Oil seal fault prediction method, device and equipment and storage medium

Abstract

The invention discloses an oil seal fault prediction method, device and equipment and a storage medium, and belongs to the technical field of automobiles, and the method comprises the steps: obtaining target vehicle operation data of a target vehicle; inputting the target vehicle operation data into the target oil seal fault prediction model to obtain an oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training a Logistic regression model. According to the method, the fault of the clutch sealing cover oil seal in the target vehicle is accurately predicted in advance, the clutch sealing cover oil seal in the target vehicle can be conveniently maintained or replaced before the fault of the oil seal occurs, so that fault expansion is avoided, the vehicle maintenance cost is reduced, and the vehicle maintenance efficiency is improved. The reliability of the oil seal of the clutch sealing cover in the vehicle is guaranteed, the service life of the clutch in the vehicle is prolonged, and the driving safety of the vehicle is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to an oil seal failure prediction method, device, equipment and storage medium. Background Art

[0002] The clutch is an important part of the automobile transmission system, and the reliability of its sealing cover oil seal directly affects the performance and life of the clutch. Oil seal failure may cause problems such as oil leakage and clutch slippage, which in turn affects the service life of the clutch and causes failures of other related components, thereby increasing maintenance costs and affecting the driving safety of the vehicle. Therefore, the study of clutch sealing cover oil seal failure is of great significance.

[0003] However, since each user's vehicle driving conditions and driving behavior habits are different, it is particularly important to monitor the clutch seal cover oil seal in the user's vehicle and identify the risk of failure. Summary of the invention

[0004] The present invention provides an oil seal failure prediction method, device, equipment and storage medium to predict the risk of oil seal failure in advance, reduce vehicle maintenance costs, ensure the reliability of the clutch sealing cover oil seal in the vehicle, increase the service life of the clutch in the vehicle, and ensure the driving safety of the vehicle.

[0005] According to one aspect of the present invention, a method for predicting oil seal failure is provided, the method comprising:

[0006] Obtain target vehicle operation data of a target vehicle;

[0007] The target vehicle operation data is input into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training the Logistic regression model.

[0008] According to another aspect of the present invention, there is provided an oil seal failure prediction device, the device comprising:

[0009] A target vehicle operation data acquisition module is used to acquire target vehicle operation data of a target vehicle;

[0010] The oil seal fault prediction result determination module is used to input the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training the Logistic regression model.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to at least one processor; wherein,

[0014] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the oil seal fault prediction method of any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the oil seal fault prediction method of any embodiment of the present invention when executed.

[0016] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the oil seal failure prediction method according to any embodiment of the present invention is implemented.

[0017] The technical solution of the embodiment of the present invention obtains the target vehicle operation data of the target vehicle; inputs the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training the Logistic regression model. The above technical solution, based on the pre-trained oil seal fault prediction model (i.e., the target oil seal fault prediction model), accurately predicts the failure of the clutch seal cover oil seal in the target vehicle in advance according to the target vehicle operation data of the target vehicle, so as to facilitate the repair or replacement of the clutch seal cover oil seal in the target vehicle before the oil seal failure occurs, thereby avoiding the expansion of the fault, reducing the vehicle maintenance cost, and ensuring the reliability of the clutch seal cover oil seal in the vehicle, thereby increasing the service life of the clutch in the vehicle and ensuring the driving safety of the vehicle.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a flow chart of an oil seal fault prediction method provided according to Embodiment 1 of the present invention;

[0021] Figure 2A is a flow chart of an oil seal fault prediction method provided according to the second embodiment of the present invention;

[0022] Figure 2B is a curve showing the change of oil temperature and engine speed over time of a sample vehicle 1 provided in accordance with the second embodiment of the present invention;

[0023] Figure 3 is a schematic structural diagram of an oil seal fault prediction device provided according to Embodiment 3 of the present invention;

[0024] Figure 4 It is a structural schematic diagram of an electronic device for implementing the oil seal fault prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "target", "sample", "first" and "second" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] In addition, it should be noted that in the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of the preset temperature, the first recognition rate threshold, the second recognition rate threshold, and the conversion relationship between the oil seal failure probability and the oil seal failure mark, etc., all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0028] Embodiment 1

[0029] Figure 1This is a flow chart of an oil seal fault prediction method provided in the first embodiment of the present invention. This embodiment can be applied to the case of predicting the fault of the clutch seal cover oil seal in the user's vehicle. The method can be executed by an oil seal fault prediction device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S101. Acquire target vehicle operation data of a target vehicle.

[0031] Among them, the target vehicle refers to the vehicle whose clutch seal cover oil seal needs to be predicted for fault. It should be noted that the number of target vehicles can be determined according to the needs of the demander. For example, if the demander needs to predict the oil seal failure of 200 target vehicles, the number of target vehicles is 200. The demander refers to the party who wants to know whether the clutch seal cover oil seal of the target vehicle will fail at a certain node in the future. The target vehicle operation data refers to the vehicle operation data required for fault prediction of the clutch seal cover oil seal in the target vehicle; optionally, the target vehicle operation data includes the target vehicle identification, target operating mileage, and the total number of oil seal revolutions of the target vehicle at different preset temperatures.

[0032] The target vehicle identifier is used to uniquely identify the target vehicle; optionally, the target vehicle identifier may be a vehicle identification number (VIN). The target mileage refers to the mileage preset by the demander. The preset temperature may be preset according to actual business needs, or may be determined according to the sampling frequency and sampling accuracy of the data, which is not specifically limited in the embodiments of the present invention. For each preset temperature, the total oil seal revolutions refers to the total number of times the clutch seal cover oil seal rotates at the preset temperature.

[0033] Specifically, the historical running mileage can be obtained from the historical vehicle running data of the target vehicle; the multiple relationship between the target running mileage and the historical running mileage can be determined; based on the multiple relationship, the target vehicle running data of the target vehicle can be determined according to the historical vehicle running data of the target vehicle. The historical vehicle running data of the target vehicle refers to the vehicle running data of the target vehicle so far. Accordingly, the historical running mileage refers to the total cumulative distance traveled by the target vehicle so far.

[0034] For example, if the historical vehicle operation data of the target vehicle is as follows: the target vehicle is identified as VIN2, the historical operation mileage is 83555 kilometers, the total oil seal revolutions when the oil temperature is less than 90 degrees Celsius are 115748 revolutions, the total oil seal revolutions when the oil temperature is 90 degrees Celsius are 5294 revolutions, and the total oil seal revolutions when the oil temperature is 91 degrees Celsius are 6864 revolutions; the target operation mileage of the target vehicle is 167110 kilometers. Through calculation, it can be known that the multiple relationship between the target mileage and the historical mileage is: the target mileage is twice the historical mileage; based on this multiple relationship, according to the historical vehicle operation data of the above-mentioned target vehicle, the target vehicle operation data of the target vehicle can be obtained by calculation as follows: the total oil seal revolutions when the oil temperature is less than 90 degrees Celsius are 115748*2=231496 revolutions, the total oil seal revolutions when the oil temperature is 90 degrees Celsius are 5294*2=10588 revolutions, and the total oil seal revolutions when the oil temperature is 91 degrees Celsius are 6864*2=13728 revolutions.

[0035] S102, inputting the target vehicle operation data into a target oil seal failure prediction model to obtain an oil seal failure prediction result corresponding to the target vehicle; wherein the target oil seal failure prediction model is obtained by training a Logistic regression model.

[0036] The logistic regression model is a linear regression model based on logistic function modeling, which is used to estimate the probability of an event based on a given independent variable data set. The oil seal fault prediction result refers to the result of fault prediction of the clutch seal cover oil seal in the target vehicle; optionally, the oil seal fault prediction result can be one of clutch seal cover oil seal fault and clutch seal cover oil seal normal.

[0037] Specifically, the target vehicle operation data is input into the target oil seal fault prediction model, and after being processed by the target oil seal fault prediction model, an oil seal fault prediction result corresponding to the target vehicle is obtained.

[0038] Optionally, in order to improve the data quality of the target vehicle operating data, before inputting the target vehicle operating data into the target oil seal failure prediction model to obtain the oil seal failure prediction result corresponding to the target vehicle, the acquired target vehicle operating data can be preprocessed, duplicate data in the target vehicle operating data can be deleted, data in the target vehicle operating data that exceeds the standard range can be cleared, and the empty values ​​in the target vehicle operating data can be filled using the adjacent point interpolation method.

[0039] The technical solution of the embodiment of the present invention obtains the target vehicle operation data of the target vehicle; inputs the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training the Logistic regression model. The above technical solution, based on the pre-trained oil seal fault prediction model (i.e., the target oil seal fault prediction model), accurately predicts the failure of the clutch seal cover oil seal in the target vehicle in advance according to the target vehicle operation data of the target vehicle, so as to facilitate the repair or replacement of the clutch seal cover oil seal in the target vehicle before the oil seal failure occurs, thereby avoiding the expansion of the fault, reducing the vehicle maintenance cost, and ensuring the reliability of the clutch seal cover oil seal in the vehicle, thereby increasing the service life of the clutch in the vehicle and ensuring the driving safety of the vehicle.

[0040] On the basis of the above-mentioned embodiment, as an optional method of the embodiment of the present invention, it is also possible to: after obtaining the target vehicle operation data of the target vehicle, determine the target oil seal failure probability of the clutch sealing cover oil seal in the target vehicle based on the target oil seal failure prediction model; based on the corresponding relationship between the oil seal failure probability and the oil seal failure risk level, determine the target failure risk level corresponding to the target vehicle according to the target oil seal failure probability; according to the target failure risk level corresponding to the target vehicle, push maintenance reminder information to the vehicle driver of the target vehicle to remind the vehicle driver of the target vehicle to promptly repair the clutch sealing cover oil seal in the target vehicle to ensure the reliability of the clutch sealing cover oil seal in the target vehicle.

[0041] The target oil seal failure probability refers to the probability of a clutch seal cover oil seal failure in the target vehicle. The target failure risk level refers to the oil seal failure risk level corresponding to the target oil seal failure probability.

[0042] For example, if the target oil seal failure probability of the clutch seal cover oil seal in target vehicle 1 is 0.8, the target oil seal failure probability of the clutch seal cover oil seal in target vehicle 2 is 0.6, and the target oil seal failure probability of the clutch seal cover oil seal in target vehicle 3 is 0.4; the corresponding relationship between the oil seal failure probability and the oil seal failure risk level is as follows: if the oil seal failure probability is in the range of (0.75,1], the oil seal failure risk level is high risk; if the oil seal failure probability is in the range of (0.5,0.75], the oil seal failure risk level is medium risk; if the oil seal failure probability is in the range of (0,0.5], the oil seal failure risk level is low risk. Based on the above oil seal failure probability and oil seal failure risk, etc. According to the correspondence between the levels, according to the target oil seal failure probability of 0.8 for the clutch sealing cover oil seal in the target vehicle 1, it can be determined that the target fault risk level corresponding to the target vehicle 1 is high risk, and a maintenance reminder message can be immediately sent to the vehicle driver of the target vehicle 1 by phone; similarly, it can be determined that the target fault risk level corresponding to the target vehicle 2 is medium risk, and a maintenance reminder message can be sent to the vehicle driver of the target vehicle 2 by text message to remind the vehicle driver of the target vehicle 2 to repair the clutch sealing cover oil seal in the target vehicle 2 as soon as possible when convenient; it can be determined that the target fault risk level corresponding to the target vehicle 3 is low risk, and no maintenance reminder message is pushed to the vehicle driver of the target vehicle 3.

[0043] Embodiment 2

[0044] Figure 2A This is a flow chart of a method for predicting oil seal failures provided in Example 2 of the present invention. Based on the above example, this example further optimizes "training the Logistic regression model" and provides an optional implementation scheme. It should be noted that for the parts not described in detail in the example of the present invention, reference can be made to the relevant descriptions of other examples. Figure 2A As shown, the method includes:

[0045] S201. Obtain historical vehicle operation data of each sample vehicle; wherein the historical vehicle operation data includes a sample vehicle identification, oil temperature, engine speed, sample operation mileage, and oil seal fault identification.

[0046] The sample vehicles refer to vehicles used to train the oil seal failure prediction model; optionally, the sample vehicles include vehicles with clutch seal cover oil seal failure and vehicles with normal clutch seal cover oil seal. It should be noted that the number of sample vehicles can be preset according to actual business needs or the experience of technicians in this field. For example, the number of sample vehicles can be 500, which is not specifically limited in the embodiment of the present invention.

[0047] The historical vehicle operation data of the sample vehicle refers to the vehicle operation data of the sample vehicle to date. The sample vehicle identification is used to uniquely identify the sample vehicle. The oil temperature refers to the temperature of the engine oil in the sample vehicle. The engine speed refers to the number of revolutions per minute of the engine crankshaft in the sample vehicle, in revolutions per minute (i.e., r / min). The sample operation mileage refers to the total distance traveled by the sample vehicle to date.

[0048] Among them, the oil seal fault mark refers to an mark used to reflect whether the clutch sealing cover oil seal in the vehicle is faulty. For example, the oil seal fault mark is 1, which indicates that the clutch sealing cover oil seal in the vehicle is faulty; the oil seal fault mark is 0, which indicates that the clutch sealing cover oil seal in the vehicle is normal.

[0049] Specifically, the historical vehicle operation data of each sample vehicle can be obtained from the user vehicle data platform, wherein the user vehicle data platform refers to a platform for storing and managing the vehicle operation data of the user vehicle.

[0050] S202: Determine the total number of oil seal revolutions of the sample vehicle at different preset temperatures according to the oil temperature and engine speed of the sample vehicle.

[0051] Specifically, for each preset temperature, the number of time intervals during which the oil temperature of the sample vehicle is equal to the preset temperature is determined; and the total number of oil seal revolutions of the sample vehicle at the preset temperature is determined based on the engine speed and the number of time intervals of the sample vehicle.

[0052] More specifically, for the preset temperature T i , the oil temperature of the statistical sample vehicles is equal to the preset temperature T i According to the engine speed and time interval of the sample vehicle, the following formula is used to determine the sample vehicle at the preset temperature T i Total oil seal revolutions under:

[0053]

[0054] Among them, N i Indicates that the sample vehicle is at a preset temperature T i The total number of oil seal revolutions under the condition, i represents the i-th preset temperature, m represents the time interval, Δt j represents the jth time interval, j=1,…,m; n(t) represents the engine speed of the sample vehicle at time t.

[0055] For example, if the first preset temperature is 90 degrees Celsius (i.e., 90°C), the number of time intervals when the oil temperature of the sample vehicle 1 is equal to 90°C is 4, namely Δt1, Δt2, Δt3, and Δt4, then the total number of oil seal revolutions of the sample vehicle 1 at 90°C is:

[0056]

[0057] The curve of the engine speed n(t) of the sample vehicle 1 changing with time is shown in Fig. Figure 2B .

[0058] S203: Generate a training data set according to the sample running mileage and oil seal fault identification of each sample vehicle, and the total oil seal revolutions of each sample vehicle at different preset temperatures.

[0059] The training data set refers to a data set used to train an oil seal fault prediction model; optionally, the training data set includes an oil seal fault data subset of a clutch seal cover oil seal fault and an oil seal normal data subset of a clutch seal cover oil seal normal.

[0060] Specifically, based on the training data set generation template, the sample running mileage and oil seal fault identification of each sample vehicle, and the total oil seal revolutions of each sample vehicle at different preset temperatures can be filled into the corresponding data position of the training data set generation template according to the data format specified in the training data set generation template to obtain the training data set. For example, the training data set can be expressed in the form of the following data table.

[0061] Table 1 Training dataset

[0062]

[0063] It should be noted that since the oil temperature below 90°C has a relatively small effect on the wear and aging of the clutch seal cover oil seal, in order to improve the calculation efficiency of subsequent model predictions, the total oil seal revolutions at each preset temperature below 90°C are summed to obtain the total oil seal revolutions at an oil temperature of 90°C.

[0064] S204: Train the Logistic regression model according to the training data set to obtain a target oil seal failure prediction model.

[0065] Among them, the basic form of the Logistic regression model is as follows:

[0066]

[0067] Where p(Y=1|x1,x2,…,x k ) means that given input x1,x2,…,x k The probability of outputting Y=1 when b0, b1,…, b k Represents the regression coefficient of the Logistic regression model.

[0068] Specifically, a regression training data set and a regression validation data set can be selected from the training data set; based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, the regression coefficient of the Logistic regression model is determined according to the total oil seal revolutions of each sample vehicle at different preset temperatures in the regression training data set and the oil seal failure identification corresponding to each sample vehicle; based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, the Logistic regression model is trained according to the regression validation data set and the regression coefficient to obtain a target oil seal failure prediction model.

[0069] The regression training data set refers to the data set used to train the Logistic regression model. The regression validation data set refers to the data set used to validate the Logistic regression model. It should be noted that the conversion relationship between the oil seal failure probability and the oil seal failure identification is pre-set, specifically including the following two sub-conversion relationships:

[0070]

[0071] Among them, p represents the oil seal failure probability, and η represents the oil seal failure indicator.

[0072] More specifically, a preset proportion of oil seal failure data can be randomly selected from the oil seal failure data subset in the training data set, and a preset proportion of oil seal normal data can be randomly selected from the oil seal normal data subset in the training data set to obtain a regression training data set composed of the selected oil seal failure data and oil seal normal data, and a data set composed of data in the training data set except the data in the regression training data set is used as a regression verification data set; wherein the preset proportion can be pre-set according to the experience of those skilled in the art, for example, the preset proportion can be 40%, which is not specifically limited in the embodiment of the present invention.

[0073] Afterwards, for each sample vehicle in the regression training data set, the total oil seal revolutions of the sample vehicle at different preset temperatures are used as the input x1, x2, …, x k ; where x k represents the total number of oil seal revolutions of the sample vehicle at the kth preset temperature, k represents the total number of preset temperatures, and k is a positive integer; based on the following sub-conversion relationship in the conversion relationship between the oil seal failure probability and the oil seal failure identification:

[0074]

[0075] The oil seal fault mark corresponding to the sample vehicle is converted into the oil seal fault probability corresponding to the sample vehicle. For example, if the oil seal fault mark corresponding to the sample vehicle is 1 (ie, η = 1), based on the above sub-conversion relationship, it can be obtained that the oil seal fault probability corresponding to the sample vehicle is 0.75 (ie, p = 0.75). In other words, p(Y = 1|x1, x2, …, x k )=0.75. Thus, we can get multiple k Unknown equations, solve these equations to get the regression coefficients of the Logistic regression model, that is, get b0, b1, ..., b k The specific value of .

[0076] Afterwards, based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, the prediction value of the oil seal failure identification corresponding to each sample vehicle in the regression verification data set is determined according to the regression verification data set and the regression coefficient; the faulty oil seal recognition rate and the non-faulty oil seal recognition rate are determined according to the oil seal failure identification and the oil seal failure identification prediction value corresponding to each sample vehicle in the regression verification data set; the Logistic regression model is trained according to the faulty oil seal recognition rate and the non-faulty oil seal recognition rate to obtain the target oil seal failure prediction model.

[0077] Among them, the oil seal fault identification prediction value refers to the oil seal fault identification determined by the Logistic regression model. The fault oil seal recognition rate is used to characterize the prediction accuracy of the Logistic regression model for the faulty clutch seal cover oil seal in the regression validation data set. Correspondingly, the non-fault oil seal recognition rate is used to characterize the prediction accuracy of the Logistic regression model for the normal clutch seal cover oil seal in the regression validation data set.

[0078] Specifically, for each sample vehicle in the regression validation data set, the total oil seal revolutions of the sample vehicle at different preset temperatures are used as the input x1, x2, …, x k ; Input the regression coefficient of the Logistic regression model into the Logistic regression model to obtain the oil seal failure probability corresponding to the sample vehicle; Based on the following sub-conversion relationship in the conversion relationship between the oil seal failure probability and the oil seal failure identification:

[0079]

[0080] The oil seal failure probability corresponding to the sample vehicle is converted into the predicted value of the oil seal failure identification corresponding to the sample vehicle. For example, if the oil seal failure probability corresponding to the sample vehicle is 0.3 (i.e., p=0.3), based on the above sub-conversion relationship, it can be obtained that the predicted value of the oil seal failure identification corresponding to the sample vehicle is 0 (i.e., η=0). Similarly, the predicted value of the oil seal failure identification corresponding to each sample vehicle in the regression verification data set can be obtained. Obtain the total number of faulty oil seals with an oil seal failure identification of 1 and the total number of non-faulty oil seals with an oil seal failure identification of 0 in the regression verification data set; and count the first statistical number of oil seal failure identifications and oil seal failure identification predicted values ​​corresponding to the sample vehicles in the regression verification data set, which are both 1, and count the second statistical number of oil seal failure identifications and oil seal failure identification predicted values ​​corresponding to the sample vehicles in the regression verification data set, which are both 0; according to the first statistical number and the total number of faulty oil seals, determine the faulty oil seal recognition rate by the following formula:

[0081]

[0082] Wherein, ρ1 represents the faulty oil seal recognition rate, a represents the first statistical quantity, and A represents the total number of faulty oil seals.

[0083] Afterwards, according to the second statistical number and the total number of non-faulty oil seals, the non-faulty oil seal recognition rate is determined by the following formula:

[0084]

[0085] Wherein, ρ2 represents the recognition rate of non-faulty oil seals, b represents the second statistical quantity, and B represents the total number of non-faulty oil seals.

[0086] Afterwards, if it is detected that the faulty oil seal recognition rate reaches the first recognition rate threshold, and the non-faulty oil seal recognition rate reaches the second recognition rate threshold, the training of the Logistic regression model is stopped, and the Logistic regression model after the training is stopped is used as the target oil seal fault prediction model; otherwise, the Logistic regression model is continued to be trained. Among them, the first recognition rate threshold and the second recognition rate threshold can be pre-set according to actual business needs, and the embodiment of the present invention does not specifically limit them. It should be noted that the first recognition rate threshold can be the same as the second recognition rate threshold, or it can be different from the second recognition rate threshold.

[0087] S205: Acquire target vehicle operation data of the target vehicle.

[0088] S206: Input the target vehicle operation data into the target oil seal failure prediction model to obtain the oil seal failure prediction result corresponding to the target vehicle.

[0089] The technical solution of the embodiment of the present invention is to obtain the historical vehicle operation data of each sample vehicle; wherein the historical vehicle operation data includes the sample vehicle identification, oil temperature, engine speed, sample operation mileage and oil seal fault identification; determine the total oil seal revolutions of the sample vehicle at different preset temperatures according to the oil temperature and engine speed of the sample vehicle; generate a training data set according to the sample operation mileage and oil seal fault identification of each sample vehicle, and the total oil seal revolutions of each sample vehicle at different preset temperatures; train a Logistic regression model according to the training data set to obtain a target oil seal fault prediction model; obtain the target vehicle operation data of the target vehicle; input the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle. The above technical scheme trains the Logistic regression model with the help of the historical vehicle operation data of the sample vehicles in the training data set and the total oil seal revolutions of the sample vehicles at different preset temperatures, so that the Logistic regression model can learn the complex relationship between the oil seal failure and these data, thereby making the oil seal failure prediction result of the obtained target oil seal failure prediction model more accurate, thereby realizing the accurate fault prediction of the clutch seal cover oil seal in the target vehicle, facilitating the repair or replacement of the clutch seal cover oil seal in the target vehicle before the oil seal failure occurs, thereby avoiding the expansion of the fault, reducing the vehicle maintenance cost, and ensuring the reliability of the clutch seal cover oil seal in the vehicle, thereby increasing the service life of the clutch in the vehicle and ensuring the driving safety of the vehicle.

[0090] Embodiment 3

[0091] Figure 3 This is a schematic diagram of the structure of an oil seal fault prediction device provided in the third embodiment of the present invention. This embodiment can be applied to the case of predicting the fault of the clutch seal cover oil seal in the user's vehicle. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 3 As shown, the device comprises:

[0092] The target vehicle operation data acquisition module 301 is used to acquire the target vehicle operation data of the target vehicle;

[0093] The oil seal fault prediction result determination module 302 is used to input the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training a Logistic regression model.

[0094] The technical solution of the embodiment of the present invention obtains the target vehicle operation data of the target vehicle; inputs the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training the Logistic regression model. The above technical solution, based on the pre-trained oil seal fault prediction model (i.e., the target oil seal fault prediction model), accurately predicts the failure of the clutch seal cover oil seal in the target vehicle in advance according to the target vehicle operation data of the target vehicle, so as to facilitate the repair or replacement of the clutch seal cover oil seal in the target vehicle before the oil seal failure occurs, thereby avoiding the expansion of the fault, reducing the vehicle maintenance cost, and ensuring the reliability of the clutch seal cover oil seal in the vehicle, thereby increasing the service life of the clutch in the vehicle and ensuring the driving safety of the vehicle.

[0095] Optionally, the device further includes a model training module, wherein the model training module includes:

[0096] A historical vehicle operation data acquisition unit is used to acquire the historical vehicle operation data of each sample vehicle; wherein the historical vehicle operation data includes the sample vehicle identification, oil temperature, engine speed, sample operation mileage and oil seal fault identification;

[0097] A total oil seal revolution number determination unit, used to determine the total oil seal revolution number of the sample vehicle at different preset temperatures according to the oil temperature and engine speed of the sample vehicle;

[0098] A training data set generating unit, used to generate a training data set according to the sample running mileage and oil seal fault identification of each sample vehicle, and the total number of oil seal revolutions of each sample vehicle at different preset temperatures;

[0099] The model training unit is used to train the Logistic regression model according to the training data set to obtain a target oil seal fault prediction model.

[0100] Optionally, a total oil seal revolution determination unit is used to:

[0101] For each preset temperature, determining the number of time intervals during which the oil temperature of the sample vehicle is equal to the preset temperature;

[0102] According to the engine speed and the time interval number of the sample vehicle, the total oil seal revolution number of the sample vehicle at the preset temperature is determined.

[0103] Optional, model training unit, including:

[0104] A regression data set selection subunit is used to select a regression training data set and a regression verification data set from the training data set;

[0105] A regression coefficient determination subunit, for determining the regression coefficient of the Logistic regression model based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, according to the total oil seal revolutions of each sample vehicle at different preset temperatures in the regression training data set and the oil seal failure identification corresponding to each sample vehicle;

[0106] The model training subunit is used to train the Logistic regression model based on the conversion relationship between the oil seal failure probability and the oil seal failure identification according to the regression verification data set and the regression coefficient to obtain the target oil seal failure prediction model.

[0107] Optional, model training subunit, specifically used to:

[0108] Based on the conversion relationship between the oil seal failure probability and the oil seal failure mark, the predicted value of the oil seal failure mark corresponding to each sample vehicle in the regression verification data set is determined according to the regression verification data set and the regression coefficient;

[0109] Determine the recognition rate of faulty oil seals and the recognition rate of non-faulty oil seals according to the oil seal fault identification and the predicted value of the oil seal fault identification corresponding to each sample vehicle in the regression validation data set;

[0110] According to the recognition rate of faulty oil seals and the recognition rate of non-faulty oil seals, the Logistic regression model is trained to obtain the target oil seal fault prediction model.

[0111] The oil seal failure prediction device provided in the embodiment of the present invention can execute the oil seal failure prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each oil seal failure prediction method.

[0112] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0113] Embodiment 4

[0114] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0115] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0117] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as an oil seal fault prediction method.

[0118] In some embodiments, the oil seal fault prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the oil seal fault prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the oil seal fault prediction method in any other appropriate manner (e.g., by means of firmware).

[0119] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0121] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0123] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0124] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0125] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0126] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting oil seal failure, characterized in that: include: Obtain target vehicle operation data of a target vehicle; The target vehicle operation data is input into a target oil seal failure prediction model to obtain an oil seal failure prediction result corresponding to the target vehicle; wherein the target oil seal failure prediction model is obtained by training a Logistic regression model.

2. The method according to claim 1, characterized in that The training process for training the Logistic Regression model is as follows: Acquire historical vehicle operation data of each sample vehicle; wherein the historical vehicle operation data includes sample vehicle identification, oil temperature, engine speed, sample operation mileage and oil seal fault identification; Determining the total number of oil seal revolutions of the sample vehicle at different preset temperatures according to the oil temperature and engine speed of the sample vehicle; Generate a training data set according to the sample running mileage and oil seal fault identification of each sample vehicle and the total number of oil seal revolutions of each sample vehicle at different preset temperatures; The Logistic regression model is trained according to the training data set to obtain a target oil seal failure prediction model.

3. The method according to claim 2, characterized in that Determining the total oil seal revolutions of the sample vehicle at different preset temperatures according to the oil temperature and engine speed of the sample vehicle includes: For each preset temperature, determining the number of time intervals during which the oil temperature of the sample vehicle is equal to the preset temperature; The total number of oil seal revolutions of the sample vehicle at the preset temperature is determined according to the engine speed of the sample vehicle and the time interval number.

4. The method according to claim 2, characterized in that: The method of training the Logistic regression model according to the training data set to obtain a target oil seal failure prediction model includes: Selecting a regression training data set and a regression verification data set from the training data set; Based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, the regression coefficient of the Logistic regression model is determined according to the total oil seal revolutions of each sample vehicle at different preset temperatures in the regression training data set and the oil seal failure identification corresponding to each sample vehicle; Based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, the Logistic regression model is trained according to the regression verification data set and the regression coefficient to obtain a target oil seal failure prediction model.

5. The method according to claim 4, characterized in that The conversion relationship between the oil seal failure probability and the oil seal failure identification is based on the regression validation data set and the regression coefficient, and the Logistic regression model is trained to obtain the target oil seal failure prediction model, including: Based on the conversion relationship between the oil seal failure probability and the oil seal failure identification, according to the regression validation data set and the regression coefficient, determine the oil seal failure identification prediction value corresponding to each sample vehicle in the regression validation data set; Determine a faulty oil seal recognition rate and a non-faulty oil seal recognition rate according to the oil seal fault identification and the predicted value of the oil seal fault identification corresponding to each sample vehicle in the regression validation data set; A Logistic regression model is trained according to the faulty oil seal recognition rate and the non-faulty oil seal recognition rate to obtain a target oil seal fault prediction model.

6. An oil seal failure prediction device, characterized in that: include: A target vehicle operation data acquisition module is used to acquire target vehicle operation data of a target vehicle; The oil seal fault prediction result determination module is used to input the target vehicle operation data into the target oil seal fault prediction model to obtain the oil seal fault prediction result corresponding to the target vehicle; wherein the target oil seal fault prediction model is obtained by training a Logistic regression model.

7. The device according to claim 6, characterized in that The device also includes a model training module, and the model training module includes: A historical vehicle operation data acquisition unit, used to acquire historical vehicle operation data of each sample vehicle; wherein the historical vehicle operation data includes sample vehicle identification, oil temperature, engine speed, sample operation mileage and oil seal fault identification; A total oil seal revolution number determination unit, used to determine the total oil seal revolution number of the sample vehicle at different preset temperatures according to the oil temperature and engine speed of the sample vehicle; A training data set generating unit, used to generate a training data set according to the sample running mileage and oil seal fault identification of each sample vehicle, and the total number of oil seal revolutions of each sample vehicle at different preset temperatures; The model training unit is used to train the Logistic regression model according to the training data set to obtain a target oil seal fault prediction model.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the oil seal failure prediction method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the oil seal failure prediction method according to any one of claims 1 to 5 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the oil seal failure prediction method according to any one of claims 1 to 5 is implemented.

Images