CN112750103A - Train brake pad thickness detection method and system thereof - Google Patents
Train brake pad thickness detection method and system thereof Download PDFInfo
- Publication number
- CN112750103A CN112750103A CN202011566655.7A CN202011566655A CN112750103A CN 112750103 A CN112750103 A CN 112750103A CN 202011566655 A CN202011566655 A CN 202011566655A CN 112750103 A CN112750103 A CN 112750103A
- Authority
- CN
- China
- Prior art keywords
- data
- brake pad
- thickness
- brake
- wear rate
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000005299 abrasion Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 5
- 230000009469 supplementation Effects 0.000 claims 1
- 238000013507 mapping Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
- G01B21/08—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness for measuring thickness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/006—Indicating maintenance
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Geometry (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Braking Arrangements (AREA)
Abstract
The invention discloses a train brake pad thickness detection method and a system thereof, wherein the method comprises the following steps: acquiring train brake pad image data and train mileage data; extracting the thickness data of the lower end of a first brake pad and the thickness data of the lower end of a second brake pad contained in the train brake pad image data; generating first brake pad lower end wear rate data and second brake pad lower end wear rate data based on the first brake pad lower end thickness data, the second brake pad lower end thickness data and the mileage data; constructing a training sample set consisting of a plurality of groups of manually marked upper end thickness data of the first brake pad, upper end thickness data of the second brake pad, lower end thickness data of the first brake pad and lower end thickness data of the second brake pad; constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data; and training a brake pad minimum thickness prediction model based on the training sample set, and generating an optimal thickness prediction model for predicting the brake pad minimum thickness value.
Description
Technical Field
The invention relates to the technical field of rail vehicle detection, in particular to a method and a system for detecting the thickness of a train brake pad.
Background
Along with the rapid development of high-speed trains, the train operation safety has become the research focus in the field of rail transit, and as the arresting gear of train operation, the brake lining can lead to the brake lining wearing and tearing because of the heat production of friction, when brake lining thickness reached the limit, can lead to the brake lining to become invalid, increases train operation risk. Therefore, how to effectively detect the thickness of the brake pad is one of the key problems for guaranteeing the operation safety of the train.
The traditional brake pad thickness detection method comprises an on-line brake pad detection system and manual brake pad detection caliper detection. Although the thickness of the lower end of the brake pad can be effectively detected by the traditional brake pad on-line monitoring system, the thickness of the upper end of the brake pad cannot be detected due to a visual angle blind zone, so that the minimum thickness of the upper end and the lower end of the brake pad cannot be judged; although the brake pad detection caliper can detect the thickness values of the upper end and the lower end of the brake pad and realize the evaluation of the minimum thickness value of the upper end and the lower end of the brake pad, for more than one hundred brake pads of one vehicle, the detection method of manual operation is higher in detection complexity, influenced by factors such as user subjective judgment, working experience and the like, the detection result is lower in accuracy, and the labor cost and the time cost are too high.
In summary, the conventional automatic thickness detection method for the brake pad has the problem of low reliability of the detection result due to the fact that the thickness of the upper end of the brake pad cannot be detected.
Disclosure of Invention
In view of the above, the invention provides a train brake pad thickness detection method and a train brake pad thickness detection system, which solve the problem of low detection result reliability caused by the fact that the thickness of the upper end of a brake pad cannot be detected in the traditional automatic brake pad thickness detection method by improving the processing mode of detection data and constructing an optimal thickness prediction model capable of representing the mapping relation between the thickness of the lower end of the brake pad and the minimum thickness of the brake pad.
In order to solve the above problems, the technical scheme of the invention is a train brake pad thickness detection method, which comprises the following steps: s1: acquiring train brake pad image data and train mileage data; s2: extracting first brake pad lower end thickness data and second brake pad lower end thickness data contained in the train brake pad image data; s3: generating first brake pad lower end wear rate data and second brake pad lower end wear rate data based on the first brake pad lower end thickness data, the second brake pad lower end thickness data and the mileage data; s4: constructing a training sample set consisting of a plurality of groups of manually marked upper end thickness data of a first brake pad and upper end thickness data of a second brake pad, and lower end thickness data of the first brake pad and lower end thickness data of the second brake pad; s5: constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data; s6: and training the brake pad minimum thickness prediction model based on the training sample set to generate an optimal thickness prediction model for predicting the brake pad minimum thickness value.
Optionally, the S3 includes: calling initial brake pad thickness data, historical brake pad lower end thickness data and historical driving mileage data corresponding to the initial brake pad thickness data and the historical brake pad lower end thickness data; and generating the first brake pad lower end abrasion rate data and the second brake pad lower end abrasion rate data by taking the travel mileage as an independent variable based on the initial brake pad thickness data, the historical brake pad lower end thickness data and the historical travel mileage corresponding to the initial brake pad thickness data, the historical brake pad lower end thickness data, the brake pad lower end thickness data and the travel mileage data.
Optionally, the S5 includes: calculating a brake pad thickness parameter, a thickness deviation parameter, a thickness continuity deviation parameter, a wear rate deviation parameter and a wear rate continuity deviation parameter based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and constructing a brake pad minimum thickness prediction model PVup=CVdown±P(a1,a2,a3,a4,a5,a6) Wherein PV isupFor brake pad minimum thickness prediction data, CVdownIs the thickness data of the lower end of the first brake pad, P (a)1,a2,a3,a4,a5,a6) In (a)1Is the thickness parameter of the brake pad, a2Is the thickness deviation parameter, a3Is the thickness continuity deviation parameter, a4Is the wear rate parameter, a5Is the wear rate deviation parameter, a6And the abrasion rate continuous deviation parameter is adopted.
Optionally, the S6 includes: s61: using the formula Err ═ PVup-RVupCalculating the prediction error of the brake pad minimum thickness prediction model, wherein Err is the prediction error, PVupFor brake pad minimum thickness prediction data, RVupA brake pad minimum thickness value for the set of training samples; s62: updating the brake pad thickness parameter, the thickness deviation parameter, the thickness continuity deviation parameter, the wear rate deviation parameter and the wear rate continuity deviation parameter based on the prediction error, and calculating the prediction error of the brake pad minimum thickness prediction model; s63: and repeating the steps S61-S62 until the prediction error of the brake pad minimum thickness prediction model converges to the minimum value, and generating the optimal thickness prediction model. Wherein, the brakeThe thickness ranges of the brake lining are different, and the corresponding wear rules are possibly different, so that the brake lining thickness parameters are set to classify the thickness intervals, the brake lining thickness variation trend corresponding to the thickness intervals is represented by other five parameters, and finally a complete parameter set is formed.
Optionally, the S2 includes: and after the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad contained in the train brake pad image data are extracted, data cleaning is carried out on the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad, wherein the data cleaning method comprises integrity judgment, data type judgment, abnormal data judgment and value compensation.
Accordingly, the present invention provides a train brake pad thickness detection system, comprising: the image acquisition unit is used for acquiring image data of the train brake pad; the train number identification unit is used for identifying train information and acquiring the driving mileage data of the train; a data processing unit, configured to extract first brake lining lower end thickness data and second brake lining lower end thickness data included in the train brake lining image data, generate first brake lining lower end wear rate data and second brake lining lower end wear rate data based on the first brake lining lower end thickness data, the second brake lining lower end thickness data, and the mileage data, and constructing a plurality of groups of manually marked upper end thickness data of the first brake pad and upper end thickness data of the second brake pad, and a training sample set consisting of the first brake pad lower end thickness data and the second brake pad lower end thickness data, constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and training the brake pad minimum thickness prediction model through the training sample set to generate an optimal thickness prediction model for predicting the brake pad minimum thickness value.
Optionally, the train brake lining thickness detection system further includes a data storage unit, configured to store initial brake lining thickness data, historical brake lining lower end thickness data, and historical driving mileage data corresponding thereto.
Optionally, the data processing unit generates the first brake lining lower end wear rate data and the second brake lining lower end wear rate data with the mileage as an independent variable based on the initial brake lining thickness data, the historical brake lining lower end thickness data and the historical mileage data corresponding thereto, the brake lining lower end thickness data and the mileage data by calling the initial brake lining thickness data, the historical brake lining lower end thickness data and the historical mileage data corresponding thereto.
Optionally, the data processing unit calculates a brake pad thickness parameter, a thickness deviation parameter, a thickness continuity deviation parameter, a wear rate deviation parameter and a wear rate continuity deviation parameter from the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and constructs the brake pad minimum thickness prediction model PVup=CVdown±P(a1,a2,a3,a4,a5,a6) Wherein PV isupFor brake pad minimum thickness prediction data, CVdownIs the thickness data of the lower end of the first brake pad, P (a)1,a2,a3,a4,a5,a6) In (a)1Is the thickness parameter of the brake pad, a2Is the thickness deviation parameter, a3Is the thickness continuity deviation parameter, a4Is the wear rate parameter, a5Is the wear rate deviation parameter, a6And the abrasion rate continuous deviation parameter is adopted.
The method for detecting the thickness of the train brake pad has the advantages that a brake pad minimum thickness prediction model is established based on currently acquired brake pad lower end thickness data and historical detection data, an optimal thickness prediction model capable of representing the mapping relation between the brake pad lower end thickness and the brake pad minimum thickness is established by taking the artificially marked brake pad data as a training sample, and the problem of low detection result reliability caused by the fact that the thickness of the upper end of the brake pad cannot be detected in the traditional automatic brake pad thickness detection method is solved.
Drawings
FIG. 1 is a simplified flow chart of a train brake pad thickness detection method of the present invention;
FIG. 2 is an exemplary illustration of the wear of the brake pads of the present invention; and
fig. 3 is a simplified block diagram of a train brake pad thickness detection system of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, the present invention provides a method for detecting a thickness of a train brake pad, comprising: s1: acquiring train brake pad image data and train mileage data; s2: extracting first brake pad lower end thickness data and second brake pad lower end thickness data contained in the train brake pad image data; s3: generating first brake pad lower end wear rate data and second brake pad lower end wear rate data based on the first brake pad lower end thickness data, the second brake pad lower end thickness data and the mileage data; s4: constructing a training sample set consisting of a plurality of groups of manually marked upper end thickness data of a first brake pad and upper end thickness data of a second brake pad, and lower end thickness data of the first brake pad and lower end thickness data of the second brake pad; s5: constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data; s6: and training the brake pad minimum thickness prediction model based on the training sample set to generate an optimal thickness prediction model for predicting the brake pad minimum thickness value.
In order to facilitate understanding of the claimed technical solution, taking a brake pad eccentric wear condition as an example, as shown in fig. 2, a conventional detecting device for train brake pads can only detect the thickness value at the B, D position, that is, only the thickness value of the lower end of the brake pad. However, since the brake pad thickness wear at the A, B, C, D position varies during the train operation, the brake pad upper end A, C position in fig. 2 may wear too much, and the minimum thickness position may occur at the A, C position, resulting in excessive brake pad wear and even a risk of train operation. Therefore, the method establishes the brake pad minimum thickness prediction model based on the currently acquired brake pad lower end thickness data and historical detection data, and establishes the optimal thickness prediction model capable of representing the mapping relation between the brake pad lower end thickness and the brake pad minimum thickness by taking the artificially marked brake pad data as the training sample, so that the problem of low detection result reliability caused by the fact that the thickness of the brake pad upper end cannot be detected in the traditional brake pad thickness automatic detection method is solved, and the safety of the train in operation is effectively improved.
Further, the S3 includes: calling initial brake pad thickness data, historical brake pad lower end thickness data and historical driving mileage data corresponding to the initial brake pad thickness data and the historical brake pad lower end thickness data; and generating the first brake pad lower end abrasion rate data and the second brake pad lower end abrasion rate data by taking the travel mileage as an independent variable based on the initial brake pad thickness data, the historical brake pad lower end thickness data and the historical travel mileage corresponding to the initial brake pad thickness data, the historical brake pad lower end thickness data, the brake pad lower end thickness data and the travel mileage data.
Further, the S5 includes: calculating a brake pad thickness parameter, a thickness deviation parameter, a thickness continuity deviation parameter, a wear rate deviation parameter and a wear rate continuity deviation parameter based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and constructing a brake pad minimum thickness prediction model PVup=CVdown±P(a1,a2,a3,a4,a5,a6) Wherein PV isupFor brake pad minimum thickness prediction data, CVdownIs the thickness data of the lower end of the first brake pad, P (a)1,a2,a3,a4,a5,a6) In (a)1Is the thickness parameter of the brake pad, a2Is the thickness deviation parameter, a3Is the thickness continuity deviation parameter, a4Is the wear rate parameter, a5Is the wear rate deviation parameter, a6And the abrasion rate continuous deviation parameter is adopted.
Further, the S6 includes: s61: using the formula Err ═ PVup-RVupCalculating the prediction error of the brake pad minimum thickness prediction model, wherein Err is the prediction error, PVupFor brake pad minimum thickness prediction data, RVupA brake pad minimum thickness value for the set of training samples; s62: updating the brake pad thickness parameter, the thickness deviation parameter, the thickness continuity deviation parameter, the wear rate deviation parameter and the wear rate continuity deviation parameter based on the prediction error, and calculating the prediction error of the brake pad minimum thickness prediction model; s63: and repeating the steps S61-S62 until the prediction error of the brake pad minimum thickness prediction model converges to the minimum value, and generating the optimal thickness prediction model.
Further, the S2 includes: and after the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad contained in the train brake pad image data are extracted, data cleaning is carried out on the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad, wherein the data cleaning method comprises integrity judgment, data type judgment, abnormal data judgment and value compensation. Specifically, the integrity judgment is to perform integrity judgment on the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad based on historical brake pad detection thickness data, so that the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad are consistent with the detection time and the data length of the detected running kilometer; the data type is judged to be that the numerical value type is ensured to be uniform by detecting the numerical value type; judging whether the numerical values of the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad exceed the upper limit and the lower limit of the thickness of the brake pads or not by the abnormal data judgment, if so, judging that the data are abnormal, rejecting the data and supplementing the data; the complement value is based on the mean value of the normal values before and after the abnormal value that are nearest to the abnormal value.
Accordingly, as shown in fig. 3, the present invention provides a train brake pad thickness detecting system, including: the image acquisition unit is used for acquiring image data of the train brake pad; the train number identification unit is used for identifying train information and acquiring the driving mileage data of the train; a data processing unit, configured to extract first brake lining lower end thickness data and second brake lining lower end thickness data included in the train brake lining image data, generate first brake lining lower end wear rate data and second brake lining lower end wear rate data based on the first brake lining lower end thickness data, the second brake lining lower end thickness data, and the mileage data, and constructing a plurality of groups of manually marked upper end thickness data of the first brake pad and upper end thickness data of the second brake pad, and a training sample set consisting of the first brake pad lower end thickness data and the second brake pad lower end thickness data, constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and training the brake pad minimum thickness prediction model through the training sample set to generate an optimal thickness prediction model for predicting the brake pad minimum thickness value. The image acquisition unit and the vehicle number identification unit are electrically connected with the data processing unit.
Further, the train brake pad thickness detection system further comprises a data storage unit, and the data storage unit is used for storing initial brake pad thickness data, historical brake pad lower end thickness data and historical driving mileage data corresponding to the historical brake pad lower end thickness data. The data storage unit is electrically connected with the data processing unit.
Further, the data processing unit generates the first brake lining lower end wear rate data and the second brake lining lower end wear rate data with the travel mileage as an independent variable based on the initial brake lining thickness data, the historical brake lining lower end thickness data and the historical travel mileage corresponding to the historical brake lining lower end thickness data, the brake lining lower end thickness data and the travel mileage data by calling the initial brake lining thickness data, the historical brake lining lower end thickness data and the historical travel mileage data corresponding to the initial brake lining thickness data and the historical brake lining lower end thickness data.
Furthermore, the data processing unit calculates a brake pad thickness parameter, a thickness deviation parameter, a thickness continuity deviation parameter, a wear rate deviation parameter and a wear rate continuity deviation parameter according to the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and constructs the brake pad minimum thickness prediction model PVup=CVdown±P(a1,a2,a3,a4,a5,a6) Which isMiddle, PVupFor brake pad minimum thickness prediction data, CVdownIs the thickness data of the lower end of the first brake pad, P (a)1,a2,a3,a4,a5,a6) In (a)1Is the thickness parameter of the brake pad, a2Is the thickness deviation parameter, a3Is the thickness continuity deviation parameter, a4Is the wear rate parameter, a5Is the wear rate deviation parameter, a6And the abrasion rate continuous deviation parameter is adopted.
The train brake pad thickness detection method and the train brake pad thickness detection system provided by the embodiment of the invention are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (9)
1. A method for detecting the thickness of a train brake pad is characterized by comprising the following steps:
s1: acquiring train brake pad image data and train mileage data;
s2: extracting first brake pad lower end thickness data and second brake pad lower end thickness data contained in the train brake pad image data;
s3: generating first brake pad lower end wear rate data and second brake pad lower end wear rate data based on the first brake pad lower end thickness data, the second brake pad lower end thickness data and the mileage data;
s4: constructing a training sample set consisting of a plurality of groups of manually marked upper end thickness data of a first brake pad and upper end thickness data of a second brake pad, and lower end thickness data of the first brake pad and lower end thickness data of the second brake pad;
s5: constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data;
s6: and training the brake pad minimum thickness prediction model based on the training sample set to generate an optimal thickness prediction model for predicting the brake pad minimum thickness value.
2. The train brake pad thickness detection method according to claim 1, wherein the S3 includes:
calling initial brake pad thickness data, historical brake pad lower end thickness data and historical driving mileage data corresponding to the initial brake pad thickness data and the historical brake pad lower end thickness data;
and generating the first brake pad lower end abrasion rate data and the second brake pad lower end abrasion rate data by taking the travel mileage as an independent variable based on the initial brake pad thickness data, the historical brake pad lower end thickness data and the historical travel mileage corresponding to the initial brake pad thickness data, the historical brake pad lower end thickness data, the brake pad lower end thickness data and the travel mileage data.
3. The train brake pad thickness detection method according to claim 2, wherein the S5 includes:
calculating a brake pad thickness parameter, a thickness deviation parameter, a thickness continuity deviation parameter, a wear rate deviation parameter and a wear rate continuity deviation parameter based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and constructing a brake pad minimum thickness prediction model PVup=CVdown±P(a1,a2,a3,a4,a5,a6) Wherein PV isupFor brake pad minimum thickness prediction data, CVdownIs the thickness data of the lower end of the first brake pad, P (a)1,a2,a3,a4,a5,a6) In (a)1Is the thickness parameter of the brake pad, a2Is the thickness deviation parameter, a3Is the thickness continuity deviation parameter, a4Is the wear rate parameter, a5Is the wear rate deviation parameter, a6And the abrasion rate continuous deviation parameter is adopted.
4. The train brake pad thickness detection method according to claim 3, wherein the S6 includes:
s61: using the formula Err ═ PVup-RVupCalculating the prediction error of the brake pad minimum thickness prediction model, wherein Err is the prediction error, PVupFor brake pad minimum thickness prediction data, RVupA brake pad minimum thickness value for the set of training samples;
s62: updating the brake pad thickness parameter, the thickness deviation parameter, the thickness continuity deviation parameter, the wear rate deviation parameter and the wear rate continuity deviation parameter based on the prediction error, and calculating the prediction error of the brake pad minimum thickness prediction model;
s63: and repeating the steps S61-S62 until the prediction error of the brake pad minimum thickness prediction model converges to the minimum value, and generating the optimal thickness prediction model.
5. The train brake pad thickness detection method according to claim 4, wherein the S2 includes:
after the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad contained in the train brake pad image data are extracted, data cleaning is carried out on the thickness data of the lower end of the first brake pad and the thickness data of the lower end of the second brake pad, wherein,
the data cleaning method comprises integrity judgment, data type judgment, abnormal data judgment and value supplementation.
6. A train brake pad thickness detection system, characterized by includes:
the image acquisition unit is used for acquiring image data of the train brake pad;
the train number identification unit is used for identifying train information and acquiring the driving mileage data of the train;
a data processing unit, configured to extract first brake lining lower end thickness data and second brake lining lower end thickness data included in the train brake lining image data, generate first brake lining lower end wear rate data and second brake lining lower end wear rate data based on the first brake lining lower end thickness data, the second brake lining lower end thickness data, and the mileage data, and constructing a plurality of groups of manually marked upper end thickness data of the first brake pad and upper end thickness data of the second brake pad, and a training sample set consisting of the first brake pad lower end thickness data and the second brake pad lower end thickness data, constructing a brake pad minimum thickness prediction model based on the first brake pad lower end wear rate data and the second brake pad lower end wear rate data, and training the brake pad minimum thickness prediction model through the training sample set to generate an optimal thickness prediction model for predicting the brake pad minimum thickness value.
7. The train brake lining thickness detection system of claim 6, further comprising a data storage unit for storing initial brake lining thickness data, historical brake lining lower end thickness data and corresponding historical mileage data.
8. The train brake lining thickness detection system of claim 7, wherein the data processing unit generates the first brake lining lower end wear rate data and the second brake lining lower end wear rate data with mileage as an argument based on the initial brake lining thickness data, the historical brake lining lower end thickness data and the historical mileage traveled by the historical brake lining data corresponding thereto, the brake lining lower end thickness data, and the mileage traveled data by calling the initial brake lining thickness data, the historical brake lining lower end thickness data, and the historical mileage traveled by the historical brake lining data corresponding thereto.
9. The train brake lining thickness detection system of claim 8, wherein the data processing unit calculates a brake lining thickness parameter, a thickness deviation parameter, a thickness continuity deviation parameter, a wear rate deviation parameter and a wear rate continuity deviation parameter from the first brake lining lower end wear rate data and the second brake lining lower end wear rate data, and constructs the brake lining minimum thickness prediction model PVup=CVdown±P(a1,a2,a3,a4,a5,a6) Wherein PV isupFor brake pad minimum thickness prediction data, CVdownIs the thickness data of the lower end of the first brake pad, P (a)1,a2,a3,a4,a5,a6) In (a)1Is the thickness parameter of the brake pad, a2Is the thickness deviation parameter, a3Is the thickness continuity deviation parameter, a4Is the wear rate parameter, a5Is the wear rate deviation parameter, a6And the abrasion rate continuous deviation parameter is adopted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011566655.7A CN112750103B (en) | 2020-12-25 | 2020-12-25 | Train brake pad thickness detection method and system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011566655.7A CN112750103B (en) | 2020-12-25 | 2020-12-25 | Train brake pad thickness detection method and system thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112750103A true CN112750103A (en) | 2021-05-04 |
CN112750103B CN112750103B (en) | 2024-02-02 |
Family
ID=75646038
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011566655.7A Active CN112750103B (en) | 2020-12-25 | 2020-12-25 | Train brake pad thickness detection method and system thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112750103B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030048932A (en) * | 2001-12-13 | 2003-06-25 | 주식회사 포스코 | Strip thickness control system and method using filtered rolling force & skid mark thickness variation |
FR2969240A1 (en) * | 2010-12-16 | 2012-06-22 | Peugeot Citroen Automobiles Sa | System for controlling wear of brake pads of e.g. front left wheel in vehicle, has control unit including measuring unit for measuring wear of pads, and detection unit detecting evolution intervals with respect to typical wear of pads |
CN103742575A (en) * | 2013-12-30 | 2014-04-23 | 北京交通大学 | Motor train unit brake lining wear loss estimation method based on on-line monitoring |
CN104455121A (en) * | 2014-12-18 | 2015-03-25 | 成都铁安科技有限责任公司 | Method and system for detecting residual thickness of brake shoe |
CN104457596A (en) * | 2014-12-18 | 2015-03-25 | 成都铁安科技有限责任公司 | Train brake pad abrasion detection method |
CN106641031A (en) * | 2016-12-02 | 2017-05-10 | 铜仁学院 | Brake pad and thickness detecting method |
WO2019206577A1 (en) * | 2018-04-25 | 2019-10-31 | Knorr-Bremse Systeme für Nutzfahrzeuge GmbH | Method for indicating a pending brake pad change of a motor vehicle brake |
CN110411729A (en) * | 2019-08-07 | 2019-11-05 | 科大讯飞股份有限公司 | Brake block life forecast method and device |
CN110905951A (en) * | 2019-12-10 | 2020-03-24 | 深圳鼎然信息科技有限公司 | Method, device, equipment and medium for dynamically monitoring automobile brake pad abrasion in real time |
CN111862082A (en) * | 2020-07-31 | 2020-10-30 | 成都盛锴科技有限公司 | Train brake pad thickness rechecking method and system thereof |
-
2020
- 2020-12-25 CN CN202011566655.7A patent/CN112750103B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030048932A (en) * | 2001-12-13 | 2003-06-25 | 주식회사 포스코 | Strip thickness control system and method using filtered rolling force & skid mark thickness variation |
FR2969240A1 (en) * | 2010-12-16 | 2012-06-22 | Peugeot Citroen Automobiles Sa | System for controlling wear of brake pads of e.g. front left wheel in vehicle, has control unit including measuring unit for measuring wear of pads, and detection unit detecting evolution intervals with respect to typical wear of pads |
CN103742575A (en) * | 2013-12-30 | 2014-04-23 | 北京交通大学 | Motor train unit brake lining wear loss estimation method based on on-line monitoring |
CN104455121A (en) * | 2014-12-18 | 2015-03-25 | 成都铁安科技有限责任公司 | Method and system for detecting residual thickness of brake shoe |
CN104457596A (en) * | 2014-12-18 | 2015-03-25 | 成都铁安科技有限责任公司 | Train brake pad abrasion detection method |
CN106641031A (en) * | 2016-12-02 | 2017-05-10 | 铜仁学院 | Brake pad and thickness detecting method |
WO2019206577A1 (en) * | 2018-04-25 | 2019-10-31 | Knorr-Bremse Systeme für Nutzfahrzeuge GmbH | Method for indicating a pending brake pad change of a motor vehicle brake |
CN110411729A (en) * | 2019-08-07 | 2019-11-05 | 科大讯飞股份有限公司 | Brake block life forecast method and device |
CN110905951A (en) * | 2019-12-10 | 2020-03-24 | 深圳鼎然信息科技有限公司 | Method, device, equipment and medium for dynamically monitoring automobile brake pad abrasion in real time |
CN111862082A (en) * | 2020-07-31 | 2020-10-30 | 成都盛锴科技有限公司 | Train brake pad thickness rechecking method and system thereof |
Non-Patent Citations (2)
Title |
---|
李欣;: "基于支持向量机与最小二乘支持向量机的闸片识别及磨耗趋势预测", 铁道技术监督, no. 10 * |
范志勇;项载毓;谭德强;唐斌;李贞;莫继良;周仲荣;: "CRH380A型高速动车组制动闸片摩擦损伤分析", 摩擦学学报, no. 02 * |
Also Published As
Publication number | Publication date |
---|---|
CN112750103B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017175555A1 (en) | Wear inspection apparatus and wear inspection method | |
FI112972B (en) | Assessment of bearing condition | |
US20190210176A1 (en) | Abnormality-detecting device and method for tool of machine tool | |
EP2863282B1 (en) | System and method for detecting anomaly associated with driving a vehicle | |
EP2767228B1 (en) | Device and method for improving identification accuracy of fetal heart rate deceleration | |
WO2017159701A1 (en) | Track state evaluation method, device, and program | |
CN107448257A (en) | The method that engine motor oil quality deterioration judges | |
CN112393906B (en) | Method for diagnosing, classifying and evaluating health of weak signal fault of bogie bearing of metro vehicle | |
CN112590465B (en) | Tire wear measuring device and tire wear measuring method using the same | |
JP2023078964A (en) | State monitoring device and state monitoring method | |
CN116871978A (en) | Drilling tool state monitoring method based on multi-sensor fusion | |
CN114220189B (en) | Monitoring method, prediction system, electronic equipment and storage medium | |
CN116308300A (en) | Power equipment state monitoring evaluation and command method and system | |
CN112750103A (en) | Train brake pad thickness detection method and system thereof | |
Ghiasi et al. | An unsupervised anomaly detection framework for onboard monitoring of railway track geometrical defects using one-class support vector machine | |
CN114001993A (en) | Bridge safety and health assessment and monitoring system based on scientific and technological intelligence | |
US11493404B2 (en) | Method and system for estimating the wear of a rotating machine including a bearing | |
CN112859741A (en) | Method and system for evaluating operation reliability of sequential action units of machine tool | |
CN114001887B (en) | Bridge damage assessment method based on deflection monitoring | |
CN112228042B (en) | Method for judging working condition similarity of pumping well based on cloud edge cooperative computing | |
CN114705995A (en) | Electric connection state identification method, device, equipment and storage medium | |
CN113343919A (en) | Method and device for detecting continuous equidistant rubbing damage of steel rail and computer equipment | |
Nugraha et al. | Detection of railroad anomalies using machine learning approach | |
CN117193058B (en) | Annular shuttle remote control system and method based on wireless communication control | |
CN117367845B (en) | Health diagnosis method for army equipment maintenance equipment |
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 |