Method, device and equipment for identifying abnormity of gas station and oil product on line

Abstract

The invention discloses a method, a device and equipment for identifying abnormity of a gas station and oil products on line, and relates to the field of fuel oil supervision. The method comprises the steps that the position of an abnormal gas station is judged according to the actual distance between a refueling vehicle in a target area and the nearest gas station; comparing the actual fuel effect parameter with the predicted fuel effect parameter after determining that the vehicle is refueled in the gas station; if the actual oil consumption is larger than the predicted oil consumption or the actual emission concentration is larger than the predicted emission concentration, it is judged that the oil product refueled by the target vehicle at the present gas station is an abnormal oil product; if the actual purification efficiency is smaller than the predicted purification efficiency, the fuel oil effect parameters are predicted again, and when the deviation between the predicted purification efficiency and the average purification efficiency of the same type of vehicle is smaller than or equal to the model error, it is judged that the oil product is the abnormal oil product. According to the invention, the abnormal gas station and the fuel quality can be identified online in real time.

Description

Technical Field

[0001] This application relates to the field of fuel supervision, and particularly to a method, device, and equipment for online identification of abnormal gas stations and oil products. Background Art

[0003] Currently, the main method for detecting the fuel quality of gas stations is manual spot-check inspection, which is time-consuming and laborious, and does not have continuity and timeliness, so it is impossible to monitor the oil quality in real time. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, and equipment for online identification of abnormal gas stations and oil products, which can identify abnormal gas stations and fuel quality online and in real time.

[0005] To achieve the above purpose, the present application provides the following solutions.

[0006] In a first aspect, the present application provides a method for online identification of abnormal gas stations and oil products, including: determining the distance deviation between the vehicle GPS positioning and the positioning of the registered gas station when a vehicle in the target area refuels at a registered gas station; 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 positioning of the refueling vehicle 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 the vehicles currently refueling at the registered gas station, and obtaining the actual vehicle condition and actual fuel effect parameters of the target vehicle after this refueling; the fuel effect parameters include fuel consumption, emission concentration of pollutants, and purification efficiency of pollutants; obtaining a fuel effect prediction model for 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 there is a deviation greater than the model error of the trained machine learning model in the same parameter between the actual fuel effect parameters and the predicted fuel effect parameters, make the following judgments: 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 this time is an abnormal oil product.

[0007] If the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, re-predict the fuel effect parameters using the fuel effect prediction model according to the current vehicle condition of the target vehicle; when 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, it is determined that the oil product refueled by the target vehicle at the registered gas station this time is an abnormal oil product.

[0008] In a second aspect, the present application provides a device for online identification of abnormal gas stations and fuels, including: 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, a primary abnormal fuel determination module, and a secondary abnormal fuel determination module.

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

[0010] The secondary abnormal fuel determination module is used to, if the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, re-predict the fuel effect parameters using the fuel effect prediction model according to the current vehicle condition of the target vehicle; when the deviation between the purification efficiency in the re-predicted fuel effect parameters and the average purification efficiency of the same vehicle type in the target area is less than or equal to the model error, determine that the fuel of the target vehicle refueling at the registered gas station this time is abnormal fuel.

[0011] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the above method for online identification of abnormal gas stations and fuels.

[0012] According to the specific embodiments provided by the present application, the present application has the following technical effects.

[0013] The present application provides a method, device and equipment for online identification of abnormal gas stations and oil products. By monitoring the actual distance between the vehicle position and the nearest registered gas station, it is determined whether the refueling vehicle refuels at the registered gas station, and abnormal gas stations are identified; the actual fuel effect parameters are compared and analyzed with the predicted fuel effect parameters. By judging whether the fuel consumption of the vehicle increases, the emission concentration of pollutants increases, or the purification efficiency of pollutants decreases, it is determined whether the oil product refueled by the target vehicle at the registered gas station is an abnormal oil product, thereby realizing the online and real-time identification of abnormal gas stations and fuel quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a schematic flowchart of a method for online identification of abnormal gas stations and oil products provided by an embodiment of the present application.

[0016] Figure 2 It is a schematic diagram of the principle of a method for online identification of abnormal gas stations and oil products provided by an embodiment of the present application.

[0017] Figure 3 It is a schematic diagram of the functional modules of a device for online identification of abnormal gas stations and oil products provided by an embodiment of the present application.

[0018] Figure 4 It is a schematic diagram of the structure of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0020] To make the above objects, features and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0021] In an exemplary embodiment, as Figure 1As shown, a method for online identification of abnormal gas stations and oil products is provided, including the following steps 101 to 108.

[0022] Step 101: Determine the distance deviation between the vehicle GPS positioning and the registered gas station positioning when a vehicle in the target area refuels at a registered gas station.

[0023] Step 102: When the actual distance between the vehicle being refueled in the target area 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.

[0024] Step 103: When the actual distance is less than or equal to the distance deviation, select a target vehicle from all the vehicles currently refueling at the registered gas stations, and obtain the actual vehicle condition and actual fuel effect parameters of the target vehicle after this refueling; the fuel effect parameters include fuel consumption, emission concentration of pollutants, and purification efficiency of pollutants.

[0025] Step 104: Obtain the fuel effect prediction model of the same vehicle type as the target vehicle in the target area.

[0026] Step 105: Input the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameters.

[0027] Step 106: 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, make the following judgment.

[0028] 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, determine that the oil product of the target vehicle's refueling at the registered gas station this time is an abnormal oil product.

[0029] Step 108: If the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, re-predict the fuel effect parameters using the fuel effect prediction model according to the current vehicle condition of the target vehicle; when the deviation between the purification efficiency in the re-predicted fuel effect parameters and the average purification efficiency of the same vehicle type in the target area is less than or equal to the model error, determine that the oil product of the target vehicle's refueling at the registered gas station this time is an abnormal oil product.

[0030] Implementing the above steps 101 to 108 can perform online automatic identification, reduce personnel input, and conduct real-time control of the oil product quality, making the identification of gas stations and fuel quality continuous and timely.

[0031] In another exemplary embodiment of the present application, in the above step 101, by obtaining the names and locations (such as longitude and latitude, address, etc.) of the registered gas stations in the target area, the distance deviation between the vehicle GPS positioning and the registered gas station positioning is calculated. , the approximate range of the deviation determined by the distance deviation is 0 to . Among them, the longitude and latitude of the vehicle GPS positioning and the longitude and latitude information of the registered gas station location need to use the same coordinate system.

[0032] In another exemplary embodiment of the present application, the criterion for determining that the vehicle is refueling mentioned in the above step 102 is: the speed of the vehicle ( Figure 2 the vehicle speed V in ) is zero, and the liquid level difference of the vehicle fuel tank between the next moment and the previous moment

[0033] is greater than zero. That is, when the vehicle stops and the fuel tank liquid level rises, it is determined that the vehicle is refueling. , the height of the fuel tank liquid level before the vehicle refuels this time is , the stable liquid level height of the fuel tank after the vehicle refuels this time is , the moment when the fuel tank reaches is . The vehicles that meet among the vehicles refueling at the registered gas station will be selected as the target vehicles. At the same time, is used as the start of the data analysis period and ends at the time when the liquid level of the vehicle fuel tank rises again during the next refueling. Among them, is the proportional threshold,

[0034] In another exemplary embodiment of the present application, the above step 104 can be replaced by the following steps 201 to 205.

[0035] Step 201: Obtain the vehicle condition and fuel effect parameters of each vehicle model under historical uniform driving after refueling at the registered gas station in the target area, and form a historical database for each vehicle model; the emission pollutants in the fuel effect parameters include multiple pollutants.

[0036] The vehicle condition includes: 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 may also include: hydrocarbons and black carbon. The emission concentration of the emission pollutants in the fuel effect parameters refers to the concentration before the emission pollutants enter the tail gas treatment device (such as a tail gas purifier), and the fuel effect parameters may further include the concentration after the emission pollutants enter the tail gas treatment device. Exemplarily, the fuel effect parameters are the fuel effect parameters under different working conditions.

[0037] The vehicle condition and fuel effect parameters are obtained when the vehicle is traveling at a constant speed, and traveling at a constant speed can eliminate the uncertainty of emissions during the starting and braking stages.

[0038] Step 202: Obtain the historical database of vehicle models of the same type as the target vehicle in the target area.

[0039] Step 203: Combine the historical vehicle condition, the historical emission concentration of any one pollutant, and the historical purification efficiency of any one pollutant in the historical database of vehicle models of the same type as the target vehicle into one piece of data, and use the historical vehicle condition as the input, and the historical emission concentration of any one pollutant and the historical purification efficiency of any one pollutant as the output to form a historical database of vehicle models of the same type as the target vehicle for each pollutant.

[0040] Grouped by pollutant type, each piece of data is expressed as , , …, . is the first piece of data, is the second piece of data, is the th piece of data. , , …, The specific form of is as follows.

[0041] ; ; … .

[0042] Among them, , , are the vehicle models of the first piece of data, the second piece of data, and the th piece of data respectively, , , are the vehicle ages of the first piece of data, the second piece of data, and the th piece of data respectively, , , They are respectively the vehicle speeds of the first piece of data, the second piece of data, and the th piece of data, , , They are respectively the emission concentrations of the pollutants of the first piece of data, the second piece of data, and the th piece of data, , , They are respectively the concentrations of the pollutants of the first piece of data, the second piece of data, and the th piece of data after entering the tail gas treatment device, , , They are respectively the purification efficiencies of the pollutants of the first piece of data, the second piece of data, and the th piece of data.

[0043] Step 204: According to the historical database of the same type of vehicle as the target vehicle for each pollutant, use the gradient boosting tree algorithm to train a machine learning model to obtain a trained machine learning model for the same type of vehicle as the target vehicle for each pollutant.

[0044] Divide the historical database into a training set and a validation set, and use the supervised learning method to train the machine learning model to obtain a machine learning model with the minimum relative error for each pollutant.

[0045] Step 205: Take the trained machine learning models for all pollutants of the same type of vehicle as the target vehicle together as the fuel effect prediction model for the same type of vehicle as the target vehicle.

[0046] In another exemplary embodiment of the present application, as shown in Figure 2 the schematic diagram of the method for online identification of abnormal gas stations and oil products, when there is a deviation between the actual fuel effect parameter and the predicted fuel effect parameter for the same parameter less than or equal to the model error, that is , it is determined that the oil product for this refueling of the target vehicle at the registered gas station is normal. Among them, is the value of a parameter in the actual fuel effect parameter, is the value of the same parameter in the predicted fuel effect parameter, is the model error, which can also be called the minimum relative error of the model. includes the situation.

[0047] In another exemplary embodiment of the present application, when the deviation between the purification efficiency in the re-predicted fuel effect parameter 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 gas purification device of the target vehicle is abnormal. The abnormality of the exhaust gas purification device is a problem of the automotive exhaust gas purifier itself, such as aging, damage, catalyst life, etc. For diesel trucks, when the deviation between the purification efficiency in the re-predicted fuel effect parameter and the average purification efficiency of the same type of vehicle in the target area is greater than the model error, it may also be caused by insufficient urea addition.

[0048] In another exemplary embodiment of the present application, the above step 108 is due to abnormal oil products (fake and inferior oil products) causing the purifier to be blocked or the catalyst to be poisoned, resulting in a decrease in purification efficiency.

[0049] In another exemplary embodiment of the present application, vehicles determined to have suspected oil product quality problems are associated with gas stations. Taking gas stations as units, in order to analyze the frequency and time pattern (daily, weekly, monthly changes, etc.) of suspected oil product quality problems, after the above step 108, the method may further include the following steps 301 to 304.

[0050] Step 301: Record the time when the oil product of the registered gas station is determined to be abnormal, and use the registered gas station whose oil product is determined to be abnormal as a suspicious gas station.

[0051] Step 302: According to the recorded time, count the proportion of the number of times the oil product of each suspicious gas station is determined to be abnormal within a preset time range.

[0052] Step 303: Check the suspicious gas stations in descending order of the said proportion of the number of times.

[0053] Step 304: Count the time period with the most times that the oil product of each suspicious gas station is determined to be abnormal, and determine the time pattern of selling abnormal oil products for each suspicious gas station.

[0054] By counting the frequency and key time periods of each gas station, surprise inspections can be carried out on gas stations.

[0055] Based on the same inventive concept, the embodiment of the present application also provides an apparatus for online identification of abnormal gas stations and oil products for implementing the above-mentioned method for online identification of abnormal gas stations and oil products. The solution provided by this apparatus to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the apparatus for online identification of abnormal gas stations and oil products provided below can refer to the limitations on the method for online identification of abnormal gas stations and oil products in the above text, and will not be repeated here.

[0056] In an exemplary embodiment, such as Figure 3As shown, a device for online identification of abnormal gas stations and oil products includes: 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 primary determination module, and an abnormal oil product secondary determination module.

[0057] The distance deviation determination module is used to determine the distance deviation between the vehicle GPS positioning and the registered gas station positioning when a vehicle in the target area refuels at a registered gas station. The abnormal gas station determination module is used to obtain the positioning of the vehicle being refueled and determine the location of the abnormal gas station when the actual distance between the vehicle being refueled in the target area and the nearest registered gas station is greater than the distance deviation. The target vehicle selection module is used to select a target vehicle from all the vehicles currently refueling at registered gas stations when the actual distance is less than or equal to the distance deviation, and obtain the actual vehicle condition and actual fuel effect parameters of the target vehicle after this refueling; the fuel effect parameters include fuel consumption, emission concentration of pollutants, and purification efficiency of pollutants. The prediction model acquisition module is used to obtain the fuel effect prediction model of the same vehicle type as the target vehicle in the target area. The prediction module is used to input the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameters. The judgment module is used to call the following modules when there is a deviation of the same parameter between the actual fuel effect parameters and the predicted fuel effect parameters greater than the model error of the trained machine learning model: The abnormal oil product primary determination module is used to determine that the oil product of the target vehicle refueling at the registered gas station this time 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; The abnormal oil product secondary determination module is used 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; when the deviation between the purification efficiency in the re-predicted fuel effect parameters and the average purification efficiency of the same vehicle type in the target area is less than or equal to the model error, it is determined that the oil product of the target vehicle refueling at the registered gas station this time is an abnormal oil product.

[0058] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 4As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a 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 capabilities. 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 locations of abnormal gas stations and abnormal oil products. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it realizes a method for online identification of abnormal gas stations and oil products.

[0059] Those skilled in the art can understand that Figure 4 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are realized.

[0060] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0061] Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on this application.

Claims

1. A method for online identification of abnormal gas stations and oil products, characterized in that, Including: Determine the distance deviation between the vehicle GPS positioning and the registered gas station positioning when the vehicle in the target area refuels at the registered gas station; When the actual distance between the vehicle refueling in the target area and the nearest registered gas station is greater than the distance deviation, obtain the positioning of the refueling vehicle and determine the location of the abnormal gas station; When the actual distance is less than or equal to the distance deviation, select a target vehicle from all the vehicles currently refueling at the registered gas stations, and obtain the actual vehicle condition and actual fuel effect parameters of the target vehicle after this refueling; The fuel effect parameters include fuel consumption, emission concentration of pollutants, and purification efficiency of pollutants; Obtain the fuel effect prediction model of the same vehicle type as the target vehicle in the target area; Input the actual vehicle condition into the fuel effect prediction model to predict the fuel effect parameters; When there is a deviation between the same parameter in the actual fuel effect parameters and the predicted fuel effect parameters greater than the model error of the trained machine learning model, make the following judgment: 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 fuel of the target vehicle during this refueling at the registered gas station is abnormal fuel; If the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, re-predict the fuel effect parameters using the fuel effect prediction model according to the current vehicle condition of the target vehicle; When the deviation between the purification efficiency in the re-predicted fuel effect parameters and the average purification efficiency of the same vehicle type in the target area is less than or equal to the model error, it is determined that the fuel of the target vehicle during this refueling at the registered gas station is abnormal fuel.

2. The method for online identification of abnormal gas stations and oil products according to claim 1, characterized in that, The criterion for a vehicle being refueled is: the vehicle speed is zero, and the liquid level difference of the vehicle fuel tank between the next moment and the previous moment is greater than zero.

3. The method for online identification of abnormal gas stations and oil products according to claim 1, characterized in that, Selecting a target vehicle from all the vehicles currently refueling at the registered gas stations specifically includes: Among the vehicles being refueled at the registered gas stations, the vehicles that meet will be selected as target vehicles; where is the fuel tank liquid level height before this refueling of the vehicle, is the stable fuel tank liquid level height after this refueling of the vehicle, is the proportional threshold.

4. The method for online identification of abnormal gas stations and oil products according to claim 1, wherein Obtaining the fuel effect prediction model of the same vehicle type as the target vehicle in the target area specifically includes: In the target area, obtain the vehicle condition and fuel effect parameters of each vehicle type during historical uniform driving after refueling at the registered gas station, and form a historical database for each vehicle type; The pollutants in the fuel effect parameters include multiple pollutants; Obtain the historical database of the same vehicle type as the target vehicle in the target area; Form a piece of data by combining the historical vehicle condition, historical emission concentration of any pollutant, and historical purification efficiency of any pollutant in the historical database of the same vehicle type as the target vehicle, and use the historical vehicle condition 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 the same vehicle type as the target vehicle for each pollutant; According to the historical database of the same vehicle type as the target vehicle for each pollutant, use the gradient boosting tree algorithm to train the machine learning model to obtain the trained machine learning model of the same vehicle type as the target vehicle for each pollutant; A machine learning model trained on all pollutants for vehicle models of the same type as the target vehicle is used together as a fuel efficiency prediction model for vehicle models of the same type as the target vehicle.

5. The method for online identification of abnormal gas stations and oil products according to claim 1, wherein When the deviation of the same parameter between the actual fuel efficiency parameter and the predicted fuel efficiency parameter is less than or equal to the model error, it is determined that the fuel quality of the target vehicle's current refueling at the registered gas station is normal.

6. The method for online identification of abnormal gas stations and oil products according to claim 1, characterized in that When the deviation between the purification efficiency in the re-predicted fuel efficiency parameter and the average purification efficiency of vehicle models of the same type in the target area is greater than the model error, it is determined that the exhaust gas purification device of the target vehicle is abnormal.

7. The method for online identification of abnormal gas stations and oil products according to claim 1, wherein If the purification efficiency in the actual fuel efficiency parameter is less than the purification efficiency in the predicted fuel efficiency parameter, then according to the current vehicle condition of the target vehicle, the fuel efficiency prediction model is used to re-predict the fuel efficiency parameter; when the deviation between the purification efficiency in the re-predicted fuel efficiency parameter and the average purification efficiency of vehicle models of the same type in the target area is less than or equal to the model error, it is determined that the fuel quality of the target vehicle's current refueling at the registered gas station is abnormal fuel. After that, it further includes: Recording the time when the fuel quality of the registered gas station is determined to be abnormal fuel, and taking the registered gas station with the fuel quality determined to be abnormal fuel as a suspicious gas station; According to the recorded time, counting the proportion of the number of times the fuel quality of each suspicious gas station is determined to be abnormal fuel within a preset time range; Checking the suspicious gas stations in descending order of the said proportion of times; Counting the time period with the most number of times the fuel quality of each suspicious gas station is determined to be abnormal fuel, and determining the time pattern of selling abnormal fuel for each suspicious gas station.

8. The method for online identification of abnormal gas stations and oil products according to claim 1, characterized in that, The vehicle condition includes: vehicle age and vehicle speed; The emission pollutants in the fuel efficiency parameter include: particulate matter, carbon monoxide, and nitrogen oxides.

9. An apparatus for online identification of abnormal gas stations and oil products, characterized in that, It includes: A distance deviation determination module for determining the distance deviation between the vehicle GPS positioning and the registered gas station positioning when a vehicle in the target area refuels at a registered gas station; An abnormal gas station determination module for obtaining the positioning of the vehicle being refueled and determining the location of the abnormal gas station when the actual distance between the vehicle being refueled in the target area and the nearest registered gas station is greater than the distance deviation; A target vehicle selection module for, when the actual distance is less than or equal to the distance deviation, selecting a target vehicle from all the vehicles currently refueling at the registered gas station 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 emission pollutants, and purification efficiency of emission pollutants; A prediction model acquisition module for obtaining a fuel efficiency prediction model for vehicle models of the same type as the target vehicle in the target area; A prediction module for inputting the actual vehicle condition into the fuel efficiency prediction model to predict the fuel efficiency parameter; A judgment module for, when there is a deviation of the same parameter between the actual fuel efficiency parameter and the predicted fuel efficiency parameter greater than the model error of the trained machine learning model, calling the following modules: An abnormal oil product primary determination module, which is used to determine that the oil product of the target vehicle during this refueling at the registered 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; An abnormal oil product secondary determination module, which is used to, if the purification efficiency in the actual fuel effect parameters is less than the purification efficiency in the predicted fuel effect parameters, re-predict the fuel effect parameters according to the current vehicle condition of the target vehicle by using the fuel effect prediction model; and determine that the oil product of the target vehicle during this refueling at the registered gas station is an abnormal oil product when 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.

10. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for online identification of abnormal gas stations and oil products according to any one of claims 1-8.

Images