CN115452255A - Vehicle coolant leakage prediction method and device - Google Patents
Vehicle coolant leakage prediction method and device Download PDFInfo
- Publication number
- CN115452255A CN115452255A CN202211109979.7A CN202211109979A CN115452255A CN 115452255 A CN115452255 A CN 115452255A CN 202211109979 A CN202211109979 A CN 202211109979A CN 115452255 A CN115452255 A CN 115452255A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- cooling liquid
- highest temperature
- time period
- preset time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/002—Investigating fluid-tightness of structures by using thermal means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The application provides a vehicle coolant leakage prediction method and device, and relates to the field of vehicle coolant leakage prediction, the highest coolant temperature of a vehicle in a current preset time period is compared with the highest coolant temperature in a historical preset time period of the vehicle, if the highest coolant temperature in the current preset time period of the vehicle is higher than the highest coolant temperature in the historical preset time period of the vehicle, the increment of the highest coolant temperature of the vehicle is obtained, whether the increment of the highest temperature exceeds the preset change range of the highest coolant temperature is judged, and if the increment of the temperature exceeds the preset change range of the highest coolant temperature, coolant leakage information is prompted to a user. Therefore, through deep learning of the neural network model, vehicle complexity and vehicle cost do not need to be additionally increased, model training is carried out by using test vehicle data, vehicle fault problems are obtained in advance through recognition of the prediction model, timely intervention is carried out on early warning information, and vehicle using safety is guaranteed.
Description
Technical Field
The application relates to the technical field of vehicle coolant leakage prediction, in particular to a vehicle coolant leakage prediction method.
Background
With the continuous upgrading and updating of the automobile structure, the complexity of the automobile engine structure is continuously increased, the types and the number of faults of the engine are increased, the leakage fault of the engine coolant is high, and the engine fault can be caused under severe conditions, so that the vehicle loses power and cannot run. Therefore, how to detect the leakage of the engine coolant is an urgent problem to be solved.
In the prior art, two methods are generally adopted to detect the leakage of the engine coolant: the cooling liquid is added with an odor agent and an odor agent detection unit to detect the leakage of the cooling liquid, and if the leakage of the cooling liquid occurs, the leakage of the cooling liquid can be prompted through vision, hearing and smell; the highest temperature of the cooling liquid of the engine is monitored through an original temperature sensor of the vehicle body, if the temperature exceeds a set threshold value, a driver is reminded through sound and light information of the vehicle, and the cooling liquid is detected by the driver.
However, in the practical application process, the above scheme has the following problems, technical scheme 1: the addition of odorants and associated detection circuitry increases vehicle development costs; after the odorant is added, the performance of the coolant is influenced, and the overall heat management of the engine needs to be readjusted; if the coolant leaks, the bad smell can be caused to stay in the vehicle for a long time, and the riding experience is influenced. The technical scheme 2 is as follows: the temperature sensor can only acquire the current temperature information, set a threshold value to alarm, and cannot predict the leakage of a small amount of cooling liquid in advance; the highest temperature of the cooling liquid is related to the length and the strength of the running of the engine, and if the vehicle running time is short and the running distance is short, the detection cannot be effectively carried out even if the cooling liquid leaks.
There is therefore a need for a method that can predict leakage of vehicle coolant in a timely manner.
Disclosure of Invention
In view of this, embodiments of the present application provide a method and an apparatus for predicting a leakage of a vehicle coolant, which aim to know a leakage situation of the vehicle coolant in advance.
In a first aspect, an embodiment of the present application provides a method for predicting coolant leakage of a vehicle, where the method uses a neural network model to predict coolant leakage, and uses the prediction model to obtain a failure problem trend in advance, perform timely intervention, and ensure vehicle safety, and the method includes:
acquiring the highest temperature of the cooling liquid of the vehicle in the current preset time period;
comparing the highest temperature of the cooling liquid in the current preset time period with the highest temperature of the cooling liquid in the historical preset time period of the vehicle;
if the highest temperature of the cooling liquid in the current preset time period of the vehicle is higher than the highest temperature of the cooling liquid in the historical preset time period of the vehicle, acquiring the increment of the highest temperature of the cooling liquid of the vehicle, comparing the increment of the highest temperature with the relation between the driving mileage and the driving time of the vehicle, and judging whether the increment of the highest temperature exceeds the preset variation range of the highest temperature of the cooling liquid;
and if the temperature increment exceeds the preset variation range of the highest temperature of the cooling liquid, prompting the leakage information of the cooling liquid to a user.
Optionally, the determining whether the maximum temperature increase exceeds a preset variation range of the maximum temperature of the cooling liquid includes:
acquiring a preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle in the current preset time period, wherein the vehicle condition comprises the driving mileage and/or the driving time;
and comparing the maximum temperature increase with the preset variation range of the maximum temperature of the cooling liquid.
Optionally, the obtaining of the preset variation range of the highest temperature of the coolant according to the vehicle condition in the current preset time period of the vehicle includes:
the prediction model obtains the vehicle condition of the vehicle within the current preset time period and obtains the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle within the current preset time period;
the prediction model is obtained by training in the following way:
obtaining sample data, wherein the sample comprises historical vehicle connection data of vehicles with the supercooling liquid leakage fault and historical vehicle connection data of vehicles without the supercooling liquid leakage fault, and the historical vehicle connection data at least comprises the following steps: coolant temperature information, vehicle mileage, and/or vehicle travel time; cleaning the historical vehicle-associated data in the sample, and correcting and supplementing the cleaned historical vehicle-associated data to obtain a processed data sample;
and training the processed data sample to obtain the prediction model.
Optionally, the highest temperature of the coolant in the current preset time period is the highest temperature of the coolant in the preset time period in the current driving process of the vehicle, and the highest temperature of the coolant in the historical preset time period is the highest temperature of the coolant in the preset time period in the last driving process of the vehicle.
Optionally, the obtaining a maximum temperature of the cooling liquid of the vehicle in a current preset time period includes:
and monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time or detecting the highest temperature of the cooling liquid of the vehicle once every preset detection period.
Optionally, the outputting of the coolant leakage alarm information to the user includes: and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
In a second aspect, an embodiment of the present application provides a vehicle coolant leakage prediction apparatus, including:
the data acquisition module is used for acquiring the highest temperature of the cooling liquid of the vehicle in the current preset time period;
the data comparison module is used for comparing the highest temperature of the cooling liquid in the current preset time period with the highest temperature of the cooling liquid in the historical preset time period of the vehicle;
the data acquisition module is used for acquiring the increment of the highest temperature of the vehicle cooling liquid if the highest temperature of the cooling liquid in the current preset time period of the vehicle is higher than the highest temperature of the cooling liquid in the historical preset time period of the vehicle;
and the alarm module is used for outputting cooling liquid leakage alarm information to a user when the temperature increment exceeds the threshold value of the highest temperature range of the cooling liquid.
Optionally, the determining whether the maximum temperature increase exceeds a preset variation range of the maximum temperature of the cooling liquid includes:
acquiring a preset variation range of the highest temperature of the cooling liquid according to the vehicle condition in the current preset time period of the vehicle, wherein the vehicle condition comprises the driving mileage and/or the driving time;
and comparing the highest temperature increasing amount with the preset variation range of the highest temperature of the cooling liquid.
Optionally, the obtaining of the preset variation range of the highest temperature of the coolant according to the vehicle condition in the current preset time period of the vehicle includes:
the prediction model acquires the vehicle condition of the vehicle within the current preset time period and acquires the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle within the current preset time period;
the prediction model is obtained by training in the following way:
obtaining sample data, wherein the sample comprises historical vehicle connection data of vehicles with the supercooling liquid leakage faults and historical vehicle connection data of vehicles without the supercooling liquid leakage faults, and the historical vehicle connection data at least comprises the following steps: coolant temperature information, vehicle mileage, and/or vehicle travel time; cleaning the historical vehicle connection data in the sample, and correcting and supplementing the cleaned historical vehicle connection data to obtain a processed data sample;
and training the processed data sample to obtain the prediction model.
Optionally, the highest temperature of the coolant in the current preset time period is the highest temperature of the coolant in the preset time period in the current driving process of the vehicle, and the highest temperature of the coolant in the historical preset time period is the highest temperature of the coolant in the preset time period in the last driving process of the vehicle.
Optionally, the data acquisition module is further configured to:
and monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time or detecting the highest temperature of the cooling liquid of the vehicle once every preset period.
Optionally, the alarm module is further configured to:
and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
In a third aspect, an embodiment of the present application provides an apparatus, which includes a memory configured to store instructions or codes and a processor configured to execute the instructions or codes, so as to cause the apparatus to perform the vehicle coolant leakage prediction method according to any one of the foregoing first aspects.
In a fourth aspect, the present application provides a computer storage medium, in which code is stored, and when the code is executed, an apparatus executing the code implements the vehicle coolant leakage prediction method according to any one of the foregoing first aspects.
Compared with the prior art, the method has the following beneficial effects:
the embodiment of the application provides a vehicle coolant leakage prediction method. When the method is executed, the highest temperature of the cooling liquid of the vehicle in the current preset time period is firstly obtained, then the highest temperature of the cooling liquid of the vehicle in the current preset time period is compared with the highest temperature of the cooling liquid of the vehicle in the historical preset time period, if the highest temperature of the cooling liquid of the vehicle in the current preset time period is higher than the highest temperature of the cooling liquid of the vehicle in the historical preset time period, the increment of the highest temperature of the cooling liquid of the vehicle is obtained, whether the increment of the highest temperature exceeds the preset change range of the highest temperature of the cooling liquid is judged, and if the increment of the temperature exceeds the preset change range of the highest temperature of the cooling liquid, the leakage information of the cooling liquid is prompted to a user.
According to the method, the deep learning neural network technology is used, under the condition that no additional sensor is added, a cooling liquid leakage fault prediction model is established based on big data by using signals such as the highest temperature of cooling liquid and the like, so that the occurrence of the cooling liquid leakage fault is predicted, the complexity and the cost of a vehicle are not increased, model training is performed by using data of a test vehicle, and a model is deployed at the end of a carrier, so that the fault problem is obtained in advance through the recognition of the prediction model, timely intervention is performed on early warning information, and the vehicle using safety is guaranteed.
Drawings
To illustrate the technical solutions in the present embodiment or the prior art more clearly, the drawings needed to be used in the description of the embodiment or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting a coolant leakage of a vehicle according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a vehicle coolant leakage prediction apparatus according to an embodiment of the present application.
Detailed Description
Along with the increase of the automobile keeping quantity year by year, the complexity of the engine structure is increased, the fault types and the number of the engines are increased, wherein the leakage ratio of the engine coolant is high, and the engine is failed under severe conditions, so that the automobile loses power and cannot run.
In the prior art, the cooling liquid is detected by adding the odor agent and the odor agent detection unit in the cooling liquid, if the cooling liquid leaks, the cooling liquid can be prompted through vision, hearing and smell, but the method has some problems, and the development cost of a vehicle is increased by adding the odor agent and a related detection circuit; after the odorant is added, the performance of the coolant is influenced, and the overall thermal management of the engine needs to be readjusted; if the coolant leaks, the odor can stay in the vehicle for a long time, and the riding experience is influenced.
The other coolant leakage detection method is that the highest temperature of the coolant of the engine is monitored through an original temperature sensor of a vehicle body, if the temperature exceeds a set threshold, a driver is reminded through sound and light information of the vehicle, and the coolant is detected by the driver, in the method, the temperature sensor can only acquire current temperature information, the threshold is set for alarming, a small amount of coolant leakage cannot be predicted in advance, the highest temperature of the coolant is strongly related to the length of the engine in operation, if the vehicle using time is short, the driving distance is short, and even if the coolant leakage occurs, the coolant leakage cannot be effectively detected.
The inventor provides a technology for utilizing a deep learning neural network, under the condition of not additionally installing any additional sensor, a cooling liquid leakage fault prediction model is established based on big data by using signals such as the highest temperature of cooling liquid and the like to predict the occurrence of the cooling liquid leakage fault, the complexity and the cost of a vehicle are not increased, model training is carried out by utilizing test vehicle data, a model is deployed at the end of a carrier, the carrier comprises hardware which is not limited to a vehicle-end controller or a cloud server and can carry out data operation, and the leakage state of the cooling liquid of the vehicle is calculated.
The method provided by the embodiment of the application is executed by a trained neural network prediction model and used for predicting the leakage of the cooling liquid of the vehicle.
In order to make the technical solutions of the embodiments of the present application better understood, the technical solutions in the embodiments of the present application will be described below clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method of predicting a coolant leakage of a vehicle according to an embodiment of the present disclosure.
The method comprises the following specific steps:
s101: and acquiring the highest temperature of the cooling liquid of the vehicle in the current preset time period.
The method comprises the steps of collecting the highest temperature of the cooling liquid of the vehicle, namely collecting the highest temperature of the cooling liquid of the engine by using a Controller Area Network (CAN), inputting a trained neural network prediction model, comparing the model with a historical value of the highest temperature of the cooling liquid of the vehicle, and participating in calculation, wherein the historical value of the highest temperature of the cooling liquid of the vehicle is the historical value of the highest temperature of the cooling liquid when the condition that the cooling liquid leaks does not occur within one year of the vehicle.
It should be explained that the CAN bus is a multi-master bus, and the communication medium CAN be twisted pair, coaxial cable or optical fiber. The CAN protocol adopts communication data blocks for coding, replaces the traditional station address coding, and enables the number of nodes in the network to be theoretically unlimited. The CAN bus has stronger error correction capability and supports differential receiving and sending, so the CAN bus is suitable for a high-interference environment, the data transmission of the CAN bus is very fast, 32bytes of effective data CAN be transmitted every second, and the effectiveness and the accuracy of the data CAN be effectively ensured. A large number of wire harnesses are required to be embedded in an engine room and a car body of a traditional car to transmit signals collected by a sensor, the number of the wire harnesses in the car body CAN be greatly reduced by applying the CAN bus technology, and the possibility of fault occurrence is reduced by reducing the wire harnesses.
S102: and comparing the highest temperature of the cooling liquid in the current preset time period with the highest temperature of the cooling liquid in the historical preset time period of the vehicle.
The highest temperature of the cooling liquid in the current preset time period of the vehicle is compared with the highest temperature of the cooling liquid in the historical preset time period of the vehicle, the highest temperature is used for comparison, the process of comparing the non-highest temperatures can be omitted, if the current highest temperature of the cooling liquid exceeds the historical highest temperature of the cooling liquid, comparison of other data is not needed, therefore, the comparison process can be simplified, and the complexity is reduced.
S103: and if the highest temperature of the cooling liquid in the current preset time period of the vehicle is higher than the highest temperature of the cooling liquid in the historical preset time period of the vehicle, acquiring the increment of the highest temperature of the cooling liquid of the vehicle, and judging whether the increment of the highest temperature exceeds the preset variation range of the highest temperature of the cooling liquid.
When the highest coolant temperature of the vehicle is found to be out of the normal range, the maximum coolant temperature increase of the vehicle is obtained, it should be noted that in this embodiment, the vehicle-to-vehicle data of 32 vehicles in which a coolant leakage fault has occurred within one year and the vehicle-to-vehicle data of 48 vehicles in which a coolant leakage fault has not occurred within one year are extracted as a data sample set, basic data processing such as missing values, abnormal values, data type conversion is performed on the sample data, and certain cleaning and screening are performed according to rules of preliminary tests and analysis and observation. The maximum value of the highest temperature of the engine coolant is approximately fluctuated in a 95-105 range under the condition of normal operation of the vehicle, three ranges of the sample set 80 vehicles occur, namely, a part of the maximum value of the highest temperature of the vehicle coolant is fluctuated in a 95-98 range, a part of the maximum value of the highest temperature of the vehicle coolant is fluctuated in a 98-102 range, and a part of the maximum value of the highest temperature of the vehicle coolant is fluctuated in a 102-105 range, so that the maximum value of the highest temperature of the engine coolant is presumed to have a relation with the service life and the running kilometers of the vehicle; once a coolant leakage condition occurs in the use process of a vehicle, the maximum value of the highest temperature of the engine coolant can fluctuate abnormally and gradually becomes obvious along with the increasing of the leakage amount.
S104: and if the temperature increment exceeds the preset variation range of the highest temperature of the cooling liquid, prompting the leakage information of the cooling liquid to a user.
And comparing the increment of the highest temperature of the cooling liquid with a preset temperature range, and when the increment exceeds the threshold of the highest temperature range of the cooling liquid, indicating that the condition of leaking the cooling liquid is likely to happen, and outputting early warning information to a user.
In an implementation manner of this embodiment, the determining whether the maximum temperature increase amount exceeds a preset variation range of the maximum temperature of the cooling liquid includes:
acquiring a preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle in the current preset time period, wherein the vehicle condition comprises the driving mileage and/or the driving time; the vehicle conditions may also include vehicle speed range, engine speed, engine state, ambient temperature, and other parameters that affect coolant temperature.
And comparing the maximum temperature increase with the preset variation range of the maximum temperature of the cooling liquid. Because the coolant temperature of the vehicle under different driving mileage and different driving time can be different, the variation range is set according to the coolant temperature of the vehicle under different driving conditions, so that the temperature error caused by the vehicle condition information of the vehicle is reduced, and the misjudgment condition of the prediction result caused by the temperature error is further reduced.
The prediction model obtains the vehicle condition of the vehicle within the current preset time period and obtains the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle within the current preset time period; specifically, after the prediction model obtains the vehicle conditions in the current preset time period of the vehicle, the vehicle conditions in the historical preset time period are also obtained, then the difference between the vehicle conditions and the historical preset time period is calculated, and then the theoretical increment of the highest temperature of the cooling liquid is obtained according to the relation between the difference and the theoretical increment of the highest temperature of the cooling liquid, wherein the theoretical increment of the highest temperature of the cooling liquid is the preset variation range of the highest temperature of the cooling liquid. For example, after obtaining the mileage and/or the travel time of the vehicle in the current preset time period, the prediction model also obtains the mileage and/or the travel time in the historical preset time period, calculates to obtain the mileage increment and/or the travel time increment, and then obtains the theoretical coolant highest temperature increment according to the mileage increment and/or the travel time increment.
In one implementation manner of this embodiment, the obtaining the preset variation range of the maximum temperature of the cooling liquid according to the vehicle condition in the current preset time period of the vehicle includes: the prediction model obtains the vehicle condition of the vehicle within the current preset time period and obtains the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle within the current preset time period; the prediction model is obtained by training in the following way:
obtaining sample data, wherein the sample comprises historical vehicle connection data of vehicles with the supercooling liquid leakage faults and historical vehicle connection data of vehicles without the supercooling liquid leakage faults, and the historical vehicle connection data at least comprises the following steps: coolant temperature information, vehicle mileage, and/or vehicle travel time; cleaning the historical vehicle-associated data in the sample, and correcting and supplementing the cleaned historical vehicle-associated data to obtain a processed data sample;
and training the processed data sample to obtain the prediction model.
The establishing of the prediction model comprises the following steps: obtaining sample data, wherein the sample comprises historical vehicle connection data of vehicles with the supercooling liquid leakage faults and historical vehicle connection data of vehicles without the supercooling liquid leakage faults, and the vehicle connection data at least comprises: coolant maximum temperature information, engine state information, and engine speed information;
cleaning the vehicle connection data in the sample, and correcting and supplementing the cleaned vehicle connection data to obtain processed data;
and training the processed data sample to obtain the prediction model.
The process of model construction comprises:
the method comprises the following steps of performing test simulation, namely simulating engine coolant leakage faults by using a test vehicle, collecting CAN signal data under different coolant leakage quantities, preliminarily judging that the highest temperature of the engine coolant is greatly influenced by the coolant leakage quantity through visual observation and analysis, and representing the coolant leakage condition to a certain extent; meanwhile, the critical value of the coolant loss is determined to be between 1.8L and 2.0L, and the fault alarm is triggered when the critical value is exceeded.
And (4) preprocessing data, namely extracting the vehicle-connected data of 32 vehicles with the coolant leakage faults within one year and the vehicle-connected data of 48 vehicles without the coolant leakage faults within one year as data sample sets. And carrying out basic data processing such as missing value, abnormal value, data type conversion and the like on the sample data, and carrying out certain cleaning and screening according to the rules of early-stage tests and analysis observation.
And (3) designing a model, wherein an unsupervised anomaly detection algorithm is mainly used, a candidate algorithm is a self-coding neural network algorithm, an isolated forest algorithm, a local outlier factor algorithm and the like, certain monthly data in a normal state before the vehicle has a fault is extracted as a training set, and all data starting ten days before the fault point when the vehicle has a coolant leakage fault is extracted as a test set.
The vehicle-associated data of 32 vehicles in which a coolant leakage failure occurred within one year and the vehicle-associated data of 48 vehicles in which a coolant leakage failure did not occur within one year were extracted as data sample sets. And carrying out basic data processing such as missing value, abnormal value and data type conversion on the sample data, and carrying out certain cleaning and screening according to the rules of early-stage tests and analysis and observation.
Specifically, the method comprises the following steps:
the engine module collects information such as the temperature of cooling liquid of an engine, the state of the engine, the rotating speed of the engine and the like through the CAN and inputs the information into the prediction model to participate in calculation.
The ESP acquires vehicle speed information through the CAN, inputs the vehicle speed information into a prediction model to participate in calculation, the vehicle state transmission module acquires vehicle power-on information, vehicle travel mileage, vehicle travel time and the like through the CAN, inputs the vehicle speed information into the prediction model to participate in calculation, the data are acquired after 32 vehicles acquire coolant leakage data of different degrees, the acquired data are input as characteristics of the prediction model and are deployed on a server to perform model training, and the prediction model is generated.
After the training of the prediction model is finished, the prediction model is deployed at a carrier end (namely a vehicle machine), the abnormal leakage of the cooling liquid of the vehicle is monitored and evaluated in real time, and the abnormal leakage information of the cooling liquid is output.
It should be explained that, in machine learning, after data acquisition and data exploration are performed, a large number of abnormal values and missing values may exist in a data set, the abnormal data can be subjected to model training through data cleaning, a missing value processing method mainly comprises an elimination method and an interpolation method, while different methods exist for processing data under different conditions, (when the data volume is large and the missing condition is not serious, data containing missing value samples in the training set (namely rows containing missing values) can be directly deleted, a fixed value filling method can be adopted, for example, a '0' is directly used for filling missing values, a mean/median is used for filling, an adjacent value filling method is an improved scheme of fixed value filling, for example, filling of missing values is carried out by using values in front of or behind the missing positions, a model is used for predicting filling, and a filled regression model is obtained by obtaining samples without missing values and fitting the samples through the regression model, so that missing values are predicted.
Therefore, there are many ways to clean data in this embodiment, and the selection of which way to clean data is selectable by those skilled in the art according to actual situations, and the data cleaning method is not specifically limited in this embodiment.
In addition, after the prediction model is deployed at the carrier end, the prediction model can monitor and process the temperature of the engine coolant reported in real time in the steady-state driving process of the vehicle to obtain the highest temperature of the coolant, then judge whether the increment of the highest temperature of the coolant is abnormal or not, judge the equivalent information of the abnormal degree and the confidence coefficient, and carry out visual real-time early warning at the background monitoring end according to the abnormal level when the abnormal proportion of the increment of the highest temperature of the continuous coolant in a certain time period reaches a certain proportion.
In an implementation manner of this embodiment, the maximum temperature of the coolant in the current preset time period is the maximum temperature of the coolant in the preset time period in the current driving process of the vehicle, and the maximum temperature of the coolant in the historical preset time period is the maximum temperature of the coolant in the preset time period in the last driving process of the vehicle.
Because the coolant leakage is a slow leakage process, the condition that a large amount of coolant leakage rarely occurs suddenly in the driving process can be obtained, the prediction model can only obtain the highest coolant temperature in each driving process, and then the highest coolant temperature in the current driving process is compared with the highest coolant temperature in the previous driving process, so that the highest coolant temperature in multiple time periods does not need to be compared, under the condition of ensuring the accuracy of a judgment result, the data volume is effectively reduced, the judgment speed is improved, and the hardware requirement on the vehicle machine is reduced.
In one implementation manner of this embodiment, the detecting a current highest temperature of the coolant of the vehicle includes: monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time; or the highest temperature detection of the cooling liquid is carried out on the vehicle every preset period.
Monitoring and reporting the highest temperature of the engine coolant in real time in the steady-state running process of the vehicle, or predicting and evaluating reported signal data of the highest temperature of the engine coolant in the latest fixed period (such as half a month) of the vehicle every morning, judging the current abnormal degree, predicting the possible failure alarm date of the leakage of the engine coolant, and making a corresponding after-sale service strategy for implementation by support business personnel according to quantitative basis.
In one implementation manner of this embodiment, the outputting of the coolant leakage alarm information to the user includes: and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
When the prediction model predicts that the current vehicle is about to have a coolant leakage accident, coolant leakage alarm information is output to a user, wherein the mode of sending early warning to the user can be various, in the embodiment, only the alarm is output to a vehicle instrument panel to be displayed, so that the user can obtain a coolant leakage prompt at the first time, or the association between the alarm information and a certain APP of a user mobile phone is established in advance, the early warning information is directly sent to the user mobile phone, and therefore a vehicle owner can be reminded in time before the fault occurs.
The embodiment of the application provides a vehicle coolant leakage prediction method. When the method is executed, the highest temperature of the cooling liquid of the vehicle in the current preset time period is firstly obtained, then the highest temperature of the cooling liquid of the vehicle in the current preset time period is compared with the highest temperature of the cooling liquid of the vehicle in the historical preset time period, if the highest temperature of the cooling liquid of the vehicle in the current preset time period is higher than the highest temperature of the cooling liquid of the vehicle in the historical preset time period, the increment of the highest temperature of the cooling liquid of the vehicle is obtained, whether the increment of the highest temperature exceeds the preset change range of the highest temperature of the cooling liquid is judged, and if the increment of the temperature exceeds the preset change range of the highest temperature of the cooling liquid, the leakage information of the cooling liquid is prompted to a user. According to the method, a deep learning neural network technology is used, under the condition that no additional sensor is added, a cooling liquid leakage fault prediction model is established based on big data by using signals such as the highest temperature of the cooling liquid and the like, so that the occurrence of the cooling liquid leakage fault is predicted, the complexity and the cost of a vehicle are not increased, model training is performed by using data of a test vehicle, and a model is deployed at the end of a carrier, so that the fault problem is obtained in advance through the recognition of the prediction model, and timely intervention is performed aiming at early warning information, and the vehicle using safety is guaranteed.
Second embodiment
Referring to fig. 2, a structure of a vehicle coolant leakage prediction apparatus according to an embodiment of the present application is shown.
Referring to the schematic structural diagram of the vehicle coolant leakage prediction apparatus 200 shown in fig. 2, the apparatus 200 includes a data acquisition module 210, a data comparison module 220, a data acquisition module 230, and an alarm module 240.
The data acquisition module 210 is used for detecting the current highest temperature of the cooling liquid of the vehicle;
the data comparison module 220 is used for comparing the current highest temperature of the cooling liquid of the vehicle with the historical value of the highest temperature of the cooling liquid of the vehicle;
the data obtaining module 230 is configured to obtain an increment of the highest temperature of the vehicle coolant if the highest temperature of the coolant in the current preset time period of the vehicle is higher than the highest temperature of the coolant in the historical preset time period of the vehicle;
and the alarm module 240 is used for outputting coolant leakage alarm information to a user when the temperature increase exceeds the coolant highest temperature range threshold.
In an implementation manner of this embodiment, the data acquisition module 210 is further configured to:
and monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time or detecting the highest temperature of the cooling liquid of the vehicle once every preset period.
In an implementation manner of this embodiment, the alarm module 240 is further configured to:
and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
In an implementation manner of this embodiment, the determining whether the maximum temperature increase amount exceeds a preset variation range of the maximum temperature of the cooling liquid includes:
acquiring a preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle in the current preset time period, wherein the vehicle condition comprises the driving mileage and/or the driving time;
and comparing the maximum temperature increase with the preset variation range of the maximum temperature of the cooling liquid.
In one implementation manner of this embodiment, the obtaining the preset variation range of the maximum temperature of the cooling liquid according to the vehicle condition in the current preset time period of the vehicle includes:
the prediction model obtains the vehicle condition of the vehicle within the current preset time period and obtains the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle within the current preset time period;
the prediction model is obtained by training in the following way:
obtaining sample data, wherein the sample comprises historical vehicle connection data of vehicles with the supercooling liquid leakage faults and historical vehicle connection data of vehicles without the supercooling liquid leakage faults, and the historical vehicle connection data at least comprises the following steps: coolant temperature information, vehicle mileage, and/or vehicle travel time; cleaning the historical vehicle-associated data in the sample, and correcting and supplementing the cleaned historical vehicle-associated data to obtain a processed data sample;
and training the processed data sample to obtain the prediction model.
In an implementation manner of this embodiment, the maximum temperature of the coolant in the current preset time period is the maximum temperature of the coolant in the preset time period in the current driving process of the vehicle, and the maximum temperature of the coolant in the historical preset time period is the maximum temperature of the coolant in the preset time period in the last driving process of the vehicle.
In an implementation manner of this embodiment, the data acquisition module is further configured to:
and monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time or detecting the highest temperature of the cooling liquid of the vehicle once every preset period.
In an implementation manner of this embodiment, the alarm module is further configured to:
and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
To sum up, according to the method and the device for predicting the leakage of the cooling liquid of the vehicle provided by the embodiment of the application, when the method is executed, the highest temperature of the cooling liquid of the vehicle in the current preset time period is obtained, then the highest temperature of the cooling liquid of the vehicle in the current preset time period is compared with the highest temperature of the cooling liquid in the historical preset time period of the vehicle, if the highest temperature of the cooling liquid in the current preset time period of the vehicle is higher than the highest temperature of the cooling liquid in the historical preset time period of the vehicle, an increment of the highest temperature of the cooling liquid of the vehicle is obtained, whether the increment of the highest temperature of the cooling liquid of the vehicle exceeds a preset variation range of the highest temperature of the cooling liquid is judged, and if the increment of the temperature exceeds the preset variation range of the highest temperature of the cooling liquid, the leakage information of the cooling liquid is prompted to a user.
According to the method, the deep learning neural network technology is used, under the condition that no additional sensor is added, a cooling liquid leakage fault prediction model is established based on big data by using signals such as the highest temperature of cooling liquid and the like, so that the occurrence of the cooling liquid leakage fault is predicted, the complexity and the cost of a vehicle are not increased, model training is performed by using data of a test vehicle, and a model is deployed at the end of a carrier, so that the fault problem is obtained in advance through the recognition of the prediction model, timely intervention is performed on early warning information, and the vehicle using safety is guaranteed.
The embodiment of the application also provides corresponding equipment and a computer storage medium, which are used for realizing the scheme provided by the embodiment of the application.
Wherein the apparatus comprises a memory for storing instructions or code and a processor for executing the instructions or code to cause the apparatus to perform the method of any embodiment of the present application.
The computer storage medium has code stored therein that, when executed, causes an apparatus that executes the code to implement a method as described in any of the embodiments of the present application.
The embodiment of the application also provides corresponding equipment and a computer storage medium, which are used for realizing the scheme provided by the embodiment of the application.
Wherein the apparatus comprises a memory for storing instructions or code and a processor for executing the instructions or code to cause the apparatus to perform the method of any embodiment of the present application.
The computer storage medium has code stored therein that, when executed, causes an apparatus that executes the code to implement a method as described in any of the embodiments of the present application.
As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a general hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a read-only memory (ROM)/RAM, a magnetic disk, an optical disk, or the like, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the method according to the embodiments or some parts of the embodiments of the present application.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, the apparatus embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the description of the method embodiments for relevant points. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement without inventive effort.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element. It should be further noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the apparatus and device embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described embodiments of the apparatus and device are merely illustrative, and units described as separate parts may or may not be physically separate, and parts indicated as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A vehicle coolant leakage prediction method, characterized by comprising:
acquiring the highest temperature of the cooling liquid of the vehicle in the current preset time period;
comparing the highest temperature of the cooling liquid in the current preset time period with the highest temperature of the cooling liquid in the historical preset time period of the vehicle;
if the highest temperature of the cooling liquid in the current preset time period of the vehicle is higher than the highest temperature of the cooling liquid in the historical preset time period of the vehicle, acquiring the increment of the highest temperature of the cooling liquid of the vehicle, and judging whether the increment of the highest temperature exceeds the preset variation range of the highest temperature of the cooling liquid;
and if the temperature increment exceeds the preset variation range of the highest temperature of the cooling liquid, prompting the leakage information of the cooling liquid to a user.
2. The method of claim 1, wherein said determining whether the maximum temperature increase exceeds a preset variation range of the maximum temperature of the cooling fluid comprises:
acquiring a preset variation range of the highest temperature of the cooling liquid according to the vehicle condition in the current preset time period of the vehicle, wherein the vehicle condition comprises the driving mileage and/or the driving time;
and comparing the maximum temperature increase with the preset variation range of the maximum temperature of the cooling liquid.
3. The method of claim 2, wherein said obtaining the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition in the current preset time period of the vehicle comprises:
the prediction model obtains the vehicle condition of the vehicle within the current preset time period and obtains the preset variation range of the highest temperature of the cooling liquid according to the vehicle condition of the vehicle within the current preset time period;
the prediction model is obtained by training in the following way:
obtaining sample data, wherein the sample comprises historical vehicle connection data of vehicles with the supercooling liquid leakage faults and historical vehicle connection data of vehicles without the supercooling liquid leakage faults, and the historical vehicle connection data at least comprises the following steps: coolant temperature information, vehicle mileage, and/or vehicle travel time; cleaning the historical vehicle connection data in the sample, and correcting and supplementing the cleaned historical vehicle connection data to obtain a processed data sample;
and training the processed data sample to obtain the prediction model.
4. The method according to claim 1, wherein the maximum coolant temperature in the current preset time period is the maximum coolant temperature in the preset time period during the current driving of the vehicle, and the maximum coolant temperature in the historical preset time period is the maximum coolant temperature in the preset time period during the last driving of the vehicle.
5. The method of claim 1, wherein the obtaining of the maximum coolant temperature of the vehicle within the current preset time period comprises:
and monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time or detecting the highest temperature of the cooling liquid of the vehicle once every preset detection period.
6. The method of claim 1, wherein the outputting of the coolant leakage warning information to the user comprises:
and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
7. A vehicle coolant leakage prediction apparatus, characterized by comprising:
the data acquisition module is used for acquiring the highest temperature of the cooling liquid of the vehicle in the current preset time period;
the data comparison module is used for comparing the highest temperature of the cooling liquid in the current preset time period with the highest temperature of the cooling liquid in the historical preset time period of the vehicle;
the data acquisition module is used for acquiring the increment of the highest temperature of the vehicle cooling liquid if the highest temperature of the cooling liquid in the current preset time period of the vehicle is higher than the highest temperature of the cooling liquid in the historical preset time period of the vehicle;
and the alarm module is used for outputting cooling liquid leakage alarm information to a user when the temperature increment exceeds the threshold value of the highest temperature range of the cooling liquid.
8. The apparatus of claim 7, wherein the data acquisition module is further configured to:
and monitoring and detecting the highest temperature of the cooling liquid of the vehicle in real time or detecting the highest temperature of the cooling liquid of the vehicle once every preset period.
9. The apparatus of claim 7, wherein the alarm module is further configured to:
and sending the coolant leakage alarm information to a mobile phone of a user or displaying the coolant leakage alarm information on an instrument panel of the vehicle.
10. A computing device, the device comprising: a memory, a processor;
the memory for storing a computer program;
the processor, when executing the computer program, is configured to implement the steps of the method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211109979.7A CN115452255A (en) | 2022-09-13 | 2022-09-13 | Vehicle coolant leakage prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211109979.7A CN115452255A (en) | 2022-09-13 | 2022-09-13 | Vehicle coolant leakage prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115452255A true CN115452255A (en) | 2022-12-09 |
Family
ID=84303793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211109979.7A Pending CN115452255A (en) | 2022-09-13 | 2022-09-13 | Vehicle coolant leakage prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115452255A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117033063A (en) * | 2023-10-08 | 2023-11-10 | 浪潮(山东)计算机科技有限公司 | Server liquid leakage processing method, system, device, electronic equipment and medium |
| CN117134040A (en) * | 2023-10-27 | 2023-11-28 | 内蒙古中电储能技术有限公司 | Intelligent operation and maintenance method and device for liquid cooling energy storage system |
-
2022
- 2022-09-13 CN CN202211109979.7A patent/CN115452255A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117033063A (en) * | 2023-10-08 | 2023-11-10 | 浪潮(山东)计算机科技有限公司 | Server liquid leakage processing method, system, device, electronic equipment and medium |
| CN117033063B (en) * | 2023-10-08 | 2024-02-09 | 浪潮(山东)计算机科技有限公司 | Server liquid leakage processing method, system, device, electronic equipment and medium |
| CN117134040A (en) * | 2023-10-27 | 2023-11-28 | 内蒙古中电储能技术有限公司 | Intelligent operation and maintenance method and device for liquid cooling energy storage system |
| CN117134040B (en) * | 2023-10-27 | 2024-03-12 | 内蒙古中电储能技术有限公司 | Intelligent operation and maintenance method and device for liquid cooling energy storage system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115452255A (en) | Vehicle coolant leakage prediction method and device | |
| CN108418841B (en) | Next-generation key message infrastructure network Security Situation Awareness Systems based on AI | |
| CN109460010B (en) | Vehicle fault detection method and device based on knowledge graph and storage medium | |
| CN106650505A (en) | Vehicle attack detection method and device | |
| CN101783749B (en) | Network fault positioning method and device | |
| CN112319489B (en) | Driving behavior monitoring method, driving behavior monitoring system, server and storage medium | |
| CN113310647B (en) | Method and device for detecting leakage of battery pack, electronic equipment and storage medium | |
| CN111058926A (en) | Urea concentration stability detection method and device and post-processor controller | |
| CN109116830B (en) | Method and system for predicting fault | |
| CN107490479A (en) | Bearing residual life Forecasting Methodology and device | |
| CN111197517B (en) | Fault diagnosis method and device for urea tank, vehicle and storage medium | |
| CN113101734B (en) | Health assessment method, device and system for filter element and mechanical equipment | |
| CN113787914B (en) | Monitoring method and device of power battery, server and storage medium | |
| CN112558592A (en) | Vehicle fault prediction method and system and vehicle | |
| CN115766514A (en) | Full link quality monitoring method and device of Internet of vehicles, storage medium and vehicle | |
| CN111340975A (en) | Abnormal data feature extraction method, device, equipment and storage medium | |
| CN113868216B (en) | Block chain monitoring method and device | |
| CN116232851A (en) | Early warning method and device for network abnormality, electronic equipment and storage medium | |
| CN112699490A (en) | Vehicle maintenance result verification method and device | |
| CN111965609A (en) | Radar reliability evaluation method and device, electronic equipment and readable storage medium | |
| CN111563319B (en) | Risk health degree calculation method for typical function structure | |
| CN115396749A (en) | Intelligent cable fault monitoring device | |
| CN116819025B (en) | Water quality monitoring system and method based on Internet of things | |
| CN116880442B (en) | Fault diagnosis method, device, electronic equipment and storage medium | |
| CN115200869A (en) | Method and device for evaluating state of engine system |
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 |