CN116561593A - Model training method, temperature prediction method, device and medium of gearbox - Google Patents
Model training method, temperature prediction method, device and medium of gearbox Download PDFInfo
- Publication number
- CN116561593A CN116561593A CN202310846467.7A CN202310846467A CN116561593A CN 116561593 A CN116561593 A CN 116561593A CN 202310846467 A CN202310846467 A CN 202310846467A CN 116561593 A CN116561593 A CN 116561593A
- Authority
- CN
- China
- Prior art keywords
- current
- gear box
- gearbox
- temperature
- training
- 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
- 238000000034 method Methods 0.000 title claims abstract description 101
- 238000012549 training Methods 0.000 title claims abstract description 64
- 238000012417 linear regression Methods 0.000 claims abstract description 36
- 230000000694 effects Effects 0.000 claims abstract description 19
- 238000009529 body temperature measurement Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 description 6
- 230000005288 electromagnetic effect Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
- G01K13/04—Thermometers specially adapted for specific purposes for measuring temperature of moving solid bodies
- G01K13/08—Thermometers specially adapted for specific purposes for measuring temperature of moving solid bodies in rotary movement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Control Of Transmission Device (AREA)
Abstract
The invention relates to the technical field of rail transit, in particular to a model training method, a temperature prediction method, a device and a medium for a gear box, and aims to solve the problem of how to accurately predict the temperature of the gear box. The method comprises the steps of acquiring historical temperature data of a plurality of gearboxes of a train, determining that other gearboxes are affected for each gearbox, training a corresponding linear regression model based on the historical temperature data of each gearbox and the other gearboxes with the effects, obtaining a trained linear regression model, and obtaining a current temperature predicted value of the gearboxes based on the trained linear regression model, so that the current temperature of the gearboxes is predicted. The method can predict the current temperature of the current gear box based on the temperature affecting other gear boxes, accurately reflect the accurate temperature of the gear box, and avoid the problem that the normal operation of the train is affected when detecting equipment such as a temperature sensor on the gear box has faults.
Description
Technical Field
The invention relates to the technical field of rail transit, and particularly provides a model training method, a temperature prediction method, a device and a medium of a gear box.
Background
The gear box of the train is a key part of the train for realizing transmission. The gear box realizes power transmission through gear engagement, and the power of traction motor is transmitted to the axletree to drive train operation.
The gearbox is generally provided with a temperature sensor and other devices for monitoring the temperature of the gearbox. However, the temperature sensor has the fault and other conditions, so that the accurate temperature of the gear box cannot be accurately reflected, and the normal operation of the train is further affected.
Accordingly, there is a need in the art for a new temperature prediction scheme for a gearbox that addresses the above-described problems.
Disclosure of Invention
The present invention has been made to overcome the above drawbacks, and to provide a solution or at least partially solve the problem of how to accurately predict the temperature of a gearbox.
In a first aspect, the present invention provides a model training method, the method comprising:
collecting historical temperature data of a plurality of gearboxes of a train;
determining, for each gearbox of the train, at least one other gearbox that has an effect on the current gearbox;
and training the linear regression model corresponding to the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box so as to acquire a trained linear regression model corresponding to each gear box.
In one technical scheme of the model training method, the training the linear regression model corresponding to the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box includes:
constructing a training set of the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box;
and training the linear regression model corresponding to the current gear box according to the training set of the current gear box.
In one technical solution of the above model training method, the constructing the training set of the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box includes:
taking historical temperature data of other gear boxes as a characteristic column;
taking the historical temperature data of the current gear box as a target column;
and constructing a feature engineering based on the feature column and the target column to serve as a training set of the current gear box.
In one aspect of the above model training method, the determining, for each gearbox of the train, at least one other gearbox having an effect on a current gearbox includes:
at least one other gearbox having an influence on the current gearbox is determined according to a preset rule.
In one embodiment of the above model training method, the influence includes an electromagnetic influence and/or a mechanical influence.
In a second aspect, the present invention provides a method of temperature prediction for a gearbox, the method comprising:
acquiring current temperature measurement data of a plurality of gear boxes of a train;
for each gearbox, current temperature measurement data of other gearboxes with influences on the current gearbox are input into a linear regression model corresponding to the current gearbox, and a current temperature predicted value of the current gearbox is obtained; the linear regression model is obtained according to the model training method according to any one of the technical schemes of the model training method;
and obtaining a temperature prediction result of each gear box according to the current temperature measurement data and the current temperature prediction value of each gear box.
In one technical scheme of the temperature prediction method of the gear boxes, the obtaining the temperature prediction result of each gear box according to the current temperature measurement data and the current temperature prediction value of each gear box includes:
comparing the current temperature measurement data with the current temperature prediction value;
and obtaining the temperature prediction result according to the comparison result.
In one technical scheme of the temperature prediction method of the gear box, a temperature sensor is arranged on the gear box;
the acquiring current temperature measurement data of a plurality of gearboxes of the train comprises:
and acquiring current temperature measurement data of each gear box according to the temperature sensor arranged on each gear box.
In a third aspect, a control device is provided, the control device comprising at least one processor and at least one storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the model training method according to any one of the solutions of the model training method or the temperature prediction method of the gearbox according to any one of the solutions of the temperature prediction method of the gearbox.
In a fourth aspect, a computer readable storage medium is provided, in which a plurality of program codes are stored, the program codes being adapted to be loaded and run by a processor to perform the model training method according to any one of the above-mentioned model training methods or the temperature prediction method of the gearbox according to any one of the above-mentioned temperature prediction methods of the gearbox.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
in the technical scheme of implementing the invention, the method collects historical temperature data of a plurality of gearboxes of the train, determines that other gearboxes are affected on each gearbox, trains the corresponding linear regression model based on the historical temperature data of each gearbox and the other gearboxes with the effects, and accordingly obtains a trained linear regression model, and can obtain a current temperature predicted value of the gearboxes based on the trained linear regression model, so that the current temperature of the gearboxes is predicted. Through the configuration mode, the method and the device can predict the current temperature of the current gear box based on the condition that the temperature of other gear boxes are influenced, can more accurately reflect the accurate temperature of the gear box, and effectively avoid the problem that the normal operation of a train is influenced when detection equipment such as a temperature sensor on the gear box is in failure.
Drawings
The present disclosure will become more readily understood with reference to the accompanying drawings. As will be readily appreciated by those skilled in the art: the drawings are for illustrative purposes only and are not intended to limit the scope of the present invention. Wherein:
FIG. 1 is a flow diagram of the main steps of a model training method according to one embodiment of the invention;
FIG. 2 is a flow chart of the main steps of a method for predicting the temperature of a gearbox according to one embodiment of the invention.
Detailed Description
Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
In the description of the present invention, a "module," "processor" may include hardware, software, or a combination of both. A module may comprise hardware circuitry, various suitable sensors, communication ports, memory, or software components, such as program code, or a combination of software and hardware. The processor may be a central processor, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and/or signal processing functions. The processor may be implemented in software, hardware, or a combination of both. Non-transitory computer readable storage media include any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like. The term "a and/or B" means all possible combinations of a and B, such as a alone, B alone or a and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and/or B" and may include A alone, B alone or A and B. The singular forms "a", "an" and "the" include plural referents.
Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of a model training method according to an embodiment of the present invention. As shown in fig. 1, the model training method in the embodiment of the present invention mainly includes the following steps S101 to S103.
Step S101: historical temperature data for a plurality of gearboxes of a train is collected.
In this embodiment, historical temperature data of a plurality of gearboxes provided on a train may be collected. For example, 32 gearboxes are provided on a train, possibly distributed in different cars.
In one embodiment, historical temperature data for 32 gearboxes a day may be acquired, with data acquired twice a day for each gearbox, i.e., 64 historical temperature data are obtained in total. The 64 historical temperature data may be divided into 32 groups based on the gearbox identification carried by the historical temperature data, one group for each gearbox.
In one embodiment, the historical temperature data for the gearbox may be obtained based on temperature sensor testing provided on the gearbox.
Step S102: for each gearbox of the train, at least one other gearbox that has an effect on the current gearbox is determined.
In this embodiment, at least one other gearbox having an effect on each gearbox may be obtained.
In one embodiment, the effect may be an electromagnetic effect. If the distance between the gear box a and the gear box B is relatively short, the gear box B may have an electromagnetic effect on the gear box a. It should be noted that the influence of the gear box B on the gear box a does not represent that the gear box a also has an influence on the gear box B; possible influences on the gearbox B are the gearbox C and the gearbox D.
In another embodiment, the effect may be a mechanical effect, for example, each gearbox may have a mechanical effect on other gearboxes when one produces a mechanical offset due to a mechanical connection.
In one embodiment, at least one other gearbox having an impact on the current gearbox may be determined according to a preset rule.
In one example, it may be measured through preliminary experimentation whether each gearbox (e.g., a) on the train is electromagnetically disturbed by the other gearboxes (e.g., greater than a certain threshold, such as the electromagnetic disturbance of gearboxes B and C to gearbox a being greater than the threshold), and if so, the disturbing gearboxes B and C will be factors affecting gearbox a (i.e., preset rules regarding gearbox a). Of course, the preset rule can also be obtained by electromagnetic simulation of the gearbox on the train through electromagnetic modeling simulation software. For the example of the mechanical influence described above, the preset rule may be determined by mechanical modeling simulation software such as ANSYS, FEM, for example.
The preset rules can be written in a configuration file, and other gearboxes with influence on the current gearboxes can be determined through the configuration file. A person skilled in the art can compile preset rules according to the needs of practical application and write the preset rules into a configuration file to obtain other gearboxes having influence on the current gearboxes.
Step S103: based on the historical temperature data of other gearboxes and the historical temperature data of the current gearboxes, training the linear regression model corresponding to the current gearboxes to obtain a trained linear regression model corresponding to each gearbox.
In this embodiment, the linear regression model corresponding to the current gearbox may be trained according to historical temperature data of the current gearbox and other gearboxes having an influence on the current gearbox, so as to obtain a trained linear regression model. Since the effects of the gearboxes are not symmetrically matched (gearbox B has an effect on gearbox A and does not represent that gearbox A will have an effect on gearbox B; gearbox B may have an effect on gearbox C and gearbox D), the steps are repeated to obtain respective linear regression models for all gearboxes on the train.
In one embodiment, step S103 may further include the following steps S1031 and S1032:
step S1031: a training set of the current gearbox is constructed based on historical temperature data of other gearboxes and historical temperature data of the current gearbox.
In the present embodiment, step S1031 may further include the following steps S10311 to S10313:
step S10311: the historical temperature data of other gearboxes are taken as a characteristic column.
Step S10312: the historical temperature data of the current gear box is taken as a target column.
Step S10313: based on the feature columns and the target columns, feature engineering is constructed as a training set of the current gearbox.
In this embodiment, the feature engineering may be constructed by using the historical temperature data of the other gear boxes as a feature column and the historical temperature data of the current gear box as a target column, so as to construct the training set based on the feature engineering. For example, 32 gearboxes, the training set constructed correspondingly is 32 groups. The feature engineering refers to a process of converting original data into features which better express the nature of a problem, so that the application of the features to a prediction model can improve model prediction accuracy of invisible data. The targets are labels or targets in the machine learning process. The feature columns are data in the training set other than the target columns in the machine learning process.
Step S1032: and training a linear regression model corresponding to the current gear box according to the training set of the current gear box.
In this embodiment, the training set of the current gearbox may be applied to train the linear regression model corresponding to the current gearbox, so as to obtain a trained linear regression model.
Based on the steps S101-S103, the embodiment of the present invention collects historical temperature data of a plurality of gearboxes of a train, determines that other gearboxes are affected for each gearbox, trains a corresponding linear regression model based on the historical temperature data of each gearbox and the other gearboxes with the affects, and thus obtains a trained linear regression model, and based on the trained linear regression model, can obtain a predicted value of the current temperature of the gearboxes, thereby realizing prediction of the current temperature of the gearboxes. Through the configuration mode, the embodiment of the invention can predict the current temperature of the current gear box based on the temperature affecting other gear boxes, can more accurately reflect the accurate temperature of the gear box, and effectively avoid the problem that the normal operation of a train is affected when detecting equipment such as a temperature sensor on the gear box has faults.
Furthermore, the invention also provides a temperature prediction method of the gear box.
Referring to fig. 2, fig. 2 is a schematic flow chart of main steps of a temperature prediction method of a gearbox according to an embodiment of the invention. As shown in fig. 2, the temperature prediction method of the gearbox in the embodiment of the present invention mainly includes the following steps S201 to S203.
Step S201: current temperature measurement data of a plurality of gearboxes of a train is acquired.
In this embodiment, current temperature measurement data of a plurality of gearboxes provided on a train may be acquired.
In one embodiment, a temperature sensor is provided on the gearbox. The current temperature measurement data may be obtained by a temperature sensor provided on each gear.
Step S202: for each gear box, current temperature measurement data of other gear boxes with influence on the current gear box are input into a linear regression model corresponding to the current gear box, and a current temperature predicted value of the current gear box is obtained; wherein the linear regression model is obtained according to the model training method described in the model training method embodiment above.
In this embodiment, the current temperature measurement data of other gearboxes having an influence on each gearbox may be input into the corresponding trained linear regression model, so as to obtain the current temperature predicted value of the gearbox. The linear regression model corresponding to each gear box is obtained by training based on the model training method described in the embodiment of the model training method.
In one embodiment, the current temperature measurement data of other gearboxes that have an effect on each gearbox may be retrieved through a preset profile. The configuration file may be written according to a preset rule. The preset rule may be a rule written according to influence, and a person skilled in the art may set the preset rule according to the needs of the actual application.
An example, the effect may be an electromagnetic effect. For example, electromagnetic effects may exist when two gearboxes are relatively close together.
Step S203: and obtaining a temperature prediction result of each gear box according to the current temperature measurement data and the current temperature prediction value of each gear box.
In this embodiment, the temperature prediction result of each gear case may be obtained from the current temperature measurement data of the gear case and the current temperature prediction value obtained based on the linear regression model.
In one embodiment, step S203 may further include the following steps S2031 and S2032:
step S2031: the current temperature measurement data is compared to the current temperature prediction value.
In the present embodiment, the current temperature measurement data obtained by the temperature sensor measurement may be compared with the current temperature prediction value predicted by the linear regression model for each gear case.
Step S2032: and obtaining a temperature prediction result according to the comparison result.
In the present embodiment, the temperature prediction result may be obtained based on the comparison result.
In one embodiment, if the comparison result is that the difference between the current temperature measurement data and the current temperature predicted value is large (for example, greater than a preset threshold value), it may be considered that the temperature sensor of the corresponding gearbox is abnormal, so that operations such as maintenance and the like may be performed on the temperature sensor.
In one embodiment, if the comparison result is that the difference between the current temperature measurement data and the current temperature predicted value is large (for example, greater than a preset threshold value), the measurement of the temperature sensor of the corresponding gearbox may be considered to be inaccurate, and then the linear regression model may be applied to obtain the current temperature predicted value as the final temperature predicted result of the gearbox.
In one embodiment, if the comparison result is that the difference between the current temperature measurement data and the current temperature predicted value is smaller (for example, smaller than or equal to the preset threshold value), the temperature sensor measurement of the corresponding gearbox can be considered to be accurate, and the current temperature measurement data measured by the temperature sensor can be directly applied as the final temperature predicted result of the gearbox.
Based on the steps S201-S203, the embodiment of the invention can predict the current temperature of the current gear box based on the temperature affecting other gear boxes, can more accurately reflect the accurate temperature of the gear box, and effectively avoid the problem that the normal operation of the train is affected when the detection equipment such as the temperature sensor on the gear box has faults.
It should be noted that, although the foregoing embodiments describe the steps in a specific order, it will be understood by those skilled in the art that, in order to achieve the effects of the present invention, the steps are not necessarily performed in such an order, and may be performed simultaneously (in parallel) or in other orders, and these variations are within the scope of the present invention.
It will be appreciated by those skilled in the art that the present invention may implement all or part of the above-described methods according to the above-described embodiments, or may be implemented by means of a computer program for instructing relevant hardware, where the computer program may be stored in a computer readable storage medium, and where the computer program may implement the steps of the above-described embodiments of the method when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable storage medium may include: any entity or device, medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signals, telecommunications signals, software distribution media, and the like capable of carrying the computer program code. It should be noted that the computer readable storage medium may include content that is subject to appropriate increases and decreases as required by jurisdictions and by jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunications signals.
Further, the invention also provides a control device. In one control device embodiment according to the present invention, the control device includes a processor and a storage device, the storage device may be configured to store a program for executing the model training method of the above-described method embodiment, and the processor may be configured to execute the program in the storage device, including, but not limited to, the program for executing the model training method of the above-described method embodiment. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The control device may be a control device formed of various electronic devices.
The control device in the embodiment of the invention can be a control device formed by various electronic devices. In some possible embodiments, the control device may include a plurality of memory devices and a plurality of processors. The program for executing the model training method of the above method embodiment may be divided into a plurality of sub-programs, and each sub-program may be loaded and executed by the processor to execute the different steps of the model training method of the above method embodiment. Specifically, each of the subroutines may be stored in different storage devices, respectively, and each of the processors may be configured to execute the programs in one or more storage devices to collectively implement the model training method of the above method embodiment, that is, each of the processors executes different steps of the model training method of the above method embodiment, respectively, to collectively implement the model training method of the above method embodiment.
The plurality of processors may be processors disposed on the same device, and for example, the control means may be a high-performance device composed of a plurality of processors, and the plurality of processors may be processors disposed on the high-performance device. In addition, the plurality of processors may be processors disposed on different devices, for example, the control apparatus may be a server cluster, and the plurality of processors may be processors on different servers in the server cluster.
Further, the invention also provides a computer readable storage medium. In one computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium may be configured to store a program for executing the model training method of the above-described method embodiment, which program may be loaded and executed by a processor to implement the above-described model training method. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The computer readable storage medium may be a storage device including various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present invention is a non-transitory computer readable storage medium.
Further, the invention also provides a control device. In one control device embodiment according to the present invention, the control device includes a processor and a storage device, the storage device may be configured to store a program for performing the temperature prediction method of the gear box of the above-described method embodiment, and the processor may be configured to execute the program in the storage device, including, but not limited to, the program for performing the temperature prediction method of the gear box of the above-described method embodiment. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The control device may be a control device formed of various electronic devices.
The control device in the embodiment of the invention can be a control device formed by various electronic devices. In some possible embodiments, the control device may include a plurality of memory devices and a plurality of processors. And the program for executing the temperature prediction method of the gear box of the above method embodiment may be divided into a plurality of sub-programs, each of which may be loaded and executed by the processor to execute different steps of the temperature prediction method of the gear box of the above method embodiment, respectively. Specifically, each of the subroutines may be stored in different storage devices, respectively, and each of the processors may be configured to execute the programs in one or more storage devices to collectively implement the temperature prediction method of the gearbox of the above method embodiment, that is, each of the processors executes different steps of the temperature prediction method of the gearbox of the above method embodiment, respectively, to collectively implement the temperature prediction method of the gearbox of the above method embodiment.
The plurality of processors may be processors disposed on the same device, and for example, the control means may be a high-performance device composed of a plurality of processors, and the plurality of processors may be processors disposed on the high-performance device. In addition, the plurality of processors may be processors disposed on different devices, for example, the control apparatus may be a server cluster, and the plurality of processors may be processors on different servers in the server cluster.
Further, the invention also provides a computer readable storage medium. In one embodiment of the computer readable storage medium according to the present invention, the computer readable storage medium may be configured to store a program for performing the temperature prediction method of the gear box of the above-described method embodiment, which may be loaded and executed by a processor to implement the temperature prediction method of the gear box described above. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The computer readable storage medium may be a storage device including various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present invention is a non-transitory computer readable storage medium.
Further, it should be understood that, since the respective modules are merely set to illustrate the functional units of the apparatus of the present invention, the physical devices corresponding to the modules may be the processor itself, or a part of software in the processor, a part of hardware, or a part of a combination of software and hardware. Accordingly, the number of individual modules in the figures is merely illustrative.
Those skilled in the art will appreciate that the various modules in the apparatus may be adaptively split or combined. Such splitting or combining of specific modules does not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solution after splitting or combining falls within the protection scope of the present invention.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.
Claims (10)
1. A method of model training, the method comprising:
collecting historical temperature data of a plurality of gearboxes of a train;
determining, for each gearbox of the train, at least one other gearbox that has an effect on the current gearbox;
and training the linear regression model corresponding to the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box so as to acquire a trained linear regression model corresponding to each gear box.
2. The method for training a model according to claim 1,
training a linear regression model corresponding to the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box, including:
constructing a training set of the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box;
and training the linear regression model corresponding to the current gear box according to the training set of the current gear box.
3. The method for training a model according to claim 2, wherein,
the step of constructing a training set of the current gear box based on the historical temperature data of the other gear boxes and the historical temperature data of the current gear box comprises the following steps:
taking historical temperature data of other gear boxes as a characteristic column;
taking the historical temperature data of the current gear box as a target column;
and constructing a feature engineering based on the feature column and the target column to serve as a training set of the current gear box.
4. The method for training a model according to claim 1,
the determining, for each gearbox of the train, at least one other gearbox having an effect on a current gearbox, comprising:
at least one other gearbox having an influence on the current gearbox is determined according to a preset rule.
5. The model training method according to any one of claim 1 to 4, characterized in that,
the influence includes an electromagnetic influence and/or a mechanical influence.
6. A method of predicting the temperature of a gearbox, the method comprising:
acquiring current temperature measurement data of a plurality of gear boxes of a train;
for each gearbox, current temperature measurement data of other gearboxes with influences on the current gearbox are input into a linear regression model corresponding to the current gearbox, and a current temperature predicted value of the current gearbox is obtained; wherein the linear regression model is obtained according to the model training method of any one of claims 1 to 5;
and obtaining a temperature prediction result of each gear box according to the current temperature measurement data and the current temperature prediction value of each gear box.
7. A method for predicting the temperature of a gear box according to claim 6, wherein,
the step of obtaining the temperature prediction result of each gear box according to the current temperature measurement data and the current temperature prediction value of each gear box comprises the following steps:
comparing the current temperature measurement data with the current temperature prediction value;
and obtaining the temperature prediction result according to the comparison result.
8. A method for predicting the temperature of a gearbox according to claim 6 or 7, wherein,
a temperature sensor is arranged on the gear box;
the acquiring current temperature measurement data of a plurality of gearboxes of the train comprises:
and acquiring current temperature measurement data of each gear box according to the temperature sensor arranged on each gear box.
9. A control device comprising at least one processor and at least one memory device, said memory device being adapted to store a plurality of program codes, characterized in that said program codes are adapted to be loaded and run by said processor to perform the model training method of any one of claims 1 to 5 or the temperature prediction method of the gearbox of any one of claims 6 to 8.
10. A computer readable storage medium, in which a plurality of program codes are stored, characterized in that the program codes are adapted to be loaded and run by a processor to perform the model training method of any one of claims 1 to 5 or the temperature prediction method of the gearbox of any one of claims 6 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310846467.7A CN116561593A (en) | 2023-07-11 | 2023-07-11 | Model training method, temperature prediction method, device and medium of gearbox |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310846467.7A CN116561593A (en) | 2023-07-11 | 2023-07-11 | Model training method, temperature prediction method, device and medium of gearbox |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116561593A true CN116561593A (en) | 2023-08-08 |
Family
ID=87503914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310846467.7A Pending CN116561593A (en) | 2023-07-11 | 2023-07-11 | Model training method, temperature prediction method, device and medium of gearbox |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116561593A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9602333D0 (en) * | 1995-02-13 | 1996-04-03 | Daimler Benz Ag | A device for detecting the temperature of a gearbox |
| CN103743563A (en) * | 2013-08-13 | 2014-04-23 | 华北电力大学（保定） | Fan gear box space failure predicating method based on temperature data |
| CN108680358A (en) * | 2018-03-23 | 2018-10-19 | 河海大学 | A kind of Wind turbines failure prediction method based on bearing temperature model |
| CN110907066A (en) * | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring method based on deep learning model |
| CN110907170A (en) * | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method |
| CN111581597A (en) * | 2020-03-17 | 2020-08-25 | 华电电力科学研究院有限公司 | Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model |
| CN112834079A (en) * | 2020-12-25 | 2021-05-25 | 山东朗进科技股份有限公司 | Method for judging parameter drift of temperature sensor of air conditioning unit of railway vehicle |
-
2023
- 2023-07-11 CN CN202310846467.7A patent/CN116561593A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9602333D0 (en) * | 1995-02-13 | 1996-04-03 | Daimler Benz Ag | A device for detecting the temperature of a gearbox |
| CN103743563A (en) * | 2013-08-13 | 2014-04-23 | 华北电力大学（保定） | Fan gear box space failure predicating method based on temperature data |
| CN108680358A (en) * | 2018-03-23 | 2018-10-19 | 河海大学 | A kind of Wind turbines failure prediction method based on bearing temperature model |
| CN110907066A (en) * | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring method based on deep learning model |
| CN110907170A (en) * | 2019-11-30 | 2020-03-24 | 华能如东八仙角海上风力发电有限责任公司 | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method |
| CN111581597A (en) * | 2020-03-17 | 2020-08-25 | 华电电力科学研究院有限公司 | Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model |
| CN112834079A (en) * | 2020-12-25 | 2021-05-25 | 山东朗进科技股份有限公司 | Method for judging parameter drift of temperature sensor of air conditioning unit of railway vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI510916B (en) | Storage device lifetime monitoring system and storage device lifetime monitoring method thereof | |
| CN102062619B (en) | For being come method system and the device of Analysis of Complex system by Forecast reasoning | |
| US11195125B2 (en) | Pollution prediction | |
| JP6456580B1 (en) | Abnormality detection device, abnormality detection method and abnormality detection program | |
| CN101999101B (en) | The defining method of system cloud gray model prediction | |
| US11429497B2 (en) | Predicting and handling of slow disk | |
| CN112257263B (en) | Equipment residual life prediction system based on self-attention mechanism | |
| US20130204809A1 (en) | Estimation of predictive accuracy gains from added features | |
| CN102495949A (en) | Fault prediction method based on air data | |
| CN115836283A (en) | Model fidelity monitoring and regeneration for manufacturing process decision support | |
| CN116415126A (en) | Method, device and computing equipment for anomaly detection of doctor blades of paper machine | |
| Liu et al. | A novel health prognosis method for system based on improved degenerated Hidden Markov model | |
| CN116561593A (en) | Model training method, temperature prediction method, device and medium of gearbox | |
| CN113487086A (en) | Method and device for predicting remaining service life of equipment, computer equipment and medium | |
| CN110398642A (en) | The failure prediction method and device of Electric plug sliding door | |
| CN117251114A (en) | Model training method, disk life prediction method, related device and equipment | |
| CN117375095A (en) | Situation awareness-based power grid dispatching method, system, device and storage medium | |
| CN116642696A (en) | Railway bearing health monitoring method, device, system, terminal and storage medium | |
| CN111859056A (en) | Data processing method, device, electronic equipment and medium | |
| CN114623799B (en) | Structural health monitoring data abnormality early warning method, system, device and storage medium | |
| CN113344150B (en) | Method, device, medium and electronic equipment for identifying stained code points | |
| US20230022253A1 (en) | Fast and accurate prediction methods and systems based on analytical models | |
| CN111400847A (en) | Method, system and equipment for calculating train speed | |
| CN111078440B (en) | Disk error detection method, device and storage medium | |
| CN114550466B (en) | Parking space state detection method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |