准静态方法进行影响线识别
经过经验模式分解的预处理后,桥梁动态响应转化成准静态情况下的桥梁响应,采用经典的准静态影响线识别模型进行识别。
本发明的有益效果:
(1)本发明的桥梁影响线识别方法和原有的影响线识别方法相比,可以对高速列车加载时的桥梁结构响应进行识别,为高铁桥梁影响线识别提供了理论基础;
(2)本发明的桥梁影响线识别方法具备严格的理论基础,基于桥梁荷载和桥梁响应的同步采集信息,并结合先进优化识别算法,可保证通过该系统识别的影响线具有较高精度;
(3)本发明的桥梁影响线识别方法使用简单,无需预知桥梁结构信息,可以对采集得到的桥梁动力响应数据进行直接处理,从而得到影响线。
图1为本发明所采用算法的实现流程图;
图2为本发明方法实施例中模拟的加载车辆过桥的振动模型;
图3为本发明方法实施例中加载车辆引起的桥梁动态响应;
图4为本发明方法实施例中通过经验模式分解处理后得到的准静态响应;
图5为本发明方法实施例中对处理后准静态响应进行识别得到的影响线;
下面结合附图和一个数值算例来对本发明做进一步的详细说明。
本发明的影响线识别方法分“采用经验模式分解对传感器测得的桥梁响应信息进行预处理”和“对经过预处理后的桥梁响应采用准静态方法进行识别”两步,具体实施方式上文已经给出,接下来结合一个算例说明发明的使用方法和特点。
实施算:72km/h双轴加载车辆过桥影响线识别
在本数值算例中,我们模拟一个速度为72km/h的双轴车辆通过简支梁,通过建立车桥耦合振动模型来分析跨中的挠度响应。双轴车辆的轴距为4m,简支梁长度为16m。将车体简化成三个质量块,质量分别是:m
1=524kg;m
2=297kg;m
3=6451kg。模型的具体情况见图2。
在本算例中,建立了四自由度车辆和分布质量体系简支梁的运动微分方程,通过求解常微分方程组获取了简支梁跨中响应的时程,如图3所示。高速列车过桥时的桥梁挠度响应可以分成准静态响应和动力叠加项两部分,通过经验模式分解可以对两部分进行分解,分解结果见图4。
对动态效应剔除后,可以用准静态的影响线识别方法对影响线进行识别,在本算例中,我们采用的是正则化LSQR迭代法。识别得到的影响线与真实影响线对比见图5。可以看出,识别得到的影响线与真实值基本吻合。本方法是识别动态加载时桥梁影响线的一种有效方法。
Claims (1)
- 一种能够剔除车辆动力效应的桥梁影响线识别方法,其特征在于,步骤如下:步骤1、采用经验模式分解对传感器测得的桥梁响应信息进行预处理(1)找出桥梁响应信号R(t)的局部极大值和局部极小值;(2)利用三次样条插值方法分别计算极小值插值和极大值插值函数,并得到对应信号包络e min(t)和e max(t);(3)计算信号极大值与极小值包络的局部均值M(t)=(e min(t)+e max(t))/2;(4)将原始输入信号减去局部均值得到震荡信号H(t)=R(t)-M(t);(5)当H(t)满足本征模函数的条件,H(t)变成一个imf(t);否则,用H(t)替换步骤(1)中的R(t)并从步骤(1)开始重复上述过程;一个本征模函数必须满足2个条件:1)函数在整个时间范围内,局部极值点和过零点的数目相等,或最多差一个;2)在任一时间点上,局部最大值的包络线和局部最小值的包络线平均值必须为0;(6)令imf 1(t)=H(t),则imf 1(t)为第一个imf(t),对应的余量Res 1(t)=R(t)-imf 1(t),将Res 1(t)作为新的信号重复上述所有步骤,得到第二个imf(t)分量,以此类推,得到Res 1(t)-imf 2(t)=Res 2(t),…Res n-1(t)-imf n(t)=Res n(t);当本征模函数无法再继续提取时,停止筛分过程;步骤2、对经过预处理后的桥梁响应采用准静态方法进行影响线识别经过经验模式分解的预处理后,桥梁动态响应转化成准静态情况下的桥梁 响应,采用经典的准静态影响线识别模型进行识别。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811016637.4 | 2018-09-03 | ||
| CN201811016637.4A CN109341989B (zh) | 2018-09-03 | 2018-09-03 | 一种能够剔除车辆动力效应的桥梁影响线识别方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020048090A1 true WO2020048090A1 (zh) | 2020-03-12 |
Family
ID=65292177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/073826 Ceased WO2020048090A1 (zh) | 2018-09-03 | 2019-01-30 | 一种能够剔除车辆动力效应的桥梁影响线识别方法 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109341989B (zh) |
| WO (1) | WO2020048090A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115292776A (zh) * | 2022-07-05 | 2022-11-04 | 大连理工大学 | 一种基于索力监测数据的斜拉桥车致索力实时在线提取方法 |
| CN117312792A (zh) * | 2023-09-27 | 2023-12-29 | 武汉烽理光电技术有限公司 | 基于阵列光栅的桥梁重车识别方法、装置及电子设备 |
| CN121682003A (zh) * | 2026-02-11 | 2026-03-17 | 吉林大学 | 基于两阶段空间加权正则化的桥梁影响线识别方法和系统 |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261305A (zh) * | 2019-06-18 | 2019-09-20 | 南京东南建筑机电抗震研究院有限公司 | 基于影响线的多跨等跨径连续梁桥损伤识别方法 |
| CN112485030B (zh) * | 2020-11-09 | 2023-03-14 | 深圳市桥博设计研究院有限公司 | 基于频率耦合的桥梁结构动态监测方法、系统和装备 |
| CN114414122B (zh) * | 2022-01-07 | 2022-09-27 | 大连理工大学 | 一种用于测量车轮多分力的传感装置 |
| CN115358088B (zh) * | 2022-09-06 | 2025-05-13 | 大连理工大学 | 一种基于高速列车激励动力响应的桥梁影响线识别方法 |
| CN116340741A (zh) * | 2023-03-16 | 2023-06-27 | 安徽建筑大学 | 一种基于车致时程响应模态分解的桥梁损伤识别方法 |
| CN116341068A (zh) * | 2023-03-22 | 2023-06-27 | 安徽建筑大学 | 一种基于经验模态分解的桥梁影响线识别方法 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003233640A (ja) * | 2001-12-03 | 2003-08-22 | Tateishi Kozo Sekkei:Kk | 建築物の構造計算装置、コンピュータプログラム、記録媒体及び建築物 |
| CN101532917A (zh) * | 2009-04-15 | 2009-09-16 | 江苏省交通科学研究院股份有限公司 | 一种桥梁承载能力快速荷载试验方法 |
| CN104819813A (zh) * | 2015-04-29 | 2015-08-05 | 中南大学 | 一种桥梁影响线动态测试方法 |
| CN104964837A (zh) * | 2015-06-12 | 2015-10-07 | 广东电网有限责任公司电力科学研究院 | 基于emd的结构刚度损伤监测方法及系统 |
| CN105973619A (zh) * | 2016-04-27 | 2016-09-28 | 厦门大学 | 结构健康监测系统下基于影响线的桥梁局部损伤识别方法 |
| CN107132011A (zh) * | 2017-05-31 | 2017-09-05 | 中南大学 | 一种基于影响线的桥梁快速检测方法 |
| CN107389168A (zh) * | 2017-07-18 | 2017-11-24 | 重庆交通大学 | 一种用于桥梁的车辆移动载荷的识别方法 |
| CN107588915A (zh) * | 2017-10-18 | 2018-01-16 | 厦门大学 | 一种桥梁影响线识别方法及系统 |
| CN207395997U (zh) * | 2017-10-18 | 2018-05-22 | 厦门大学 | 一种桥梁影响线识别系统 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11326108A (ja) * | 1998-05-07 | 1999-11-26 | Shimadzu Corp | ヘリウムリークディテクタ |
| CN102509005B (zh) * | 2011-10-27 | 2015-02-25 | 招商局重庆交通科研设计院有限公司 | 基于准静态广义影响线的桥梁承载力评定方法 |
| JP2014010572A (ja) * | 2012-06-28 | 2014-01-20 | Strauss Technology Co Ltd | ベクター画像描画装置及びベクター画像描画方法 |
| WO2015026350A1 (en) * | 2013-08-22 | 2015-02-26 | Empire Technology Development, Llc | Influence of line of sight for driver safety |
| CN104389275B (zh) * | 2014-12-10 | 2017-02-01 | 邢兵 | 一种基于影响线原理的无铰拱桥预应力综合加固方法 |
| CN104897180B (zh) * | 2015-05-26 | 2018-01-26 | 广州大学 | 用于桥梁监测信号的预处理方法 |
| CN105628381B (zh) * | 2016-01-13 | 2018-09-04 | 东北石油大学 | 一种基于改进的局部均值分解的往复压缩机轴承故障诊断方法 |
| NL2016794B1 (en) * | 2016-05-18 | 2017-11-30 | Heijmans N V | Method for determining the structural integrity of an infrastructural element |
| CN105973627A (zh) * | 2016-05-26 | 2016-09-28 | 东南大学 | 一种基于长标距应变影响包络线的桥梁损伤识别方法 |
| CN106482917B (zh) * | 2016-10-11 | 2018-09-14 | 广州大学 | 一种斜拉桥主梁动态挠度的检测方法 |
| CN107300452A (zh) * | 2017-08-10 | 2017-10-27 | 天津市德力电子仪器有限公司 | 一种桥梁荷载试验快速检测系统 |
-
2018
- 2018-09-03 CN CN201811016637.4A patent/CN109341989B/zh not_active Expired - Fee Related
-
2019
- 2019-01-30 WO PCT/CN2019/073826 patent/WO2020048090A1/zh not_active Ceased
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003233640A (ja) * | 2001-12-03 | 2003-08-22 | Tateishi Kozo Sekkei:Kk | 建築物の構造計算装置、コンピュータプログラム、記録媒体及び建築物 |
| CN101532917A (zh) * | 2009-04-15 | 2009-09-16 | 江苏省交通科学研究院股份有限公司 | 一种桥梁承载能力快速荷载试验方法 |
| CN104819813A (zh) * | 2015-04-29 | 2015-08-05 | 中南大学 | 一种桥梁影响线动态测试方法 |
| CN104964837A (zh) * | 2015-06-12 | 2015-10-07 | 广东电网有限责任公司电力科学研究院 | 基于emd的结构刚度损伤监测方法及系统 |
| CN105973619A (zh) * | 2016-04-27 | 2016-09-28 | 厦门大学 | 结构健康监测系统下基于影响线的桥梁局部损伤识别方法 |
| CN107132011A (zh) * | 2017-05-31 | 2017-09-05 | 中南大学 | 一种基于影响线的桥梁快速检测方法 |
| CN107389168A (zh) * | 2017-07-18 | 2017-11-24 | 重庆交通大学 | 一种用于桥梁的车辆移动载荷的识别方法 |
| CN107588915A (zh) * | 2017-10-18 | 2018-01-16 | 厦门大学 | 一种桥梁影响线识别方法及系统 |
| CN207395997U (zh) * | 2017-10-18 | 2018-05-22 | 厦门大学 | 一种桥梁影响线识别系统 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115292776A (zh) * | 2022-07-05 | 2022-11-04 | 大连理工大学 | 一种基于索力监测数据的斜拉桥车致索力实时在线提取方法 |
| CN117312792A (zh) * | 2023-09-27 | 2023-12-29 | 武汉烽理光电技术有限公司 | 基于阵列光栅的桥梁重车识别方法、装置及电子设备 |
| CN121682003A (zh) * | 2026-02-11 | 2026-03-17 | 吉林大学 | 基于两阶段空间加权正则化的桥梁影响线识别方法和系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109341989B (zh) | 2020-06-12 |
| CN109341989A (zh) | 2019-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109341989B (zh) | 一种能够剔除车辆动力效应的桥梁影响线识别方法 | |
| He et al. | Train bearing fault diagnosis based on multi-sensor data fusion and dual-scale residual network | |
| CN110175434B (zh) | 一种基于卷积神经网络的铁路扣件系统损伤检测方法 | |
| Chen et al. | Fault diagnosis of high-speed train bogie based on capsule network | |
| CN106844949B (zh) | 一种用于实现机车节能操纵的双向lstm模型的训练方法 | |
| CN101604322B (zh) | 一种决策级文本自动分类融合方法 | |
| CN103196682B (zh) | 基于d-s证据理论的信息融合的列车悬挂系统故障分离方法 | |
| CN115526864A (zh) | 基于改进的特征金字塔网络和度量学习的钢轨表面缺陷检测方法 | |
| CN114861719A (zh) | 基于集成学习的高速列车轴承故障诊断方法 | |
| CN114065809B (zh) | 一种乘用车异响识别方法、装置、电子设备以及存储介质 | |
| CN103196681B (zh) | 基于转向架加速度的列车运行舒适度预测方法 | |
| CN107121285B (zh) | 一种滚动轴承振动信号故障特征提取方法 | |
| CN109409008B (zh) | 一种城市轨道交通工具线路典型速度-时间行驶工况构建方法 | |
| Li et al. | A multitask learning method for rail corrugation detection using in-vehicle responses and noise data | |
| CN109813511B (zh) | 基于移动车辆的桥梁快速测试与参数识别方法 | |
| CN103471865A (zh) | 基于线性判别法的列车悬挂系统故障分离方法 | |
| CN107679452A (zh) | 大数据下基于卷积神经网络的货运列车车号实时识别系统 | |
| Duan et al. | A novel classification method for flutter signals based on the CNN and STFT | |
| Xie et al. | Detection of wheel diameter difference of railway wagon by ACMD-FBD and optimized MKELM | |
| Zhang et al. | Multi-sensor graph transfer network for health assessment of high-speed rail suspension systems | |
| CN115544763A (zh) | 一种路面平整度预测方法、系统及介质 | |
| Wang et al. | Road surface state recognition based on semantic segmentation | |
| Winarno et al. | Roles of Vibration-Based Machine Learning Algorithms in Railway Vehicle Monitoring for Track Condition Assessment: A Review | |
| CN116644304A (zh) | 基于相似性的货车轴承异常特征提取与分类方法 | |
| CN108981906B (zh) | 一种轨道波磨故障综合诊断方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19857281 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19857281 Country of ref document: EP Kind code of ref document: A1 |

