CN114674562B - Rail transit tapered roller bearing service life prediction method considering service life monitoring conditions - Google Patents
Rail transit tapered roller bearing service life prediction method considering service life monitoring conditions Download PDFInfo
- Publication number
- CN114674562B CN114674562B CN202210304750.2A CN202210304750A CN114674562B CN 114674562 B CN114674562 B CN 114674562B CN 202210304750 A CN202210304750 A CN 202210304750A CN 114674562 B CN114674562 B CN 114674562B
- Authority
- CN
- China
- Prior art keywords
- bearing
- service life
- temperature
- life monitoring
- condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to a method for predicting the service life of a track traffic tapered roller bearing by considering service life monitoring conditions, which comprises the following steps of configuring position identification information and detection data for each service life monitoring position of the bearing; circularly determining whether a life monitoring condition is triggered, if so, further judging which of two preset tracking identification mechanisms belongs to; if the condition is judged to belong to the triggering condition of the temperature detection tracking identification mechanism, continuously tracking the bearing service life monitoring position with the abnormal state based on the temperature detection tracking identification strategy until the abnormal state is removed; if the judgment belongs to the triggering condition of the vibration signal detection tracking identification mechanism, bearing service life prediction analysis is carried out based on the vibration signal detection tracking identification strategy, corresponding position identification information is used as a fault tracking identification, and an identification result is synchronously output. The invention can accurately position and track the bearing state of each type of specific position and carry out effective fault prediction, identification and evaluation.
Description
Technical Field
The invention relates to the technical field of locomotive bearing measurement, in particular to a method for predicting the service life of a track traffic tapered roller bearing by considering service life monitoring conditions.
Background
The bearing is used as a general component in a large amount in various mechanical equipment, and the quality of the running state of the bearing directly influences the safe and effective operation of the whole component and even the whole set of equipment. That is, a component such as a bearing is prone to wear, fatigue, overload, corrosion, etc. during long-term operation, and further causes local damage to the component, thereby affecting the safety and stability of the operation of the mechanical equipment.
Therefore, it is necessary to accurately grasp the operation state of the device to monitor the life condition of the device in real time.
At present, bearing running state monitoring technology is more important than bearing fault diagnosis in an experimental stage, namely damage forms, positions and the like of a target bearing are analyzed and judged through historical data, for example, vibration signals of a mechanical device contain rich information of equipment health conditions, so that the bearing fault monitoring technology can be used for bearing fault identification, analysis and processing technology and the like, although the requirement of running state analysis of a rolling bearing can be met to a certain extent, most of the bearing fault monitoring technology belongs to a bearing fault diagnosis and analysis method with hysteresis, subsequent analysis is often carried out after an accident or a fault occurs to determine the damage forms and positions of the bearing, dynamic tracking analysis of the bearing health state is difficult to be effectively carried out, and potential fault risks are timely discovered and early warned.
Disclosure of Invention
Based on the method, in order to solve the defects in the prior art, the method for predicting the service life of the track traffic tapered roller bearing considering the service life monitoring condition is particularly provided.
In order to achieve the purpose, the corresponding technical scheme is as follows:
a method for predicting the service life of a track traffic tapered roller bearing by considering service life monitoring conditions is characterized by comprising the following steps:
s1, determining positions of the whole vehicle, which need to be subjected to bearing life monitoring, and configuring position identification information for each bearing life monitoring position;
s2, configuring a temperature detection module and a vibration signal detection module at each bearing service life monitoring position to acquire temperature detection data and vibration signal detection data of corresponding positions in real time in each sampling period;
s3, circularly determining whether a service life monitoring condition is triggered or not when a certain time interval is reached, and if so, further judging which of two preset tracking identification mechanisms belongs to, wherein the tracking identification mechanisms comprise a temperature detection tracking identification mechanism and a vibration signal detection tracking identification mechanism; the triggering rule of the life monitoring condition comprises: (1) The temperature detection module corresponding to a certain bearing service life monitoring position determines that the bearing at the position has abnormal high temperature under the condition of high temperature abnormality, namely that the bearing is in a continuous running state; (2) Under the bearing service life prediction condition, namely under the condition that the bearing is in a continuous operation state, a vibration signal detection module corresponding to a certain bearing service life monitoring position determines that the bearing enters an initial damage stage;
s4, if the condition is judged to belong to the triggering condition of the temperature detection tracking identification mechanism, continuously tracking the monitoring position of the service life of the bearing with the abnormal state based on the temperature detection tracking identification strategy until the abnormal state is removed;
and S5, if the judgment result belongs to the triggering condition of the vibration signal detection tracking and identification mechanism, performing bearing service life prediction analysis on the bearing service life monitoring position corresponding to the triggering rule based on the vibration signal detection tracking and identification strategy, and synchronously outputting an identification result by taking the corresponding position identification information as a fault tracking identifier.
Optionally, in one embodiment, the temperature detection module includes a plurality of temperature sensors, each temperature sensor acquires a corresponding temperature value according to a preset sampling rule and stores the temperature value locally, the sampling rule is used to control two or more temperature sensors to simultaneously trigger and acquire temperature data in the sampling period, and control any two or more temperature sensors that are not triggered in the current sampling period to trigger and acquire temperature data in the next sampling period, and continuously monitor the temperature of the bearing based on the polling rule.
Optionally, in one embodiment, in each sampling period, a temperature step response fitting is performed on the collected multiple temperature values to obtain a corresponding temperature step response prediction curve of the monitored surface.
Optionally, in one embodiment, the S4 continuously tracking the bearing life monitoring position where the abnormal state exists until the abnormal state is resolved based on the temperature detection tracking identification strategy includes: s41, if the temperature value acquired in the current sampling period exceeds a preset early warning temperature value, calling a temperature step response prediction curve to predict the temperature corresponding to the next sampling period, and if the obtained prediction result exceeds the limit, recording position identification information corresponding to the bearing service life monitoring position and carrying out fault alarm; and S42, forming a temperature abnormity tracking identifier based on the position identification information, and continuously tracking and monitoring the temperature value corresponding to the service life monitoring position until the obtained temperature value is recovered to a temperature value smaller than the early warning temperature value.
Optionally, in one embodiment, the step of determining that the bearing enters the initial damage stage in the bearing life prediction condition is: determining the bearing model of a bearing corresponding to the bearing service life monitoring position; based on the bearing model, searching an initial damage database matched with the bearing model to call a corresponding initial damage data fitting curve; and determining that the bearing corresponding to the bearing service life monitoring position enters an initial damage stage based on the similarity between the obtained initial damage data fitting curve and the vibration signal obtained in the current sampling period and meeting the set requirement.
Optionally, in one embodiment, the initial damage data fitting curve in the initial damage database acquires vibration signals corresponding to a certain type of bearing through an acoustic emission sensor or an acceleration sensor based on resonance to form a corresponding sample set, and performs fault feature extraction analysis on the sample set to obtain a data fitting curve.
The embodiment of the invention has the following beneficial effects:
after the technology is adopted, the bearing loss condition can be detected in real time and the service life prediction result can be synchronously obtained in the actual running process of the bearing, namely, the bearing state of specific positions of each type can be accurately positioned and tracked, and effective fault prediction identification and evaluation can be carried out.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a flow diagram of an implementation technique in one embodiment;
FIG. 2 is a schematic diagram illustrating vibration signature characteristics of an initial damage phase in a bearing life monitoring phase according to an embodiment;
FIG. 3 is a graphical representation of vibration signature during a failure development phase of a bearing life monitoring phase in one embodiment.
In the figure: e represents energy, HZ represents signal frequency, A represents a 3-time conversion frequency band, B represents a fault characteristic frequency band, C represents a resonance frequency band, and D represents an ultrasonic frequency band.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present application. The first and second elements are both elements, but they are not the same element.
In this embodiment, a method for predicting the service life of a track traffic tapered roller bearing is specifically proposed, as shown in fig. 1, the method includes the following steps:
s1, determining positions of the whole vehicle, which need to be subjected to bearing life monitoring, and configuring position identification information for each bearing life monitoring position;
s2, configuring a temperature detection module and a vibration signal detection module at each bearing service life monitoring position to acquire temperature detection data and vibration signal detection data of corresponding positions in real time in each sampling period;
s3, circularly determining whether a service life monitoring condition is triggered or not when a certain time interval is reached, and if yes, further judging which mechanism belongs to two preset tracking identification mechanisms, wherein the tracking identification mechanisms comprise a temperature detection tracking identification mechanism and a vibration signal detection tracking identification mechanism; the triggering rule of the life monitoring condition comprises: (1) The temperature detection module corresponding to a certain bearing service life monitoring position determines that the bearing at the position has abnormal high temperature under the condition of high temperature abnormality, namely that the bearing is in a continuous operation state; (2) Under the bearing service life prediction condition, namely under the condition that the bearing is in a continuous operation state, a vibration signal detection module corresponding to a certain bearing service life monitoring position determines that the bearing enters an initial damage stage;
s4, if the condition is judged to belong to the triggering condition of the temperature detection tracking identification mechanism, continuously tracking the bearing service life monitoring position with the abnormal state based on the temperature detection tracking identification strategy until the abnormal state is removed;
and S5, if the judgment result belongs to the triggering condition of the vibration signal detection tracking and identification mechanism, performing bearing service life prediction analysis on the bearing service life monitoring position corresponding to the triggering rule based on the vibration signal detection tracking and identification strategy, and synchronously outputting an identification result by taking the corresponding position identification information as a fault tracking identifier.
Based on the steps, the bearing loss condition can be detected in real time and the service life prediction result can be synchronously obtained in the actual running process of the bearing, namely, the bearing state of specific positions of each type can be accurately positioned and tracked, and effective fault prediction identification and evaluation can be carried out.
In some specific embodiments, in S1, according to the actual bearing life early warning monitoring requirement, all positions where bearing life monitoring is required are determined, and data is assumedFor N, while providing position-identifying information for each bearing life-monitoring position to give corresponding coded information, e.g. setting the code, IS, in the following order 1 、IS 2 、IS 3 ·····IS N 。
In some specific embodiments, in S2, the temperature detection module includes a plurality of temperature sensors disposed at the same detection position, the temperature sensors are infrared temperature sensors (which can reflect the temperature value of the object according to the energy of the received infrared ray), and the infrared temperature sensors can accurately monitor the surface temperature of the object without contacting the surface of the monitored object. The vibration signal detection module includes, but is not limited to, any one or two combined applications of an acoustic emission sensor or a resonance-based acceleration sensor.
In some more specific embodiments, the temperature detection module includes a plurality of temperature sensors, each temperature sensor collects a corresponding temperature value according to a preset sampling rule and stores the temperature value locally, the sampling rule is used for controlling more than two temperature sensors to simultaneously trigger and collect temperature data in the sampling period, controlling any more than two temperature sensors which are not triggered in the current sampling period to trigger and collect temperature data in the next sampling period, and continuously monitoring the temperature of the bearing based on the polling rule.
In some more specific embodiments, a temperature step response fit is performed on the plurality of temperature values collected during each sampling period to obtain a predicted temperature step response curve for the corresponding monitored surface. The temperature step response curve can reflect the temperature change condition of the temperature monitoring point in advance, so that the temperature change condition of the temperature monitoring point can be reasonably predicted and can be used for temperature early warning analysis. The sampling period is set according to actual sampling requirements, and can be preferably set to 1s or 2s.
The reason that the temperature of the bearing is continuously monitored based on the temperature detection tracking identification strategy in combination with the detection data of the temperature detection module is that the temperature of the bearing slowly rises along with the operation of the bearing at the starting stage of the operation of the whole vehicle and reaches a stable state after 1-2 hours, and the normal temperature of each type of bearing is different due to the heat capacity, the heat dissipation capacity, the rotating speed and the load of the machine. In fact, even if the mounting structure parameters of the bearing are reasonable and the lubricating effect is appropriate, the temperature of the bearing rises suddenly in the operation process, namely, abnormal high temperature occurs, at the moment, high-temperature early warning is needed, the operation is stopped if necessary, and then automatic warning or stopping is realized when the temperature exceeds a specified value so as to prevent shaft burning accidents. Generally, the long-term operation of the bearing at the temperature exceeding 125 ℃ can reduce the actual service life of the bearing, so that a certain strategy for early warning of the temperature of the bearing is necessary.
In some more specific embodiments, the specific process of fitting the temperature step response to the collected plurality of temperature values includes, but is not limited to: the step response parameters are obtained and a parametric curve is formed for subsequent prediction based on the following fitting formula.
Y＝a+bX+cX 2 +dX 3 +eX 4 +fX 5 +gX 6 +h+..+zX m
Wherein, Y represents corresponding m temperature values, and m is the number of the temperature values, then X is [1,2,3 … m +1];
a, b … h, etc. are the values of the parameters of the step response fitting equation, for example, if X = [1,2,3,4,5,6,7,8,9]The collected temperature value is Y = [35, 36, 38, 40, 50, 46, 30, 28, 40 = [35, 36, 38, 40, 50, 46 ]]Corresponding formula is Y = a + bX + cX 2 +dX 3 +eX 4 +fX 5 +gX 6 +hX 7 +iX 8 Then a =475.000968593151, b = -1129.53243347086, c = -1122.91530859959 are obtained by simultaneous calculation,
d＝-575.891236667028，e＝169.09377194945，f＝-29.4167730060083，g＝2.99063724250036，h＝-0.163988858030867，i＝0.00374505950066338。
in some specific embodiments, in S3, when a certain time interval is reached, cyclically determining whether to trigger a life monitoring condition, and if so, further determining which of two preset tracking identification mechanisms belongs to, where the tracking identification mechanisms include a temperature detection tracking identification mechanism and a vibration signal detection tracking identification mechanism; the triggering rule of the life monitoring condition comprises the following steps: (1) The temperature detection module corresponding to a certain bearing service life monitoring position determines that the bearing at the position has abnormal high temperature under the condition of high temperature abnormality, namely that the bearing is in a continuous operation state; (2) Under the bearing service life prediction condition, namely under the condition that the bearing is in a continuous operation state, a vibration signal detection module corresponding to a certain bearing service life monitoring position determines that the bearing enters an initial damage stage; since the bearing forms micro-cracks or dislocation of crystal lattices on the secondary surface at the beginning of bearing failure, and the surface of the bearing has less cracks or micro-peeling, a relatively obvious impact signal cannot be formed in the low-frequency section of the vibration signal, and the fault characteristics of the bearing are mainly reflected in the ultrasonic frequency section (shown as the measured signal peak value or the energy value is larger and exceeds the limit) in the stage, as shown in fig. 2; preferably, the step of determining that the bearing enters the initial damage stage in the bearing life prediction condition is as follows: determining the bearing model of the bearing corresponding to the bearing service life monitoring position; based on the bearing model, searching an initial damage database matched with the bearing model to call a corresponding initial damage data fitting curve; and if the similarity between the obtained initial damage data fitting curve and the obtained vibration signal in the current sampling period meets the set requirement, determining that the bearing corresponding to the bearing service life monitoring position enters an initial damage stage. Preferably, the initial damage data fitting curve in the initial damage database acquires vibration signals corresponding to a certain type of bearing through an acoustic emission sensor or an acceleration sensor based on resonance to form a corresponding sample set, and the sample set is subjected to fault feature extraction analysis to obtain a data fitting curve.
In some specific embodiments, in S4, continuously tracking the bearing life monitoring position where the abnormal state exists until the abnormal state is released based on the temperature detection tracking identification strategy includes: s41, if the collected temperature value in the current sampling period exceeds a preset early warning temperature value (such as 120 degrees), calling a temperature step response prediction curve to predict the temperature corresponding to the next sampling period, and if the obtained prediction result exceeds the limit (such as 125 degrees)), recording position identification information corresponding to the service life monitoring position of the bearing and carrying out fault warning, for example, carrying out linkage early warning by combining an audible and visual alarm of the whole vehicle; and S42, forming a temperature abnormity tracking identifier based on the position identification information, and continuously tracking and monitoring the temperature value corresponding to the service life monitoring position in a plurality of sampling periods until the obtained temperature value is recovered to a temperature value smaller than the early warning temperature value or the personnel in the vehicle carries out fault emergency treatment on the fault bearing. In some more specific embodiments, the position information of the bearing with abnormal temperature can be displayed in an early warning way through a driver display screen, so that a person in the vehicle can quickly locate, search and replace the failed bearing.
In some specific embodiments, in S5, based on the vibration signal detection tracking identification strategy, performing bearing life prediction analysis on the bearing at the bearing life monitoring position corresponding to the trigger rule, and using the corresponding position identification information as the fault tracking identifier, and the step of synchronously outputting the identification result includes: after the bearing on a certain bearing service life monitoring position is determined to be in an initial damage stage, a fault tracking identifier is formed on the basis of a position identification number corresponding to the bearing service life monitoring position, a corresponding fault tracking process is generated so as to continuously track and analyze a vibration signal acquired on the bearing service life monitoring position in a subsequent sampling period and obtain a corresponding tracking analysis prediction result.
In some more specific embodiments, microscopic deterioration of the bearing at this stage during the bearing failure development begins to propagate from the sub-surface to the surface and creates more damage points, such as cracks or micro-spalling, at the contact surface of the bearing. When the surface of the bearing element is in contact with the damaged points, impact pulses with a certain frequency are formed, namely, fault characteristic frequency extraction determination (frequency doubling characteristic parameters and side frequency characteristic parameters) is carried out on the vibration signals. The tracking analysis process comprises: firstly, extracting fault characteristics of an acquired vibration signal to determine whether the frequency characteristics of the extracted vibration signal accord with the fault characteristics of a bearing failure development stage, if so, calling a bearing failure development stage data fitting curve, and if so, determining that the bearing corresponding to the bearing service life monitoring position enters a bearing failure development stage if the similarity between the obtained bearing failure development stage data fitting curve (based on the model of the bearing, searching an initial damage database matched with the model of the bearing to call a corresponding bearing failure development stage data fitting curve) and the vibration signal obtained in the current sampling period meets the set requirement; and finally, predicting the invalid time of the bearing based on a data fitting curve of the final stage of the bearing failure. Preferably, the bearing failure development stage data fitting curve/initial bearing failure final stage data fitting curve is obtained by collecting vibration signals corresponding to a certain type of bearing through an acoustic emission sensor or an acceleration sensor based on resonance to form a corresponding sample set, and performing fault feature extraction and analysis on the sample set to obtain a data fitting curve. And the fault characteristics of the bearing at the stage can be determined by extracting the power spectrum of the vibration signal from the data fitting curve at the bearing failure development stage.
In some more specific embodiments, in S5, the method further includes synchronously acquiring and sorting external operating environment parameters in each sampling period, where the external operating environment parameters include an operating environment list corresponding to each driving road section of a certain type of bearing on an operating line, and the operating environment list is used to represent a bearing rotation speed, an external driving environment temperature, an external driving environment humidity, and driving time information corresponding to each driving road section; in some more specific embodiments, the operating environment list is associated with the bearing model number so as to facilitate subsequent analysis and processing of the bearing temperature variation along with the operating environment parameter variation.
Because vibration signal analysis can cause certain influence to the prediction result because of external factors such as environmental noise, the method for detecting the bearing life state of the bearing at the bearing life monitoring position at each bearing failure stage based on the image signal detection strategy is also designed.
In some more specific embodiments, in S5, monitoring the bearing life state parameters of the bearings at the bearing life monitoring positions of the bearing failure stages in each driving section parking stage of the vehicle body through an image signal detection strategy:
the method specifically comprises the following steps:
the state parameter s of the life of the bearing,
wherein, I corresponds to a three-dimensional array [ a, b,3] of real-time images of the bearing at the bearing life monitoring position]Where a denotes the length of the image, b denotes the width of the image, n denotes the number of blocks into which the image is cut, e.g. n =15,
extracting characteristics of a certain image block t by using a residual network trained by a perception loss function, namely acquiring a training pair using the image block t and the service life of a bearing by using the residual network trained by the perception loss function, establishing a corresponding relation between a residual network training picture of the perception loss function and the service life of the bearing by using the loss function, wherein W is a linear regression matrix, the function omega represents weight, f represents extracting image characteristics by using a convolution network, namely extracting a three-dimensional array of a real-time image of the bearing at a corresponding bearing service life monitoring position into [ a b ] through the convolution network]And fun (×) represents the extraction features of the convolutional network trained using the cross entropy loss function.
Specifically, an input image I is set, I is represented as a three-dimensional array [ a, b,3]]If I is divided into n blocks, for each image block t, f is used to extract the image features, i.e. the three-dimensional array [ a, b,3] of the real-time image of the bearing at the corresponding bearing life monitoring position]Decimated by the convolutional network to [ a x b]Is given (i.e. such that the three-dimensional array [ a, b,3]]The convolutional layers, pooling layers and fully-connected layers fed to the convolutional network-FractalNet finally output a one-dimensional array [ a b [ ]]) (ii) a Then use
Extracting features to use the residual network pairs [ a x b ] trained by the perceptual loss function]One-dimensional array of (a) extract features (its corresponding volume)Product network is ResNeXt) to form the corresponding relation between the residual network training picture and the bearing life, so that the residual network pair [ a x b ] of the perception loss function training]The one-dimensional array extraction features are bearing life values obtained corresponding to the blocks t, the bearing life values of the blocks t need to be correlated with the bearing life values of the whole picture I after the bearing life values of the blocks t are obtained, the correlation process is that a linear regression matrix W is needed and minimum is obtained, and meanwhile, a function represented by fum (#) is utilized
The method for extracting features by using the cross entropy loss function through the convolution network specifically refers to the method for extracting features of a three-dimensional array [ a, b,3] by using the convolution network (inclusion V4) trained by using the cross entropy loss function, and the extracted features
The extracted characteristic is a bearing life value obtained corresponding to the real-time picture I, and the predicted bearing life s is obtained by multiplying the minimum predicted bearing life obtained by using the network trained by the perceptual loss and the predicted bearing life obtained by using the network trained by the cross entropy loss function and dividing the minimum predicted bearing life by the maximum predicted bearing life obtained by using the network trained by the perceptual loss.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (4)
1. The method for predicting the service life of the track traffic tapered roller bearing by considering the service life monitoring condition is characterized by comprising the following steps
S1, determining positions of the whole vehicle, which need to be subjected to bearing life monitoring, and configuring position identification information for each bearing life monitoring position;
s2, configuring a temperature detection module and a vibration signal detection module at each bearing service life monitoring position to acquire temperature detection data and vibration signal detection data of corresponding positions in real time in each sampling period;
s3, circularly determining whether a service life monitoring condition is triggered or not when a certain time interval is reached, and if yes, further judging which mechanism belongs to two preset tracking identification mechanisms, wherein the tracking identification mechanisms comprise a temperature detection tracking identification mechanism and a vibration signal detection tracking identification mechanism;
s4, if the condition is judged to belong to the triggering condition of the temperature detection tracking identification mechanism, continuously tracking the bearing service life monitoring position with the abnormal state based on the temperature detection tracking identification strategy until the abnormal state is removed;
s5, if the judgment belongs to the triggering condition of the vibration signal detection tracking recognition mechanism, bearing life prediction analysis is carried out on the bearing life monitoring position corresponding to the triggering rule based on the vibration signal detection tracking recognition strategy, the corresponding position recognition information is used as a fault tracking identifier, and a recognition result is synchronously output, wherein in the S3, the triggering rule of the life monitoring condition comprises the following steps: (1) The temperature detection module corresponding to a certain bearing service life monitoring position determines that the bearing at the position has abnormal high temperature under the condition of high temperature abnormality, namely that the bearing is in a continuous operation state; (2) Under the bearing service life prediction condition, namely under the condition that the bearing is in a continuous operation state, a vibration signal detection module corresponding to a certain bearing service life monitoring position determines that the bearing enters an initial damage stage; the temperature detection module comprises a plurality of temperature sensors, each temperature sensor acquires a corresponding temperature value according to a preset sampling rule and stores the temperature value locally, the sampling rule is used for controlling more than two temperature sensors to trigger and acquire temperature data in the sampling period at the same time, controlling more than two temperature sensors which are not triggered in the current sampling period to trigger and acquire temperature data in the next sampling period, and continuously monitoring the temperature of the bearing based on the polling rule; in each sampling period, carrying out temperature step response fitting on a plurality of collected temperature values to obtain a corresponding temperature step response prediction curve of the monitored surface;
the step S4 of continuously tracking the bearing service life monitoring position with the abnormal state based on the temperature detection tracking identification strategy until the abnormal state is relieved comprises the following steps: s41, if the temperature value acquired in the current sampling period exceeds a preset early warning temperature value, calling a temperature step response prediction curve to predict the temperature corresponding to the next sampling period, and if the obtained prediction result exceeds the limit, recording position identification information corresponding to the bearing service life monitoring position and carrying out fault alarm; and S42, forming a temperature abnormity tracking identifier based on the position identification information, and continuously tracking and monitoring the temperature value corresponding to the service life monitoring position until the obtained temperature value is recovered to a temperature value smaller than the early warning temperature value.
2. The method for predicting the service life of the tapered roller bearing in the rail transit with the service life monitoring condition taken into consideration as claimed in claim 1, wherein the step of determining that the bearing enters the initial damage stage is as follows: determining the bearing model of the bearing corresponding to the bearing service life monitoring position; based on the bearing model, searching an initial damage database matched with the bearing model to call a corresponding initial damage data fitting curve; and determining that the bearing corresponding to the bearing service life monitoring position enters an initial damage stage based on the similarity between the obtained initial damage data fitting curve and the vibration signal obtained in the current sampling period and meeting the set requirement.
3. The method for predicting the life of a tapered roller bearing for rail transit in consideration of the life monitoring condition according to claim 2,
and acquiring a vibration signal corresponding to a bearing of a certain model by an acoustic emission sensor or an acceleration sensor based on resonance to form a corresponding sample set through an initial damage data fitting curve in the initial damage database, and extracting and analyzing fault characteristics of the sample set to obtain a data fitting curve.
4. The method for predicting the life of a tapered roller bearing in rail transit considering the life monitoring condition as claimed in claim 1, wherein in the S3, the triggering rule of the life monitoring condition further comprises: (3) And monitoring the bearing service life state parameters of the bearings at the bearing service life monitoring positions of the bearing failure stages by an image signal detection algorithm at the parking stage of each driving section of the vehicle body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210304750.2A CN114674562B (en) | 2022-03-22 | 2022-03-22 | Rail transit tapered roller bearing service life prediction method considering service life monitoring conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210304750.2A CN114674562B (en) | 2022-03-22 | 2022-03-22 | Rail transit tapered roller bearing service life prediction method considering service life monitoring conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114674562A CN114674562A (en) | 2022-06-28 |
| CN114674562B true CN114674562B (en) | 2022-10-25 |
Family
ID=82076760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210304750.2A Active CN114674562B (en) | 2022-03-22 | 2022-03-22 | Rail transit tapered roller bearing service life prediction method considering service life monitoring conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114674562B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117332233B (en) * | 2023-10-07 | 2024-05-31 | 江苏丰昌机电科技有限公司 | Intelligent maintenance system for motor |
| CN117147608B (en) * | 2023-10-27 | 2024-01-26 | 万向钱潮股份公司 | Bearing surface peeling failure detection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110044624A (en) * | 2019-04-24 | 2019-07-23 | 华东交通大学 | A kind of box bearing fault detection method and system |
| CN111734885A (en) * | 2020-06-30 | 2020-10-02 | 全球能源互联网研究院有限公司 | Converter valve on-line monitoring and evaluating method and system |
| WO2021117752A1 (en) * | 2019-12-11 | 2021-06-17 | Ntn株式会社 | Rolling bearing state monitoring method and rolling bearing state monitoring device |
| CN113740063A (en) * | 2021-09-26 | 2021-12-03 | 重庆大学 | Train bearing monitoring and early warning method and system |
-
2022
- 2022-03-22 CN CN202210304750.2A patent/CN114674562B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110044624A (en) * | 2019-04-24 | 2019-07-23 | 华东交通大学 | A kind of box bearing fault detection method and system |
| WO2021117752A1 (en) * | 2019-12-11 | 2021-06-17 | Ntn株式会社 | Rolling bearing state monitoring method and rolling bearing state monitoring device |
| CN111734885A (en) * | 2020-06-30 | 2020-10-02 | 全球能源互联网研究院有限公司 | Converter valve on-line monitoring and evaluating method and system |
| CN113740063A (en) * | 2021-09-26 | 2021-12-03 | 重庆大学 | Train bearing monitoring and early warning method and system |
Non-Patent Citations (1)
| Title |
|---|
| 高速动车组轴承温度监测与逻辑控制方法研究;师玲萍;《电子设计工程》;20200705(第13期);85-89 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114674562A (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114674562B (en) | Rail transit tapered roller bearing service life prediction method considering service life monitoring conditions | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN106586796B (en) | A kind of escalator condition monitoring system and method | |
| EP2399104B1 (en) | Method and apparatus for monitoring and analyzing vibrations in rotary machines | |
| US5710723A (en) | Method and apparatus for performing pre-emptive maintenance on operating equipment | |
| US20150160101A1 (en) | Method and System for Testing Operational Integrity of a Drilling Rig | |
| MX2014014577A (en) | Methods apparatuses for defect diagnosis in a mechanical system. | |
| WO2007137132A2 (en) | Probabilstic stress wave analysis system and method | |
| CN102441579B (en) | The on-line monitoring method of hot tandem rolling mill running status | |
| US10677765B2 (en) | Structural health monitoring of cyclically loaded structures | |
| Medjaher et al. | Feature extraction and evaluation for health assessment and failure prognostics | |
| CN112907901B (en) | Tunnel monitoring entity risk early warning assessment model | |
| US20020105429A1 (en) | Bearing condition monitoring method and apparatus | |
| KR20230127337A (en) | Method and device for identifying abnormalities in mechanical devices or mechanical parts | |
| CN112199410A (en) | Bridge health monitoring system based on Internet of things | |
| Suman et al. | Early detection of mechanical malfunctions in vehicles using sound signal processing | |
| CN115014617B (en) | Cable-stayed bridge cable force synchronous monitoring method based on ground radar | |
| CN114813124B (en) | Bearing fault monitoring method and device | |
| Nowakowski et al. | Diagnostics of the drive shaft bearing based on vibrations in the high-frequency range as a part of the vehicle's self-diagnostic system | |
| CN111579001A (en) | Fault detection method and device for robot | |
| CN109115271B (en) | Digit control machine tool remote monitoring system | |
| Satishkumar et al. | Vibration based health assessment of bearings using random forest classifier | |
| Klausen et al. | Novel threshold calculations for remaining useful lifetime estimation of rolling element bearings | |
| CN113483815A (en) | Mechanical fault monitoring system based on industrial big data | |
| CN107562041A (en) | Goat fault early warning method, device, equipment and computer-readable recording medium |
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 |