CN112054806B - Subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet - Google Patents
Subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet Download PDFInfo
- Publication number
- CN112054806B CN112054806B CN202010968468.5A CN202010968468A CN112054806B CN 112054806 B CN112054806 B CN 112054806B CN 202010968468 A CN202010968468 A CN 202010968468A CN 112054806 B CN112054806 B CN 112054806B
- Authority
- CN
- China
- Prior art keywords
- matrix
- dimensional
- data
- wavelet
- plug door
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
Abstract
The invention discloses a subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet, which comprises the following steps: s1, collecting door opening and closing data of a subway sliding plug door, and preprocessing the door opening and closing data to obtain a two-dimensional gray matrix; s2, performing multi-scale decomposition on the two-dimensional gray matrix; s3, carrying out default threshold processing in the process of obtaining and compressing the two-dimensional gray matrix to obtain a default threshold; s4, carrying out two-dimensional wavelet compression reconstruction on the two-dimensional gray matrix to obtain wavelet coefficients and reconstructed compressed signals; s5, saving the wavelet coefficients, obtaining the size of a saved file, and calculating the compression rate according to the size of the saved file; s6, calculating the signal-to-noise ratio of the reconstructed compressed signal; s7, taking the wavelet coefficient as subway sliding plug door compression data under the condition that the compression rate and the signal-to-noise ratio reach respective preset thresholds; the invention solves the problem of lower reconstruction precision in the existing data compression method.
Description
Technical Field
The invention relates to the field of data compression, in particular to a subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet.
Background
Along with the continuous improvement of the speed of the high-speed railway train, basic equipment and a train operation control system for controlling the safe, reliable, stable and high-speed operation of the train are moving towards electronization, intellectualization and complicacy. Therefore, PHM technology is increasingly gaining importance in order to improve the safety and reliability of high-speed rail train infrastructure and operation control systems during operation. The subway door is used as a core component for directly relating to the safety of passengers, is an important subsystem in rail transit system equipment, and is extremely frequent in opening and closing of the doors due to short rail transit operation station distance, and the electromechanical components are frequently operated for a long time, and due to the fact that a plurality of passenger interference factors are added, the frequent occurrence of door faults is caused, the normal operation of a train is influenced, the traveling of passengers is delayed, and the personal safety of the passengers is even endangered. The PHM system of the vehicle door passes through a sensor built in a door controller. And a large amount of data in the running process of the vehicle door, such as the running speed of the vehicle door, the current of a motor and the like, are acquired. The data contains rich information, which has important significance for analyzing the production running state, providing control and optimization strategies, fault diagnosis and data mining. However, due to the huge amount of data, it is not practical to store the data in a prototype form for a long time, so research on a compression method suitable for engineering practice to reduce redundancy existing in mass data has become an urgent need for subway sliding plug doors.
However, the change of the data amplitude of the subway sliding plug door is large, and the reconstruction precision is low under the condition of a certain compression rate by adopting a global threshold mode, so that the subway sliding plug door compression method adopting the two-dimensional adaptive threshold wavelet is provided.
Disclosure of Invention
Aiming at the defects in the prior art, the subway sliding plug door data compression method based on the two-dimensional self-adaptive threshold wavelet solves the problem that the existing data compression method is low in reconstruction accuracy.
In order to achieve the aim of the invention, the invention adopts the following technical scheme: a subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet comprises the following steps:
s1, collecting door opening and closing data of a subway sliding plug door, and preprocessing the door opening and closing data to obtain a two-dimensional gray matrix;
s2, performing multi-scale decomposition on the two-dimensional gray matrix to obtain decomposition coefficients of each layer and the lengths of the decomposition coefficients of each layer;
s3, carrying out default threshold processing in the process of obtaining and compressing the two-dimensional gray matrix to obtain a default threshold;
s4, carrying out two-dimensional wavelet compression reconstruction on the two-dimensional gray matrix according to the decomposition coefficients of each layer, the decomposition coefficient lengths of each layer and a default threshold value to obtain wavelet coefficients and a reconstructed compressed signal;
s5, saving the wavelet coefficients, obtaining the size of a saved file, and calculating the compression rate according to the size of the saved file;
s6, calculating the signal-to-noise ratio of the reconstructed compressed signal;
and S7, judging whether the compression rate and the signal to noise ratio reach respective preset thresholds, if so, taking the wavelet coefficient as subway sliding plug door compression data, ending the compression flow, and if not, adjusting the size of the default threshold and jumping to the step S4.
Further: step S1 comprises the steps of:
s11, collecting door opening and closing data of a subway sliding plug door to form a two-dimensional data matrix;
s12, averaging each row of the two-dimensional data matrix to obtain a column matrix;
s13, drawing a column matrix amplitude curve according to elements of a column matrix, and dividing the column matrix amplitude curve by adopting a plurality of parallel lines to obtain block data and block positions;
s14, constructing a block matrix according to the block data and the block positions, and carrying out normalization processing on the block matrix to obtain a two-dimensional gray matrix.
Further: the column matrix in step S12 is:
wherein m is the sampling period, n is the number of sampling points in each sampling period, a 1,1 To a m,n Subway sliding plug door opening and closing door data of m multiplied by n sampling points, A m×n Is a two-dimensional data matrix, B m I is the ith sampling point in the sampling period, b 1 To b m Is an element of a column matrix.
Further: step S13 includes the steps of:
s131, taking the sampling point as the abscissa and taking the sampling point as the x axis, taking b as 1 To b m Drawing a column matrix amplitude curve by taking the ordinate as the y-axis;
s132, intercepting a column matrix amplitude curve by a plurality of parallel lines parallel to an x axis to obtain a plurality of divided curves and intersections of the parallel lines and the column matrix amplitude curve;
s133, classifying elements of a column matrix corresponding to each section of curve into a block;
s134, taking an abscissa corresponding to an intersection point of parallel lines and a column matrix amplitude curve as a blocking position.
Further: the specific formula for normalizing the block matrix in step S14 is as follows:
D m×L ＝(C m×L -min(C m×L ))/(max(C m×L )-min(C m×L ))
wherein C is m×L For a block matrix, m is the sampling period, L is the number of segment curves,for the matrix of elements of the column matrix corresponding to the first segment of the piecewise curve,/for the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve>For the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve,/for the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve>Matrix composed of elements of column matrix corresponding to L-th segment piecewise curve, L 1 For the position corresponding to the first segment of the piecewise curve, l 2 For the position corresponding to the second segment of the piecewise curve, l L For the position corresponding to the L-th segment of the piecewise curve, D m×L Is a two-dimensional gray matrix.
Further: the formula for calculating the compression ratio in step S5 is:
wherein C is R For the compression ratio N in And storing the size of the two-dimensional gray matrix file, wherein Nout is the size of the stored wavelet coefficient file.
Further: the formula for calculating the signal-to-noise ratio in step S6 is:
wherein N is R For signal-to-noise ratio, m is sampling period, n is sampling point number in each sampling period, A (j) is two-dimensional data matrix A m×n N (j) is the j-th element of the reconstructed compressed signal.
In summary, the invention has the following beneficial effects:
1) And one-dimensional wavelets are replaced, redundancy during the data period is reduced, and the compression rate is improved.
2) The method adopts a block threshold value mode to replace the prior two-dimensional wavelet compression mode adopting a global threshold value mode, and under the condition of a certain compression rate, the reconstruction accuracy is improved.
Drawings
Fig. 1 is a flow chart of a subway sliding plug door data compression method based on two-dimensional adaptive threshold wavelet.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, a subway sliding plug door data compression method based on two-dimensional adaptive threshold wavelet comprises the following steps:
s1, collecting door opening and closing data of a subway sliding plug door, and preprocessing the door opening and closing data to obtain a two-dimensional gray matrix;
step S1 comprises the steps of:
s11, collecting door opening and closing data of a subway sliding plug door to form a two-dimensional data matrix;
s12, averaging each row of the two-dimensional data matrix to obtain a column matrix;
the column matrix in step S12 is:
wherein m is the sampling period, n is the number of sampling points in each sampling period, a 1,1 To a m,n Subway sliding plug door opening and closing door data of m multiplied by n sampling points, A m×n Is a two-dimensional data matrix, B m I is the ith sampling point in the sampling period, b 1 To b m Is an element of a column matrix.
S13, drawing a column matrix amplitude curve according to elements of a column matrix, and dividing the column matrix amplitude curve by adopting a plurality of parallel lines to obtain block data and block positions;
step S13 includes the steps of:
s131, taking the sampling point as the abscissa and taking the sampling point as the x axis, taking b as 1 To b m Drawing a column matrix amplitude curve by taking the ordinate as the y-axis;
s132, intercepting a column matrix amplitude curve by a plurality of parallel lines parallel to an x axis to obtain a plurality of divided curves and intersections of the parallel lines and the column matrix amplitude curve;
s133, classifying elements of a column matrix corresponding to each section of curve into a block;
s134, taking an abscissa corresponding to an intersection point of parallel lines and a column matrix amplitude curve as a blocking position.
S14, constructing a block matrix according to the block data and the block positions, and carrying out normalization processing on the block matrix to obtain a two-dimensional gray matrix.
The specific formula for normalizing the block matrix in step S14 is as follows:
D m×L ＝(C m×L -min(C m×L ))/(max(C m×L )-min(C m×L ))
wherein C is m×L For a block matrix, m is the sampling period, L is the number of segment curves,for the matrix of elements of the column matrix corresponding to the first segment of the piecewise curve,/for the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve>For the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve,/for the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve>Matrix composed of elements of column matrix corresponding to L-th segment piecewise curve, L 1 For the position corresponding to the first segment of the piecewise curve, l 2 For the position corresponding to the second segment of the piecewise curve, l L For the position corresponding to the L-th segment of the piecewise curve, D m×L Is a two-dimensional gray matrix.
S2, performing multi-scale decomposition on the two-dimensional gray matrix to obtain decomposition coefficients of each layer and the lengths of the decomposition coefficients of each layer;
in this embodiment, the multi-scale decomposition performed in step S2 may be implemented using a wavedec2 function.
S3, carrying out default threshold processing in the process of obtaining and compressing the two-dimensional gray matrix to obtain a default threshold;
in this embodiment, the default thresholding in the acquisition and compression process in step S3 may be implemented using a ddencmp function.
S4, carrying out two-dimensional wavelet compression reconstruction on the two-dimensional gray matrix according to the decomposition coefficients of each layer, the decomposition coefficient lengths of each layer and a default threshold value to obtain wavelet coefficients and a reconstructed compressed signal;
in this embodiment, the two-dimensional wavelet compression reconstruction in step S4 may be implemented using a wdencmp function.
S5, saving the wavelet coefficients, obtaining the size of a saved file, and calculating the compression rate according to the size of the saved file;
the formula for calculating the compression ratio in step S5 is:
wherein C is R For the compression ratio N in And storing the size of the two-dimensional gray matrix file, wherein Nout is the size of the stored wavelet coefficient file.
S6, calculating the signal-to-noise ratio of the reconstructed compressed signal;
the formula for calculating the signal-to-noise ratio in step S6 is:
wherein N is R For signal-to-noise ratio, m is sampling period, n is sampling point number in each sampling period, A (j) is two-dimensional data matrix A m×n N (j) is the j-th element of the reconstructed compressed signal.
And S7, judging whether the compression rate and the signal to noise ratio reach respective preset thresholds, if so, taking the wavelet coefficient as subway sliding plug door compression data, ending the compression flow, and if not, adjusting the size of the default threshold and jumping to the step S4.
Claims (7)
1. A subway sliding plug door data compression method based on a two-dimensional self-adaptive threshold wavelet is characterized by comprising the following steps:
s1, collecting door opening and closing data of a subway sliding plug door, and preprocessing the door opening and closing data to obtain a two-dimensional gray matrix;
s2, performing multi-scale decomposition on the two-dimensional gray matrix to obtain decomposition coefficients of each layer and the lengths of the decomposition coefficients of each layer;
s3, carrying out default threshold processing in the process of obtaining and compressing the two-dimensional gray matrix to obtain a default threshold;
s4, carrying out two-dimensional wavelet compression reconstruction on the two-dimensional gray matrix according to the decomposition coefficients of each layer, the decomposition coefficient lengths of each layer and a default threshold value to obtain wavelet coefficients and a reconstructed compressed signal;
s5, saving the wavelet coefficients, obtaining the size of a saved file, and calculating the compression rate according to the size of the saved file;
s6, calculating the signal-to-noise ratio of the reconstructed compressed signal;
and S7, judging whether the compression rate and the signal to noise ratio reach respective preset thresholds, if so, taking the wavelet coefficient as subway sliding plug door compression data, ending the compression flow, and if not, adjusting the size of the default threshold and jumping to the step S4.
2. The subway sliding-plug door data compression method based on the two-dimensional adaptive threshold wavelet according to claim 1, wherein the step S1 comprises the following steps:
s11, collecting door opening and closing data of a subway sliding plug door to form a two-dimensional data matrix;
s12, averaging each row of the two-dimensional data matrix to obtain a column matrix;
s13, drawing a column matrix amplitude curve according to elements of a column matrix, and dividing the column matrix amplitude curve by adopting a plurality of parallel lines to obtain block data and block positions;
s14, constructing a block matrix according to the block data and the block positions, and carrying out normalization processing on the block matrix to obtain a two-dimensional gray matrix.
3. The subway sliding-plug door data compression method based on the two-dimensional adaptive threshold wavelet according to claim 2, wherein the column matrix in the step S12 is:
wherein m is the sampling period, n is the number of sampling points in each sampling period, a 1, To a m, Subway sliding plug door opening and closing door data of m multiplied by n sampling points, A m×n Is a two-dimensional data matrix, B m I is the ith sampling point in the sampling period, b 1 To b m Is an element of a column matrix.
4. A subway sliding-plug door data compression method based on a two-dimensional adaptive threshold wavelet according to claim 3, wherein the step S13 comprises the steps of:
s131, taking the sampling point as the abscissa and taking the sampling point as the x axis, taking b as 1 To b m Drawing a column matrix amplitude curve by taking the ordinate as the y-axis;
s132, intercepting a column matrix amplitude curve by a plurality of parallel lines parallel to an x axis to obtain a plurality of divided curves and intersections of the parallel lines and the column matrix amplitude curve;
s133, classifying elements of a column matrix corresponding to each section of curve into a block;
s134, taking an abscissa corresponding to an intersection point of parallel lines and a column matrix amplitude curve as a blocking position.
5. The subway sliding-plug door data compression method based on the two-dimensional adaptive threshold wavelet according to claim 2, wherein the specific formula for normalizing the block matrix in step S14 is as follows:
D m×L ＝(C m×L -min(C m×L ))/(max(C m×L )-min(C m×L ))
wherein C is m×L For a block matrix, m is the sampling period, L is the number of segment curves,for the matrix of elements of the column matrix corresponding to the first segment of the piecewise curve,/for the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve>For the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve,/for the matrix of elements of the column matrix corresponding to the second segment of the piecewise curve>Matrix composed of elements of column matrix corresponding to L-th segment piecewise curve, L 1 For the position corresponding to the first segment of the piecewise curve, l 2 For the position corresponding to the second segment of the piecewise curve, l L For the position corresponding to the L-th segment of the piecewise curve, D m×L Is a two-dimensional gray matrix.
6. The subway sliding-plug door data compression method based on the two-dimensional adaptive threshold wavelet according to claim 1, wherein the formula for calculating the compression rate in the step S5 is:
wherein C is R For the compression ratio N in And storing the size of the two-dimensional gray matrix file, wherein Nout is the size of the stored wavelet coefficient file.
7. The subway sliding-plug door data compression method based on the two-dimensional adaptive threshold wavelet according to claim 1, wherein the formula for calculating the signal-to-noise ratio in the step S6 is:
wherein N is R For signal-to-noise ratio, m is sampling period, n is sampling point number in each sampling period, A (j) is two-dimensional data matrix A m×n N (j) is the j-th element of the reconstructed compressed signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010968468.5A CN112054806B (en) | 2020-09-15 | 2020-09-15 | Subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010968468.5A CN112054806B (en) | 2020-09-15 | 2020-09-15 | Subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112054806A CN112054806A (en) | 2020-12-08 |
| CN112054806B true CN112054806B (en) | 2023-07-25 |
Family
ID=73603181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010968468.5A Active CN112054806B (en) | 2020-09-15 | 2020-09-15 | Subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112054806B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289793A (en) * | 2011-07-19 | 2011-12-21 | 天津理工大学 | Cyber foraging-oriented multi-scale image processing method |
| CN103345636A (en) * | 2013-06-24 | 2013-10-09 | 中南大学 | Method for identifying foam working condition on copper flotation site based on wavelet multi-scale binaryzation |
| CN103427845A (en) * | 2013-08-05 | 2013-12-04 | 广西电网公司电力科学研究院 | Method for compressing and reconstructing harmonic data of power system on basis of two-dimensional block DCT (discrete cosine transformation) |
| CN105718877A (en) * | 2016-01-19 | 2016-06-29 | 昆明理工大学 | Signal coincidence degree matching method based on dynamic time warping and wavelet characteristics |
| CN105913370A (en) * | 2016-04-08 | 2016-08-31 | 重庆邮电大学 | Wavelet layering and combining chaos-based image encryption algorithm |
| CN107045142A (en) * | 2017-07-04 | 2017-08-15 | 吉林大学 | Wavelet field geological data Real Time Compression and High precision reconstruction method based on compressed sensing |
| CN109981109A (en) * | 2019-03-28 | 2019-07-05 | 华北科技学院 | Based on 2-d wavelet promotion-dct transform electric field value compression algorithm over the ground |
| CN111507386A (en) * | 2020-04-09 | 2020-08-07 | 中国科学院声学研究所南海研究站 | Method and system for detecting encrypted communication of storage file and network data stream |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8374450B2 (en) * | 2009-03-14 | 2013-02-12 | Amir Averbuch | Method for data compression using local cosine transform |
| US8981971B2 (en) * | 2013-03-27 | 2015-03-17 | Total E&P Research & Technology Usa, Inc. | Wavelet-based seismic data compression |
| WO2015052388A1 (en) * | 2013-10-10 | 2015-04-16 | Sas I-Ces (Innovative Compression Engineering Solutions) | Method for encoding a matrix, in particular a matrix representative of a still or video image, using a wavelet transform, with numbers of wavelet levels that vary according to the image and different quantization factors for each wavelet level |
-
2020
- 2020-09-15 CN CN202010968468.5A patent/CN112054806B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289793A (en) * | 2011-07-19 | 2011-12-21 | 天津理工大学 | Cyber foraging-oriented multi-scale image processing method |
| CN103345636A (en) * | 2013-06-24 | 2013-10-09 | 中南大学 | Method for identifying foam working condition on copper flotation site based on wavelet multi-scale binaryzation |
| CN103427845A (en) * | 2013-08-05 | 2013-12-04 | 广西电网公司电力科学研究院 | Method for compressing and reconstructing harmonic data of power system on basis of two-dimensional block DCT (discrete cosine transformation) |
| CN105718877A (en) * | 2016-01-19 | 2016-06-29 | 昆明理工大学 | Signal coincidence degree matching method based on dynamic time warping and wavelet characteristics |
| CN105913370A (en) * | 2016-04-08 | 2016-08-31 | 重庆邮电大学 | Wavelet layering and combining chaos-based image encryption algorithm |
| CN107045142A (en) * | 2017-07-04 | 2017-08-15 | 吉林大学 | Wavelet field geological data Real Time Compression and High precision reconstruction method based on compressed sensing |
| CN109981109A (en) * | 2019-03-28 | 2019-07-05 | 华北科技学院 | Based on 2-d wavelet promotion-dct transform electric field value compression algorithm over the ground |
| CN111507386A (en) * | 2020-04-09 | 2020-08-07 | 中国科学院声学研究所南海研究站 | Method and system for detecting encrypted communication of storage file and network data stream |
Non-Patent Citations (3)
| Title |
|---|
| An efficient architecture for two-dimensional discrete wavelet transform;Po-Cheng Wu等;《IEEE Trans. On Circuits and Systems for Video Technology》;第11卷(第4期);536-545 * |
| 分段自适应阈值小波的地铁塞拉门数据压缩方法;李城汐等;《哈尔滨工业大学学报》;第52卷(第9期);101-106 * |
| 基于计算机视觉的运动物体的检测与识别;唐岑等;《电子技术与软件工程》(第4期);128-129 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112054806A (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2011353672B2 (en) | Data improvement system and method | |
| CN110361180B (en) | Intelligent train pantograph service performance dynamic monitoring and evaluating method and system | |
| CN110209999A (en) | A kind of mobile unit failure trend prediction method | |
| CN112215409B (en) | Rail transit station passenger flow prediction method and system | |
| CN112054806B (en) | Subway sliding plug door data compression method based on two-dimensional self-adaptive threshold wavelet | |
| WO2019042615A1 (en) | System and method for acquiring operating data of a rail vehicle | |
| CN111547105B (en) | Non-contact speed measurement positioning method for medium-low speed maglev train | |
| CN110927497B (en) | Point switch fault detection method and device | |
| CN112541480A (en) | Online identification method and system for tunnel foreign matter invasion event | |
| DE102016116415A1 (en) | Apparatus and method for determining the condition of railways | |
| CN113487561B (en) | Pantograph foreign matter detection method and device based on gray gradient abnormal voting | |
| CN111046940A (en) | Vehicle door fault diagnosis method based on decision tree and neural network | |
| CN112127718B (en) | Method for detecting running state of sliding door lock of platform door system | |
| CN113610188A (en) | Bow net contact force non-section abnormity identification method and device | |
| CN116206263B (en) | Logistics vehicle monitoring method and system | |
| CN117009872A (en) | Heavy-load electric locomotive coupler instability early warning method based on vehicle body lateral acceleration | |
| CN112722003A (en) | Method and equipment for monitoring train derailment risk | |
| CN116611864A (en) | Urban rail transit train speed and passenger flow prediction method based on RNN | |
| CN114537481B (en) | Mobile closed train operation control method based on grating array | |
| CN113568393B (en) | Platform door fault detection method, device, computer equipment and storage medium | |
| CN115062867A (en) | Bearing fault prediction method based on Teager energy spectrum and improved CNN model | |
| CN111027719B (en) | Multi-component system state opportunity maintenance optimization method | |
| CN113792906B (en) | Train long-time window running track prediction method, device, equipment and storage medium | |
| CN114219039B (en) | Ship track compression method and system based on ship behavior characteristics | |
| CN116340725A (en) | Subway door system sub-health state identification method and system based on SSTCA |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |