Vehicle oil level monitoring and compensation model updating method, system, equipment and medium

Abstract

The embodiment of the invention discloses a vehicle oil level monitoring and compensation model updating method, system and device and a medium, the method is applied to an oil level monitoring repeater, and the method mainly comprises the steps that oil tank temperature monitoring data, oil level pressure difference monitoring data and operation state monitoring data of a vehicle are obtained in real time and input into a pre-trained oil level compensation model; the oil level compensation model comprises a temperature compensation sub-model and a vibration compensation sub-model; based on the real-time oil tank temperature data and the oil level pressure difference monitoring data, a real-time temperature compensation value of the oil level pressure difference is obtained through a temperature compensation sub-model; and obtaining a vehicle oil level monitoring result through the vibration compensation sub-model based on the real-time temperature compensation value and the operation state monitoring data. The embodiment of the invention can reduce the monitoring error of oil level monitoring.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, system, device and medium for vehicle oil level monitoring and compensation model updating. Background Technology

[0002] Existing technologies for monitoring fuel levels in vehicle fuel tanks primarily rely on float-type, capacitive, or pressure sensors. However, fuel level monitoring methods based on float-type, capacitive, or pressure sensors are greatly affected by the vehicle's operating conditions. Furthermore, changes in ambient temperature can cause variations in medium density and sensor zero drift and temperature drift, resulting in relatively large errors in the monitoring results obtained by existing fuel level monitoring methods. Summary of the Invention

[0003] This invention provides a method, system, device, and medium for vehicle oil level monitoring and compensation model updating, which can reduce monitoring errors in oil level monitoring.

[0004] In a first aspect, embodiments of the present invention provide a vehicle fuel level monitoring method, applied to a fuel level monitoring repeater, comprising:

[0005] Real-time acquisition and input of vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data into a pre-trained fuel level compensation model, which includes a temperature compensation sub-model and a vibration compensation sub-model;

[0006] Based on real-time tank temperature data and oil level differential pressure monitoring data, the real-time temperature compensation value of oil level differential pressure is obtained through a temperature compensation sub-model.

[0007] The vehicle oil level monitoring results are obtained through a vibration compensation sub-model based on real-time temperature compensation values ​​and operating status monitoring data.

[0008] Secondly, embodiments of the present invention provide an oil level compensation model update method, applied to an oil level monitoring cloud platform, comprising:

[0009] The system acquires vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and vehicle fuel level monitoring results from the repeater.

[0010] The estimated fuel quantity error is determined based on the vehicle fuel level monitoring results. When the estimated fuel quantity error exceeds the error threshold, the fuel level compensation model is retrained based on the vehicle's fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and the vehicle fuel level monitoring results.

[0011] The latest model parameters obtained by retraining the oil level compensation model are sent to the repeater to update the model parameters of the oil level compensation model in the repeater.

[0012] Thirdly, embodiments of the present invention also provide a vehicle fuel level monitoring system, including a fuel level monitoring repeater, which is used to execute the vehicle fuel level monitoring method applied to the fuel level monitoring repeater in embodiments of the present invention. The fuel level monitoring repeater includes:

[0013] The monitoring data acquisition and input module is used to acquire and input the vehicle's fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data in real time into a pre-trained fuel level compensation model. The fuel level compensation model includes a temperature compensation sub-model and a vibration compensation sub-model.

[0014] The real-time temperature compensation value acquisition module is used to obtain the real-time temperature compensation value of the oil level pressure difference based on real-time tank temperature data and oil level pressure difference monitoring data through a temperature compensation sub-model; and

[0015] The vehicle oil level monitoring result acquisition module is used to obtain the vehicle oil level monitoring result based on the real-time temperature compensation value and operating status monitoring data through a vibration compensation sub-model.

[0016] Fourthly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the vehicle oil level monitoring method or the oil level compensation model update method as described in any of the embodiments of the present invention.

[0017] Fifthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle oil level monitoring method or the oil level compensation model update method as described in any of the embodiments of the present invention.

[0018] This invention provides a vehicle oil level monitoring, compensation model update method, system, device, and medium. It acquires and inputs real-time vehicle fuel tank temperature monitoring data, oil level differential pressure monitoring data, and operating status monitoring data into a pre-trained oil level compensation model. Then, based on the real-time fuel tank temperature data and oil level differential pressure monitoring data, a temperature compensation sub-model obtains the real-time temperature compensation value of the oil level differential pressure. Further, based on the real-time temperature compensation value and operating status monitoring data, a vibration compensation sub-model obtains the vehicle oil level monitoring result. This method can accurately compensate for measurement deviations in oil level differential pressure caused by changes in ambient temperature and vehicle operating status, thereby obtaining an accurate oil level differential pressure value. This reduces monitoring errors during oil level monitoring and yields more accurate vehicle oil level monitoring results. Attached Figure Description

[0019] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart of a vehicle oil level monitoring method provided in an embodiment of the present invention;

[0021] Figure 2 This is another schematic flowchart of the vehicle oil level monitoring method provided in this embodiment of the invention;

[0022] Figure 3 This is another schematic flowchart of the vehicle oil level monitoring method provided in this embodiment of the invention;

[0023] Figure 4 This is another schematic flowchart of the vehicle oil level monitoring method provided in this embodiment of the invention;

[0024] Figure 5 This is another schematic flowchart of the vehicle oil level monitoring method provided in this embodiment of the invention;

[0025] Figure 6 This is a schematic diagram of a vehicle oil level monitoring system provided in an embodiment of the present invention;

[0026] Figure 7 This is another structural schematic diagram of the vehicle fuel level monitoring system provided in this embodiment of the invention.

[0027] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Figure 1 This is a flowchart illustrating a vehicle fuel level monitoring method provided in an embodiment of the present invention. The method can be applied to a fuel level monitoring repeater, which can be implemented using software and / or hardware. In a specific embodiment, the device can be integrated into an electronic device, such as a computer or server. The following embodiments will illustrate this using the integration of the device into an electronic device as an example. (Reference) Figure 1 The method may specifically include the following steps:

[0031] Step 101: Real-time acquisition and input of vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data into a pre-trained fuel level compensation model. The fuel level compensation model includes a temperature compensation sub-model and a vibration compensation sub-model. This step enables accurate compensation for measurement deviations in fuel level differential pressure caused by changes in ambient temperature and vehicle operating status through the fuel level compensation model.

[0032] Specifically, the above oil level pressure difference monitoring data can be understood as: the quantitative result of the difference between the static pressure of the oil in the tank and the ambient atmospheric pressure.

[0033] Specifically, data on oil tank temperature monitoring, oil level differential pressure monitoring, and operating status monitoring can be acquired through slave devices including temperature sensors, pressure sensors, and six-axis sensors.

[0034] Specifically, the pressure sensor mentioned above can be a dual absolute pressure sensor, and the two absolute pressure measuring units of the dual absolute pressure sensor can be installed at the bottom and top of the oil tank, respectively.

[0035] Specifically, the aforementioned pressure sensor may also include two independent absolute pressure sensors.

[0036] Specifically, the temperature sensor can be placed next to the pressure sensor or integrated into the pressure sensor.

[0037] Specifically, the aforementioned operational status monitoring data may include acceleration monitoring data and / or angular velocity monitoring data.

[0038] Optionally, the acceleration monitoring data mentioned above includes the vehicle's three-axis acceleration monitoring data.

[0039] Optionally, the aforementioned angular velocity monitoring data includes the vehicle's roll angular velocity monitoring data and pitch angular velocity monitoring data.

[0040] Specifically, the process of acquiring and storing the vehicle's fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data in real time may include: acquiring temperature sensor output data and preprocessing the temperature sensor output data to obtain the aforementioned fuel tank temperature monitoring data; acquiring pressure sensor output data and preprocessing the pressure sensor data to obtain preprocessed pressure sensor data, and then calculating the aforementioned fuel level differential pressure monitoring data based on the preprocessed pressure sensor data; and acquiring six-axis sensor output data and preprocessing the six-axis sensor output data to obtain the aforementioned operating status monitoring data.

[0041] Specifically, the process of preprocessing the output data of the temperature sensor, the pressure sensor, or the six-axis sensor may include: noise elimination, error correction, and / or data format conversion and normalization of the corresponding data.

[0042] Specifically, before step 101, the latest model parameters can be obtained from the oil level monitoring cloud platform, and the oil level compensation model can be updated using the latest model parameters.

[0043] Specifically, the latest model parameters can be obtained from the oil level monitoring cloud platform through a smart network terminal (T-Box).

[0044] Specifically, the oil level compensation model can be trained and updated on a cloud platform. This allows for complex training in the cloud and lightweight inference at the edge, which helps to achieve the best balance between computing power and power consumption.

[0045] Specifically, when training and updating the oil level compensation model, the sub-models of the oil level compensation model can be trained jointly, or the differential pressure compensation model can be trained separately.

[0046] Understandably, by optimizing parameters through cloud collaboration, complex training can be performed in the cloud and lightweight inference can be performed at the edge, achieving the best balance between computing power and power consumption. At the same time, optimization experience can be accumulated quickly, and customized parameters can be provided for different vehicle models, fuel tanks, and usage environments. Moreover, the system can continuously perform self-diagnosis and self-optimization, constantly improving the fuel level monitoring accuracy under various conditions.

[0047] Step 102: Based on real-time tank temperature data and oil level pressure difference monitoring data, obtain the real-time temperature compensation value of the oil level pressure difference through a temperature compensation sub-model. This step can accurately compensate for the measurement deviation of the oil level pressure difference caused by changes in ambient temperature.

[0048] Specifically, the temperature compensation sub-model mentioned above can be a back propagation (BP) neural network model, or it can be other types of neural network models, such as convolutional neural networks.

[0049] Specifically, the temperature compensation sub-model mentioned above can be trained based on the sample data corresponding to the temperature compensation sub-model. The sample monitoring data corresponding to the temperature compensation sub-model can include oil level pressure difference monitoring data and temperature monitoring data corresponding to different real oil levels under different temperature ranges. For example, different oil levels can be 0%, 25%, 50%, 75%, and 100%, and different temperature ranges can be obtained by dividing [-40℃, 85℃] into multiple temperature intervals.

[0050] Specifically, the sample monitoring data corresponding to the temperature compensation sub-model can be used as the training input of the BP neural network. The temperature compensation value obtained by the BP neural network is used as the training output. The training loss is determined based on the corresponding real oil level and temperature compensation value. The Particle Swarm Optimization algorithm is used to optimize the weights and thresholds of the BP neural network with the goal of minimizing the training loss, so as to obtain the trained temperature compensation sub-model.

[0051] Specifically, using particle swarm optimization to optimize the BP neural network can effectively prevent the BP neural network from getting trapped in local optima, improve the model convergence accuracy, and at the same time, the BP neural network can accurately model the complex nonlinear relationship between temperature and pressure, taking into account the comprehensive impact of internal temperature effects and liquid density changes in the sensor. The overall algorithm has good real-time performance, and the computational load of the trained forward network is small, making it suitable for embedded real-time processing.

[0052] Step 103: Obtain vehicle oil level monitoring results through a vibration compensation sub-model based on real-time temperature compensation values ​​and operating status monitoring data. Building upon steps 101 and 102, this step acquires and inputs real-time vehicle fuel tank temperature monitoring data, oil level differential pressure monitoring data, and operating status monitoring data into a pre-trained oil level compensation model. Then, based on the real-time fuel tank temperature data and oil level differential pressure monitoring data, the real-time temperature compensation value of the oil level differential pressure is obtained through the temperature compensation sub-model. Furthermore, based on the real-time temperature compensation value and operating status monitoring data, the vehicle oil level monitoring results are obtained through a vibration compensation sub-model. This approach accurately compensates for measurement deviations in oil level differential pressure caused by changes in ambient temperature and vehicle operating status, thereby obtaining accurate oil level differential pressure values. This reduces monitoring errors during oil level monitoring and yields more accurate vehicle oil level monitoring results.

[0053] Optionally, the vibration compensation sub-model includes a vibration intensity grading module and an adaptive filtering module. The adaptive filtering module includes a vibration intensity level-noise parameter mapping table.

[0054] Optionally, the process of obtaining vehicle oil level monitoring results based on real-time temperature compensation values ​​and operating status monitoring data through a vibration compensation sub-model includes: obtaining the real-time vibration intensity level of the vehicle through a vibration intensity grading module based on the vehicle's three-axis acceleration monitoring data.

[0055] Specifically, the root mean square (RMS) of triaxial acceleration can be used as an indicator of vehicle vibration intensity.

[0056] Specifically, the weighted root mean square value obtained by taking the square root of the weighted sum of the squares of accelerations along different axes can also be used as a vibration intensity index for vehicles.

[0057] Specifically, the aforementioned real-time vibration intensity levels can be static with no vibration, weak vibration, slight vibration, moderate vibration, or severe vibration.

[0058] Specifically, the process of obtaining the real-time vibration intensity level of a vehicle based on its triaxial acceleration monitoring data through the vibration intensity grading module may include: calculating the real-time triaxial acceleration root mean square (RMS) based on the triaxial acceleration monitoring data, and determining the real-time vibration intensity level of the vehicle based on the real-time triaxial acceleration RMS and the range of RMS corresponding to different vibration intensity levels. Specifically, when the real-time triaxial acceleration RMS falls within the range of RMS corresponding to any vibration intensity level, the real-time vibration intensity level of the vehicle is determined as that vibration intensity level.

[0059] Optionally, the process of obtaining vehicle oil level monitoring results based on real-time temperature compensation values ​​and operating status monitoring data through a vibration compensation sub-model includes: determining the adaptive process noise covariance and adaptive observation noise covariance of the Kalman filter through an adaptive filtering module based on the vehicle's real-time vibration intensity level and vibration intensity level-noise parameter mapping table, and constructing an adaptive Kalman filter based on the adaptive process noise covariance and adaptive observation noise covariance.

[0060] Specifically, the vibration intensity level-noise parameter mapping table mentioned above can be shown in Table 1:

[0061]

[0062] Specifically, the aforementioned vibration intensity level-noise parameter mapping table, used as model parameters for the vibration compensation sub-model, can be obtained after training the vibration compensation sub-model.

[0063] Specifically, the process of determining the adaptive process noise covariance and adaptive observation noise covariance of the Kalman filter through the adaptive filtering module based on the real-time vibration intensity level and vibration intensity level-noise parameter mapping table of the vehicle may include: when the vibration intensity level is high, determining the adaptive process noise covariance to a larger value and the adaptive observation noise covariance to a smaller value to reduce the predicted value of the gain-first trust Kalman filter; when the vibration intensity level is low, determining the adaptive process noise covariance to a smaller value and the adaptive observation noise covariance to a larger value to reduce process noise and improve the gain trust measurement value.

[0064] Optionally, the process of obtaining vehicle oil level monitoring results based on real-time temperature compensation values ​​and operating status monitoring data through a vibration compensation sub-model includes: obtaining real-time operating condition compensation values ​​of oil level pressure difference through an adaptive Kalman filter based on real-time temperature compensation values.

[0065] Specifically, before constructing the adaptive Kalman filter based on the adaptive process noise covariance and the adaptive observation noise covariance, a prediction equation for the oil level pressure difference can be constructed as the state equation, and an observation mapping equation for the oil level pressure difference can be constructed as the measurement equation.

[0066] Specifically, the process of constructing an adaptive Kalman filter based on the adaptive process noise covariance and the adaptive observation noise covariance may include: constructing the adaptive Kalman filter based on the adaptive process noise covariance, the adaptive observation noise covariance, the state equation, and the measurement equation.

[0067] Specifically, the vibration compensation sub-model can be trained using a reinforcement learning algorithm based on the sample data corresponding to the vibration compensation sub-model. The sample data corresponding to the vibration compensation sub-model can include oil level pressure difference monitoring data and triaxial acceleration monitoring data corresponding to different real oil levels under different vibration levels.

[0068] Specifically, the process of obtaining vehicle oil level monitoring results based on real-time temperature compensation values ​​and operating status monitoring data through a vibration compensation sub-model includes: obtaining real-time operating condition compensation values ​​of oil level pressure difference through a vibration compensation sub-model based on real-time temperature compensation values ​​and operating status monitoring data, and determining vehicle oil level monitoring results based on real-time operating condition compensation values.

[0069] Specifically, real-time temperature compensation values ​​and operating status monitoring data can be input into the vibration compensation sub-model, and the real-time operating condition compensation value of oil level pressure difference can be calculated and output through the vibration compensation sub-model.

[0070] Optionally, after obtaining the real-time operating condition compensation value of oil level pressure difference through the vibration compensation sub-model based on the real-time temperature compensation value and operating status monitoring data, the estimated oil quantity after compensation is obtained based on the real-time temperature compensation value of oil level pressure difference and the pressure difference-oil quantity relationship. The oil tank temperature monitoring data, oil level pressure difference monitoring data, operating status monitoring data and the estimated oil quantity after compensation are then sent to the oil level monitoring cloud platform so that the oil level monitoring cloud platform can update and train the oil level compensation model based on the oil tank temperature monitoring data, oil level pressure difference monitoring data, operating status monitoring data and the estimated oil quantity after compensation.

[0071] Specifically, the oil tank temperature monitoring data, oil level differential pressure monitoring data, operating status monitoring data, and the estimated oil quantity after compensation can be sent to the oil level monitoring cloud platform via the T-Box.

[0072] Specifically, the aforementioned pressure difference-oil quantity relationship can be predetermined, or it can be determined before estimating the oil quantity after obtaining compensation based on the real-time temperature compensation value of the oil level pressure difference and the pressure difference-oil quantity relationship.

[0073] Specifically, the above-mentioned vehicle oil level monitoring results can be the actual oil level fill height or the percentage of the actual oil level fill height to the effective oil level height range of the fuel tank.

[0074] Specifically, when the vehicle oil level monitoring result can be the actual oil level filling height, the process of determining the vehicle oil level monitoring result based on the real-time operating condition compensation value can be derived based on the static pressure formula.

[0075] The static pressure formula can be expressed as:

[0076]

[0077] Where h represents the actual oil level filling height. This represents the real-time operating condition compensation value, and ρ represents the oil density.

[0078] Specifically, when the vehicle fuel level monitoring result is a percentage of the actual fuel level fill height relative to the effective fuel level range of the fuel tank, the process of determining the vehicle fuel level monitoring result based on the real-time operating condition compensation value can include: obtaining the actual fuel level fill height from the real-time operating condition compensation value; and calculating the vehicle fuel level monitoring result based on the actual fuel level fill height and the predetermined minimum effective fuel level height and effective fuel level range of the fuel tank. This can be calculated using the following formula:

[0079]

[0080] in, This indicates the minimum effective oil level in the fuel tank. This indicates the effective oil level range in the fuel tank.

[0081] Specifically, the vibration compensation sub-model provided in this embodiment of the invention can also be other types of models, such as a neural network model, specifically a Long Short-Term Memory (LSTM) network model.

[0082] Specifically, the vibration compensation sub-model can be obtained by training the original LSTM model based on the sample data corresponding to the vibration compensation sub-model.

[0083] Specifically, when training the original LSTM, mean squared error can be used as the loss function, and the Adam optimizer can be used to adaptively adjust the learning rate of each parameter during the training process to balance the speed and stability of gradient descent.

[0084] The vehicle oil level monitoring method provided in the embodiments of the present invention will be further described below.

[0085] Optionally, the vehicle's operating status monitoring data may also include: the vehicle's angular velocity monitoring data.

[0086] Optionally, the oil level compensation model may also include: tilt angle compensation sub-model.

[0087] Optional, Figure 1 Step 103 may include the following steps:

[0088] Step 1031: Based on the real-time temperature compensation value, the real-time temperature and vibration compensation value of the oil level pressure difference is calculated and output through the vibration compensation sub-model.

[0089] Step 1032: Based on the real-time temperature and vibration compensation value of the oil level pressure difference and the vehicle's angular velocity monitoring data, the vehicle oil level monitoring result is obtained through the tilt angle compensation sub-model.

[0090] Optionally, the tilt compensation sub-model includes a regular height compensation value prediction function and an irregular shape adaptation calibration function. The regular height compensation value prediction function is constructed based on the fuel tank level height as a function of the fuel tank size parameters and the vehicle tilt angle. It is used to predict the regular height compensation value, which is the fuel tank level height value after compensating for the influence of the vehicle tilt angle on the real-time fuel tank level height, assuming that the shape of the corresponding fuel tank is regular. The irregular shape adaptation calibration function is constructed based on the irregular shape influence factor and is used to perform irregular adaptation calibration on the regular height compensation value.

[0091] Specifically, before step 1032, the real-time vehicle roll angle can be obtained based on the vehicle roll rate monitoring data, and the real-time vehicle pitch angle can be obtained based on the real-time vehicle pitch rate monitoring data.

[0092] Specifically, for a cuboid fuel tank, the above-mentioned rule height compensation value prediction function can be expressed as:

[0093]

[0094] Where z represents the fuel level in the tank. The values ​​represent the installation height of the pressure sensor, x and y represent the length and width of the fuel tank, φ represents the vehicle roll angle, θ represents the vehicle pitch angle, and V represents the fuel volume. This indicates the rule height compensation value. This represents the volume-level state oil level mapping function.

[0095] Specifically, the irregular shape adaptation calibration function mentioned above can be expressed as:

[0096]

[0097] Where ω represents the influence factor of irregular shape.

[0098] Specifically, ω, as a model parameter of the tilt compensation sub-model, can be obtained after training the tilt compensation sub-model.

[0099] Specifically, the tilt compensation sub-model can be trained using reinforcement learning algorithms based on the sample data corresponding to the tilt compensation sub-model. The sample data corresponding to the tilt compensation sub-model can include oil level pressure difference monitoring data and vehicle angular velocity monitoring data corresponding to different real oil levels at different tilt angles.

[0100] Specifically, in the tilt compensation sub-model, the initial value of the irregular shape influence factor ω can be set to 0.

[0101] Specifically, the tilt compensation sub-model can also be other types of models, such as neural network models, specifically LSTM models.

[0102] Specifically, the tilt compensation sub-model can be obtained by training the original LSTM model based on the sample data corresponding to the tilt compensation sub-model.

[0103] Specifically, when training the original LSTM, mean squared error can be used as the loss function, and the Adam optimizer can be used to adaptively adjust the learning rate of each parameter during the training process to balance the speed and stability of gradient descent.

[0104] Optionally, before step 1032, the vehicle's fuel tank size parameters are obtained.

[0105] Specifically, the aforementioned fuel tank size parameters may include the length and width of the fuel tank.

[0106] Specifically, the aforementioned fuel tank size parameters may also include other geometric dimensions of the fuel tank, such as the lengths of the various sides of the fuel tank's cross-section.

[0107] Optionally, step 1032 includes the following steps:

[0108] 1032A determines the real-time temperature and vibration compensation oil level based on the real-time temperature and vibration compensation value, and determines the real-time vehicle tilt angle based on the vehicle's angular velocity monitoring data.

[0109] Specifically, the real-time temperature and vibration compensation oil level can be calculated using the static pressure formula based on the real-time temperature and vibration compensation value.

[0110] Optionally, the process of determining the real-time vehicle tilt angle based on the vehicle's angular velocity monitoring data includes: determining the real-time vehicle roll angle based on the vehicle's roll angular velocity monitoring data, specifically by integrating the roll angular velocity monitoring data to obtain the real-time vehicle roll angle.

[0111] Optionally, the process of determining the real-time vehicle tilt angle based on the vehicle's angular velocity monitoring data includes: determining the real-time vehicle pitch angle based on the vehicle's pitch angular velocity monitoring data, specifically by integrating the pitch angular velocity monitoring data to obtain the actual vehicle roll angle.

[0112] 1032B obtains the rule height compensation value through a rule height compensation value prediction function based on the fuel tank size parameters, real-time temperature and vibration compensation fuel level height, and real-time vehicle tilt angle.

[0113] Specifically, the fuel tank size parameters, real-time temperature and vibration compensation fuel level height, and real-time vehicle tilt angle can be substituted into the rule height compensation value prediction function to calculate and output the rule height compensation value.

[0114] 1032C obtains irregular height compensation values ​​by performing irregular adaptation calibration on regular height compensation values ​​through irregular shape adaptation calibration function.

[0115] Specifically, the regular height compensation value can be substituted into the irregular shape adaptation calibration function to output the irregular height compensation value.

[0116] 1033D, determining vehicle oil level monitoring results based on irregular height compensation values.

[0117] Specifically, the process of determining the vehicle oil level monitoring result based on the irregular height compensation value may include: when the vehicle oil level monitoring result is the actual oil level filling height, the irregular height compensation value is determined as the vehicle oil level monitoring result.

[0118] Specifically, the process of determining the vehicle oil level monitoring result based on the irregular height compensation value may include: when the vehicle oil level monitoring result is the percentage of the actual oil level filling height to the effective oil level height range of the oil tank, the vehicle oil level monitoring result is calculated based on the irregular height compensation value and the predetermined minimum effective oil level height and effective oil level height range of the oil tank.

[0119] The embodiments of the present invention are based on rigorous geometric derivation and integral calculation to compensate for the impact of changes in vehicle tilt angle on the fuel level in the vehicle's fuel tank, resulting in high compensation accuracy. The embodiments of the present invention also dynamically correct for irregular fuel tank shape differences through influence factors, which can adapt to fuel tanks of various shapes and has a wide range of applications.

[0120] Specifically, the vehicles in the embodiments of the present invention may include various vehicles with different shapes and specifications of vehicle fuel tanks.

[0121] Specifically, for various vehicles with different shapes and specifications, the temperature compensation sub-model and the vibration compensation sub-model can be the same.

[0122] Specifically, for various vehicles with different shapes and specifications, the tilt compensation sub-models can be different for each other.

[0123] Specifically, the temperature compensation sub-model, vibration compensation sub-model, and tilt compensation sub-model can all be different for different vehicles.

[0124] Figure 4This is a flowchart illustrating an oil level compensation model update method provided in an embodiment of the present invention. This method can be applied to an oil level monitoring cloud platform, which can be implemented using software and / or hardware. In a specific embodiment, the device can be integrated into an electronic device, such as a computer or server. The following embodiments will illustrate this using the integration of the device into an electronic device as an example. (Reference) Figure 4 The method may specifically include the following steps:

[0125] Step 401: Obtain vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and estimated fuel quantity after compensation from the repeater.

[0126] Specifically, the T-Box can obtain vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and estimated fuel quantity after compensation from the repeater.

[0127] Optionally, the vehicle's operating status monitoring data includes the vehicle's three-axis acceleration monitoring data and angular velocity monitoring data.

[0128] Optionally, the oil level compensation model includes a temperature compensation sub-model, a vibration compensation sub-model, and an tilt angle compensation sub-model.

[0129] Specifically, it can receive fuel tank temperature monitoring data, fuel level and pressure differential monitoring data, operating status monitoring data, and estimated fuel quantity after compensation from the repeater, and can also obtain fuel tank temperature monitoring data, fuel level and pressure differential monitoring data, operating status monitoring data, and estimated fuel quantity after compensation from the repeater's storage unit.

[0130] Step 402: Determine the estimated fuel quantity error based on the compensated estimated fuel quantity, and when the estimated fuel quantity error is greater than the error threshold, retrain the fuel level compensation model based on the vehicle's fuel tank temperature monitoring data, fuel level pressure difference monitoring data, operating status monitoring data, and the compensated estimated fuel quantity.

[0131] Specifically, the process of determining the estimated oil quantity error based on the compensated estimated oil quantity may include: determining the estimated oil quantity error based on the compensated estimated oil quantity.

[0132] Specifically, the aforementioned error thresholds can be determined based on empirical data.

[0133] Optional, such as Figure 5 As shown, step 402 may include the following steps:

[0134] Step 4021: Retrain the temperature compensation sub-model based on the monitoring data of different fuel tank temperatures when the vehicle is stationary, the corresponding fuel level pressure difference monitoring data, and the corresponding actual fuel level obtained in the most recent historical period.

[0135] Specifically, the aforementioned temperature compensation sub-model can be a BP neural network model.

[0136] Specifically, the duration of the most recent historical period can be set based on empirical data or on the results of multiple related experiments.

[0137] Specifically, the process of retraining the temperature compensation sub-model based on the monitoring data of different fuel tank temperatures, corresponding fuel level pressure difference monitoring data, and corresponding actual fuel levels obtained from the most recent historical period when the vehicle is stationary can include: using the monitoring data of different fuel tank temperatures and corresponding fuel level pressure difference monitoring data obtained from the most recent historical period when the vehicle is stationary as the training input of the original temperature compensation sub-model; obtaining the temperature compensation value through the cloud mouse of the original temperature compensation sub-model as the training output; determining the training loss based on the corresponding actual fuel level and temperature compensation value; and using the particle swarm optimization algorithm to optimize the weights and thresholds of the original temperature compensation sub-model with the goal of minimizing the training loss, thereby obtaining the latest temperature compensation sub-model.

[0138] Specifically, the actual oil level mentioned above can be either calibrated or determined based on the amount of oil added to the vehicle's fuel tank.

[0139] Step 4022: Retrain the vibration compensation sub-model based on the same vehicle angular velocity and temperature data obtained in the most recent historical period, the corresponding oil level and pressure difference monitoring data, and the corresponding actual oil level.

[0140] Optionally, the model parameters of the above vibration compensation sub-model include the vibration intensity level-noise parameter mapping table as described above.

[0141] Specifically, the process of retraining the vibration compensation sub-model based on the same vehicle angular velocity and temperature corresponding to different triaxial acceleration monitoring data, corresponding oil level and pressure difference monitoring data, and corresponding actual oil level obtained in the most recent historical period may include: optimizing and updating the model parameters of the original vibration compensation sub-model's vibration intensity level-noise parameter mapping table based on the same vehicle angular velocity and temperature corresponding to different triaxial acceleration monitoring data, corresponding oil level and pressure difference monitoring data, and corresponding actual oil level obtained in the most recent historical period to obtain the latest vibration compensation sub-model.

[0142] Step 4023: Retrain the tilt compensation sub-model based on the same vehicle triaxial acceleration and temperature monitoring data, corresponding oil level and pressure difference monitoring data, and corresponding actual oil level obtained in the most recent historical period.

[0143] Optionally, the model parameters of the tilt compensation sub-model include the irregular shape influence factor as described above.

[0144] Specifically, the process of retraining the tilt compensation sub-model based on the same vehicle triaxial acceleration and temperature monitoring data, corresponding oil level and pressure difference monitoring data, and corresponding actual oil level obtained in the most recent historical period may include: updating the model parameter of the tilt compensation sub-model, namely the irregular shape influence factor, based on the same vehicle triaxial acceleration and temperature monitoring data, corresponding oil level and pressure difference monitoring data, and corresponding actual oil level obtained in the most recent historical period, to obtain the latest tilt compensation sub-model.

[0145] Step 403: Send the latest model parameters obtained by retraining the oil level compensation model to the repeater to update the model parameters of the oil level compensation model in the repeater.

[0146] Specifically, the latest model parameters obtained by retraining the oil level compensation model can be sent to the repeater via the T-Box.

[0147] The oil level compensation model update method provided in this invention continuously monitors the "estimation error" of the vehicle's oil level through a cloud platform and automatically triggers the model retraining process when the estimation error is too large. Simultaneously, it continuously iterates and optimizes the system through a process of "data collection - model training - parameter distribution - effect evaluation - new data collection," thereby preventing the system accuracy from declining over time and due to equipment aging, which would hinder self-evolution and continuous optimization, and improving the accuracy of oil level monitoring under different environmental conditions.

[0148] Figure 6 This is a structural diagram of a vehicle fuel level monitoring system provided in an embodiment of the present invention. The system includes a fuel level monitoring repeater, which is adapted to execute the vehicle fuel level monitoring method provided in this embodiment. Figure 6 As shown, the oil level monitoring repeater may specifically include:

[0149] The monitoring data acquisition and input module 601 is used to acquire and input real-time vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data into a pre-trained fuel level compensation model. The fuel level compensation model includes a temperature compensation sub-model and a vibration compensation sub-model. This module can accurately compensate for measurement deviations in fuel level differential pressure caused by changes in ambient temperature and vehicle operating status through the fuel level compensation model.

[0150] Optionally, the vibration compensation sub-model includes a vibration intensity grading module and an adaptive filtering module. The adaptive filtering module includes a vibration intensity level-noise parameter mapping table. The vehicle's operating status monitoring data includes the vehicle's three-axis acceleration monitoring data.

[0151] Optionally, the vehicle's operating status monitoring data may also include: vehicle angular velocity monitoring data; the oil level compensation model may also include: tilt angle compensation sub-model.

[0152] Optionally, the tilt compensation sub-model includes a regular height compensation value prediction function and an irregular shape adaptation calibration function. The regular height compensation value prediction function is constructed based on the fuel tank level height as a function of the fuel tank size parameters and the vehicle tilt angle. It is used to predict the regular height compensation value, which is the fuel tank level height value after compensating for the influence of the vehicle tilt angle on the real-time fuel tank level height, assuming that the shape of the corresponding fuel tank is regular. The irregular shape adaptation calibration function is constructed based on the irregular shape influence factor and is used to perform irregular adaptation calibration on the regular height compensation value.

[0153] The real-time temperature compensation value acquisition module 602 is used to obtain the real-time temperature compensation value of the oil level pressure difference based on real-time oil tank temperature data and oil level pressure difference monitoring data through a temperature compensation sub-model. This module can accurately compensate for the measurement deviation of oil level pressure difference caused by changes in ambient temperature.

[0154] The vehicle oil level monitoring result acquisition module 603 is used to acquire vehicle oil level monitoring results based on real-time temperature compensation values ​​and operating status monitoring data through a vibration compensation sub-model. This module, in conjunction with modules 601 and 602, acquires and inputs real-time vehicle oil tank temperature monitoring data, oil level pressure difference monitoring data, and operating status monitoring data into a pre-trained oil level compensation model. Then, based on the real-time oil tank temperature data and oil level pressure difference monitoring data, it obtains the real-time temperature compensation value of the oil level pressure difference through the temperature compensation sub-model. Further, based on the real-time temperature compensation value and operating status monitoring data, it obtains the vehicle oil level monitoring result through a vibration compensation sub-model. This allows for accurate compensation of measurement deviations in oil level pressure difference caused by changes in ambient temperature and vehicle operating status, thereby obtaining accurate oil level pressure difference values. This reduces monitoring errors during oil level monitoring and yields more accurate vehicle oil level monitoring results.

[0155] Optionally, the vehicle oil level monitoring result acquisition module 603 can be specifically used to: obtain the real-time vibration intensity level of the vehicle based on the vehicle's triaxial acceleration monitoring data through the vibration intensity grading module; determine the adaptive process noise covariance and adaptive observation noise covariance of the Kalman filter based on the vehicle's real-time vibration intensity level and vibration intensity level-noise parameter mapping table through the adaptive filtering module, and construct an adaptive Kalman filter based on the adaptive process noise covariance and adaptive observation noise covariance; and obtain the real-time operating condition compensation value of the oil level pressure difference based on the real-time temperature compensation value through the adaptive Kalman filter.

[0156] Optionally, the aforementioned vehicle oil level monitoring result acquisition module 603 can be specifically used to calculate and output the real-time temperature and vibration compensation value of the oil level pressure difference based on the real-time temperature compensation value through a vibration compensation sub-model; and

[0157] Based on the real-time temperature and vibration compensation value of the oil level pressure difference and the vehicle's angular velocity monitoring data, the vehicle oil level monitoring results are obtained through the tilt angle compensation sub-model.

[0158] Optionally, the fuel level monitoring repeater provided in this embodiment of the invention further includes: a fuel tank size acquisition module, used to acquire the fuel tank size parameters of the vehicle.

[0159] Optionally, the vehicle oil level monitoring result acquisition module 603 can be specifically used to determine the real-time temperature and vibration compensation oil level height based on the real-time temperature and vibration compensation value, and to determine the real-time vehicle tilt angle based on the vehicle's angular velocity monitoring data.

[0160] Based on the fuel tank size parameters, real-time temperature and vibration compensation fuel level height, and real-time vehicle tilt angle, the regular height compensation value is obtained through a regular height compensation value prediction function.

[0161] Irregular height compensation values ​​are obtained by performing irregular shape adaptation calibration on regular height compensation values ​​using an irregular shape adaptation calibration function, and

[0162] The vehicle fuel level monitoring results are determined based on the irregular height compensation value.

[0163] Optionally, the repeater provided in this embodiment of the invention further includes a data acquisition and transmission module, which is used to acquire the latest model parameters from the oil level monitoring cloud platform and update the oil level compensation model using the latest model parameters before acquiring and inputting the vehicle's fuel tank temperature monitoring data, oil level pressure difference monitoring data, and operating status monitoring data into the pre-trained oil level compensation model in real time; and after obtaining the real-time temperature compensation value of the oil level pressure difference through the temperature compensation sub-model based on the real-time temperature compensation value of the oil level pressure difference and the pressure difference-fuel quantity relationship, obtain the estimated fuel quantity after compensation based on the real-time temperature compensation value of the oil level pressure difference and the pressure difference-fuel quantity relationship, and send the fuel tank temperature monitoring data, oil level pressure difference monitoring data, operating status monitoring data, and estimated fuel quantity after compensation to the oil level monitoring cloud platform, so that the oil level monitoring cloud platform can update and train the oil level compensation model based on the fuel tank temperature monitoring data, oil level pressure difference monitoring data, operating status monitoring data, and estimated fuel quantity after compensation.

[0164] Optional, such as Figure 7 As shown, the vehicle oil level monitoring system provided in this embodiment of the invention further includes: an oil level monitoring cloud platform, which is used to execute the oil level compensation model update method provided in any embodiment of the invention. Specifically, the oil level monitoring cloud platform may include:

[0165] The raw data acquisition module 701 is used to acquire vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and estimated fuel quantity after compensation from the repeater.

[0166] Training module 702 is used to determine the estimated fuel quantity error based on the compensated estimated fuel quantity, and when the estimated fuel quantity error is greater than the error threshold, to retrain the fuel level compensation model based on the vehicle's fuel tank temperature monitoring data, fuel level pressure difference monitoring data, operating status monitoring data, and the compensated estimated fuel quantity.

[0167] Optionally, the oil level compensation model includes a temperature compensation sub-model, a vibration compensation sub-model, and a tilt angle compensation sub-model, and the vehicle's operating status monitoring data includes the vehicle's three-axis acceleration monitoring data and angular velocity monitoring data.

[0168] Optionally, the training module 702 can be specifically used to: retrain the temperature compensation sub-model based on monitoring data of different fuel tank temperatures, corresponding fuel level pressure difference monitoring data, and corresponding actual fuel levels obtained from the most recent historical period when the vehicle is stationary; retrain the vibration compensation sub-model based on monitoring data of different triaxial accelerations corresponding to the same vehicle angular velocity and temperature, corresponding fuel level pressure difference monitoring data, and corresponding actual fuel levels obtained from the most recent historical period; and retrain the tilt compensation sub-model based on monitoring data of different angular velocities corresponding to the same vehicle triaxial acceleration and temperature, corresponding fuel level pressure difference monitoring data, and corresponding actual fuel levels obtained from the most recent historical period.

[0169] The parameter update module 703 is used to send the latest model parameters obtained by retraining the oil level compensation model to the repeater to update the model parameters of the oil level compensation model in the repeater.

[0170] This invention enables continuous monitoring of the vehicle's fuel level "estimation error" via a cloud platform, and automatically triggers a model retraining process when the estimation error is too large. Simultaneously, it continuously iterates and optimizes the system through a process of "data collection - model training - parameter distribution - effect evaluation - new data collection," thereby preventing the system's accuracy from declining over time and with equipment aging, hindering self-evolution and continuous optimization, and improving fuel level monitoring accuracy under different environmental conditions.

[0171] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0172] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the vehicle oil level monitoring method or the oil level compensation model update method provided in any of the above embodiments.

[0173] This invention also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle oil level monitoring method or the oil level compensation model update method provided in any of the above embodiments.

[0174] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle oil level monitoring method or the oil level compensation model update method as described in any of the embodiments of this invention.

[0175] The following is for reference. Figure 8 It shows a schematic diagram of the structure of a computer system 800 suitable for implementing an electronic device according to embodiments of the present invention. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0176] like Figure 8 As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 802 or programs loaded from storage section 808 into random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the system 800. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0177] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0178] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs the functions defined above in the system of this invention.

[0179] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0180] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0181] The modules and / or units described in the embodiments of the present invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor may include a monitoring data acquisition and input module, a real-time temperature compensation value acquisition module, and a vehicle oil level monitoring result acquisition module; or, a processor may include a raw data acquisition module, a training module, and a parameter update module. The names of these modules do not necessarily constitute a limitation on the module itself.

[0182] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to: acquire in real time vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data and input them into a pre-trained fuel level compensation model, the fuel level compensation model including a temperature compensation sub-model and a vibration compensation sub-model; obtain a real-time temperature compensation value for the fuel level differential pressure based on the real-time fuel tank temperature data and fuel level differential pressure monitoring data through the temperature compensation sub-model; and obtain the vehicle fuel level monitoring result based on the real-time temperature compensation value and operating status monitoring data through the vibration compensation sub-model.

[0183] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle fuel level monitoring method, applied to a fuel level monitoring repeater, characterized in that, include: Real-time acquisition and input of vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data into a pre-trained fuel level compensation model, which includes a temperature compensation sub-model and a vibration compensation sub-model; Based on real-time tank temperature data and oil level differential pressure monitoring data, the real-time temperature compensation value of oil level differential pressure is obtained through a temperature compensation sub-model. as well as The vehicle oil level monitoring results are obtained through a vibration compensation sub-model based on real-time temperature compensation values ​​and operating status monitoring data.

2. The vehicle oil level monitoring method according to claim 1, characterized in that, The vibration compensation sub-model includes a vibration intensity grading module and an adaptive filtering module. The adaptive filtering module includes a vibration intensity level-noise parameter mapping table. The vehicle's operating status monitoring data includes: vehicle's three-axis acceleration monitoring data. The method for obtaining vehicle oil level monitoring results based on real-time temperature compensation values ​​and operational status monitoring data through a vibration compensation sub-model includes: The vehicle's real-time vibration intensity level is obtained through a vibration intensity grading module based on the vehicle's three-axis acceleration monitoring data. Based on the vehicle's real-time vibration intensity level and vibration intensity level-noise parameter mapping table, the adaptive process noise covariance and adaptive observation noise covariance of the Kalman filter are determined by an adaptive filtering module, and an adaptive Kalman filter is constructed based on these two parameters; and The real-time operating condition compensation value of the oil level pressure difference is obtained through an adaptive Kalman filter based on the real-time temperature compensation value.

3. The vehicle oil level monitoring method according to claim 1, characterized in that, The vehicle's operating status monitoring data also includes: vehicle angular velocity monitoring data; the oil level compensation model also includes: tilt angle compensation sub-model; The method for obtaining vehicle oil level monitoring results based on real-time temperature compensation values ​​and operational status monitoring data through a vibration compensation sub-model includes: The real-time temperature and vibration compensation value is calculated and output based on the real-time temperature compensation value through a vibration compensation sub-model; and Based on the real-time temperature and vibration compensation value of the oil level pressure difference and the vehicle's angular velocity monitoring data, the vehicle oil level monitoring results are obtained through the tilt angle compensation sub-model.

4. The vehicle oil level monitoring method according to claim 3, characterized in that, The tilt compensation sub-model includes a regular height compensation value prediction function and an irregular shape adaptation calibration function. The regular height compensation value prediction function is constructed based on the fuel tank level height as a function of the fuel tank size parameters and the vehicle tilt angle. It is used to predict the regular height compensation value, which is the fuel tank level height value after compensating for the influence of the vehicle tilt angle on the real-time fuel tank level height, assuming the corresponding fuel tank has a regular shape. The irregular shape adaptation calibration function is constructed based on the irregular shape influence factor and is used to perform irregular adaptation calibration on the regular height compensation value. Before obtaining the vehicle oil level monitoring result through the tilt angle compensation sub-model using the real-time temperature and vibration compensation value based on the oil level pressure difference and the vehicle's angular velocity monitoring data, the method further includes: Obtain the vehicle's fuel tank size parameters; The real-time temperature and vibration compensation value based on oil level pressure difference and the vehicle's angular velocity monitoring data are used to obtain the vehicle oil level monitoring results through a tilt angle compensation sub-model, including: The real-time temperature and vibration compensation oil level is determined based on the real-time temperature and vibration compensation value, and the real-time vehicle tilt angle is determined based on the vehicle's angular velocity monitoring data. Based on the fuel tank size parameters, real-time temperature and vibration compensation fuel level height, and real-time vehicle tilt angle, the regular height compensation value is obtained through a regular height compensation value prediction function. Irregular height compensation values ​​are obtained by performing irregular shape adaptation calibration on regular height compensation values ​​using an irregular shape adaptation calibration function, and The vehicle fuel level monitoring results are determined based on the irregular height compensation value.

5. The vehicle oil level monitoring method according to claim 1, characterized in that, Before acquiring and inputting the vehicle's fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data into the pre-trained fuel level compensation model in real time, the method further includes: Obtain the latest model parameters from the oil level monitoring cloud platform and update the oil level compensation model using the latest model parameters; After obtaining the real-time temperature compensation value of the oil level pressure difference through a temperature compensation sub-model based on real-time tank temperature data and oil level pressure difference monitoring data, the method further includes: Based on the real-time temperature compensation value of the oil level pressure difference and the pressure difference-oil quantity relationship, the estimated oil quantity after compensation is obtained. The oil tank temperature monitoring data, oil level pressure difference monitoring data, operating status monitoring data, and the estimated oil quantity after compensation are sent to the oil level monitoring cloud platform so that the oil level monitoring cloud platform can update and train the oil level compensation model based on the oil tank temperature monitoring data, oil level pressure difference monitoring data, operating status monitoring data, and the estimated oil quantity after compensation.

6. A method for updating an oil level compensation model, applied to an oil level monitoring cloud platform, characterized in that, include: The system acquires vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and compensated estimated fuel quantity from the repeater. The estimated fuel quantity error is determined based on the compensated estimated fuel quantity. When the estimated fuel quantity error is greater than the error threshold, the fuel level compensation model is retrained based on the vehicle's fuel tank temperature monitoring data, fuel level pressure difference monitoring data, operating status monitoring data, and the compensated estimated fuel quantity. as well as The latest model parameters obtained by retraining the oil level compensation model are sent to the repeater to update the model parameters of the oil level compensation model in the repeater.

7. The oil level compensation model update method according to claim 6, characterized in that, The oil level compensation model includes a temperature compensation sub-model, a vibration compensation sub-model, and a tilt angle compensation sub-model. The vehicle's operating status monitoring data includes the vehicle's three-axis acceleration monitoring data and angular velocity monitoring data. The model based on vehicle fuel tank temperature monitoring data, fuel level differential pressure monitoring data, operating status monitoring data, and the compensated estimated fuel quantity is retrained, including: The temperature compensation sub-model was retrained based on the monitoring data of different fuel tank temperatures when the vehicle was stationary, the corresponding fuel level pressure difference monitoring data, and the corresponding actual fuel level obtained from the most recent historical period. The vibration compensation sub-model was retrained based on different triaxial acceleration monitoring data corresponding to the same vehicle angular velocity and temperature obtained from recent historical periods, corresponding oil level and pressure difference monitoring data, and corresponding actual oil levels; and The tilt compensation sub-model was retrained based on the same vehicle triaxial acceleration and temperature monitoring data, corresponding oil level and pressure difference monitoring data, and the corresponding actual oil level obtained from the most recent historical period.

8. A vehicle fuel level monitoring system, comprising a fuel level monitoring repeater for executing the vehicle fuel level monitoring method according to any one of claims 1 to 5, characterized in that, The oil level monitoring repeater includes: The monitoring data acquisition and input module is used to acquire and input the vehicle's fuel tank temperature monitoring data, fuel level differential pressure monitoring data, and operating status monitoring data in real time into a pre-trained fuel level compensation model. The fuel level compensation model includes a temperature compensation sub-model and a vibration compensation sub-model. The real-time temperature compensation value acquisition module is used to obtain the real-time temperature compensation value of the oil level pressure difference based on real-time tank temperature data and oil level pressure difference monitoring data through a temperature compensation sub-model; and The vehicle oil level monitoring result acquisition module is used to obtain the vehicle oil level monitoring result based on the real-time temperature compensation value and operating status monitoring data through a vibration compensation sub-model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the vehicle oil level monitoring method or the oil level compensation model update method as described in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the vehicle oil level monitoring method as described in any one of claims 1 to 5, or when the processor executes the program, it implements the oil level compensation model update method as described in claim 6 or 7.

Images