CN113657025A - Track structure multisensor developments matching system - Google Patents
Track structure multisensor developments matching system Download PDFInfo
- Publication number
- CN113657025A CN113657025A CN202110835301.6A CN202110835301A CN113657025A CN 113657025 A CN113657025 A CN 113657025A CN 202110835301 A CN202110835301 A CN 202110835301A CN 113657025 A CN113657025 A CN 113657025A
- Authority
- CN
- China
- Prior art keywords
- data
- track structure
- module
- state
- matching system
- 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.)
- Pending
Links
- 238000011161 development Methods 0.000 title description 4
- 230000018109 developmental process Effects 0.000 title description 4
- 230000007704 transition Effects 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims abstract description 10
- 239000002245 particle Substances 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000002087 whitening effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The invention discloses a track structure multi-sensor dynamic matching system which comprises a plurality of data sensors and a matching system, wherein the data sensors are used for detecting data of a track structure and sending the data to the matching system; the state division module divides intervals according to the states of the track structure, corresponds the data corresponding to each interval to the states, establishes a transition frequency matrix and a one-step transition probability matrix according to the states of the intervals to obtain the marginal probability of the states, obtains the data intervals of the states, and sends the data intervals to the matching module. The invention realizes the automatic matching of the damage degree of the track structure, improves the matching precision and reduces the labor cost.
Description
Technical Field
The invention relates to the technical field of track structures, in particular to a track structure multi-sensor dynamic matching system.
Background
Along with the acceleration of urbanization process, the subway becomes the important component part of people's life traffic, however along with the increase of people's flow, subway track structure's load is also strengthening, make track structure appear damaging, damage track system gradually, if can not discover and restore immediately, hidden danger accumulation can make the damage more and more serious, cause the incident, need generally to join in marriage the sensor on track structure and detect in order to detect track structure's security performance and fault degree at present, but the testing result of sensor needs the manual work to match with fault degree according to experience, this kind of great increase cost of labor of matching mode, simultaneously also be not accurate enough, be unfavorable for modernized track structure's development.
Disclosure of Invention
In order to solve or partially solve above-mentioned problem at least, provide a track structure multisensor developments matching system, realize the degree of damage of automatic matching track structure, improve the matching precision, reduce the cost of labor.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention discloses a track structure multi-sensor dynamic matching system, which comprises a plurality of data sensors and a matching system, wherein the data sensors are used for detecting data of a track structure and sending the data to the matching system, the matching system comprises a data modeling module, a state dividing module and a matching module,
the data modeling module takes the detection data of each time interval as a variable to correspond to the time interval, forms an original data array and sends the original data array to the state dividing module;
the state division module divides intervals according to the states of the track structure, corresponds data corresponding to each interval to the states, establishes a transition frequency matrix and a one-step transition probability matrix according to the states of the intervals to obtain marginal probabilities of the states, obtains a data interval of each state and sends the data interval to the matching module;
and the matching module matches the currently detected data with the data interval to obtain the state of the track structure.
As a preferred solution of the invention, the data of the track structure comprise longitudinal forces of the track structure, inclinations between the track structures and temperatures, and adhesion parameters of the track structure.
The invention further comprises a correction module, wherein the correction module performs whitening correction on the data interval by utilizing a particle swarm algorithm and sends correction data to the matching module.
As a preferred technical solution of the present invention, the correction module records the data interval as αab[xab，yab]Wherein x isab，yabRepresenting the minimum and maximum predicted values of the state interval corresponding to the transition from state a to state b, which interval is now optimized, αab＝xabρb+(1-ρb)yab，ρb[0,1]When rhobWhen the value is 0.5, outputting a data result;
the particle length d of the particle swarm algorithm is 3, the particle number m of the particle swarm algorithm is 200, the iteration number k of the particle swarm algorithm is 500, the learning factor c1 of the particle swarm algorithm is c2 of the particle swarm algorithm is 2, and the weighting factor w of the particle swarm algorithm is 1.
As a preferable technical solution of the present invention, the matching system further comprises a communication module, and the data sensor and the matching system perform data transmission through the communication module.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, the data detected by the sensor is modeled, and the Markov chain is established by adopting the transition frequency matrix and the one-step transition probability matrix, so that the detected data can be automatically matched with the data of the sensor, the damage degree of the track structure is automatically matched, the matching precision is improved, and the labor cost is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic view of the overall structure of the present invention;
in the figure: 1. a data sensor; 2. a matching system; 3. a data modeling module; 4. a state division module; 5. a matching module; 6. a correction module; 7. and a communication module.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation. Wherein like reference numerals refer to like parts throughout.
In addition, if a detailed description of the known art is not necessary to show the features of the present invention, it is omitted.
Example 1
As shown in fig. 1, the present invention provides a track structure multi-sensor dynamic matching system, which comprises a plurality of data sensors 1 and a matching system 2, wherein the plurality of data sensors 1 are used for detecting data of a track structure and sending the data to the matching system 2, the matching system 2 comprises a data modeling module 3, a state dividing module 4 and a matching module 5,
the data modeling module 3 takes the detection data of each time interval as a variable to correspond to the time interval to form an original data array, and sends the original data array to the state dividing module 4;
the state division module 4 divides the interval according to the state of the track structure, corresponds the data corresponding to each time interval to the state, establishes a transition frequency matrix and a one-step transition probability matrix according to the state of each time interval to obtain the marginal probability of each state, thereby obtaining the data interval of each state, and sends the data interval to the matching module 5;
the matching module 5 matches the currently detected data with the data interval to obtain the state of the track structure.
Specifically, in the process of dynamic matching, data of the track structure including longitudinal force of the track structure, inclination between the track structures, temperature of the track structure, and force parameters are recorded and stored, a database is established, and a Markov chain is established by means of modeling and the like.
In order to further improve the accuracy of the Markov chain, the Markov chain matching system further comprises a correction module 6, wherein the correction module 6 performs whitening correction on the data interval by using a particle swarm algorithm, improves the accuracy of a result by using the correction module 6 to correct the data interval, and sends correction data to the matching module 5 to realize data matching.
The correction module 6 records the data interval as alphaab[xab，yab]Wherein x isab，yabRepresenting the minimum and maximum predicted values of the state interval corresponding to the transition from state a to state b, which interval is now optimized, αab＝xabρb+(1-ρb)yab，ρb[0,1]When rhobWhen the value is 0.5, outputting a data result;
the particle length d of the particle swarm algorithm is 3, the particle number m is 200, the iteration number k is 500, the learning factor c1 is c2 is 2, and the weighting factor w is 1.
The device also comprises a communication module 7, and the data sensor 1 and the matching system 2 perform data transmission through the communication module 7.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A track structure multi-sensor dynamic matching system is characterized by comprising a plurality of data sensors (1) and a matching system (2), wherein the data sensors (1) are used for detecting data of a track structure and sending the data to the matching system (2), the matching system (2) comprises a data modeling module (3), a state dividing module (4) and a matching module (5),
the data modeling module (3) takes the detection data of each time interval as a variable to correspond to the time interval, forms an original data array, and sends the original data array to the state dividing module (4);
the state division module (4) divides intervals according to the state of the track structure, corresponds data corresponding to each interval to the state, establishes a transition frequency matrix and a one-step transition probability matrix according to the state of each interval to obtain the marginal probability of each state, thereby obtaining the data interval of each state, and sends the data interval to the matching module (5);
and the matching module (5) matches the currently detected data with the data interval to obtain the state of the track structure.
2. The track structure multi-sensor dynamic matching system according to claim 1, wherein the data of the track structure comprises longitudinal force of the track structure, inclination between the track structures and temperature, and force parameters of the track structure.
3. The track structure multi-sensor dynamic matching system according to claim 1, further comprising a correction module (6), wherein the correction module (6) performs whitening correction on the data interval by using a particle swarm algorithm and sends the correction data to the matching module (5).
4. The track structure multisensor dynamic matching system of claim 3, wherein the correction module (6) records data intervals as αab[xab，yab]Wherein x isab，yabRepresenting the minimum and maximum predicted values of the state interval corresponding to the transition from state a to state b, which interval is now optimized, αab＝xabρb+(1-ρb)yab，ρb[0,1]When rhobWhen the value is 0.5, outputting a data result;
the particle length d of the particle swarm algorithm is 3, the particle number m of the particle swarm algorithm is 200, the iteration number k of the particle swarm algorithm is 500, the learning factor c1 of the particle swarm algorithm is c2 of the particle swarm algorithm is 2, and the weighting factor w of the particle swarm algorithm is 1.
5. The track structure multi-sensor dynamic matching system according to claim 1, further comprising a communication module (7), wherein the data sensor (1) and the matching system (2) perform data transmission through the communication module (7).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110835301.6A CN113657025A (en) | 2021-07-23 | 2021-07-23 | Track structure multisensor developments matching system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110835301.6A CN113657025A (en) | 2021-07-23 | 2021-07-23 | Track structure multisensor developments matching system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113657025A true CN113657025A (en) | 2021-11-16 |
Family
ID=78489795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110835301.6A Pending CN113657025A (en) | 2021-07-23 | 2021-07-23 | Track structure multisensor developments matching system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657025A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156591A (en) * | 2014-08-06 | 2014-11-19 | 北京信息科技大学 | Markov fault trend prediction method |
| CN109800875A (en) * | 2019-01-08 | 2019-05-24 | 华南理工大学 | Chemical industry fault detection method based on particle group optimizing and noise reduction sparse coding machine |
| CN110674752A (en) * | 2019-09-25 | 2020-01-10 | 广东省智能机器人研究院 | Hidden Markov model-based tool wear state identification and prediction method |
| CN111079827A (en) * | 2019-12-13 | 2020-04-28 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Railway data state evaluation method and system |
| CN111315630A (en) * | 2017-10-30 | 2020-06-19 | 科路实有限责任公司 | Data fusion concept |
-
2021
- 2021-07-23 CN CN202110835301.6A patent/CN113657025A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156591A (en) * | 2014-08-06 | 2014-11-19 | 北京信息科技大学 | Markov fault trend prediction method |
| CN111315630A (en) * | 2017-10-30 | 2020-06-19 | 科路实有限责任公司 | Data fusion concept |
| CN109800875A (en) * | 2019-01-08 | 2019-05-24 | 华南理工大学 | Chemical industry fault detection method based on particle group optimizing and noise reduction sparse coding machine |
| CN110674752A (en) * | 2019-09-25 | 2020-01-10 | 广东省智能机器人研究院 | Hidden Markov model-based tool wear state identification and prediction method |
| CN111079827A (en) * | 2019-12-13 | 2020-04-28 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Railway data state evaluation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 余丹丹 等: "基于粒子群改进灰色马尔可夫模型的公路路基沉降自适应预测", 道路工程, no. 3, 31 December 2019 (2019-12-31), pages 4 - 7 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704801B (en) | Bridge cluster structure operation safety intelligent monitoring and rapid detection complete method | |
| EP1363005A3 (en) | Engine control system using a cascaded neural network | |
| US20080312756A1 (en) | Virtual sensor system and method | |
| CN110750875B (en) | Structure dynamic and static parameter uncertainty quantitative analysis system only using output response | |
| JP2009520948A (en) | Process model based virtual sensor system and method | |
| CN103529822A (en) | Method and device for detecting vehicle failure | |
| JP6699301B2 (en) | Abnormality detection device, abnormality detection method, and abnormality detection system | |
| US6292738B1 (en) | Method for adaptive detection of engine misfire | |
| CN110398775B (en) | Tunnel water burst disaster micro-seismic event signal fluctuation first arrival pickup method and system | |
| CN101950483A (en) | Repairing method and device for traffic data fault | |
| CN114889488A (en) | Battery pack collision detection device and method | |
| CN113657025A (en) | Track structure multisensor developments matching system | |
| CN115659782A (en) | Bridge damage identification method based on PGDNN under action of mobile vehicle load | |
| CN114386715A (en) | Prediction method, system, equipment and medium for main braking air path pressure leakage | |
| CN115803644A (en) | System and method for battery diagnosis based on altitude using barometric pressure sensor | |
| CN111351628B (en) | Hypersonic wind tunnel continuous variable attack angle test data processing method | |
| US11132851B2 (en) | Diagnosis device and diagnosis method | |
| CN113747270B (en) | Cloud data center thing allies oneself with management and control system | |
| CN115310367A (en) | Mine air quality monitoring system based on LSTM neural network | |
| CN112257750B (en) | Distributed fusion system for composite detection node | |
| CN114935450A (en) | Failure monitoring and alarming method for large-span cable-stayed bridge inhaul cable damper | |
| CN107273594B (en) | EMD-DNMPSO-based dynamic variable parameter tracking method for metal bellows of automobile exhaust system | |
| CN116560219B (en) | Self-adaptive monitoring control method and system based on transmission tower wind speed joint analysis | |
| CN103761817A (en) | Circumference rail alarm based on vibration sensor and control method of circumference rail alarm | |
| CN114741923B (en) | Large-span bridge sling force identification method based on high-density measuring point strain |
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 |