CN118190469A - Railway train bearing piece state analysis and prediction system - Google Patents
Railway train bearing piece state analysis and prediction system Download PDFInfo
- Publication number
- CN118190469A CN118190469A CN202410612944.8A CN202410612944A CN118190469A CN 118190469 A CN118190469 A CN 118190469A CN 202410612944 A CN202410612944 A CN 202410612944A CN 118190469 A CN118190469 A CN 118190469A
- Authority
- CN
- China
- Prior art keywords
- bearing
- state
- outer ring
- wheel
- detection frame
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 122
- 238000005461 lubrication Methods 0.000 claims abstract description 79
- 238000005299 abrasion Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 239000000428 dust Substances 0.000 claims description 10
- 230000003068 static effect Effects 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 3
- 238000012360 testing method Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a railway train bearing part state analysis and prediction system, which belongs to the technical field of bearing part state detection and comprises an initial state information acquisition module, a lubrication state detection module, a structural wear state detection module and a result output module. According to the invention, the initial sound information is used as an initial characteristic for representing the lubrication state of the wheel, and the distance average value D Average of is used as a judgment basis for the abrasion state of the wheel bearing structure, so that the lubrication state of the wheel bearing can be more conveniently analyzed and predicted on line, and the abrasion state of the wheel bearing structure can be accurately analyzed and predicted on line; the abrasion of the inner wall of the bearing outer ring and the abrasion of the inner wall of the bearing inner ring are characterized by adopting the standard deviation SD, so that the structural abrasion state grade information of the current wheel bearing is more conveniently and accurately determined, and more accurate available time length information is facilitated to be acquired, and the accurate analysis and prediction work of the available time length of the railway train wheel bearing is realized.
Description
Technical Field
The invention relates to the technical field of bearing part state detection, in particular to a railway train bearing part state analysis and prediction system.
Background
Bearing parts are an important part in modern mechanical equipment. Its main function is to support the mechanical rotator, reduce the friction coefficient in the course of its movement and ensure its rotation accuracy. The bearing piece works on the principle that rolling friction is used for replacing sliding friction, and the bearing piece is a mechanical base piece which is formed by two ferrules (an inner ring and an outer ring), a group of rolling bodies and a retainer and has strong universality and high standardization and serialization degree. Because of the different operating conditions of various machines, various requirements are placed on the rolling bearings (bearing elements) in terms of load capacity, structure and service performance. For this reason, various structures are required for the rolling bearing. But the most basic structure is composed of an inner ring, an outer ring, rolling bodies and a cage.
Wheel bearings of a railway train are key components in a railway vehicle wheel pair, and the main functions of the wheel bearings are to support a wheel shaft and reduce friction, so that the train can run stably and efficiently on a track. During the running of the train, the wheel bearings receive various forces such as gravity, inertial force, and bending force from the train. The wheel and the track generate friction force, so that the rolling bodies in the bearing are driven to rotate, and further, the relative rotation between the wheel shaft and the bearing is realized. Because the contact area of the rolling bodies is small and the number of contact points is small, the bearing can generate higher contact stress during working. The design and quality of the bearings therefore have a crucial effect on the safety and transport efficiency of the train.
When the wheel bearing is in a good lubrication state, low buzzing or buzzing sounds are generated, the frequency and amplitude of the sound are in a certain range, and when the wheel bearing structure is not excessively worn, the wheel rotating shaft is basically in a coaxial state with the inner ring and the outer ring of the bearing. How to accurately analyze and predict the available time length of a railway train wheel bearing is a problem to be solved, and therefore, a railway train bearing piece state analysis and prediction system is provided.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: how to accurately analyze and predict the available time length of the railway train wheel bearing provides a railway train bearing piece state analysis and prediction system.
The invention solves the technical problems through the following technical scheme that the invention comprises an initial state information acquisition module, a lubrication state detection module, a structural wear state detection module and a result output module;
The initial state information acquisition module is used for acquiring initial state information of the wheel bearing in an initial state;
the lubrication state detection module is used for acquiring the lubrication state grade information of the current wheel bearing;
The structural wear state detection module is used for acquiring structural wear state grade information of the current wheel bearing;
The result output module is used for predicting the time length which can be used for the current wheel bearing according to the lubrication state grade information and the structural wear state grade information of the current wheel bearing and combining a preset available time length database, and outputting a prediction result.
Further, the initial state information acquisition module comprises an initial operation sound information acquisition unit and a wear state judgment basis acquisition unit; the initial operation sound information acquisition unit is used for acquiring initial sound information of operation of the wheel bearing in an initial state within a set time period, wherein the initial sound information comprises a maximum frequency f max, a minimum frequency f min, a maximum amplitude a max and a minimum amplitude a min; the abrasion state judgment basis acquisition unit is used for shooting an image of the wheel bearing in an initial state when the wheel bearing is stationary from the front through the camera, acquiring an average value of distances from a center point Z of a wheel rotating shaft detection frame in the image to points on an outer contour line of the outer ring of the bearing, and recording the average value as a distance average value D Average of ; the initial state information comprises initial sound information and a distance average value D Average of ; the image comprises a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft.
Furthermore, the camera is arranged on the train body, the optical axis of the camera is coaxial with the wheel rotating shaft and is horizontally arranged, the camera is used for shooting images of the wheel bearings from the front, and the camera does not rotate along with the wheels when the wheels rotate and is static relative to the train body.
Further, the specific processing procedure of the abrasion state judgment basis acquisition unit is as follows:
S11: shooting an image of the wheel bearing in an initial state when the wheel bearing is static through a camera from the front, and marking the image as img1;
S12: detecting img1 by using the trained target detection model, detecting and identifying a wheel rotating shaft in the img1, acquiring coordinates of an upper left corner and a lower right corner of a wheel rotating shaft detection frame in an image, and further calculating the coordinates of a central point Z of the wheel rotating shaft detection frame according to the coordinates of the upper left corner and the lower right corner of the wheel rotating shaft detection frame;
S13: detecting img1 again by using the trained target detection model, detecting and identifying the outer ring of the bearing, acquiring coordinates of an upper left corner point and a lower right corner point of a bearing outer ring detection frame in an image, and cutting the bearing outer ring detection frame from img1 according to the coordinates of the upper left corner point and the lower right corner point of the bearing outer ring detection frame to obtain a bearing outer ring detection frame image;
S14: carrying out contour detection on the bearing outer ring detection frame image by utilizing a contour detection function in OpenCV to obtain coordinates of each point on the outer contour line of the bearing outer ring, wherein points on the outer contour line of the bearing outer ring are marked as C m, and m is a positive integer and represents the mth point;
S15: the average value D Average of of the distances between the center point Z of the wheel rotating shaft detection frame and each point on the outer contour line of the bearing outer ring is calculated, and the calculation formula is as follows:
L Average of =（D1+D2+……+Dm-1+Dm）/m
D 1～Dm represents the distance between the 1 st to m points on the outer contour line of the bearing outer ring and the center point Z of the wheel rotating shaft detection frame, and is calculated by using Euclidean distance formula according to the coordinate of the center point Z of the wheel rotating shaft detection frame and the coordinate of each point on the outer contour line of the bearing outer ring.
Further, the lubrication state detection module comprises an on-line operation sound information acquisition unit and a lubrication state grade acquisition unit; the online operation sound information acquisition unit is used for acquiring operation sound information when the current wheel axle is operated, and the operation sound information comprises a maximum frequency F max, a minimum frequency F min, a maximum amplitude A max and a minimum amplitude A min; the lubrication state grade obtaining unit is used for calculating the absolute value of the difference between the maximum frequency F max and the maximum frequency F max, the absolute value of the difference between the minimum frequency F min and the minimum frequency F min, the absolute value of the difference between the maximum amplitude a max and the maximum amplitude A max and the absolute value of the difference between the minimum amplitude a min and the minimum amplitude A min, and the absolute values are respectively recorded as P c1、Pc2、Vc1、Vc2, and the lubrication state grade information of the current wheel bearing is obtained according to P c1、Pc2、Vc1、Vc2.
Further, the specific processing procedure of the lubrication state grade obtaining unit is as follows:
s21: calculating the absolute value of the difference between the maximum frequency F max and the maximum frequency F max, the absolute value of the difference between the minimum frequency F min and the minimum frequency F min, the absolute value of the difference between the maximum amplitude a max and the maximum amplitude A max and the absolute value of the difference between the minimum amplitude a min and the minimum amplitude A min, and respectively recording as P c1、Pc2、Vc1、Vc2;
S22: summing P c1 and P c2 to obtain a sum denoted as P total, and summing V c1 and V c2 to obtain a sum denoted as V total;
S23: the current lubrication state score R is calculated as follows:
R=w1*Ptotal+w2*Vtotal
Wherein w 1 is the weight ratio of P total in the lubrication state score R, and w 2 is the weight ratio of V total in the lubrication state score R;
s24: and searching and comparing in a lubrication state grading-lubrication state grade database according to the lubrication state grading R, and obtaining lubrication state grade information corresponding to the current lubrication state grading R.
Further, the structural wear state detection module comprises a distance value calculation unit and a structural wear state grade acquisition unit; the distance value calculation unit is used for shooting an image of the current wheel bearing from the front through the camera in the abrasion state judgment basis acquisition unit, acquiring the distance from the center point Z' of the wheel rotating shaft detection frame in the image to each point on the outer contour line of the bearing outer ring, and recording the distance as a distance value d m; the structural wear state grade acquisition is used for acquiring structural wear state grade information of the current wheel bearing according to the distance value D m and a pre-acquired distance average value D Average of ; the image comprises a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft.
Further, the specific processing procedure of the distance value calculating unit is as follows:
S31: shooting an image of a current wheel bearing from the front through a camera, and recording the image as img2;
s32: detecting img2 by using the target detection model in the step S12, detecting and identifying a wheel rotating shaft in the img2, acquiring coordinates of an upper left corner and a lower right corner of a wheel rotating shaft detection frame in an image, and further calculating the coordinates of a center point Z' of the wheel rotating shaft detection frame according to the coordinates of the upper left corner and the lower right corner of the wheel rotating shaft detection frame;
S33: detecting img2 again by using the target detection model in the step S12, detecting and identifying the outer ring of the bearing, obtaining coordinates of an upper left corner point and a lower right corner point of a detection frame of the outer ring of the bearing in the image, and cutting the detection frame of the outer ring of the bearing from the img2 according to the coordinates of the upper left corner point and the lower right corner point of the detection frame of the outer ring of the bearing, so as to obtain an image of the detection frame of the outer ring of the bearing;
S34: carrying out contour detection on the bearing outer ring detection frame image by utilizing a contour detection function in OpenCV to obtain coordinates of each point on the outer contour line of the bearing outer ring, wherein points on the outer contour line of the bearing outer ring are marked as C m, and m is a positive integer and represents the mth point;
s35: according to the coordinate of the center point Z 'of the wheel rotating shaft detection frame and the coordinate of each point on the outer contour line of the bearing outer ring, the distance between the center point Z' of the wheel rotating shaft detection frame and each point on the outer contour line of the bearing outer ring is calculated by adopting the Euclidean distance formula, and the distance is recorded as a distance value d m.
Further, the specific processing procedure of the structural wear state grade obtaining unit is as follows:
s41: calculating the absolute value of the difference between the distance value D m and the distance average value D Average of of each point, and recording as G m;
S42: calculating a standard deviation SD of an absolute value G m of a difference value between a distance value D m and a distance average value D Average of of each point;
S43: and searching and comparing in a standard deviation-structural wear state grade database according to the standard deviation SD to obtain structural wear state grade information corresponding to the current standard deviation SD.
Further, the specific processing procedure of the result output module is as follows:
S51: searching and comparing in a lubrication state grade-available time length database according to the lubrication state grade information of the current wheel bearing to obtain a first available time length T 1 corresponding to the lubrication state grade information of the current wheel bearing;
S52: searching and comparing in a structural wear state grade-available time length database according to the structural wear state grade information of the current wheel bearing to obtain a second available time length T 2 corresponding to the structural wear state grade information of the current wheel bearing;
S53: and comparing the length of the first available time length T 1 with the length of the second available time length T 2, and selecting shorter time length data in the two as the final available time length to output, namely obtaining the time length which can be used by the current wheel bearing.
Compared with the prior art, the invention has the following advantages: according to the railway train bearing piece state analysis and prediction system, initial sound information is adopted as initial characteristics for representing the wheel lubrication state, and a distance average value D Average of is adopted as a judging basis of the wheel bearing structure abrasion state, so that the wheel bearing lubrication state can be more conveniently analyzed and predicted on line, and the wheel bearing structure abrasion state can be accurately analyzed and predicted on line; the abrasion of the inner wall of the bearing outer ring and the abrasion of the inner wall of the bearing inner ring are characterized by adopting the standard deviation SD, so that the structural abrasion state grade information of the current wheel bearing is more conveniently and accurately determined, and more accurate available time length information is facilitated to be acquired, and the accurate analysis and prediction work of the available time length of the railway train wheel bearing is realized.
Drawings
FIG. 1 is a schematic block diagram of a railway train bearing member state analysis and prediction system in an embodiment of the invention;
FIG. 2 is a schematic view (front side) of a wheel bearing mounting location in an embodiment of the present invention;
FIG. 3 is a schematic image of an initial state wheel bearing at rest in an embodiment of the present invention;
In the figure: 1. a wheel spindle; 2. a bearing inner ring; 3. a bearing outer ring; 4. a dust cover; 5. and (3) a wheel.
Detailed Description
The following describes in detail the examples of the present invention, which are implemented on the premise of the technical solution of the present invention, and detailed embodiments and specific operation procedures are given, but the scope of protection of the present invention is not limited to the following examples.
As shown in fig. 1, this embodiment provides a technical solution: a railway train bearing piece state analysis and prediction system specifically comprises: the device comprises an initial state information acquisition module, a lubrication state detection module, a structural wear state detection module and a result output module;
In this embodiment, the initial state information acquisition module is configured to acquire initial state information of the wheel bearing in an initial state;
Further, the initial state information acquisition module comprises an initial operation sound information acquisition unit and a wear state judgment basis acquisition unit; the initial operation sound information acquisition unit is used for acquiring initial sound information of operation of the wheel bearing in an initial state within a set time period, wherein the initial sound information comprises a maximum frequency f max, a minimum frequency f min, a maximum amplitude a max and a minimum amplitude a min; the abrasion state judgment basis acquisition unit is used for shooting an image of the wheel bearing in an initial state from the front through a camera, acquiring an average value of distances (Euclidean distance) from a center point Z of a wheel rotating shaft detection frame in the image to points on an outer contour line of the outer ring of the bearing, and recording the average value as a distance average value D Average of ; the initial state information comprises initial sound information and a distance average value D Average of ; the image comprises a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft.
According to the invention, the initial sound information is used as an initial characteristic for representing the wheel lubrication state, and the distance average value D Average of is used as a judgment basis for the wheel bearing structure abrasion state, so that the wheel bearing lubrication state can be more conveniently analyzed and predicted on line, and the wheel bearing structure abrasion state can be accurately analyzed and predicted on line during operation.
In the present embodiment, the wheel bearing in the initial state is a new bearing that is not used. As shown in fig. 2, the wheel 5 is rotatably connected with the wheel rotating shaft 1at the lower end of the train body through a wheel bearing, wherein the wheel bearing comprises a bearing outer ring 3, a dust cover 4 (made of rubber materials) and a bearing inner ring 2; a retainer and rolling bodies are arranged between the bearing inner ring 2 and the bearing outer ring 3, and the rolling bodies are arranged on the retainer and covered by a dust cover 4.
Further, the camera is installed on the train body, the optical axis of the camera is coaxial with the wheel rotating shaft and is horizontally arranged, the camera is used for shooting images of the wheel bearings from the front, and the camera does not rotate along with the wheels when the wheels rotate and is static relative to the train body.
Further, the specific processing procedure of the abrasion state judgment basis acquisition unit is as follows:
s11: taking an image of the wheel bearing at rest in an initial state from the front through a camera (of the high-speed camera), noted as img1 (see fig. 3);
S12: detecting img1 by using the trained target detection model, detecting and identifying a wheel rotating shaft in the img1, acquiring coordinates of an upper left corner and a lower right corner of a wheel rotating shaft detection frame in an image, and further calculating the coordinates of a central point Z of the wheel rotating shaft detection frame according to the coordinates of the upper left corner and the lower right corner of the wheel rotating shaft detection frame;
S13: detecting img1 again by using the trained target detection model, detecting and identifying the outer ring of the bearing, acquiring coordinates of an upper left corner point and a lower right corner point of a bearing outer ring detection frame in an image, and cutting the bearing outer ring detection frame from img1 according to the coordinates of the upper left corner point and the lower right corner point of the bearing outer ring detection frame to obtain a bearing outer ring detection frame image;
S14: carrying out contour detection on the bearing outer ring detection frame image by utilizing a contour detection function in OpenCV to obtain coordinates of each point on the outer contour line of the bearing outer ring, wherein points on the outer contour line of the bearing outer ring are marked as C m, and m is a positive integer and represents the mth point;
S15: the average value D Average of of the distances between the center point Z of the wheel rotating shaft detection frame and each point on the outer contour line of the bearing outer ring is calculated, and the calculation formula is as follows:
L Average of =（D1+D2+……+Dm-1+Dm）/m
D 1～Dm represents the distance between the 1 st to m points on the outer contour line of the bearing outer ring and the center point Z of the wheel rotating shaft detection frame, and is calculated by using Euclidean distance formula according to the coordinate of the center point Z of the wheel rotating shaft detection frame and the coordinate of each point on the outer contour line of the bearing outer ring.
In the steps S12 and S13, the target detection model is obtained based on Yolo V network training, during training, firstly, a plurality of images including a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft are collected through an industrial camera as a data set, the images in the data set are divided into a training set and a testing set, then, the images in the training set are manually marked, the images in the training set are sent into a Yolo V network for training, after the training is completed, network parameters are saved, a trained network model is obtained, finally, the performance index of the trained network model is detected through the images in the testing set, and after the performance index meets a set value, the network model is saved, so that the target detection model is obtained. Yolo V3 the network also classifies the object after it is identified.
In this embodiment, the lubrication state detection module is configured to obtain lubrication state level information of a current wheel bearing;
Further, the lubrication state detection module comprises an online running sound information acquisition unit and a lubrication state grade acquisition unit; the online operation sound information acquisition unit is used for acquiring operation sound information when the current wheel axle is operated, and the operation sound information comprises a maximum frequency F max, a minimum frequency F min, a maximum amplitude A max and a minimum amplitude A min; the lubrication state grade obtaining unit is used for calculating the absolute value of the difference between the maximum frequency F max and the maximum frequency F max, the absolute value of the difference between the minimum frequency F min and the minimum frequency F min, the absolute value of the difference between the maximum amplitude a max and the maximum amplitude A max and the absolute value of the difference between the minimum amplitude a min and the minimum amplitude A min, and the absolute values are respectively recorded as P c1、Pc2、Vc1、Vc2, and the lubrication state grade information of the current wheel bearing is obtained according to P c1、Pc2、Vc1、Vc2.
Further, the specific processing procedure of the lubrication state grade obtaining unit is as follows:
s21: calculating the absolute value of the difference between the maximum frequency F max and the maximum frequency F max, the absolute value of the difference between the minimum frequency F min and the minimum frequency F min, the absolute value of the difference between the maximum amplitude a max and the maximum amplitude A max and the absolute value of the difference between the minimum amplitude a min and the minimum amplitude A min, and respectively recording as P c1、Pc2、Vc1、Vc2;
S22: summing P c1 and P c2 to obtain a sum denoted as P total, and summing V c1 and V c2 to obtain a sum denoted as V total;
S23: the current lubrication state score R is calculated as follows:
R=w1*Ptotal+w2*Vtotal
Wherein w 1 is the weight ratio of P total in the lubrication state score R, w 2 is the weight ratio of V total in the lubrication state score R, and may be adaptively set according to different wheel bearings, in this embodiment, w 1=0.75,w2 =0.25;
s24: and searching and comparing in a lubrication state grading-lubrication state grade database according to the lubrication state grading R, and obtaining lubrication state grade information corresponding to the current lubrication state grading R.
As a further step S24, the lubrication state score-lubrication state level database is stored with a correspondence relationship between the lubrication state score R and the lubrication state level, which is established in advance.
As a further step S24, the lubrication state is classified into 1 to n stages, and the lubrication state is worse from 1 to n stages.
As a further step, the two operation sound information acquisition units acquire corresponding sound information by means of sound collectors mounted at the wheel bearings and using acoustic analyzers.
In this embodiment, the structural wear state detection module is configured to obtain structural wear state level information of a current wheel bearing;
Further, the structural wear state detection module comprises a distance value calculation unit and a structural wear state grade acquisition unit; the distance value calculation unit is used for shooting an image of the current wheel bearing from the front through a camera (namely, a camera in the abrasion state judgment basis acquisition unit), acquiring the distance from the center point Z' of the wheel rotating shaft detection frame in the image to each point on the outer contour line of the bearing outer ring, and recording the distance as a distance value d m; the structural wear state grade acquisition is used for acquiring structural wear state grade information of the current wheel bearing according to the distance value D m and a pre-acquired distance average value D Average of ; the image comprises a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft.
Further, the specific processing procedure of the distance value calculating unit is as follows:
S31: shooting an image of a current wheel bearing from the front through a camera, and recording the image as img2;
s32: detecting img2 by using the target detection model in the step S12, detecting and identifying a wheel rotating shaft in the img2, acquiring coordinates of an upper left corner and a lower right corner of a wheel rotating shaft detection frame in an image, and further calculating the coordinates of a center point Z' of the wheel rotating shaft detection frame according to the coordinates of the upper left corner and the lower right corner of the wheel rotating shaft detection frame;
S33: detecting img2 again by using the target detection model in the step S12, detecting and identifying the outer ring of the bearing, obtaining coordinates of an upper left corner point and a lower right corner point of a detection frame of the outer ring of the bearing in the image, and cutting the detection frame of the outer ring of the bearing from the img2 according to the coordinates of the upper left corner point and the lower right corner point of the detection frame of the outer ring of the bearing, so as to obtain an image of the detection frame of the outer ring of the bearing;
S34: carrying out contour detection on the bearing outer ring detection frame image by utilizing a contour detection function in OpenCV to obtain coordinates of each point on the outer contour line of the bearing outer ring, wherein points on the outer contour line of the bearing outer ring are marked as C m, and m is a positive integer and represents the mth point;
s35: according to the coordinate of the center point Z 'of the wheel rotating shaft detection frame and the coordinate of each point on the outer contour line of the bearing outer ring, the distance between the center point Z' of the wheel rotating shaft detection frame and each point on the outer contour line of the bearing outer ring is calculated by adopting the Euclidean distance formula, and the distance is recorded as a distance value d m.
When any one or two of the inner wall of the outer ring and the inner wall of the inner ring of the bearing wear, the positions of the center point Z' of the wheel rotating shaft detection frame and the center point Z of the wheel rotating shaft detection frame deviate in the image.
Further, the specific processing procedure of the structural wear state grade acquisition unit is as follows:
s41: calculating the absolute value of the difference between the distance value D m and the distance average value D Average of of each point, and recording as G m;
S42: calculating a standard deviation SD of an absolute value G m of a difference value between a distance value D m and a distance average value D Average of of each point;
S43: and searching and comparing in a standard deviation-structural wear state grade database according to the standard deviation SD to obtain structural wear state grade information corresponding to the current standard deviation SD.
In the embodiment, the abrasion of the inner wall of the bearing outer ring and the abrasion of the inner wall of the bearing inner ring are innovatively represented by adopting the standard deviation SD, so that the structural abrasion state grade information of the current wheel bearing is more conveniently and accurately determined, and more accurate available time length information is facilitated to be acquired.
Further, in the step S43, the correspondence relationship between the standard deviation SD and the structural wear state level is stored in a standard deviation-structural wear state level database, which is established in advance.
As a further step S44, the structural wear state is classified into 1 to k, and from 1 to k, the structural wear state becomes worse, that is, the wear becomes worse.
The result output module is used for predicting the time length which can be used for the current wheel bearing according to the lubrication state grade information and the structural wear state grade information of the current wheel bearing and combining a preset available time length database, and outputting a prediction result;
further, the specific processing procedure of the result output module is as follows:
S51: searching and comparing in a lubrication state grade-available time length database according to the lubrication state grade information of the current wheel bearing to obtain a first available time length T 1 corresponding to the lubrication state grade information of the current wheel bearing;
S52: searching and comparing in a structural wear state grade-available time length database according to the structural wear state grade information of the current wheel bearing to obtain a second available time length T 2 corresponding to the structural wear state grade information of the current wheel bearing;
S53: and comparing the length of the first available time length T 1 with the length of the second available time length T 2, and selecting shorter time length data in the two as the final available time length to output, namely obtaining the time length which can be used by the current wheel bearing. In this embodiment, the second available time period T 2 is selected as the final available time period output according to the comparison result.
Further, in the step S51, the correspondence between the lubrication state level and the first available time period T 1 is stored in the lubrication state level-available time period database, which is pre-established based on a large amount of sample data.
Further, in the step S52, the correspondence between the structural wear state level and the second available time period T 2 is stored in the structural wear state level-available time period database, which is previously established based on a large amount of sample data.
The lubrication state detection module and the structural wear state detection module synchronously detect, and the detection interval is set to be 1s.
In summary, in the railway train bearing member state analysis and prediction system of the embodiment, initial sound information is adopted as initial characteristics for representing the wheel lubrication state, and a distance average value D Average of is adopted as a judging basis of the wheel bearing structure abrasion state, so that the wheel bearing lubrication state can be more conveniently analyzed and predicted on line, and the wheel bearing structure abrasion state can be accurately analyzed and predicted on line; the abrasion of the inner wall of the bearing outer ring and the abrasion of the inner wall of the bearing inner ring are characterized by adopting the standard deviation SD, so that the structural abrasion state grade information of the current wheel bearing is more conveniently and accurately determined, and more accurate available time length information is facilitated to be acquired, and the accurate analysis and prediction work of the available time length of the railway train wheel bearing is realized.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1.A railway train bearing condition analysis and prediction system, comprising: the device comprises an initial state information acquisition module, a lubrication state detection module, a structural wear state detection module and a result output module;
The initial state information acquisition module is used for acquiring initial state information of the wheel bearing in an initial state;
the lubrication state detection module is used for acquiring the lubrication state grade information of the current wheel bearing;
The structural wear state detection module is used for acquiring structural wear state grade information of the current wheel bearing;
The result output module is used for predicting the time length which can be used for the current wheel bearing according to the lubrication state grade information and the structural wear state grade information of the current wheel bearing and combining a preset available time length database, and outputting a prediction result.
2. The railway train bearing piece state analysis and prediction system according to claim 1, wherein the initial state information acquisition module comprises an initial operation sound information acquisition unit and a wear state judgment basis acquisition unit; the initial operation sound information acquisition unit is used for acquiring initial sound information of operation of the wheel bearing in an initial state within a set time period, wherein the initial sound information comprises a maximum frequency f max, a minimum frequency f min, a maximum amplitude a max and a minimum amplitude a min; the abrasion state judgment basis acquisition unit is used for shooting an image of the wheel bearing in an initial state when the wheel bearing is stationary from the front through the camera, acquiring an average value of distances from a center point Z of a wheel rotating shaft detection frame in the image to points on an outer contour line of the outer ring of the bearing, and recording the average value as a distance average value D Average of ; the initial state information comprises initial sound information and a distance average value D Average of ; the image comprises a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft.
3. The system according to claim 2, wherein the camera is mounted on the train body with its optical axis coaxial with the wheel axis of rotation and horizontally arranged for capturing images of the wheel bearings from the front, the camera not rotating with the wheels when the wheels rotate and being stationary relative to the train body.
4. The railway train bearing piece state analysis and prediction system according to claim 2, wherein the specific processing procedure of the abrasion state judgment basis acquisition unit is as follows:
S11: shooting an image of the wheel bearing in an initial state when the wheel bearing is static through a camera from the front, and marking the image as img1;
S12: detecting img1 by using the trained target detection model, detecting and identifying a wheel rotating shaft in the img1, acquiring coordinates of an upper left corner and a lower right corner of a wheel rotating shaft detection frame in an image, and further calculating the coordinates of a central point Z of the wheel rotating shaft detection frame according to the coordinates of the upper left corner and the lower right corner of the wheel rotating shaft detection frame;
S13: detecting img1 again by using the trained target detection model, detecting and identifying the outer ring of the bearing, acquiring coordinates of an upper left corner point and a lower right corner point of a bearing outer ring detection frame in an image, and cutting the bearing outer ring detection frame from img1 according to the coordinates of the upper left corner point and the lower right corner point of the bearing outer ring detection frame to obtain a bearing outer ring detection frame image;
S14: carrying out contour detection on the bearing outer ring detection frame image by utilizing a contour detection function in OpenCV to obtain coordinates of each point on the outer contour line of the bearing outer ring, wherein points on the outer contour line of the bearing outer ring are marked as C m, and m is a positive integer and represents the mth point;
S15: the average value D Average of of the distances between the center point Z of the wheel rotating shaft detection frame and each point on the outer contour line of the bearing outer ring is calculated, and the calculation formula is as follows:
L Average of =（D1+D2+……+Dm-1+Dm）/m
D 1～Dm represents the distance between the 1 st to m points on the outer contour line of the bearing outer ring and the center point Z of the wheel rotating shaft detection frame, and is calculated by using Euclidean distance formula according to the coordinate of the center point Z of the wheel rotating shaft detection frame and the coordinate of each point on the outer contour line of the bearing outer ring.
5. The railway train bearing piece state analysis and prediction system according to claim 4, wherein the lubrication state detection module comprises an on-line running sound information acquisition unit and a lubrication state grade acquisition unit; the online operation sound information acquisition unit is used for acquiring operation sound information when the current wheel axle is operated, and the operation sound information comprises a maximum frequency F max, a minimum frequency F min, a maximum amplitude A max and a minimum amplitude A min; the lubrication state grade obtaining unit is used for calculating the absolute value of the difference between the maximum frequency F max and the maximum frequency F max, the absolute value of the difference between the minimum frequency F min and the minimum frequency F min, the absolute value of the difference between the maximum amplitude a max and the maximum amplitude A max and the absolute value of the difference between the minimum amplitude a min and the minimum amplitude A min, and the absolute values are respectively recorded as P c1、Pc2、Vc1、Vc2, and the lubrication state grade information of the current wheel bearing is obtained according to P c1、Pc2、Vc1、Vc2.
6. The railway train bearing component state analysis and prediction system according to claim 5, wherein the specific processing procedure of the lubrication state grade obtaining unit is as follows:
s21: calculating the absolute value of the difference between the maximum frequency F max and the maximum frequency F max, the absolute value of the difference between the minimum frequency F min and the minimum frequency F min, the absolute value of the difference between the maximum amplitude a max and the maximum amplitude A max and the absolute value of the difference between the minimum amplitude a min and the minimum amplitude A min, and respectively recording as P c1、Pc2、Vc1、Vc2;
S22: summing P c1 and P c2 to obtain a sum denoted as P total, and summing V c1 and V c2 to obtain a sum denoted as V total;
S23: the current lubrication state score R is calculated as follows:
R=w1*Ptotal+w2*Vtotal
Wherein w 1 is the weight ratio of P total in the lubrication state score R, and w 2 is the weight ratio of V total in the lubrication state score R;
s24: and searching and comparing in a lubrication state grading-lubrication state grade database according to the lubrication state grading R, and obtaining lubrication state grade information corresponding to the current lubrication state grading R.
7. The railway train bearing piece state analysis and prediction system according to claim 2 or 6, wherein the structural wear state detection module comprises a distance value calculation unit and a structural wear state grade acquisition unit; the distance value calculation unit is used for shooting an image of the current wheel bearing from the front through the camera in the abrasion state judgment basis acquisition unit, acquiring the distance from the center point Z' of the wheel rotating shaft detection frame in the image to each point on the outer contour line of the bearing outer ring, and recording the distance as a distance value d m; the structural wear state grade acquisition is used for acquiring structural wear state grade information of the current wheel bearing according to the distance value D m and a pre-acquired distance average value D Average of ; the image comprises a complete bearing outer ring, a dust cover, a bearing inner ring and a wheel rotating shaft.
8. The railway train bearing piece state analysis and prediction system according to claim 7, wherein the specific processing procedure of the distance value calculation unit is as follows:
S31: shooting an image of a current wheel bearing from the front through a camera, and recording the image as img2;
s32: detecting img2 by using the target detection model in the step S12, detecting and identifying a wheel rotating shaft in the img2, acquiring coordinates of an upper left corner and a lower right corner of a wheel rotating shaft detection frame in an image, and further calculating the coordinates of a center point Z' of the wheel rotating shaft detection frame according to the coordinates of the upper left corner and the lower right corner of the wheel rotating shaft detection frame;
S33: detecting img2 again by using the target detection model in the step S12, detecting and identifying the outer ring of the bearing, obtaining coordinates of an upper left corner point and a lower right corner point of a detection frame of the outer ring of the bearing in the image, and cutting the detection frame of the outer ring of the bearing from the img2 according to the coordinates of the upper left corner point and the lower right corner point of the detection frame of the outer ring of the bearing, so as to obtain an image of the detection frame of the outer ring of the bearing;
S34: carrying out contour detection on the bearing outer ring detection frame image by utilizing a contour detection function in OpenCV to obtain coordinates of each point on the outer contour line of the bearing outer ring, wherein points on the outer contour line of the bearing outer ring are marked as C m, and m is a positive integer and represents the mth point;
s35: according to the coordinate of the center point Z 'of the wheel rotating shaft detection frame and the coordinate of each point on the outer contour line of the bearing outer ring, the distance between the center point Z' of the wheel rotating shaft detection frame and each point on the outer contour line of the bearing outer ring is calculated by adopting the Euclidean distance formula, and the distance is recorded as a distance value d m.
9. The railway train bearing piece state analysis and prediction system according to claim 8, wherein the specific processing procedure of the structural wear state grade acquisition unit is as follows:
s41: calculating the absolute value of the difference between the distance value D m and the distance average value D Average of of each point, and recording as G m;
S42: calculating a standard deviation SD of an absolute value G m of a difference value between a distance value D m and a distance average value D Average of of each point;
S43: and searching and comparing in a standard deviation-structural wear state grade database according to the standard deviation SD to obtain structural wear state grade information corresponding to the current standard deviation SD.
10. The railway train bearing piece state analysis and prediction system according to claim 1, wherein the specific processing procedure of the result output module is as follows:
S51: searching and comparing in a lubrication state grade-available time length database according to the lubrication state grade information of the current wheel bearing to obtain a first available time length T 1 corresponding to the lubrication state grade information of the current wheel bearing;
S52: searching and comparing in a structural wear state grade-available time length database according to the structural wear state grade information of the current wheel bearing to obtain a second available time length T 2 corresponding to the structural wear state grade information of the current wheel bearing;
S53: and comparing the length of the first available time length T 1 with the length of the second available time length T 2, and selecting shorter time length data in the two as the final available time length to output, namely obtaining the time length which can be used by the current wheel bearing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410612944.8A CN118190469A (en) | 2024-05-17 | 2024-05-17 | Railway train bearing piece state analysis and prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410612944.8A CN118190469A (en) | 2024-05-17 | 2024-05-17 | Railway train bearing piece state analysis and prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118190469A true CN118190469A (en) | 2024-06-14 |
Family
ID=91402067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410612944.8A Pending CN118190469A (en) | 2024-05-17 | 2024-05-17 | Railway train bearing piece state analysis and prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118190469A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107110703A (en) * | 2014-12-10 | 2017-08-29 | 日本精工株式会社 | Apparatus for diagnosis of abnormality, bearing, rotating device, industrial machine and vehicle |
| CN114216681A (en) * | 2021-11-22 | 2022-03-22 | 中国国家铁路集团有限公司 | Method and device for determining health state of rolling bearing of motor train unit |
| CN114663433A (en) * | 2022-05-25 | 2022-06-24 | 山东科技大学 | Method and device for detecting running state of roller cage shoe, computer equipment and medium |
| CN115575126A (en) * | 2022-09-29 | 2023-01-06 | 华电电力科学研究院有限公司 | Information fusion-based rolling bearing lubricating grease filling management method |
| CN116008287A (en) * | 2023-02-03 | 2023-04-25 | 嘉善迪克精密机械有限公司 | Online monitoring and management method and system for self-lubricating bearing wear |
| CN116642696A (en) * | 2023-04-14 | 2023-08-25 | 石家庄铁道大学 | Railway bearing health monitoring method, device, system, terminal and storage medium |
-
2024
- 2024-05-17 CN CN202410612944.8A patent/CN118190469A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107110703A (en) * | 2014-12-10 | 2017-08-29 | 日本精工株式会社 | Apparatus for diagnosis of abnormality, bearing, rotating device, industrial machine and vehicle |
| CN114216681A (en) * | 2021-11-22 | 2022-03-22 | 中国国家铁路集团有限公司 | Method and device for determining health state of rolling bearing of motor train unit |
| CN114663433A (en) * | 2022-05-25 | 2022-06-24 | 山东科技大学 | Method and device for detecting running state of roller cage shoe, computer equipment and medium |
| CN115575126A (en) * | 2022-09-29 | 2023-01-06 | 华电电力科学研究院有限公司 | Information fusion-based rolling bearing lubricating grease filling management method |
| CN116008287A (en) * | 2023-02-03 | 2023-04-25 | 嘉善迪克精密机械有限公司 | Online monitoring and management method and system for self-lubricating bearing wear |
| CN116642696A (en) * | 2023-04-14 | 2023-08-25 | 石家庄铁道大学 | Railway bearing health monitoring method, device, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1548419B1 (en) | Method and device for monitoring status of mechanical equipment and abnormality diagnosing device | |
| CN111947928B (en) | Multi-source information fusion bearing fault prediction system and method | |
| JP4394893B2 (en) | Fault diagnosis system | |
| CN105527104B (en) | A kind of bearing running abnormal sound detecting system | |
| CN101010578A (en) | State detection device, state detection method, state detection program, and information recording medium, state display device, state display method, state display program, and information recording | |
| CN1223735A (en) | Condition analyzer | |
| CN110789566B (en) | Track defect monitoring method and monitoring equipment based on axle box acceleration signal | |
| CN113569451B (en) | Train axle box bearing life prediction and fault maintenance system based on digital twin | |
| CN112098090B (en) | Railway wagon wheel pair bearing intelligent detection system | |
| KR20110131411A (en) | Hub bearing test method | |
| CN114996654A (en) | Road flatness detection method and device, electronic equipment and medium | |
| CN112488995A (en) | Intelligent injury judging method and system for automatic train maintenance | |
| CN118190469A (en) | Railway train bearing piece state analysis and prediction system | |
| CN206496901U (en) | A kind of box bearing fault detection system | |
| CN114386467A (en) | System and method for monitoring rail vehicle chassis fault abnormal sound based on acoustic characteristics | |
| CN106644483A (en) | Bearing fault detection method and system for gear box | |
| CN112278012A (en) | EMUs wheel pair management system | |
| CN115035087A (en) | Novel railway line image detection method and system | |
| CN113222907B (en) | Detection robot based on curved rail | |
| CN113044710A (en) | Intelligent settlement system and method for truck-mounted crane | |
| CN118170125B (en) | Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method | |
| CN111637857A (en) | Highway engineering quality detection car convenient to use | |
| KR20070062849A (en) | Activeness maintenance system for vehicle using telematics | |
| CN117168776B (en) | Heavy trundle running stability detection system and application method thereof | |
| CN114906692A (en) | Vertical elevator safety monitoring and early warning information platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |