CN112572522A - Early warning method and device for axle temperature fault of vehicle bearing - Google Patents
Early warning method and device for axle temperature fault of vehicle bearing Download PDFInfo
- Publication number
- CN112572522A CN112572522A CN202011248732.4A CN202011248732A CN112572522A CN 112572522 A CN112572522 A CN 112572522A CN 202011248732 A CN202011248732 A CN 202011248732A CN 112572522 A CN112572522 A CN 112572522A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- bearing
- temperature
- model
- regression
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/04—Detectors for indicating the overheating of axle bearings and the like, e.g. associated with the brake system for applying the brakes in case of a fault
- B61K9/06—Detectors for indicating the overheating of axle bearings and the like, e.g. associated with the brake system for applying the brakes in case of a fault by detecting or indicating heat radiation from overheated axles
Abstract
The application discloses a method and a device for early warning of shaft temperature faults of a vehicle bearing. The method comprises the following steps: acquiring working data of the vehicle in the current operation, wherein the working data is data related to the temperature of a bearing of the vehicle; analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process; and determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperature of the vehicle in different time periods in the subsequent operation process. Through the method and the device, the problem of poor early warning effect on the axle temperature fault of the vehicle bearing in the related technology is solved.
Description
Technical Field
The application relates to the technical field of train safety, in particular to a method and a device for early warning of axle temperature faults of a vehicle bearing.
Background
With the formal application and the gradual improvement of a PHM system of a motor train unit, the requirement on the running safety of a train is higher and higher, and a bearing is a key part for ensuring the safe running of a high-speed train, so that the service environment is severe, the faults such as abrasion, peeling, cracks and the like are easily caused, and the running state of the bearing is required to be monitored. At present, a high-speed train mainly monitors the state of the bearing temperature and gives an alarm based on a set threshold value, so that serious safety accidents caused by hot shafts and burning shafts can be effectively avoided, and once the alarm occurs, vehicle operation accidents are caused, so that economic loss and adverse social effects are caused. Because the fault has already occurred during the alarm, and it takes time to remove the fault, therefore there are technical problems of high occurrence of train accident and poor safety.
Aiming at the problem that the early warning effect on the axle temperature fault of the vehicle bearing in the related technology is poor, no effective solution is provided at present.
Disclosure of Invention
The application mainly aims to provide a method and a device for early warning of a shaft temperature fault of a vehicle bearing, so as to solve the problem that the early warning effect on the shaft temperature fault of the vehicle bearing in the related technology is poor.
In order to achieve the above object, according to one aspect of the present application, there is provided a method of early warning of a shaft temperature failure of a vehicle bearing. The method comprises the following steps: acquiring working data of a vehicle in the current operation, wherein the working data is data related to the temperature of a bearing of the vehicle; analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process; and determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperatures of the vehicle in different time periods in the subsequent operation process.
Further, before predicting the bearing temperature of the vehicle in different time periods during subsequent operation, the method further comprises: acquiring sample data of the vehicle, wherein the sample data is collected historical working data, and the historical working data at least comprises: a historical bearing temperature of the vehicle detected over a historical period of time, a vehicle speed corresponding to the historical bearing temperature, and an ambient temperature; extracting sample features from the historical working data; training the sample characteristics by adopting at least one regression model to obtain the regression prediction model under the normal running state of the vehicle, wherein the regression model comprises at least one of the following: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
Further, any regression model is selected to fit the sample characteristics, and the regression prediction model characterized by a standard curve is generated.
Further, after obtaining the regression prediction model with the vehicle in a normal running state, the method includes: obtaining a model error of the regression prediction model; based on the model error, a boundary range value for determining that the bearing temperature is within a safe range is determined.
Further, after predicting the bearing temperature of the vehicle for different periods of time during subsequent operation, the method comprises: detecting whether the bearing temperature in different time periods in the subsequent operation process is within the boundary range value; and if the bearing temperature predicted in any time period is detected to exceed the boundary range value, inputting the predicted bearing temperature into an early warning model for analysis.
Further, determining whether the bearing of the vehicle has a fault in a subsequent corresponding time period based on the predicted bearing temperatures of the vehicle in the subsequent operation process in different time periods comprises: analyzing the bearing temperature of the vehicle in different time periods in the subsequent running process by adopting an early warning model; and if the bearing temperature in any time period in the subsequent operation process meets the warning condition determined by the warning model, determining that the bearing of the vehicle has a fault in the time period, and sending warning information.
In order to achieve the above object, according to another aspect of the present application, there is provided an early warning apparatus for a shaft temperature failure of a vehicle bearing. The device includes: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring working data of a vehicle in the current operation process, and the working data is data related to the bearing temperature of the vehicle; the prediction module is used for analyzing the working data by adopting a regression prediction model and predicting the bearing temperature of the vehicle in different time periods in the subsequent operation process; and the fault analysis module is used for determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperature of the vehicle in different time periods in the subsequent operation process.
Further, the apparatus further comprises: a second obtaining module, configured to obtain sample data of the vehicle, where the sample data is collected historical working data, and the historical working data at least includes: historical bearing temperatures of the vehicle detected over a historical period of time, vehicle speeds corresponding to the historical bearing temperatures, and ambient temperatures; the extraction module is used for extracting sample characteristics from the historical working data; the second obtaining module is used for training the sample characteristics by adopting at least one regression model to obtain the regression prediction model of the vehicle in a normal running state, wherein the regression model comprises at least one of the following: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
In order to achieve the above object, according to another aspect of the present application, there is provided a storage medium including a stored program, wherein the program performs the method of any one of the above.
To achieve the above object, according to another aspect of the present application, there is provided a processor for executing a program, wherein the program executes to perform the method of any one of the above.
Through the application, the following steps are adopted: acquiring working data of the vehicle in the current operation, wherein the working data is data related to the temperature of a bearing of the vehicle; analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process; whether the bearing of the vehicle has a fault in a subsequent corresponding time period is determined based on the predicted bearing temperature of the vehicle in the subsequent running process in different time periods, and the problem of poor early warning effect on the axle temperature fault of the vehicle bearing in the related technology is solved. Therefore, the effect of predicting the temperature of the bearing position of the vehicle in advance to determine whether the fault exists or not, the early warning effect on the axle temperature fault is improved, and the running safety of the vehicle is ensured is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
FIG. 1 is a flow chart of a method for early warning of an axle temperature fault of a vehicle bearing provided according to an embodiment of the application;
FIG. 2 is a schematic diagram of an alternative method for early warning of a shaft temperature fault of a vehicle bearing provided in accordance with an embodiment of the present application; and
fig. 3 is a schematic diagram of an early warning device for a shaft temperature fault of a vehicle bearing provided according to an embodiment of the application.
Detailed Description
It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to the embodiment of the application, a method for early warning of the axle temperature fault of the vehicle bearing is provided.
Fig. 1 is a flowchart of a method for warning of an axle temperature fault of a vehicle bearing according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S101, acquiring working data of the vehicle in the current operation, wherein the working data is data related to the temperature of a bearing of the vehicle;
step S102, analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent running process;
and step S103, determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperature of the vehicle in different time periods in the subsequent operation process.
Through the steps S101 to S103, the real-time monitoring of the temperature of the bearing can be realized, the monitoring of a ground platform system is earlier than the alarm on the vehicle through a regression prediction model of the shaft temperature (bearing temperature) which is constructed in advance, and the aim of early warning the shaft temperature on the platform is fulfilled, so that the bearing fault of the vehicle is predicted in advance, and an important early warning means is provided for the vehicle running at high speed.
Optionally, in the method for warning axle temperature fault of a vehicle bearing provided in the embodiment of the present application, before predicting the bearing temperature of the vehicle in different time periods in the subsequent operation process, the method further includes: acquiring sample data of a vehicle, wherein the sample data is collected historical working data, and the historical working data at least comprises the following steps: historical bearing temperatures of the vehicle detected within the historical time period, vehicle speeds corresponding to the historical bearing temperatures, and ambient temperatures; extracting sample features from historical working data; training sample characteristics by adopting at least one regression model, and obtaining a regression prediction model of the vehicle in a normal running state, wherein the regression model comprises at least one of the following models: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
In the above scheme, the result will, for example, include at least: and extracting characteristics from historical bearing temperature of the vehicle detected in the historical time period and historical working data of vehicle speed and environment temperature corresponding to the historical bearing temperature to obtain sample characteristics. And then modeling is carried out, and a model of the train in normal state is obtained by utilizing multiple regression models and selecting an optimal regression model to fit a standard curve. That is, any one regression model is selected to fit the sample characteristics, and a regression prediction model characterized by a standard curve is generated.
The regression model may be as follows:
1. multiple linear regression model
Commonly used regression methods are the ordinary least squares regression (OLS) methods, including simple linear regression, polynomial regression, and multiple linear regression, which predict the quantified dependent variable by a weighted sum of the predicted variables, where the weights are parameters estimated from the data. In this study, the shaft temperature is influenced by a plurality of factors such as speed, the shaft temperature is a dependent variable, and the other influencing factors are independent variables.
Form of the multiple regression fit model:
Y＝b0+b1*X1+b2*X2+...bp*Xp
wherein b0 is the intercept term, b1, b2pIn order to be the regression coefficient, the method,
our goal is to obtain the model parameters (intercept terms and slope) by reducing the difference between the true and predicted values of the response variables. Utensil for cleaning buttockIn a concrete sense, i.e. the sum of the squares of the residuals
And minimum.
2. Support vector machine regression
A Support Vector Machine (SVM) is a good method to realize the idea of minimizing structural risk. Its machine learning strategy is that the structural risk minimization principle should minimize both empirical risk and confidence range in order to minimize the expected risk
The idea of the support vector machine method is as follows:
(1) it is a learning machine that is specific to limited sample situations, what is achieved is that structural risk is minimized: a compromise is sought between the accuracy of the approximation for a given data and the complexity of the approximation function in order to obtain the best generalization ability;
(2) the method finally solves the problem of convex quadratic programming, theoretically, the obtained solution is a global optimal solution, and the problem of local extremum which cannot be avoided in a neural network method is solved;
(3) the method converts the practical problem into a high-dimensional characteristic space through nonlinear transformation, constructs a linear decision function in the high-dimensional space to realize the nonlinear decision function in the original space, skillfully solves the dimension problem, ensures better popularization capability, and has irrelevant algorithm complexity to the dimension of a sample.
At present, the SVM algorithm is applied to aspects such as pattern recognition, regression estimation, probability density function estimation and the like, and the efficiency and the precision of the algorithm are superior to or comparable to those of the traditional learning algorithm.
3. Random forest regression
The model combination + Decision tree related algorithm has two more basic forms, namely random forest and GBDT (gradient Boost Decision Tree), and other more new model combination + Decision tree algorithms are extensions from the two algorithms.
Random forests can be used for almost any kind of predictive problem (including non-linear problems). It is a relatively new machine learning strategy (born in bell laboratories in the 90 s) that can be used in any aspect. It belongs to the general class of ensemble learning in machine learning.
The random forest aggregation is a regression tree, and a decision tree is formed by combining a series of decisions and can be used for classifying observed values of a data set. Learning algorithms of the decision tree include an ID3 algorithm, a C4.5 algorithm and the like.
The random forest trains a series of decision trees respectively, so the training process is parallel. Because a random process is added into the algorithm, each decision tree has a small amount of difference. The predicted variance is reduced by combining the predicted results of each tree, and the performance on the test set is improved.
(1) The method has good performance on a data set, and due to the introduction of two randomness properties, the random forest is not easy to fall into overfitting;
(2) compared with other algorithms, the method has great advantages on the basis of a great number of data sets at present, and due to the introduction of two randomness properties, the random forest has good anti-noise capability;
(3) the method can process data with high dimensionality (much feature), does not need feature selection, and has strong adaptability to a data set: the method can process discrete data and continuous data, and a data set does not need to be normalized;
(4) the training speed is high, and variable importance ranking (two types are increased based on OOB error rate and decreased based on GINI during splitting;
(5) in the training process, the interaction among features can be detected;
(6) the parallelization method is easy to make;
(7) the realization is simpler.
Optionally, in the early warning method for the axle temperature fault of the vehicle bearing provided in the embodiment of the present application, after obtaining the regression prediction model of the vehicle in the normal operation state, the method includes: obtaining a model error of a regression prediction model; based on the model error, a boundary range value for determining that the bearing temperature is within a safe range is determined.
I.e. based on the model error, a boundary range value is determined, within which the actual temperature is considered to be a normal value, otherwise an abnormal value,
optionally, in the method for warning an axle temperature fault of a vehicle bearing provided in the embodiment of the present application, after the bearing temperature of the vehicle in different time periods in the subsequent operation process is predicted, the method includes: detecting whether the temperature of the bearing in different time periods in the subsequent operation process is within a boundary range value; and if the bearing temperature predicted in any time period is detected to exceed the boundary range value, inputting the predicted bearing temperature into an early warning model for analysis.
Namely, substituting real-time data into a regression prediction model to obtain the predicted bearing temperature; judging the predicted bearing temperature based on the boundary range value to obtain whether the current bearing temperature exceeds the boundary range value; and if the result exceeds the preset threshold value, substituting the early warning model for further judgment.
Optionally, in the early warning method for the axle temperature fault of the vehicle bearing provided in the embodiment of the present application, determining whether the bearing of the vehicle has a fault in a subsequent corresponding time period based on the bearing temperature of the vehicle measured in advance in the subsequent operation process in different time periods includes: analyzing the bearing temperature of the vehicle in different time periods in the subsequent running process by adopting an early warning model; and if the bearing temperature in any time period in the subsequent operation process meets the alarm condition determined by the early warning model, determining that the bearing of the vehicle has a fault in the time period, and sending out early warning information.
It should be noted that the early warning information is used for early warning the abnormality of the axle temperature, and the overhaul is intervened in advance, so that the safe operation of the vehicle is ensured.
In summary, the axle temperature fault early warning method for the vehicle bearing in the embodiment of the application is characterized in that a bearing training data set is mostly normal data, an axle temperature early warning model is abstracted into a regression prediction mode in machine learning, and the idea is novel and ingenious; modeling based on training data by utilizing various machine learning algorithms, and selecting an optimal model, wherein the result has higher accuracy and generalization; the machine learning optimization model is combined with the mechanism rule model, the deep fusion of the AI algorithm and the expert experience is realized, the actual operation characteristics of the bearing are better met, and the technical scheme has universality for solving the equipment faults of the motor train unit.
The present solution is described below with reference to some data.
1. Model data preparation
Selecting a learning sample: data from No. 8/10 in 2017 to No. 8/20 in 2017 of AA vehicle models are sampled and selected, the data packet interval is 30 seconds, the number of samples is 428732 cases in total, and a model cross validation training set and a test set are divided according to 0.7 proportion.
Verifying sample data: samples No. 8 and 22 in 2017 of the AA vehicle model are selected, and the number of the samples is 3658. When the early warning is carried out in the vehicle, the shaft temperature is 100 degrees, and the early warning time is 16: 49.
2. Results of the experiment
2.1 regression model analysis
The regression model was evaluated mainly for R2, RMSE (root mean square error). R2 represents the quality of model fitting, and the closer to 1, the better the model fitting; the RMSE (root mean square error) represents the error between the real value and the predicted value, and the smaller the RMSE is, the smaller the difference between the real value and the predicted value is, and the more accurate the prediction effect is.
The results of the three regression models are shown in table 1 below:
TABLE 1
As can be seen from the above table 1, random forest regression should be selected, which has a good effect and is suitable for modeling a large amount of data.
2.2 axle temperature Filter rule validation
After a normal train running axle temperature model is established by random forest regression, the maximum value of the absolute value of the difference between the real value and the model value is a threshold value, so the tolerance boundary of the model is set to be [ 5 degrees ] and [ 5 degrees ]. And after the temperature abnormal point is determined, a fault point needs to be found out from the temperature abnormal point, and the fault filtering model is adopted for realizing. As shown in table 2 below:
TABLE 2
2.3 model conclusion
The filtered anomaly data is shown in table 3 below:
TABLE 3
And (4) conclusion: firstly, obtaining that the difference between an actual value and a normal regression value exceeds a normal boundary through a regression model; and thirdly, obtaining a threshold value of the shaft temperature exceeding and the external temperature through the regular filtering model, and early warning by the mixed model, wherein the control strategy of the on-vehicle early warning is that the shaft temperature is more than 100 degrees, so that the model can realize early warning for 5min in advance relative to the on-vehicle shaft temperature, and a feasible technical scheme is provided for the on-vehicle shaft temperature early warning.
As shown in fig. 2, a regression prediction model is obtained through regression modeling, then it is determined that the abnormality is convenient and fast, an abnormal temperature fault point is identified through a fault filtering model, and then it is determined whether a fault exists, so that the early warning effect on the axle temperature fault is improved, and the operation safety effect of the vehicle is ensured
In summary, according to the early warning method for the axle temperature fault of the vehicle bearing provided by the embodiment of the present application, the working data of the vehicle in the current operation is obtained, wherein the working data is data related to the bearing temperature of the vehicle; analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process; whether the bearing of the vehicle has a fault in a subsequent corresponding time period is determined based on the predicted bearing temperature of the vehicle in different time periods in the subsequent operation process, and the problem of poor early warning effect on the axle temperature fault of the vehicle bearing in the related technology is solved. And the effect of predicting the temperature of the bearing position of the vehicle in advance to determine whether the fault exists or not, so as to improve the early warning effect on the axle temperature fault and ensure the running safety of the vehicle is achieved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
The embodiment of the application also provides an early warning device for the axle temperature fault of the vehicle bearing, and it needs to be explained that the early warning device for the axle temperature fault of the vehicle bearing provided by the embodiment of the application can be used for executing the early warning method for the axle temperature fault of the vehicle bearing provided by the embodiment of the application. The early warning device for the axle temperature fault of the vehicle bearing provided by the embodiment of the application is introduced below.
Fig. 3 is a schematic diagram of an early warning device for a shaft temperature fault of a vehicle bearing according to an embodiment of the application. As shown in fig. 3, the apparatus includes: a first acquisition module 301, a prediction module 302, and a fault analysis module 303.
The first obtaining module 301 is configured to obtain working data of a vehicle during current operation, where the working data is data related to a bearing temperature of the vehicle;
the prediction module 302 is used for analyzing the working data by adopting a regression prediction model and predicting the bearing temperature of the vehicle in different time periods in the subsequent operation process;
and the fault analysis module 303 is configured to determine whether a fault exists in a bearing of the vehicle in a subsequent corresponding time period based on the predicted bearing temperatures of the vehicle in different time periods in the subsequent operation process.
In summary, the early warning device for the axle temperature fault of the vehicle bearing provided by the embodiment of the present application obtains the working data of the vehicle in the current operation through the first obtaining module 301, where the working data is data related to the bearing temperature of the vehicle; the prediction module 302 analyzes the working data by adopting a regression prediction model, and predicts the bearing temperature of the vehicle in different time periods in the subsequent operation process; the fault analysis module 303 determines whether the bearing of the vehicle has a fault in a subsequent corresponding time period based on the predicted bearing temperature of the vehicle in different time periods in the subsequent operation process, so that the problem of poor early warning effect on the axle temperature fault of the vehicle bearing in the related art is solved. Therefore, the effect of predicting the temperature of the bearing position of the vehicle in advance to determine whether the fault exists or not, the early warning effect on the axle temperature fault is improved, and the running safety of the vehicle is ensured is achieved.
Optionally, in the early warning device for the axle temperature fault of the vehicle bearing provided in the embodiment of the present application, the device further includes: the second acquisition module is used for acquiring sample data of the vehicle, wherein the sample data is collected historical working data, and the historical working data at least comprises: historical bearing temperatures of the vehicle detected within the historical time period, vehicle speeds corresponding to the historical bearing temperatures, and ambient temperatures; the extraction module is used for extracting sample characteristics from historical working data; the second obtaining module is used for training the sample characteristics by adopting at least one regression model and obtaining a regression prediction model of the vehicle in a normal running state, wherein the regression model comprises at least one of the following models: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
Optionally, in the device for warning of axle temperature fault of a vehicle bearing provided in this embodiment of the application, the second obtaining module includes: and the generating module is used for selecting any regression model to fit the sample characteristics to generate a regression prediction model represented by a standard curve.
Optionally, in the early warning device for the axle temperature fault of the vehicle bearing provided in the embodiment of the present application, the device further includes: the third obtaining module is used for obtaining a model error of the regression prediction model; and the safe range determining module is used for determining a boundary range value for determining that the temperature of the bearing is in the safe range based on the model error.
Optionally, in the early warning device for the axle temperature fault of the vehicle bearing provided in the embodiment of the present application, the device further includes: the detection module is used for detecting whether the bearing temperature in different time periods in the subsequent operation process is within a boundary range value; and the input module is used for inputting the predicted bearing temperature into the early warning model for analysis if the predicted bearing temperature exceeds the boundary range value in any time period.
Optionally, in the early warning apparatus for axle temperature fault of a vehicle bearing provided in an embodiment of the present application, the fault analysis module includes: the analysis module is used for analyzing the bearing temperature of the vehicle in different time periods in the subsequent operation process by adopting the early warning model; the fault determining module is used for determining that the bearing of the vehicle has a fault in any time period in the subsequent operation process if the temperature of the bearing in any time period meets the alarm condition determined by the pre-alarm model; and the warning module is used for sending out early warning information.
The early warning device for the axle temperature fault of the vehicle bearing comprises a processor and a memory, wherein the first acquiring module 301, the predicting module 302, the fault analyzing module 303 and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The inner core can be set to be one or more than one, and the axle temperature fault of the vehicle bearing is pre-warned by adjusting the inner core parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a storage medium having a program stored thereon, the program implementing the method for early warning of an axle temperature failure of a vehicle bearing when being executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein when the program runs, an early warning method for the axle temperature fault of a vehicle bearing is executed.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps: acquiring working data when a vehicle runs currently, wherein the working data is data related to the temperature of a bearing of the vehicle; analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process; and determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperatures of the vehicle in different time periods in the subsequent operation process.
The processor executes the program and further realizes the following steps: before predicting the bearing temperature of the vehicle during the subsequent operation in different time periods, the method further comprises: acquiring sample data of the vehicle, wherein the sample data is collected historical working data, and the historical working data at least comprises: a historical bearing temperature of the vehicle detected over a historical period of time, a vehicle speed corresponding to the historical bearing temperature, and an ambient temperature; extracting sample features from the historical working data; training the sample characteristics by adopting at least one regression model to obtain the regression prediction model of the vehicle under the normal running state, wherein the regression model comprises at least one of the following: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
The processor executes the program and further realizes the following steps: and selecting any regression model to fit the sample characteristics to generate the regression prediction model characterized by a standard curve.
The processor executes the program and further realizes the following steps: after obtaining the regression prediction model with the vehicle in a normal operating state, the method includes: obtaining a model error of the regression prediction model; based on the model error, a boundary range value for determining that the bearing temperature is within a safe range is determined.
The processor executes the program and further realizes the following steps: after predicting the bearing temperatures of the vehicle over different time periods during subsequent operation, the method comprises: detecting whether the bearing temperature in different time periods in the subsequent operation process is within the boundary range value; and if the bearing temperature predicted in any time period is detected to exceed the boundary range value, inputting the predicted bearing temperature into an early warning model for analysis.
The processor executes the program and further realizes the following steps: determining whether the bearing of the vehicle has a fault in a subsequent corresponding time period based on the predicted bearing temperatures of the vehicle in different time periods in the subsequent operation process, wherein the determining comprises the following steps: analyzing the bearing temperature of the vehicle in different time periods in the subsequent running process by adopting an early warning model; and if the bearing temperature in any time period in the subsequent operation process meets the warning condition determined by the warning model, determining that the bearing of the vehicle has a fault in the time period, and sending warning information. The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program of initializing the following method steps when executed on a data processing device: acquiring working data of a vehicle in the current operation, wherein the working data is data related to the temperature of a bearing of the vehicle; analyzing the working data by adopting a regression prediction model, and predicting the bearing temperature of the vehicle in different time periods in the subsequent operation process; and determining whether the bearing of the vehicle has faults in the corresponding subsequent time period or not based on the predicted bearing temperatures of the vehicle in different time periods in the subsequent operation process.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: before predicting the bearing temperature of the vehicle over different time periods during subsequent operation, the method further comprises: obtaining sample data of the vehicle, wherein the sample data is collected historical working data, and the historical working data at least comprises: historical bearing temperatures of the vehicle detected over a historical period of time, vehicle speeds and ambient temperatures corresponding to the historical bearing temperatures; extracting sample features from the historical working data; training the sample characteristics by adopting at least one regression model to obtain the regression prediction model of the vehicle under the normal running state, wherein the regression model comprises at least one of the following: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: and selecting any regression model to fit the sample characteristics to generate the regression prediction model characterized by a standard curve.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: after obtaining the regression prediction model with the vehicle in a normal operating state, the method includes: obtaining a model error of the regression prediction model; based on the model error, a boundary range value for determining that the bearing temperature is within a safe range is determined.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: after predicting the bearing temperatures of the vehicle over different periods of time during subsequent operation, the method comprises: detecting whether the bearing temperature in different time periods in the subsequent operation process is within the boundary range value; and if the bearing temperature predicted in any time period is detected to exceed the boundary range value, inputting the predicted bearing temperature into an early warning model for analysis.
When executed on a data processing device, is further adapted to perform a procedure for initializing the following method steps: determining whether the bearing of the vehicle has a fault in a subsequent corresponding time period based on the bearing temperature of the vehicle in different time periods in the subsequent operation process, wherein the step of determining whether the bearing of the vehicle has the fault in the subsequent corresponding time period comprises the following steps: analyzing the bearing temperature of the vehicle in different time periods in the subsequent running process by adopting an early warning model; and if the temperature of the bearing in any time period in the subsequent operation process meets the warning condition determined by the warning model, determining that the bearing of the vehicle has a fault in the time period, and sending warning information.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the recitation of an element by the phrase "comprising an … …" does not exclude the presence of additional like elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. The early warning method for the axle temperature fault of the vehicle bearing is characterized by comprising the following steps:
acquiring working data of a vehicle in the current operation, wherein the working data is data related to the temperature of a bearing of the vehicle;
analyzing the working data by adopting a regression prediction model, and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process;
and determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperatures of the vehicle in different time periods in the subsequent operation process.
2. The method of claim 1, wherein prior to predicting the bearing temperature for different periods of time during subsequent operation of the vehicle, the method further comprises:
acquiring sample data of the vehicle, wherein the sample data is collected historical working data, and the historical working data at least comprises: a historical bearing temperature of the vehicle detected over a historical period of time, a vehicle speed corresponding to the historical bearing temperature, and an ambient temperature;
extracting sample features from the historical working data;
training the sample characteristics by adopting at least one regression model to obtain the regression prediction model of the vehicle under the normal running state, wherein the regression model comprises at least one of the following: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
3. The method of claim 2, wherein any one regression model is selected to fit the sample features to generate the regression prediction model characterized by a standard curve.
4. The method of claim 2, wherein after obtaining the regression prediction model with the vehicle in a normal operating condition, the method comprises:
obtaining a model error of the regression prediction model;
based on the model error, a boundary range value for determining that the bearing temperature is within a safe range is determined.
5. The method of claim 4, wherein after predicting the bearing temperature for different periods of time during subsequent operation of the vehicle, the method comprises:
detecting whether the bearing temperature in different time periods in the subsequent operation process is within the boundary range value;
and if the bearing temperature predicted in any time period is detected to exceed the boundary range value, inputting the predicted bearing temperature into an early warning model for analysis.
6. The method of any one of claims 1 to 5, wherein determining whether the bearing of the vehicle has a fault in a subsequent corresponding time period based on predicted bearing temperatures of the vehicle in the subsequent operation for different time periods comprises:
analyzing the bearing temperature of the vehicle in different time periods in the subsequent running process by adopting an early warning model;
and if the bearing temperature in any time period in the subsequent operation process meets the warning condition determined by the warning model, determining that the bearing of the vehicle has a fault in the time period, and sending warning information.
7. A warning device for a vehicle bearing, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring working data of a vehicle in the current operation process, and the working data is data related to the bearing temperature of the vehicle;
the prediction module is used for analyzing the working data by adopting a regression prediction model and predicting to obtain the bearing temperature of the vehicle in different time periods in the subsequent operation process;
and the fault analysis module is used for determining whether the bearing of the vehicle has faults in the subsequent corresponding time period or not based on the predicted bearing temperature of the vehicle in different time periods in the subsequent operation process.
8. The apparatus of claim 7, further comprising:
the second obtaining module is configured to obtain sample data of the vehicle, where the sample data is collected historical working data, and the historical working data at least includes: a historical bearing temperature of the vehicle detected over a historical period of time, a vehicle speed corresponding to the historical bearing temperature, and an ambient temperature;
the extraction module is used for extracting sample characteristics from the historical working data;
the second obtaining module is used for training the sample characteristics by adopting at least one regression model to obtain the regression prediction model of the vehicle in a normal running state, wherein the regression model comprises at least one of the following: a multiple linear regression model, a support vector machine regression model, and a random forest regression model.
9. A storage medium, characterized in that the storage medium comprises a stored program, wherein the program performs the method of any one of claims 1 to 6.
10. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011248732.4A CN112572522A (en) | 2020-11-10 | 2020-11-10 | Early warning method and device for axle temperature fault of vehicle bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011248732.4A CN112572522A (en) | 2020-11-10 | 2020-11-10 | Early warning method and device for axle temperature fault of vehicle bearing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112572522A true CN112572522A (en) | 2021-03-30 |
Family
ID=75122400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011248732.4A Pending CN112572522A (en) | 2020-11-10 | 2020-11-10 | Early warning method and device for axle temperature fault of vehicle bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112572522A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912509A (en) * | 2022-04-06 | 2022-08-16 | 上海擎测机电工程技术有限公司 | Equipment evaluation model establishing method based on equipment historical data and real-time data |
| CN116380251A (en) * | 2023-06-06 | 2023-07-04 | 山东金帝精密机械科技股份有限公司 | Bearing retainer state detection method, equipment and medium based on temperature rise |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010044899A1 (en) * | 2009-09-09 | 2011-03-10 | Knorr-Bremse Systeme für Schienenfahrzeuge GmbH | Method for predicting the temperature of a wheel bearing of a wheel of a vehicle |
| EP2998183A1 (en) * | 2014-09-22 | 2016-03-23 | General Electric Company | Method and system for operating a vehicle system to reduce wheel and track wear |
| CN105976578A (en) * | 2016-07-21 | 2016-09-28 | 西安理工大学 | High-speed train axle temperature dynamic alarm threshold setting method based on monitoring data |
| CN108860211A (en) * | 2018-05-25 | 2018-11-23 | 中车青岛四方机车车辆股份有限公司 | A kind of wrong report recognition methods and device based on shaft temperature sensor |
| CN109615121A (en) * | 2018-11-27 | 2019-04-12 | 西安理工大学 | Bullet train axle temperature predicting method based on data-driven support vector machines |
| CN109711111A (en) * | 2019-02-27 | 2019-05-03 | 盐城师范学院 | A method of the prediction of axis temperature is carried out using layering stepwise regression analysis showed |
| CN110210174A (en) * | 2019-06-21 | 2019-09-06 | 西南交通大学 | A kind of EMU axle box bearing temperature predicting method based on multilayer LSTM |
| CN110243598A (en) * | 2019-06-12 | 2019-09-17 | 中国神华能源股份有限公司 | Processing method, device and the storage medium of train bearing temperature |
| CN111351664A (en) * | 2020-02-13 | 2020-06-30 | 成都运达科技股份有限公司 | Bearing temperature prediction and alarm diagnosis method based on LSTM model |
| CN111829693A (en) * | 2020-07-30 | 2020-10-27 | 成都运达科技股份有限公司 | Bearing temperature detection method and system based on LSTM model of time and space dimensions |
-
2020
- 2020-11-10 CN CN202011248732.4A patent/CN112572522A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010044899A1 (en) * | 2009-09-09 | 2011-03-10 | Knorr-Bremse Systeme für Schienenfahrzeuge GmbH | Method for predicting the temperature of a wheel bearing of a wheel of a vehicle |
| CN102574534A (en) * | 2009-09-09 | 2012-07-11 | 克诺尔-布里姆斯轨道车辆系统有限公司 | Method for predicting the temperature of a wheel bearing of a wheel of a vehicle |
| EP2998183A1 (en) * | 2014-09-22 | 2016-03-23 | General Electric Company | Method and system for operating a vehicle system to reduce wheel and track wear |
| CN105976578A (en) * | 2016-07-21 | 2016-09-28 | 西安理工大学 | High-speed train axle temperature dynamic alarm threshold setting method based on monitoring data |
| CN108860211A (en) * | 2018-05-25 | 2018-11-23 | 中车青岛四方机车车辆股份有限公司 | A kind of wrong report recognition methods and device based on shaft temperature sensor |
| CN109615121A (en) * | 2018-11-27 | 2019-04-12 | 西安理工大学 | Bullet train axle temperature predicting method based on data-driven support vector machines |
| CN109711111A (en) * | 2019-02-27 | 2019-05-03 | 盐城师范学院 | A method of the prediction of axis temperature is carried out using layering stepwise regression analysis showed |
| CN110243598A (en) * | 2019-06-12 | 2019-09-17 | 中国神华能源股份有限公司 | Processing method, device and the storage medium of train bearing temperature |
| CN110210174A (en) * | 2019-06-21 | 2019-09-06 | 西南交通大学 | A kind of EMU axle box bearing temperature predicting method based on multilayer LSTM |
| CN111351664A (en) * | 2020-02-13 | 2020-06-30 | 成都运达科技股份有限公司 | Bearing temperature prediction and alarm diagnosis method based on LSTM model |
| CN111829693A (en) * | 2020-07-30 | 2020-10-27 | 成都运达科技股份有限公司 | Bearing temperature detection method and system based on LSTM model of time and space dimensions |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912509A (en) * | 2022-04-06 | 2022-08-16 | 上海擎测机电工程技术有限公司 | Equipment evaluation model establishing method based on equipment historical data and real-time data |
| CN116380251A (en) * | 2023-06-06 | 2023-07-04 | 山东金帝精密机械科技股份有限公司 | Bearing retainer state detection method, equipment and medium based on temperature rise |
| CN116380251B (en) * | 2023-06-06 | 2023-08-04 | 山东金帝精密机械科技股份有限公司 | Bearing retainer state detection method, equipment and medium based on temperature rise |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elnour et al. | A dual-isolation-forests-based attack detection framework for industrial control systems | |
| CN107086944B (en) | Anomaly detection method and device | |
| CN110766059A (en) | Transformer fault prediction method, device and equipment | |
| Manco et al. | Fault detection and explanation through big data analysis on sensor streams | |
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| CN112572522A (en) | Early warning method and device for axle temperature fault of vehicle bearing | |
| CN110162422A (en) | One kind being based on the problem of decision tree localization method and device | |
| CN111489166A (en) | Risk prevention and control method, device, processing equipment and system | |
| CN116821750A (en) | Data security risk monitoring traceability system based on artificial intelligence | |
| CN112926636A (en) | Method and device for detecting abnormal temperature of traction converter cabinet body | |
| CN111767957A (en) | Method and device for detecting log abnormity, storage medium and electronic equipment | |
| CN113313479A (en) | Payment service big data processing method and system based on artificial intelligence | |
| Abid et al. | Distributed architecture of an intrusion detection system in industrial control systems | |
| CN112446389A (en) | Fault judgment method and device | |
| CN109951326A (en) | Data processing method, device, storage medium and processor | |
| Alem et al. | A hybrid intrusion detection system in industry 4.0 based on ISA95 standard | |
| CN111259869A (en) | Non-invasive electrical cluster load fault identification method | |
| CN109871711B (en) | Ocean big data sharing and distributing risk control model and method | |
| Luo et al. | A prediction method based on improved ridge regression | |
| CN113468384B (en) | Processing method, device, storage medium and processor for network information source information | |
| WO2023023412A2 (en) | Vulnerability-driven cyberattack protection system and method for industrial assets | |
| CN114330569A (en) | Method and equipment for detecting fan unit component fault and storage medium | |
| CN114676002A (en) | PHM technology-based system operation and maintenance method and device | |
| CN117033913A (en) | Abnormality detection method and device based on power equipment portrait, and storage medium | |
| CN115831339B (en) | Medical system risk management and control pre-prediction method and system based on deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210330 |