A method, device and equipment for online identification of abnormal gas stations and oil products

Abstract

The application discloses a method, device and equipment for identifying abnormal gas stations and oil products online, and relates to the field of fuel supervision. The method comprises the following steps: determining the position of an abnormal gas station according to the actual distance between a vehicle being refueled in a target area and a nearest registered gas station; comparing an actual fuel effect parameter with a predicted fuel effect parameter after determining that the vehicle is being refueled at the registered gas station; if the actual fuel consumption is greater than the predicted fuel consumption, or the actual emission concentration is greater than the predicted emission concentration, determining that the oil product refueled by the target vehicle at the registered gas station is an abnormal oil product; and if the actual purification efficiency is less than the predicted purification efficiency, re-predicting the fuel effect parameter, and determining that the oil product is an abnormal oil product when the deviation between the re-predicted purification efficiency and the average purification efficiency of the same vehicle type is less than or equal to the model error. The application can identify abnormal gas stations and fuel quality online and in real time.

Description

Technical Field

[0001] This application relates to the field of fuel regulation, and in particular to a method, apparatus, and equipment for online identification of gas stations and fuel anomalies. Background Technology

[0002] Currently, the main method for testing the quality of fuel at gas stations is manual spot checks, which is time-consuming and labor-intensive, lacks continuity and timeliness, and cannot control the quality of fuel in real time. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, and equipment for online identification of gas stations and fuel quality anomalies, which can identify abnormal gas stations and fuel quality online and in real time.

[0004] To achieve the above objectives, this application provides the following solution.

[0005] Firstly, this application provides a method for online identification of gas station and fuel quality anomalies, comprising: determining the distance deviation between the GPS location of a vehicle and the location of a registered gas station when the vehicle is refueling at a registered gas station within a target area; when the actual distance between a vehicle refueling in the target area and the nearest registered gas station is greater than the distance deviation, obtaining the location of the vehicle being refueled and determining it as the location of an abnormal gas station; when the actual distance is less than or equal to the distance deviation, selecting a target vehicle from all vehicles currently refueling at registered gas stations, and obtaining the actual vehicle condition and actual fuel efficiency parameters of the target vehicle after this refueling; the fuel efficiency parameters include fuel consumption, emission concentration of pollutants, and purification efficiency of pollutants; obtaining a fuel efficiency prediction model for vehicles of the same type as the target vehicle within the target area; inputting the actual vehicle condition into the fuel efficiency prediction model to predict the fuel efficiency parameters; when there is a deviation between the actual fuel efficiency parameters and the predicted fuel efficiency parameters for the same parameter that is greater than the model error of the trained machine learning model, making the following judgment:

[0006] If the actual fuel consumption in the fuel efficiency parameters is greater than the predicted fuel consumption in the fuel efficiency parameters, or if the actual emission concentration in the fuel efficiency parameters is greater than the predicted emission concentration in the fuel efficiency parameters, then the fuel used by the target vehicle at the registered gas station for this refueling is determined to be abnormal fuel.

[0007] If the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, then the fuel effect parameters are re-predicted using the fuel effect prediction model based on the current vehicle condition of the target vehicle. If the deviation between the purification efficiency in the re-predicted fuel effect parameters and the average purification efficiency of similar models in the target area is less than or equal to the model error, the fuel used by the target vehicle at the registered gas station is determined to be abnormal fuel.

[0008] In a second aspect, the present application provides an apparatus for online identification of abnormal gas stations and abnormal oil products, comprising: a distance deviation determination module, an abnormal gas station determination module, a target vehicle selection module, a prediction model acquisition module, a prediction module, a judgment module, an abnormal oil product first determination module, and an abnormal oil product second determination module.

[0009] The distance deviation determination module is configured to determine a distance deviation between a vehicle GPS positioning and an enrolled gas station positioning when the vehicle is refueling at an enrolled gas station in a target area. The abnormal gas station determination module is configured to obtain a refueling vehicle positioning and determine a position of an abnormal gas station when an actual distance between the refueling vehicle and a nearest enrolled gas station in the target area is greater than the distance deviation. The target vehicle selection module is configured to select a target vehicle from all vehicles currently refueling at the enrolled gas station and obtain actual vehicle conditions and actual fuel effect parameters after the target vehicle refuels when the actual distance is less than or equal to the distance deviation. The fuel effect parameters include fuel consumption, emission concentration of emission pollutants, and purification efficiency of emission pollutants. The prediction model acquisition module is configured to obtain a fuel effect prediction model of the same vehicle type as the target vehicle in the target area. The prediction module is configured to input the actual vehicle conditions into the fuel effect prediction model to predict the fuel effect parameters. The judgment module is configured to call the following modules when a deviation of a same parameter between the actual fuel effect parameters and the predicted fuel effect parameters is greater than a model error of a trained machine learning model:

[0010] The abnormal oil product first determination module is configured to determine that an oil product refueled by the target vehicle at the enrolled gas station is an abnormal oil product if the fuel consumption in the actual fuel effect parameters is greater than the fuel consumption in the predicted fuel effect parameters or the emission concentration in the actual fuel effect parameters is greater than the emission concentration in the predicted fuel effect parameters.

[0011] The abnormal oil product second determination module is configured to re-predict the fuel effect parameters using the fuel effect prediction model according to the current vehicle conditions of the target vehicle when the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters. The abnormal oil product second determination module is configured to determine that the oil product refueled by the target vehicle at the enrolled gas station is an abnormal oil product when a deviation between the purification efficiency in the re-predicted fuel effect parameters and an average purification efficiency of the same vehicle type in the target area is less than or equal to the model error.

[0012] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for online identification of abnormal gas stations and abnormal oil products.

[0013] According to the embodiments provided in the present application, the following technical effects are achieved.

[0014] The application provides a method, device and equipment for online identification of abnormal gas stations and oil products. The method comprises the following steps: monitoring the actual distance between a vehicle position and a nearest registered gas station, judging whether the vehicle is refueling at the registered gas station, and identifying an abnormal gas station; comparing and analyzing actual fuel effect parameters with predicted fuel effect parameters, judging whether the fuel consumption of the vehicle, the emission concentration of emission pollutants or the purification efficiency of emission pollutants is increased or decreased, and determining whether the oil product refueled by the target vehicle at the registered gas station is an abnormal oil product, so as to realize online and real-time identification of abnormal gas stations and fuel quality. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 A flowchart of a method for online identification of abnormal gas stations and oil products provided by an embodiment of the present application.

[0017] Figure 2 A principle diagram of a method for online identification of abnormal gas stations and oil products provided by an embodiment of the present application.

[0018] Figure 3 A functional module diagram of a device for online identification of abnormal gas stations and oil products provided by an embodiment of the present application.

[0019] Figure 4 A structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] The above purposes, features and advantages of the present application can be more obvious and easy to understand. The present application will be further described in detail below with reference to the drawings and specific embodiments.

[0022] In an exemplary embodiment, as shown in Figure 1As shown, a method for online identification of gas stations and abnormal oil products is provided, comprising steps 101 to 108.

[0023] Step 101: Determine the distance deviation between the GPS positioning of a vehicle and the positioning of a registered gas station when the vehicle is refueling at a registered gas station in a target area.

[0024] Step 102: When the actual distance between the vehicle being refueled and the nearest registered gas station is greater than the distance deviation, obtain the positioning of the vehicle being refueled and determine the location of the abnormal gas station.

[0025] Step 103: When the actual distance is less than or equal to the distance deviation, select a target vehicle from all vehicles being refueled at registered gas stations in the current time, and obtain the actual vehicle condition and actual fuel effect parameters after refueling. Fuel effect parameters include fuel consumption, emission concentration of emission pollutants, and purification efficiency of emission pollutants.

[0026] Step 104: Obtain a fuel effect prediction model for vehicles of the same type as the target vehicle in the target area.

[0027] Step 105: Input the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameters.

[0028] Step 106: When there is a deviation between the actual fuel effect parameters and the predicted fuel effect parameters greater than the model error of the trained machine learning model, the following judgment is made.

[0029] Step 107: If the fuel consumption in the actual fuel effect parameters is greater than the fuel consumption in the predicted fuel effect parameters, or the emission concentration in the actual fuel effect parameters is greater than the emission concentration in the predicted fuel effect parameters, it is determined that the oil product refueled by the target vehicle at the registered gas station is an abnormal oil product.

[0030] Step 108: If the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, the fuel effect parameters are re-predicted using the fuel effect prediction model based on the current vehicle condition of the target vehicle. When the deviation between the re-predicted purification efficiency and the average purification efficiency of vehicles of the same type in the target area is less than or equal to the model error, it is determined that the oil product refueled by the target vehicle at the registered gas station is an abnormal oil product.

[0031] Implementing the above steps 101 to 108 can perform online automatic identification, reduce personnel investment, and real-time control of oil product quality, making the identification of gas stations and fuel quality continuous and timely.

[0032] In another exemplary embodiment of this application, in step 101 above, the distance deviation between the vehicle's GPS positioning and the positioning of the registered gas stations is calculated by obtaining the names and locations (e.g., latitude, longitude, address, etc.) of the registered gas stations within the target area. The deviation determined by the distance deviation is approximately in the range of 0~ The latitude and longitude coordinates of the vehicle's GPS positioning must use the same coordinate system as the latitude and longitude information of the registered gas station locations.

[0033] In another exemplary embodiment of this application, the criterion for determining whether the vehicle is refueling, as mentioned in step 102 above, is: the vehicle's speed ( Figure 2 The vehicle speed (V) is zero, and the difference in fuel level between the vehicle's fuel tank and the previous moment is... Greater than zero. That is, when the vehicle stops and the fuel level in the tank rises, it is determined that the vehicle has been refueled.

[0034] In another exemplary embodiment of this application, when the actual distance between a vehicle refueling in the target area and the nearest registered gas station is less than or equal to the distance deviation, the nearest registered gas station is marked as the refueling point for this vehicle. The fuel tank level of the vehicle before this refueling is... The stable fuel level in the vehicle's fuel tank after this refueling is: The fuel tank arrived The time is The vehicles that meet the requirements at the registered gas stations will be eligible. The vehicle was selected as the target vehicle. At the same time... As the start of a data analysis cycle, the time until the next time the vehicle's fuel level rises. Deadline. Among them, This is the proportional threshold. The value can be 0.6, or other values.

[0035] In another exemplary embodiment of this application, step 104 described above may be replaced by steps 201 to 205.

[0036] Step 201: Obtain vehicle condition and fuel efficiency parameters for each vehicle type within the target area after refueling at registered gas stations, under historical constant speed driving conditions, and form a historical database for each vehicle type; the emission pollutants in the fuel efficiency parameters include multiple pollutants.

[0037] The vehicle conditions include: vehicle age and vehicle speed. The emission pollutants in the fuel effect parameters include: particulate matter, carbon monoxide and nitrogen oxides. Further, the emission pollutants in the fuel effect parameters can also include: hydrocarbons and black carbon. The emission concentration of the emission pollutants in the fuel effect parameters refers to the concentration of the emission pollutants before entering the exhaust treatment device (e.g. the exhaust purifier), and the fuel effect parameters can further include the concentration of the emission pollutants after entering the exhaust treatment device. The fuel effect parameters are exemplary fuel effect parameters under different working conditions.

[0038] The vehicle conditions and the fuel effect parameters are obtained when the vehicle is running at a constant speed, which can eliminate the uncertainty of the emissions during the starting and braking stages.

[0039] Step 202: Obtain a historical database of vehicles of the same type as the target vehicle in the target area.

[0040] Step 203: Form a data composed of the historical vehicle conditions, the historical emission concentration of any pollutant and the historical purification efficiency of any pollutant in the historical database of vehicles of the same type as the target vehicle, and take the historical vehicle conditions as the input and the historical emission concentration of any pollutant and the historical purification efficiency of any pollutant as the output, to form a historical database of vehicles of the same type as the target vehicle about each pollutant.

[0041] According to the pollutant type grouping, each data is represented as , , . is the first data, is the second data, is the nth data. , , The specific forms of

[0042] ;

[0043] ;

[0044] ...

[0045] .

[0046] wherein, , , are the vehicle types of the first data, the second data and the nth data, , , are the vehicle conditions of the first data, the second data and the nth data, , ​The vehicle age of the data, , , These are the first data entry, the second data entry, and the third data entry. The vehicle speed of the data, , , These are the first data entry, the second data entry, and the third data entry. The data shows the emission concentration of pollutants. , , These are the first data entry, the second data entry, and the third data entry. The concentration of pollutants emitted after entering the exhaust gas treatment device. , , These are the first data entry, the second data entry, and the third data entry. The purification efficiency of pollutants emitted by each data point.

[0047] Step 204: Based on the historical database of each pollutant for the same type of vehicle as the target vehicle, train the machine learning model using the gradient boosting tree algorithm to obtain a well-trained machine learning model for each pollutant for the same type of vehicle as the target vehicle.

[0048] The historical database is divided into a training set and a validation set. A supervised learning method is used to train a machine learning model to obtain a machine learning model with the minimum relative error for each pollutant.

[0049] Step 205: Combine the machine learning models trained on all pollutants for the same type of vehicle as the target vehicle with the fuel efficiency prediction model for the same type of vehicle as the target vehicle.

[0050] In another exemplary embodiment of this application, such as Figure 2 The diagram illustrates the principle of an online method for identifying gas station and fuel quality anomalies. When the deviation between the actual fuel performance parameter and the predicted fuel performance parameter for the same parameter is less than or equal to the model error, i.e. The system determined that the fuel used by the target vehicle at the registered gas station was normal. This refers to the value of one of the parameters in the actual fuel efficiency parameters. For the value of the same parameter in the predicted fuel efficiency parameters, This is the model error, also known as the minimum relative error of the model. It includes The situation.

[0051] In another example embodiment of the present application, when the deviation of the purification efficiency in the re-predicted fuel effect parameter from the average purification efficiency of the same type of vehicle in the target region is greater than the model error, it is determined that the exhaust purification device of the target vehicle is abnormal. The exhaust purification device abnormality is a problem of the automobile exhaust purifier itself, such as aging, damage, catalyst life, etc. For diesel trucks, when the deviation of the purification efficiency in the re-predicted fuel effect parameter from the average purification efficiency of the same type of vehicle in the target region is greater than the model error, it may also be caused by insufficient urea addition.

[0052] In another example embodiment of the present application, the step 108 is caused by abnormal oil products (fake oil products) to cause the purification efficiency to be low due to the blockage of the purifier or the poisoning of the catalyst.

[0053] In another example embodiment of the present application, the vehicle determined to be suspected of oil quality problems is associated with the gas station, and the gas station is taken as a unit to analyze the frequency and time regularity (daily, weekly, monthly changes, etc.) of suspected oil quality problems. After the step 108, the method can further include the following steps 301-304.

[0054] Step 301: Record the time when the oil product of the listed gas station is determined to be an abnormal oil product, and take the listed gas station whose oil product is determined to be an abnormal oil product as a suspicious gas station.

[0055] Step 302: According to the recorded time, the number of times that the oil product of each suspicious gas station is determined to be an abnormal oil product in a preset time range is counted.

[0056] Step 303: According to the descending order of the number of times, the suspicious gas stations are investigated in turn.

[0057] Step 304: The time period with the most number of times that the oil product of each suspicious gas station is determined to be an abnormal oil product is counted, and the time regularity of the sale of abnormal oil products by each suspicious gas station is determined.

[0058] By counting the frequency and key period of each gas station, the gas station can be suddenly inspected.

[0059] Based on the same inventive concept, the embodiments of the present application also provide an online identification of gas station and oil product abnormalities for implementing the online identification of gas station and oil product abnormalities. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more online identification of gas station and oil product abnormalities device embodiments provided below can be referred to the limitations of the online identification of gas station and oil product abnormalities method in the above, which will not be described here.

[0060] In one example embodiment, as Figure 3As shown, a device for online identification of abnormal gas stations and oil products is provided, comprising a distance deviation determination module, an abnormal gas station determination module, a target vehicle selection module, a prediction model acquisition module, a prediction module, a judgment module, an abnormal oil product first determination module, and an abnormal oil product second determination module.

[0061] The distance deviation determination module is configured to determine the distance deviation between the GPS positioning of a vehicle and the positioning of a registered gas station when the vehicle is refueling at the registered gas station in a target area. The abnormal gas station determination module is configured to obtain the positioning of a vehicle that is refueling when the actual distance between the vehicle and the nearest registered gas station is greater than the distance deviation, and determine the position of the abnormal gas station. The target vehicle selection module is configured to select a target vehicle from all vehicles that are refueling at the registered gas station in the target area when the actual distance is less than or equal to the distance deviation, and obtain the actual vehicle condition and actual fuel effect parameters after the target vehicle refuels; the fuel effect parameters include fuel consumption, emission concentration of emission pollutants, and purification efficiency of emission pollutants. The prediction model acquisition module is configured to obtain a fuel effect prediction model of the same type of vehicle as the target vehicle in the target area. The prediction module is configured to input the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameters. The judgment module is configured to call the following modules when the deviation of the same parameter between the actual fuel effect parameters and the predicted fuel effect parameters is greater than the model error of the trained machine learning model:

[0062] The abnormal oil product first determination module is configured to determine that the oil product refueled by the target vehicle at the registered gas station is abnormal if the fuel consumption in the actual fuel effect parameters is greater than the fuel consumption in the predicted fuel effect parameters, or the emission concentration in the actual fuel effect parameters is greater than the emission concentration in the predicted fuel effect parameters.

[0063] The abnormal oil product second determination module is configured to re-predict the fuel effect parameters using the fuel effect prediction model according to the current vehicle condition of the target vehicle if the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters; and determine that the oil product refueled by the target vehicle at the registered gas station is abnormal if the deviation between the purification efficiency in the re-predicted fuel effect parameters and the average purification efficiency of the same type of vehicle in the target area is less than or equal to the model error.

[0064] In an exemplary embodiment, a computer device, which can be a server or a terminal, is provided, and an internal structure diagram of the computer device can be as shown in Figure 4As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the location of the abnormal gas station and the abnormal oil product. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the terminal outside through the network connection. The computer program is executed by the processor to realize an online identification method of gas station and oil product anomaly.

[0065] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in each method embodiment described above.

[0066] The technical features of the above embodiments can be combined in any way. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0067] The principles and implementation modes of the present application are described by applying specific examples in this paper, and the above embodiment description is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method of online identification of abnormality in a fuel station and fuel, characterized in that, The method for identifying abnormal gas stations and oil products comprises the following steps: determining the distance deviation between the GPS positioning of a vehicle and the positioning of a listed gas station when the vehicle is refueling at the listed gas station in a target area; when the actual distance between the vehicle being refueled and the nearest listed gas station is greater than the distance deviation, obtaining the positioning of the vehicle being refueled and determining the position of the abnormal gas station; when the actual distance is less than or equal to the distance deviation, selecting a target vehicle from all vehicles being refueled at listed gas stations in the target area, and obtaining the actual vehicle condition and actual fuel effect parameters after the target vehicle is refueled; the fuel effect parameters include fuel consumption, emission concentration of emission pollutants, and purification efficiency of emission pollutants; obtaining a fuel effect prediction model of the same type of vehicle as the target vehicle in the target area; inputting the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameters; when the deviation of the same parameter between the actual fuel effect parameters and the predicted fuel effect parameters is greater than the model error of the trained machine learning model, the following judgment is made: if the fuel consumption in the actual fuel effect parameters is greater than the fuel consumption in the predicted fuel effect parameters, or the emission concentration in the actual fuel effect parameters is greater than the emission concentration in the predicted fuel effect parameters, it is determined that the oil product refueled by the target vehicle at the listed gas station is an abnormal oil product; if the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, the fuel effect parameters are re-predicted using the fuel effect prediction model according to the current vehicle condition of the target vehicle; when the deviation between the re-predicted purification efficiency and the average purification efficiency of the same type of vehicle in the target area is less than or equal to the model error, it is determined that the oil product refueled by the target vehicle at the listed gas station is an abnormal oil product; when the deviation between the re-predicted purification efficiency and the average purification efficiency of the same type of vehicle in the target area is greater than the model error, it is determined that the exhaust purification device of the target vehicle is abnormal; recording the time when the oil product of the listed gas station is determined to be an abnormal oil product, and regarding the listed gas station whose oil product is determined to be an abnormal oil product as a suspicious gas station; according to the recorded time, calculating the proportion of the number of times that the oil product of each suspicious gas station is determined to be an abnormal oil product within a preset time range; sequentially investigating the suspicious gas stations in descending order of the proportion of the number of times that the oil product of each suspicious gas station is determined to be an abnormal oil product; calculating the time period with the most number of times that the oil product of each suspicious gas station is determined to be an abnormal oil product, and determining the time regularity of the sale of abnormal oil products by each suspicious gas station; obtaining a fuel effect prediction model of the same type of vehicle as the target vehicle in the target area, specifically comprising: obtaining the vehicle condition and fuel effect parameters of each vehicle type after refueling at a listed gas station under historical uniform speed driving in the target area, and forming a historical database for each vehicle type; the emission pollutants in the fuel effect parameters include multiple pollutants; obtaining the historical database of the same type of vehicle as the target vehicle in the target area; The historical database of the same type of vehicle as the target vehicle is formed by combining the historical vehicle condition, the historical emission concentration of any pollutant, and the historical purification efficiency of any pollutant, and taking the historical vehicle condition as the input, the historical emission concentration of any pollutant and the historical purification efficiency of any pollutant as the output, to form the historical database of the same type of vehicle as the target vehicle about each pollutant; The machine learning model is trained by using the gradient boosting tree algorithm according to the historical database of the same type of vehicle as the target vehicle about each pollutant, to obtain the trained machine learning model of the same type of vehicle as the target vehicle about each pollutant; The trained machine learning models of the same type of vehicle as the target vehicle about all pollutants are used as the fuel effect prediction model of the same type of vehicle as the target vehicle.

2. The method of online identification of a fueling station and fuel anomalies of claim 1, wherein, The criterion for determining that the vehicle is being refueled is that the speed of the vehicle is zero, and the difference between the liquid level of the fuel tank at the next time and the liquid level of the fuel tank at the previous time is greater than zero.

3. The method of online identification of a fueling station and fuel anomalies of claim 1, wherein, The target vehicle is selected from all vehicles being refueled at the registered refueling station, which specifically includes: The vehicles currently refueling at the registered gas stations will meet the requirements. The vehicles were selected as target vehicles; among them, This refers to the fuel level in the vehicle's tank before this refueling. To maintain a stable fuel level in the vehicle's fuel tank after this refueling. This is the proportional threshold.

4. The method of online identification of a fueling station and fuel anomalies of claim 1, wherein, When the deviation of the same parameter in the actual fuel effect parameter and the predicted fuel effect parameter is less than or equal to the model error, it is determined that the oil product refueled by the target vehicle at the registered refueling station is normal.

5. The method of online identification of a fueling station and fuel anomalies of claim 1, wherein, The vehicle condition includes vehicle age and vehicle speed. The emission pollutants in the fuel effect parameter include particulate matter, carbon monoxide, and nitrogen oxides.

6. An apparatus for online identification of abnormality in a fueling station and fuel, characterized by, The device for online identification of abnormal refueling stations and oil products is used to identify the fuel quality of abnormal refueling stations and registered refueling stations, and the device for online identification of abnormal refueling stations and oil products includes: A distance deviation determination module is configured to determine the distance deviation between the GPS positioning of a vehicle and the positioning of a registered refueling station when the vehicle is being refueled at the registered refueling station in a target area. An abnormal refueling station determination module is configured to obtain the positioning of the vehicle being refueled when the actual distance between the vehicle being refueled and the nearest registered refueling station in the target area is greater than the distance deviation, and determine the position of the abnormal refueling station. A target vehicle selection module is configured to select the target vehicle from all vehicles being refueled at the registered refueling station when the actual distance is less than or equal to the distance deviation, and obtain the actual vehicle condition and the actual fuel effect parameter of the target vehicle after the current refueling. A prediction model acquisition module is configured to acquire the fuel effect prediction model of the same type of vehicle as the target vehicle in the target area. A prediction module is configured to input the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameter. A judgment module is configured to call the following modules when the deviation of the same parameter in the actual fuel effect parameter and the predicted fuel effect parameter is greater than the model error of the trained machine learning model: An abnormal oil product first determination module is configured to determine that the oil product refueled by the target vehicle at the registered refueling station is an abnormal oil product if the fuel consumption in the actual fuel effect parameter is greater than the fuel consumption in the predicted fuel effect parameter, or the emission concentration in the actual fuel effect parameter is greater than the emission concentration in the predicted fuel effect parameter. The abnormal oil product secondary determination module is configured to: if the purification efficiency in the actual fuel effect parameter is less than the purification efficiency in the predicted fuel effect parameter, then re-predicting the fuel effect parameter using the fuel effect prediction model according to the current vehicle condition of the target vehicle; if the deviation of the purification efficiency in the re-predicted fuel effect parameter from the average purification efficiency of the same type of vehicle in the target region is less than or equal to the model error, then determining that the oil product of the target vehicle at the registered refueling station for this time is an abnormal oil product; and if the deviation of the purification efficiency in the re-predicted fuel effect parameter from the average purification efficiency of the same type of vehicle in the target region is greater than the model error, then determining that the exhaust purification device of the target vehicle is abnormal. Recording the time when the oil product of the registered refueling station is determined to be an abnormal oil product, and taking the registered refueling station where the oil product is determined to be an abnormal oil product as a suspicious refueling station. According to the recorded time, the number of times that the oil product of each suspicious refueling station is determined to be an abnormal oil product within a preset time range is counted, and the proportion of the number of times is calculated. The suspicious refueling stations are sequentially investigated in descending order of the proportion of the number of times. The time period in which the number of times that the oil product of each suspicious refueling station is determined to be an abnormal oil product is the largest is counted, and the time rule for selling abnormal oil products by each suspicious refueling station is determined. The fuel effect prediction model of the same type of vehicle as the target vehicle in the target region is obtained, specifically including: In the target region, the vehicle condition and fuel effect parameter of each type of vehicle after refueling at the registered refueling station under historical uniform speed driving are obtained, and a historical database of each type of vehicle is formed; the emission pollutants in the fuel effect parameter include multiple pollutants. The fuel effect prediction model of the same type of vehicle as the target vehicle in the target region is obtained, specifically including: In the target region, the vehicle condition and fuel effect parameter of each type of vehicle after refueling at the registered refueling station under historical uniform speed driving are obtained, and a historical database of each type of vehicle is formed; the emission pollutants in the fuel effect parameter include multiple pollutants. The historical database of the same type of vehicle as the target vehicle in the target region is obtained. A piece of data is composed of the historical vehicle condition, the historical emission concentration of any type of pollutant, and the historical purification efficiency of any type of pollutant in the historical database of the same type of vehicle as the target vehicle, and the historical vehicle condition is taken as the input, and the historical emission concentration of any type of pollutant and the historical purification efficiency of any type of pollutant are taken as the output, to form the historical database of the same type of vehicle as the target vehicle about each type of pollutant. According to the historical database of the same type of vehicle as the target vehicle about each type of pollutant, a machine learning model is trained using a gradient boosting tree algorithm to obtain a trained machine learning model of the same type of vehicle as the target vehicle about each type of pollutant. The trained machine learning models of the same type of vehicle as the target vehicle about all types of pollutants are taken together as the fuel effect prediction model of the same type of vehicle as the target vehicle.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the online identification method of the refueling station and the abnormal oil product according to any one of claims 1-5.

Images