Digital control method and system for opening degree of vehicle carbon tank control valve

Abstract

The invention relates to a digital control method and system for the opening degree of a vehicle carbon tank control valve, and relates to the field of valve opening degree control. According to the service duration of the engine, integrated configuration is conducted on the fuel steam flow prediction unit, and a fuel steam flow prediction model is obtained; the engine torque, the engine rotating speed, the engine power and the engine monitoring temperature are input into the fuel steam flow prediction model, and the fuel steam expected flow is obtained; and opening correlation is conducted according to the expected flow of the fuel steam, the expected opening of the valve is obtained, and the carbon tank electromagnetic valve is controlled. The technical problem that in the prior art, the control precision of the opening degree of the vehicle carbon tank control valve is not high due to the fact that the influence of the engine service duration on the fuel steam flow requirement is not considered is solved, the carbon tank electromagnetic valve is precisely controlled by introducing the engine service duration factor, and the control precision of the opening degree of the vehicle carbon tank control valve is improved. The technical effect of improving the opening degree control precision of the vehicle carbon tank control valve is achieved.

Description

Technical Field

[0001] The invention relates to the field of valve opening control, and in particular to a digital control method and system for the opening of a vehicle carbon canister control valve. Background Art

[0002] The vehicle carbon canister is a key component of the gasoline evaporation control system. Its main function is to temporarily store the fuel vapor in the fuel tank to prevent it from being directly discharged into the atmosphere and to prevent the fuel vapor from escaping into the atmosphere after the engine stops running. The carbon canister solenoid valve is an actuator that controls the working state of the carbon canister, and its opening size directly affects the working efficiency of the carbon canister. In the prior art, the vehicle carbon canister control valve opening control is based on the real-time operating parameters of the engine, such as speed, load, temperature, etc., to obtain the required fuel vapor flow through linear calculation, and then send out the corresponding control signal accordingly. The control signal is sent to the carbon canister solenoid valve in the form of current or voltage, and the solenoid valve opening is controlled by changing the current size of the solenoid valve coil. However, this control method does not take into account the impact of the engine service time on the fuel vapor flow demand. The amount of fuel vapor generated by the engine and the adsorption capacity of the carbon canister will change at different service stages. Ignoring the service time factor will lead to inaccurate estimation of the fuel vapor flow, thereby affecting the accuracy of the carbon canister solenoid valve opening control. Summary of the invention

[0003] The present invention aims to solve the technical problem that the prior art fails to consider the influence of the engine service life on the fuel vapor flow demand, resulting in low control accuracy of the vehicle carbon canister control valve opening, and provides a digital control method and system for the vehicle carbon canister control valve opening to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a digital control method for the opening of a vehicle carbon canister control valve, comprising: receiving engine operating conditions, wherein the engine operating conditions include engine torque, engine speed, engine power and engine monitoring temperature; integrating a fuel vapor flow prediction unit according to the engine service life to obtain a fuel vapor flow prediction model; inputting the engine torque, engine speed, engine power and engine monitoring temperature into the fuel vapor flow prediction model to obtain an expected fuel vapor flow; correlating the opening according to the expected fuel vapor flow to obtain an expected valve opening, and controlling the carbon canister solenoid valve.

[0005] In the second aspect, the present invention provides a digital control system for the opening of a vehicle carbon canister control valve, including: an operating condition receiving module, used to receive engine operating conditions, wherein the engine operating conditions include engine torque, engine speed, engine power and engine monitoring temperature; a prediction configuration module, used to integrate the configuration of the fuel vapor flow prediction unit according to the engine service life, and obtain a fuel vapor flow prediction model; a flow prediction module, used to input the engine torque, engine speed, engine power and engine monitoring temperature into the fuel vapor flow prediction model, and obtain the expected fuel vapor flow; an opening control module, used to associate the opening according to the expected fuel vapor flow, obtain the expected valve opening, and control the carbon canister solenoid valve.

[0006] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute a digital control method for the opening of a vehicle carbon canister control valve provided in the present application.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute a digital control method for the opening of a vehicle carbon canister control valve provided in the present application.

[0008] The beneficial effects of the present invention are: Receive engine operating conditions, where the engine operating conditions include engine torque, engine speed, engine power and engine monitoring temperature. By obtaining these parameters, the real-time working status of the engine is fully understood, providing input data for subsequent fuel vapor flow prediction; according to the service life of the engine, the fuel vapor flow prediction unit is integrated and configured to obtain a fuel vapor flow prediction model, and the engine service life factor is introduced to dynamically adjust the fuel vapor flow prediction model so that it can adapt to the working characteristics of the engine at different service stages; input the engine torque, engine speed, engine power and engine monitoring temperature into the fuel vapor flow prediction model to obtain the expected fuel vapor flow, and by substituting the engine operating condition parameters into the prediction model, a more accurate expected fuel vapor flow value is obtained; the opening is associated with the expected fuel vapor flow to obtain the expected valve opening, and the carbon canister solenoid valve is controlled. Based on the predicted expected fuel vapor flow, the optimal opening value of the carbon canister solenoid valve is determined, and a control instruction is issued accordingly to achieve precise control of the carbon canister solenoid valve. By introducing the engine service time factor, the fuel vapor flow prediction model is dynamically integrated and configured, and the flow prediction is performed in combination with the engine operating conditions parameters to obtain a more accurate expected fuel vapor flow, and the carbon canister solenoid valve opening control is optimized accordingly, thereby improving the vehicle carbon canister control valve opening control accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1A schematic flow chart of a digital control method for the opening of a vehicle carbon canister control valve provided by the present invention; Figure 2 A schematic diagram of the structure of a digital control system for the opening of a vehicle carbon canister control valve provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0010] In the accompanying drawings, the components represented by the reference numerals are as follows: Working condition receiving module 11, prediction configuration module 12, flow prediction module 13, opening control module 14, electronic device 200, memory 210, processor 220, first computer program 211, computer readable storage medium 300, second computer program 311. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0012] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0013] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0014] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a digital control method for the opening of a vehicle carbon canister control valve, which is applied to a digital control system for the opening of a vehicle carbon canister control valve. The system is deployed in a carbon canister electronic valve central control unit, and the carbon canister electronic valve central control unit is communicatively connected with the carbon canister solenoid valve.

[0015] Specifically, a digital control method for the opening of a vehicle carbon canister control valve provided in an embodiment of the present invention is applied to a digital control system for the opening of a vehicle carbon canister control valve, which is deployed on a carbon canister electronic valve central control unit. In specific implementation, a communication connection is established between the carbon canister electronic valve central control unit and the carbon canister solenoid valve to achieve control of the carbon canister solenoid valve. Among them, the carbon canister electronic valve central control unit is responsible for generating the corresponding desired valve opening; the carbon canister solenoid valve acts as an actuator and adjusts its opening size according to the received desired valve opening.

[0016] The digital control method of the vehicle carbon canister control valve opening includes: S100: receiving engine operating conditions, wherein the engine operating conditions include engine torque, engine speed, engine power and engine monitoring temperature.

[0017] Specifically, it receives engine operating conditions, including engine torque, engine speed, engine power and engine monitoring temperature, reflects the current operating status of the engine, and provides data support for subsequent fuel vapor flow prediction and valve opening control.

[0018] Among them, the engine torque indicates the torque on the engine output shaft, reflecting the output capacity of the engine. The engine torque is measured in real time by a torque sensor installed on the engine crankshaft; the engine speed indicates the number of rotations of the engine crankshaft per unit time (for example, per minute), which is directly related to the running speed of the engine. The engine speed is obtained by calculation based on the signal of the crankshaft position sensor; the engine power comprehensively reflects the operating state of the engine, indicating the work done by the engine per unit time. The power is converted through a formula based on the two parameters of engine torque and engine speed; the engine monitoring temperature refers to the real-time temperature data of key engine components such as the cylinder block, cylinder head, intake manifold, etc., reflecting the thermodynamic state of the engine, and is collected by temperature sensors installed at corresponding positions.

[0019] In actual application, the vehicle communicates with the engine control unit through the on-board CAN bus. The engine control unit is responsible for summarizing and managing the data of each sensor, so you only need to send a data request to the engine control unit, and the engine control unit will package the current engine operating conditions and transmit them through the CAN bus. Since the engine operating conditions directly reflect the current engine operation, and these factors will affect the generation of fuel vapor, obtaining accurate and reliable engine operating conditions provides a data basis for the precise control of the carbon canister control valve opening.

[0020] S200: Integrate and configure the fuel vapor flow prediction unit according to the service life of the engine to obtain a fuel vapor flow prediction model.

[0021] Specifically, during the use of the engine, due to factors such as wear and carbon deposition, there will be a certain deviation between the actual operating conditions of the engine and the calibrated operating conditions, resulting in changes in the amount of fuel vapor generated. In order to improve the accuracy of the prediction, the prediction model needs to be adjusted accordingly based on the actual service life of the engine.

[0022] First, the service life of the engine is divided into several stages, and each stage corresponds to a group of pre-trained fuel vapor flow prediction units. When the service life of the engine is at a certain stage, the prediction units corresponding to the stage are selected to integrate into a fuel vapor flow prediction model. For example, the service life of the engine is divided into stages such as 0-1 years, 1-2 years, and 2-3 years, which correspond to different numbers of fuel vapor flow prediction units. When the engine is used for 1.5 years, the fuel vapor flow prediction units corresponding to the 1-2 year stage are selected for integration to form the fuel vapor flow prediction model at this time. Among them, the integration method of the fuel vapor flow prediction unit can adopt common integrated learning algorithms such as weighted average and voting, and improve the robustness and accuracy of the fuel vapor flow prediction model by integrating the output results of multiple fuel vapor flow prediction units.

[0023] In this way, the fuel vapor flow prediction model can be adaptively adjusted according to the actual service life of the engine, dynamically adapting to changes in engine performance, thereby improving the accuracy of fuel vapor flow prediction.

[0024] S300: Inputting the engine torque, the engine speed, the engine power and the engine monitoring temperature into the fuel vapor flow prediction model to obtain the expected fuel vapor flow.

[0025] Specifically, first, the acquired engine operating conditions (i.e., engine torque, engine speed, engine power, and engine monitoring temperature) are organized into a data set in a predetermined order and format. This data set corresponds to the input of the fuel vapor flow prediction model. Next, the data set of the engine operating conditions is input into the fuel vapor flow prediction model. The fuel vapor flow prediction model performs mathematical operations and logical judgments on the input engine operating conditions, and returns a numerical result representing the expected flow of fuel vapor. Since the fuel vapor flow prediction model is composed of a plurality of fuel vapor flow prediction units, wherein the plurality of fuel vapor flow prediction units can be different types of machine learning models such as linear functions, nonlinear functions, decision trees, neural networks, etc. Therefore, the calculation process within the fuel vapor flow prediction model involves comprehensive processing such as weighted averaging and voting on the output results of each fuel vapor flow prediction unit, so as to obtain an accurate overall prediction value as the expected flow of fuel vapor.

[0026] By obtaining the expected flow rate of fuel vapor, a key reference is provided for the opening control of the carbon canister solenoid valve. Subsequently, based on the expected flow rate of fuel vapor, it will be decided how to adjust the opening degree of the carbon canister solenoid valve, thereby achieving effective control of the fuel vapor flow rate.

[0027] S400: Performing opening association according to the expected fuel vapor flow rate to obtain the expected valve opening and controlling the carbon canister solenoid valve.

[0028] Specifically, the target opening of the carbon canister solenoid valve, that is, the expected valve opening, is determined based on the predicted expected fuel vapor flow rate, and the carbon canister solenoid valve is controlled accordingly, thereby achieving precise regulation of the fuel vapor flow rate.

[0029] First, a correspondence table between the fuel vapor flow rate and the carbon canister solenoid valve opening is established, and the correspondence table can be obtained through offline calibration test. The correspondence table takes the fuel vapor flow rate as the independent variable and the corresponding carbon canister solenoid valve opening as the dependent variable to form a mapping of flow rate to opening. After the expected fuel vapor flow rate is obtained, the corresponding relationship table is searched to find the flow value closest to the expected fuel vapor flow rate, and the carbon canister solenoid valve opening value corresponding to the flow value is read, and it is used as the target opening of the valve control in the current state, that is, the expected valve opening. Subsequently, the actual opening feedback value of the carbon canister solenoid valve is obtained, and it is compared with the expected valve opening to calculate the deviation between the two. If the deviation value exceeds the preset threshold range, the valve opening of the carbon canister solenoid valve is adjusted. Among them, the adjustment of the valve opening is achieved by changing the energized current of the valve coil. For example, according to the target opening, the actual opening and the control characteristics of the valve, the PID control algorithm is used to calculate the current adjustment amount to be applied to the valve coil, and it is converted into a corresponding PWM control signal, and the valve coil is driven by the actuator circuit to change the valve opening accordingly.

[0030] By obtaining the desired valve opening and controlling the carbon canister solenoid valve, the actual opening of the carbon canister solenoid valve can be automatically adjusted dynamically following the change in the desired fuel vapor flow rate, thereby improving the control accuracy of the carbon canister solenoid valve, so that the fuel vapor flow rate entering the engine intake manifold is always controlled at the optimal state, avoiding problems such as unstable engine operation or excessive exhaust gas due to excessive or insufficient vapor flow rate.

[0031] Furthermore, the embodiment of the present application also includes: S110: receiving engine operating conditions; S120: Compare the engine operating condition with the pre-stored engine operating condition to obtain an operating condition fluctuation coefficient; S130: When the operating condition fluctuation coefficient is greater than or equal to the fluctuation coefficient threshold, continue to execute the process; S140: When the operating condition fluctuation coefficient is less than the fluctuation coefficient threshold, stop executing the process.

[0032] In a feasible implementation, a deviation judgment of the engine operating condition is introduced to avoid repeated execution of unnecessary fuel vapor flow prediction and carbon canister solenoid valve control when the engine operating condition does not change much, thereby reducing the calculation burden and control adjustment frequency and improving overall efficiency.

[0033] First, the current engine operating condition is received periodically from the engine control unit. Then, the deviation check is performed on the engine operating condition received in this cycle and the engine operating condition of the previous cycle (i.e., the engine pre-stored operating condition). The engine operating condition and each operating condition parameter corresponding to the engine pre-stored operating condition are subtracted one by one, the change amount of each operating condition parameter is calculated, and the maximum value of the change amount is taken as an indicator to measure the operating condition deviation, i.e., the operating condition fluctuation coefficient, which reflects the maximum change amplitude of the engine operating condition between the two sampling cycles. After that, according to the comparison result between the operating condition fluctuation coefficient and the fluctuation coefficient threshold, it is determined whether it is necessary to continue to execute the subsequent prediction control process. If the operating condition fluctuation coefficient is greater than or equal to the fluctuation coefficient threshold, it means that the engine operating condition in this cycle has changed greatly compared with the previous cycle, and the process is continued to be executed. The fuel vapor flow rate is re-predicted according to the new engine operating condition and the carbon canister solenoid valve opening is adjusted accordingly. On the contrary, if the operating condition fluctuation coefficient is less than the fluctuation coefficient threshold, it means that the engine operating condition in this cycle has not changed much compared with the previous cycle. The prediction and control steps can be skipped, the execution process can be stopped, and the carbon canister solenoid valve can continue to be controlled using the expected valve opening of the previous cycle until the next sampling cycle arrives.

[0034] Through periodic sampling and operating condition deviation judgment, the control calculation amount and execution frequency can be effectively reduced when the engine operating condition is stable, while it can respond quickly and dynamically adjust the control amount when the operating condition changes suddenly, thereby improving the control efficiency while ensuring the control accuracy and real-time performance.

[0035] Furthermore, the embodiment of the present application also includes: S210: Obtaining a reference service time of an engine, wherein 0 years ≤ the reference service time of the engine ≤ 1 year; S220: rounding down the ratio of the engine service time to the engine service reference time to obtain a fuel vapor flow prediction unit integration index; S230: Taking the fuel vapor flow prediction unit integration index as an index of 2, obtaining the fuel vapor flow prediction unit integration number; S240: According to the integrated number of the fuel vapor flow prediction units, a plurality of fuel vapor flow prediction units are configured to perform mean full connection to obtain the fuel vapor flow prediction model.

[0036] In a preferred embodiment, as the service time of the engine increases, the law of fuel vapor generation will change to a certain extent, so the complexity and accuracy of the fuel vapor flow prediction model need to be adjusted accordingly to meet the prediction requirements of different service stages.

[0037] First, the engine service benchmark duration is determined as a reference for subsequent calculations. The engine service benchmark duration is set between 0 and 1 year and is selected based on factors such as the engine model, process, and material. Then, the ratio of the current engine service duration to the engine service benchmark duration is calculated, and the ratio is rounded down to obtain an integer value as the fuel vapor flow prediction unit integration index, which reflects how many complete cycles the current engine service duration has completed based on the engine service benchmark duration. For example, if the engine service benchmark duration is 1 year and the current engine service duration is 3.8 years, the fuel vapor flow prediction unit integration index is 3. Subsequently, the calculated fuel vapor flow prediction unit integration index is used as the index and 2 is used as the base to calculate the power value of 2, which is used as the integrated number of fuel vapor flow prediction units. For example, if the fuel vapor flow prediction unit integration index is 3, the integrated number of fuel vapor flow prediction units is 2³=8. Among them, the power relationship determines that the number of fuel vapor flow prediction units increases exponentially with the engine service duration to increase the complexity of the fuel vapor flow prediction model. Afterwards, the fuel vapor flow prediction model is actually constructed according to the determined number of integrated fuel vapor flow prediction units. Specifically, a number of independent fuel vapor flow prediction units equal to the number of integrated fuel vapor flow prediction units are configured. Each fuel vapor flow prediction unit can use common machine learning models such as neural networks and support vector machines to establish a mapping relationship between engine operating conditions and fuel vapor flow by training and learning historical data; then, the outputs of all fuel vapor flow prediction units are arithmetic averaged as the final output result of the fuel vapor flow prediction model. Through the method of multi-model integrated averaging, the prediction capabilities of different fuel vapor flow prediction units can be effectively integrated, the limitations of a single model can be reduced, and the overall prediction accuracy and robustness of the fuel vapor flow prediction model can be improved.

[0038] By introducing the influencing factor of engine service time, the complexity and integration scale of the fuel vapor flow prediction model are dynamically adjusted to adapt to the operating condition changes and prediction requirements of the engine at different service stages.

[0039] Furthermore, the embodiment of the present application also includes: S250: collecting a positive sample carbon canister solenoid valve control log based on the engine model as a constraint, wherein the positive sample carbon canister solenoid valve control log refers to control record data in which the carbon canister solenoid valve working coefficient has no abnormal state; Wherein, the positive sample carbon canister solenoid valve control log includes engine operating condition record data and fuel vapor flow record data; S260: Using mean square error loss as a loss function, retrieving the engine operating condition record data and the fuel vapor flow record data for regression training to obtain the fuel vapor flow prediction unit.

[0040] In a feasible implementation, by performing machine learning on historical carbon canister solenoid valve control data, a mathematical mapping relationship between engine operating conditions and fuel vapor flow is established, thereby obtaining a fuel vapor flow prediction unit.

[0041] First, according to the engine model to be trained, the corresponding positive sample carbon canister solenoid valve control log data is collected. Among them, the positive sample refers to the control data recorded when the carbon canister solenoid valve is in normal and stable working state, that is, the control record when the carbon canister solenoid valve working coefficient is in normal state, so as to ensure the quality and reliability of the training data and avoid the introduction of noise data in abnormal or failed state. The positive sample carbon canister solenoid valve control log contains two parts: one is the engine operating condition record data related to the carbon canister solenoid valve control decision, such as engine speed, load, temperature and other parameters; the other is the fuel vapor flow record data actually measured under these working conditions. These two parts of data form a set of input-output pairs, which reflect the generation law of fuel vapor under different working conditions and are the basis for training the fuel vapor flow prediction unit. Then, the fuel vapor flow prediction unit is actually trained using the collected positive sample carbon canister solenoid valve control log. Specifically, first, the engine operating condition record data and the fuel vapor flow record data are used as input and output respectively, and sent to the fuel vapor flow prediction unit; then, the mean square error is selected as the loss function, the difference between the predicted output and the actual fuel vapor flow is calculated, and the internal parameters of the fuel vapor flow prediction unit are adjusted accordingly to minimize the mean square error. Through iterative optimization, the fuel vapor flow prediction unit is gradually fitted to the training data, and a mapping from the engine operating condition to the fuel vapor flow is established, thereby obtaining the fuel vapor flow prediction unit. The fuel vapor flow prediction unit can predict the corresponding fuel vapor flow value based on the input engine operating condition. By mining and learning the carbon canister solenoid valve control log, a fuel vapor flow prediction unit for fuel vapor flow prediction is constructed, and the intrinsic relationship between engine operating conditions and fuel vapor flow is established. Based on this, the flow under unknown operating conditions is estimated and predicted, thus achieving accurate prediction of fuel vapor flow.

[0042] Furthermore, the embodiment of the present application also includes: S411: taking the expected fuel vapor flow rate and the carbon canister solenoid valve model as constraint data, collecting valve opening record values ​​and valve opening support, wherein the valve opening support represents the common triggering frequency of the valve opening record values ​​and the expected fuel vapor flow rate in at least 5000 sets of data under the constraint of the carbon canister solenoid valve model; S412: deleting the valve opening record values ​​whose valve opening support is less than or equal to the valve opening support threshold, to obtain high-frequency valve opening record values; S413: Performing mode mean evaluation on the high-frequency valve opening record values ​​to obtain the expected valve opening.

[0043] In a feasible implementation, through statistical analysis of historical data, the intrinsic correlation between the fuel vapor flow rate and the carbon canister solenoid valve opening is discovered, and based on this, the optimal control value of the valve opening under the current expected fuel vapor flow rate is determined.

[0044] First, according to the current expected fuel vapor flow and the model of the carbon canister solenoid valve to be controlled, the relevant historical control data are collected, including the valve opening record value and the valve opening support. Among them, the valve opening record value represents the opening value actually executed by the carbon canister solenoid valve under similar working conditions; the valve opening support is an indicator used to measure the strength of the correlation between a certain valve opening record value and a given expected fuel vapor flow. The calculation method is to count the frequency of the valve opening record value and the expected fuel vapor flow in at least 5000 groups of historical data under the premise of the carbon canister solenoid valve model as a constraint condition. The higher the frequency, the greater the correlation between the valve opening record value and the given expected fuel vapor flow under the corresponding carbon canister solenoid valve model, that is, when the expected fuel vapor flow reaches a given value, the carbon canister solenoid valve is more likely to actually execute the opening value.

[0045] Then, the collected valve opening record values ​​are screened to remove those samples with weak correlation with the current working conditions. Specifically, a valve opening support threshold is set, and valve opening record values ​​with valve opening support lower than the threshold are regarded as noise data and removed, while valve opening record values ​​with valve opening support higher than the valve opening support threshold are retained and regarded as high-frequency valve opening record values. In this way, the opening values ​​with high correlation with the given fuel vapor flow in the historical data can be focused on, providing a more reliable reference for subsequent decision-making. After that, a comprehensive evaluation is performed on the screened high-frequency valve opening record values ​​to determine the final expected valve opening. Among them, the evaluation method based on the mode mean is used to first find the value with the highest frequency among all high-frequency valve opening record values, and define it as the valve opening mode value; and calculate the arithmetic mean of all high-frequency valve opening record values, which is defined as the valve opening mean; then the valve opening mode value and the valve opening mean are weighted averaged, and the result is used as the final expected valve opening.

[0046] By fully mining the historical data during the operation of the carbon canister solenoid valve, selecting and focusing on high-quality samples according to the correlation strength, and using strategies such as mode mean evaluation to obtain the expected valve opening, support is provided for the refined control of the carbon canister solenoid valve.

[0047] Furthermore, the embodiment of the present application also includes: S121: The engine pre-stored operating conditions include engine pre-stored torque timing information, engine pre-stored speed timing information, engine pre-stored power timing information and engine pre-stored temperature timing information of a preset time step; S122: The engine operating condition includes the engine torque timing information, engine speed timing information, engine power timing information and engine monitoring temperature timing information of the preset time step; S123: comparing the torque deviation of the engine pre-stored torque time series information with the torque deviation of the engine torque time series information at the same time, obtaining the torque deviation absolute value time series information, and counting the proportion of the time when the absolute value of the torque deviation is greater than the torque deviation threshold in the torque deviation absolute value time series information, and setting it as the torque fluctuation coefficient; S124: comparing the speed deviation of the engine pre-stored speed time series information with the speed time series information of the engine at the same time, obtaining the speed deviation absolute value time series information, and counting the proportion of the time when the absolute value of the speed deviation is greater than the speed deviation threshold in the speed deviation absolute value time series information, and setting it as the speed fluctuation coefficient; S125: comparing the power deviation of the engine pre-stored power time series information with the power deviation of the engine at the same time, obtaining the power deviation absolute value time series information, and counting the proportion of the time when the absolute value of the power deviation is greater than the power deviation threshold in the power deviation absolute value time series information, and setting it as the power fluctuation coefficient; S126: Compare the temperature deviations at the same time of the engine pre-stored temperature time series information and the engine monitoring temperature time series information to obtain the temperature deviation absolute value time series information, and count the proportion of the time when the absolute value of the temperature deviation is greater than the temperature deviation threshold in the temperature deviation absolute value time series information, and set it as the temperature fluctuation coefficient; S127: The maximum value of the torque fluctuation coefficient, the speed fluctuation coefficient, the power fluctuation coefficient and the temperature fluctuation coefficient is set as the operating condition fluctuation coefficient.

[0048] In a preferred embodiment, when comparing the deviations between the engine operating condition and the pre-stored engine operating condition to obtain the operating condition fluctuation coefficient, the degree of fluctuation of the operating condition is quantitatively evaluated by comparing the deviation distribution characteristics between the current engine operating condition and the pre-stored operating condition in the time series to determine whether it is necessary to trigger subsequent fuel vapor flow prediction and carbon canister solenoid valve control.

[0049] The engine pre-stored operating condition refers to a series of engine state parameters recorded according to a preset sampling time interval (i.e., preset time step) during a specific historical period, including engine pre-stored torque timing information, engine pre-stored speed timing information, engine pre-stored power timing information, and engine pre-stored temperature timing information. These timing information reflects the engine's operating mode during the historical period and serves as a reference for judging the current operating condition. The engine operating condition also includes the timing information of the same four parameters as the engine pre-stored operating condition, and uses the same time step as the engine pre-stored operating condition, including engine torque timing information, engine speed timing information, engine power timing information, and engine monitoring temperature timing information. In this way, the engine operating condition and the engine pre-stored operating condition form two sets of time series data that can be directly compared and analyzed.

[0050] Next, for the four parameters of engine torque, engine speed, engine power and engine monitoring temperature, the deviation distribution ratio between the current working condition timing information and the pre-stored working condition timing information is calculated, and it is defined as the corresponding fluctuation coefficient. For each moment in the engine pre-stored torque timing information and the engine torque timing information, the absolute value of the difference between the torque values ​​of the engine torque at that moment is calculated, and it is judged whether the absolute value is greater than the preset torque deviation threshold, and the number of moments exceeding the torque deviation threshold is counted, and the ratio obtained by dividing it by the total number of moments of the timing information is the torque fluctuation coefficient. The larger the torque fluctuation coefficient, the stronger the volatility of the engine torque in the time series. For each moment in the engine pre-stored speed timing information and the engine speed timing information, the absolute value of the difference between the speed values ​​of the engine speed at that moment is calculated, and it is judged whether the absolute value is greater than the preset speed deviation threshold, and the number of moments exceeding the speed deviation threshold is counted, and the ratio obtained by dividing it by the total number of moments of the timing information is the speed fluctuation coefficient. The larger the speed fluctuation coefficient, the stronger the volatility of the engine speed in the time series. For each moment in the engine pre-stored power time series information and the engine power time series information, the absolute value of the difference between the power values ​​of the engine power at that moment is calculated, and it is judged whether the absolute value is greater than the preset power deviation threshold, and the number of moments exceeding the power deviation threshold is counted, and the ratio obtained is divided by the total number of moments of the time series information, and the power fluctuation coefficient is obtained. The larger the power fluctuation coefficient, the stronger the volatility of the engine power in the time series. For each moment in the engine pre-stored temperature time series information and the engine monitoring temperature time series information, the absolute value of the difference between the temperature values ​​of the engine monitoring temperature at that moment is calculated, and it is judged whether the absolute value is greater than the preset temperature deviation threshold, and the number of moments exceeding the temperature deviation threshold is counted, and the ratio obtained is divided by the total number of moments of the time series information, and the temperature fluctuation coefficient is obtained. The larger the temperature fluctuation coefficient, the stronger the volatility of the engine temperature in the time series. Afterwards, the maximum value is selected from the torque fluctuation coefficient, the speed fluctuation coefficient, the power fluctuation coefficient and the temperature fluctuation coefficient as the operating condition fluctuation coefficient that comprehensively reflects the degree of deviation of the engine operating condition. The reason for selecting the maximum value is to find the parameter with the most drastic fluctuation among the four dimensions of engine torque, engine speed, engine power and engine monitoring temperature, so as to judge the degree of deviation of the working condition from the most sensitive perspective. Among them, selecting the maximum value is only a possible strategy. In practical applications, other comprehensive evaluation methods can also be considered, such as weighted average.

[0051] By judging the engine operating condition deviation based on the statistics of the distribution of time series deviation, introducing the fluctuation coefficient reflecting the proportion of the deviation of each parameter exceeding the standard, a multi-index comprehensive evaluation system is established to quantify the degree to which the engine operating condition deviates from the engine's pre-stored operating condition, so as to determine whether to start the predictive control and improve the adaptability of the carbon canister solenoid valve control. At the same time, the idea of ​​using time series comparison also takes into account the dynamic characteristics of fluctuations, and can more accurately describe the degree of deviation of the operating condition evolution than single moment comparison.

[0052] Furthermore, the embodiment of the present application also includes: S421: processing the expected valve opening according to a magnetic field strength calibration curve to obtain an expected magnetic field strength, wherein the magnetic field strength calibration curve is a preset correlation function curve representing the valve opening of the carbon canister solenoid valve and the magnetic field strength; S422: Collecting ambient temperature monitoring values ​​through a temperature sensor; S423: randomly assigning values ​​according to the current intensity interval to obtain a current intensity assignment result; S424: taking the ambient temperature monitoring value and the current intensity assignment result as constraints and the magnetic field intensity as target data, sampling the carbon canister solenoid valve model at least 50 times to obtain a first-level magnetic field intensity record sample, wherein the first-level magnetic field intensity record sample has a first-level ambient temperature label and a first-level current intensity label; S425: Taking the primary ambient temperature label and the primary current intensity label as constraints and the magnetic field intensity as target data, sampling the carbon canister solenoid valve model at least 50 times to obtain a secondary magnetic field intensity record sample, wherein the secondary magnetic field intensity record sample has a secondary ambient temperature label and a secondary current intensity label; S426: performing a central trend analysis on the primary magnetic field strength record sample and the secondary magnetic field strength record sample to obtain a central magnetic field strength; S427: When the deviation between the concentrated magnetic field strength and the expected magnetic field strength is less than or equal to a magnetic field strength deviation threshold, controlling the carbon canister solenoid valve according to the current strength assignment result; Among them, taking the ambient temperature monitoring value and the current intensity assignment result as constraints, taking the magnetic field intensity as the target data, sampling the carbon canister solenoid valve model at least 50 times, and obtaining the first-level magnetic field intensity record sample, including: S428: taking magnetic field intensity as target data, randomly sampling the carbon canister solenoid valve model to obtain a first sample to be sorted, wherein the first sample to be sorted has a label of an ambient temperature to be sorted and a label of a current intensity to be sorted; S429: When the ambient temperature deviation between the ambient temperature label to be sorted and the ambient temperature monitoring value is less than or equal to the ambient temperature deviation threshold, and the current intensity deviation between the current intensity label to be sorted and the current intensity assignment result is less than or equal to the current intensity deviation threshold, the first sample to be sorted is added to the first-level magnetic field strength record sample.

[0053] In a preferred embodiment, the magnetic field strength of the carbon canister solenoid valve is graded and closed-loop regulated to achieve accurate conversion and optimized control from the desired valve opening to the actual control amount.

[0054] First, according to the pre-calibrated magnetic field strength calibration curve, the desired valve opening is converted into the corresponding desired magnetic field strength value. The magnetic field strength calibration curve is a function curve that reflects the mapping relationship between the opening of the carbon canister solenoid valve and the magnetic field strength of its coil. It is measured by an offline calibration test, and the conversion from opening to magnetic field strength is realized by table lookup or function calculation. Since the ambient temperature is an important factor affecting the magnetic field characteristics of the solenoid valve, the temperature monitoring value of the carbon canister solenoid valve in the environment is collected in real time by the ambient temperature sensor as one of the constraints for the subsequent current intensity optimization control. The initial current intensity assignment result is obtained by randomly taking values ​​within the preset current intensity interval. Among them, the current intensity interval is pre-set according to the rated working current range of the carbon canister solenoid valve and the control strategy requirements. It must cover the current range required for the normal operation of the valve, and avoid excessive or too small currents that damage the valve or reduce the control effect. The random assignment is to perform a global search for the current within the interval to provide an initial solution for subsequent further optimization.

[0055] Subsequently, the first round of sampling of the carbon canister solenoid valve was carried out with the ambient temperature monitoring value and the current intensity assignment result as the constraint conditions and the magnetic field intensity as the sampling target, and the first round of sampling of the carbon canister solenoid valve was obtained to obtain the first-level magnetic field intensity recording sample. During the sampling process, for each sampling point, the corresponding ambient temperature monitoring value and the current intensity assignment result were recorded as the temperature label and current label of the sample. In this way, each first-level magnetic field intensity recording sample contains the magnetic field intensity target value and the corresponding first-level ambient temperature label and first-level current intensity label, which reflects the correlation between the magnetic field intensity and the ambient temperature and current intensity. Among them, considering the statistical characteristics of the sample, at least 50 sample data are obtained for the carbon canister solenoid valve model each time. Then, with the first-level ambient temperature label and the first-level current intensity label of the first-level magnetic field intensity recording sample as the constraint conditions and the magnetic field intensity as the sampling target, the second round of sampling of the carbon canister solenoid valve was carried out to obtain the second-level magnetic field intensity recording sample. Unlike the first-level sampling, the constraint conditions here no longer directly use the ambient temperature monitoring value and the current intensity assignment result, but use the first-level ambient temperature label and the first-level current intensity label already obtained in the first-level magnetic field intensity recording sample. In this way, the secondary magnetic field strength record sample is actually further expanded on the basis of the primary magnetic field strength record sample. Similarly, in order to ensure the statistical characteristics of the sample, the secondary sampling also needs to obtain at least 50 sample data. Subsequently, the primary magnetic field strength record sample and the secondary magnetic field strength record sample are subjected to central trend analysis to obtain the concentrated magnetic field strength that comprehensively reflects the distribution characteristics of the sample. Among them, the central trend analysis can use commonly used central measurements such as mean and median, with the purpose of extracting the most representative magnetic field strength control target value from the sample data. Subsequently, the concentrated magnetic field strength is compared with the expected magnetic field strength for deviation. If the deviation is less than the preset magnetic field strength deviation threshold, it is considered that the current current strength assignment result can meet the control requirements of the expected magnetic field strength, and the control instruction is output accordingly to adjust the actual working current of the carbon canister solenoid valve. By comparing the deviation between the actual magnetic field strength and the expected magnetic field strength, it is judged whether the current current strength setting meets the control accuracy requirements. If the deviation is within the allowable range, the current current strength can be directly used to control the valve; otherwise, the current strength assignment result is further randomly obtained in the current strength interval until the corresponding concentrated magnetic field strength is less than or equal to the magnetic field strength deviation threshold.

[0056] Among them, when obtaining the first-level magnetic field strength record sample, it is necessary to use the ambient temperature monitoring value and the current intensity assignment result as constraints, and use the magnetic field intensity as the target data to sample the carbon canister solenoid valve model at least 50 times. In each sampling, first, the carbon canister solenoid valve of the specified model is randomly sampled to obtain a magnetic field strength sample data, which is called the first sample to be sorted. Each first sample to be sorted contains an ambient temperature label to be sorted and a current intensity label to be sorted. Then, the first sample to be sorted is judged and screened to determine whether it meets the conditions for inclusion in the first-level magnetic field strength record sample. Specifically, for the first sample to be sorted, the deviation between its ambient temperature label to be sorted and the current ambient temperature monitoring value is calculated respectively to obtain the ambient temperature deviation, and the deviation between its current intensity label to be sorted and the current intensity assignment result is calculated to obtain the current intensity deviation. If the ambient temperature deviation is less than or equal to the preset ambient temperature deviation threshold, and the current intensity deviation is less than or equal to the preset current intensity deviation threshold, it is considered that the first sample to be sorted is close enough to the current actual control condition and can be included in the first-level magnetic field strength record sample as a valid sample. On the contrary, if the ambient temperature deviation is greater than the ambient temperature deviation threshold, or the current intensity deviation is greater than the current intensity deviation threshold, the first sample to be sorted is considered to have a weak correlation with the current control condition and is eliminated. Through this screening process, the most representative and relevant magnetic field intensity samples under the constraints of ambient temperature and current intensity can be selected from a large number of random sampling data, laying a data foundation for subsequent secondary sampling and overall magnetic field intensity analysis.

[0057] The mapping between valve opening and magnetic field strength is established through the magnetic field strength calibration curve. On this basis, combined with the ambient temperature monitoring value, the current intensity is taken as the optimization variable, and the precise magnetic field strength control target is obtained by two-level sampling and central trend analysis. Finally, the closed-loop optimization control of the current intensity is realized through deviation comparison and feedback correction. While meeting the requirements of precise valve opening control, the intelligent adjustment of the solenoid valve drive current is realized, which has good control performance and environmental adaptability.

[0058] The digital control method for the opening of a vehicle carbon canister control valve provided by the embodiment of the present invention has at least the following technical effects: Receive the engine operating conditions, including engine torque, engine speed, engine power and engine monitoring temperature, obtain key parameters reflecting the real-time working state of the engine, and provide data support for the subsequent fuel vapor flow prediction. According to the service time of the engine, the fuel vapor flow prediction unit is integrated and configured to obtain the fuel vapor flow prediction model. Through the integrated configuration, the service state of the engine is dynamically adapted to improve the accuracy of the fuel vapor flow prediction. The engine torque, engine speed, engine power and engine monitoring temperature are input into the fuel vapor flow prediction model to obtain the expected fuel vapor flow. Compared with the traditional linear estimation method, the prediction model adjusted by the service time factor can give a more accurate flow estimation value. According to the expected fuel vapor flow, the opening is associated to obtain the expected valve opening, and the carbon canister solenoid valve is controlled. Based on the predicted expected fuel vapor flow, the optimal opening value of the carbon canister solenoid valve is determined, and it is converted into a corresponding control instruction to accurately adjust the actual opening of the carbon canister solenoid valve and improve the control accuracy of the vehicle carbon canister control valve opening.

[0059] Embodiment 2: like Figure 2 As shown, based on the same inventive concept as the digital control method for the opening of a vehicle carbon canister control valve provided in the first embodiment, the embodiment of the present invention further provides a digital control system for the opening of a vehicle carbon canister control valve, which is deployed in a carbon canister electronic valve central control unit, and the carbon canister electronic valve central control unit is communicatively connected to the carbon canister solenoid valve and is communicatively connected to the carbon canister solenoid valve, including: The operating condition receiving module 11 is used to receive the engine operating condition, wherein the engine operating condition includes engine torque, engine speed, engine power and engine monitoring temperature; A prediction configuration module 12, for integrating and configuring the fuel vapor flow prediction unit according to the service life of the engine to obtain a fuel vapor flow prediction model; A flow prediction module 13, used for inputting the engine torque, the engine speed, the engine power and the engine monitoring temperature into the fuel vapor flow prediction model to obtain the expected fuel vapor flow; The opening control module 14 is used to associate the opening with the expected fuel vapor flow rate, obtain the expected valve opening, and control the carbon canister solenoid valve.

[0060] Furthermore, the operating condition receiving module 11 includes the following execution steps: Receiving engine operating conditions; Compare the deviation between the engine operating condition and the pre-stored engine operating condition to obtain the operating condition fluctuation coefficient; When the operating condition fluctuation coefficient is greater than or equal to the fluctuation coefficient threshold, continue to execute the process; When the operating condition fluctuation coefficient is less than the fluctuation coefficient threshold, the execution process is stopped.

[0061] Furthermore, the prediction configuration module 12 includes the following execution steps: Obtaining a benchmark service time of an engine, wherein 0 years ≤ the benchmark service time of the engine ≤ 1 year; Rounding down the ratio of the engine service time to the engine service reference time to obtain a fuel vapor flow prediction unit integration index; Taking the fuel vapor flow prediction unit integration index as an index of 2, obtaining the fuel vapor flow prediction unit integration number; According to the integrated number of the fuel vapor flow prediction units, a plurality of fuel vapor flow prediction units are configured to perform mean full connection to obtain the fuel vapor flow prediction model.

[0062] Furthermore, the prediction configuration module 12 also includes the following execution steps: Taking the engine model as a constraint, collecting positive sample carbon canister solenoid valve control logs, wherein the positive sample carbon canister solenoid valve control logs refer to control record data in which the carbon canister solenoid valve working coefficient has no abnormal state; Wherein, the positive sample carbon canister solenoid valve control log includes engine operating condition record data and fuel vapor flow record data; The mean square error loss is used as the loss function, the engine operating condition record data and the fuel vapor flow record data are retrieved for regression training, and the fuel vapor flow prediction unit is obtained.

[0063] Furthermore, the opening control module 14 includes the following execution steps: Taking the expected fuel vapor flow rate and the carbon canister solenoid valve model as constraint data, collecting valve opening record values ​​and valve opening support, wherein the valve opening support represents the common triggering frequency of the valve opening record values ​​and the expected fuel vapor flow rate in at least 5000 sets of data under the constraint of the carbon canister solenoid valve model; The valve opening record values ​​whose valve opening support is less than or equal to the valve opening support threshold are deleted to obtain high-frequency valve opening record values; The high-frequency valve opening record values ​​are evaluated by means of a mode mean to obtain the expected valve opening.

[0064] Furthermore, the operating condition receiving module 11 further includes the following execution steps: The engine pre-stored working conditions include engine pre-stored torque timing information, engine pre-stored speed timing information, engine pre-stored power timing information and engine pre-stored temperature timing information of preset time steps; The engine operating condition includes the engine torque timing information, engine speed timing information, engine power timing information and engine monitoring temperature timing information of the preset time step; Compare the torque deviation of the engine pre-stored torque time series information with the torque deviation of the engine torque time series information at the same time, obtain the torque deviation absolute value time series information, count the time proportion of the torque deviation absolute value time series information that is greater than the torque deviation threshold, and set it as the torque fluctuation coefficient; Compare the speed deviation of the engine pre-stored speed timing information with the speed timing information of the engine at the same time, obtain the speed deviation absolute value timing information, count the proportion of the time when the absolute value of the speed deviation is greater than the speed deviation threshold in the speed deviation absolute value timing information, and set it as the speed fluctuation coefficient; Compare the power deviation of the engine pre-stored power time series information with the power deviation of the engine power time series information at the same time, obtain the power deviation absolute value time series information, count the proportion of the time when the absolute value of the power deviation is greater than the power deviation threshold in the power deviation absolute value time series information, and set it as the power fluctuation coefficient; Compare the temperature deviations at the same time of the engine pre-stored temperature time series information and the engine monitoring temperature time series information to obtain the temperature deviation absolute value time series information, and count the proportion of the time when the absolute value of the temperature deviation is greater than the temperature deviation threshold in the temperature deviation absolute value time series information, and set it as the temperature fluctuation coefficient; The maximum value of the torque fluctuation coefficient, the speed fluctuation coefficient, the power fluctuation coefficient and the temperature fluctuation coefficient is set as the operating condition fluctuation coefficient.

[0065] Furthermore, the opening control module 14 further includes the following execution steps: According to the magnetic field strength calibration curve, the desired valve opening is processed to obtain the desired magnetic field strength, wherein the magnetic field strength calibration curve is a preset correlation function curve representing the valve opening of the carbon canister solenoid valve and the magnetic field strength; Collect environmental temperature monitoring values ​​through temperature sensors; Randomly assign values ​​according to the current intensity interval to obtain the current intensity assignment result; Taking the ambient temperature monitoring value and the current intensity assignment result as constraints and the magnetic field intensity as target data, the carbon canister solenoid valve model is sampled at least 50 times to obtain a first-level magnetic field intensity record sample, wherein the first-level magnetic field intensity record sample has a first-level ambient temperature label and a first-level current intensity label; Taking the primary ambient temperature label and the primary current intensity label as constraints and the magnetic field intensity as target data, sampling the carbon canister solenoid valve model at least 50 times to obtain a secondary magnetic field intensity record sample, wherein the secondary magnetic field intensity record sample has a secondary ambient temperature label and a secondary current intensity label; Performing a central trend analysis on the primary magnetic field strength record samples and the secondary magnetic field strength record samples to obtain a central magnetic field strength; When the deviation between the concentrated magnetic field strength and the expected magnetic field strength is less than or equal to a magnetic field strength deviation threshold, controlling the carbon canister solenoid valve according to the current strength assignment result; Among them, taking the ambient temperature monitoring value and the current intensity assignment result as constraints, taking the magnetic field intensity as the target data, sampling the carbon canister solenoid valve model at least 50 times, and obtaining the first-level magnetic field intensity record sample, including: Taking magnetic field intensity as target data, randomly sampling the carbon canister solenoid valve model to obtain a first sample to be sorted, wherein the first sample to be sorted has a label of an ambient temperature to be sorted and a label of a current intensity to be sorted; When the ambient temperature deviation between the ambient temperature label to be sorted and the ambient temperature monitoring value is less than or equal to the ambient temperature deviation threshold, and the current intensity deviation between the current intensity label to be sorted and the current intensity assignment result is less than or equal to the current intensity deviation threshold, the first sample to be sorted is added to the first-level magnetic field strength record sample.

[0066] Embodiment three: See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a first computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the first computer program 211, a digital control method for the opening of a vehicle carbon canister control valve is implemented.

[0067] Embodiment 4: See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a second computer program 311 is stored. When the second computer program 311 is executed by a processor, a digital control method for the opening of a vehicle carbon canister control valve is implemented.

[0068] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0071] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A digital control method for the opening of a vehicle carbon canister control valve, characterized in that: The invention is applied to a digital control system for the opening of a vehicle carbon canister control valve, wherein the system is deployed in a carbon canister electronic valve central control unit, and the carbon canister electronic valve central control unit is communicatively connected with the carbon canister solenoid valve, and comprises: Receiving engine operating conditions, wherein the engine operating conditions include engine torque, engine speed, engine power, and engine monitoring temperature; According to the service life of the engine, the fuel vapor flow prediction unit is integrated and configured to obtain a fuel vapor flow prediction model; Inputting the engine torque, the engine speed, the engine power and the engine monitoring temperature into the fuel vapor flow prediction model to obtain the expected fuel vapor flow; The opening degree is associated with the expected flow rate of fuel vapor, the expected valve opening degree is obtained, and the carbon canister solenoid valve is controlled.

2. The method according to claim 1, characterized in that Receiving an engine operating condition, wherein the engine operating condition includes engine torque, engine speed, engine power, and engine monitoring temperature, and further comprising: Receiving engine operating conditions; Compare the deviation between the engine operating condition and the pre-stored engine operating condition to obtain the operating condition fluctuation coefficient; When the operating condition fluctuation coefficient is greater than or equal to the fluctuation coefficient threshold, continue to execute the process; When the operating condition fluctuation coefficient is less than the fluctuation coefficient threshold, the execution process is stopped.

3. The method according to claim 1, characterized in that According to the service life of the engine, the fuel vapor flow prediction unit is integrated and configured to obtain the fuel vapor flow prediction model, including: Obtaining a benchmark service time of an engine, wherein 0 years ≤ the benchmark service time of the engine ≤ 1 year; Rounding down the ratio of the engine service time to the engine service reference time to obtain a fuel vapor flow prediction unit integration index; Taking the fuel vapor flow prediction unit integration index as an index of 2, obtaining the fuel vapor flow prediction unit integration number; According to the integrated number of the fuel vapor flow prediction units, a plurality of fuel vapor flow prediction units are configured to perform mean full connection to obtain the fuel vapor flow prediction model.

4. The method according to claim 1, characterized in that The fuel vapor flow prediction unit training step comprises: Taking the engine model as a constraint, collecting positive sample carbon canister solenoid valve control logs, wherein the positive sample carbon canister solenoid valve control logs refer to control record data in which the carbon canister solenoid valve working coefficient has no abnormal state; Wherein, the positive sample carbon canister solenoid valve control log includes engine operating condition record data and fuel vapor flow record data; The mean square error loss is used as the loss function, the engine operating condition record data and the fuel vapor flow record data are retrieved for regression training, and the fuel vapor flow prediction unit is obtained.

5. The method according to claim 1, characterized in that The opening degree is associated with the expected fuel vapor flow rate to obtain the expected valve opening degree, including: Taking the expected fuel vapor flow rate and the carbon canister solenoid valve model as constraint data, collecting valve opening record values ​​and valve opening support, wherein the valve opening support represents the common triggering frequency of the valve opening record values ​​and the expected fuel vapor flow rate in at least 5000 sets of data under the constraint of the carbon canister solenoid valve model; The valve opening record values ​​whose valve opening support is less than or equal to the valve opening support threshold are deleted to obtain high-frequency valve opening record values; The high-frequency valve opening record values ​​are evaluated by means of a mode mean to obtain the expected valve opening.

6. The method according to claim 2, characterized in that Compare the engine operating condition with the engine pre-stored operating condition to obtain the operating condition fluctuation coefficient, including: The engine pre-stored working conditions include engine pre-stored torque timing information, engine pre-stored speed timing information, engine pre-stored power timing information and engine pre-stored temperature timing information of preset time steps; The engine operating condition includes the engine torque timing information, engine speed timing information, engine power timing information and engine monitoring temperature timing information of the preset time step; Compare the torque deviation of the engine pre-stored torque time series information with the torque deviation of the engine torque time series information at the same time, obtain the torque deviation absolute value time series information, count the time proportion of the torque deviation absolute value time series information that is greater than the torque deviation threshold, and set it as the torque fluctuation coefficient; Compare the speed deviation of the engine pre-stored speed timing information with the speed timing information of the engine at the same time, obtain the speed deviation absolute value timing information, count the proportion of the time when the absolute value of the speed deviation is greater than the speed deviation threshold in the speed deviation absolute value timing information, and set it as the speed fluctuation coefficient; Compare the power deviation of the engine pre-stored power time series information with the power deviation of the engine power time series information at the same time, obtain the power deviation absolute value time series information, count the proportion of the time when the absolute value of the power deviation is greater than the power deviation threshold in the power deviation absolute value time series information, and set it as the power fluctuation coefficient; Compare the temperature deviations at the same time of the engine pre-stored temperature time series information and the engine monitoring temperature time series information to obtain the temperature deviation absolute value time series information, and count the proportion of the time when the absolute value of the temperature deviation is greater than the temperature deviation threshold in the temperature deviation absolute value time series information, and set it as the temperature fluctuation coefficient; The maximum value of the torque fluctuation coefficient, the speed fluctuation coefficient, the power fluctuation coefficient and the temperature fluctuation coefficient is set as the operating condition fluctuation coefficient.

7. The method according to claim 1, characterized in that The opening degree is associated according to the expected flow rate of the fuel vapor, the expected valve opening degree is obtained, and the carbon canister solenoid valve is controlled, including: According to the magnetic field strength calibration curve, the desired valve opening is processed to obtain the desired magnetic field strength, wherein the magnetic field strength calibration curve is a preset correlation function curve representing the valve opening of the carbon canister solenoid valve and the magnetic field strength; Collect environmental temperature monitoring values ​​through temperature sensors; Randomly assign values ​​according to the current intensity interval to obtain the current intensity assignment result; Taking the ambient temperature monitoring value and the current intensity assignment result as constraints and the magnetic field intensity as target data, the carbon canister solenoid valve model is sampled at least 50 times to obtain a first-level magnetic field intensity record sample, wherein the first-level magnetic field intensity record sample has a first-level ambient temperature label and a first-level current intensity label; Taking the primary ambient temperature label and the primary current intensity label as constraints and the magnetic field intensity as target data, sampling the carbon canister solenoid valve model at least 50 times to obtain a secondary magnetic field intensity record sample, wherein the secondary magnetic field intensity record sample has a secondary ambient temperature label and a secondary current intensity label; Performing a central trend analysis on the primary magnetic field strength record samples and the secondary magnetic field strength record samples to obtain a central magnetic field strength; When the deviation between the concentrated magnetic field strength and the expected magnetic field strength is less than or equal to a magnetic field strength deviation threshold, controlling the carbon canister solenoid valve according to the current strength assignment result; Among them, taking the ambient temperature monitoring value and the current intensity assignment result as constraints, taking the magnetic field intensity as the target data, sampling the carbon canister solenoid valve model at least 50 times, and obtaining the first-level magnetic field intensity record sample, including: Taking magnetic field intensity as target data, randomly sampling the carbon canister solenoid valve model to obtain a first sample to be sorted, wherein the first sample to be sorted has a label of an ambient temperature to be sorted and a label of a current intensity to be sorted; When the ambient temperature deviation between the ambient temperature label to be sorted and the ambient temperature monitoring value is less than or equal to the ambient temperature deviation threshold, and the current intensity deviation between the current intensity label to be sorted and the current intensity assignment result is less than or equal to the current intensity deviation threshold, the first sample to be sorted is added to the first-level magnetic field strength record sample.

8. A digital control system for the opening of a vehicle carbon canister control valve, characterized in that: A digital control method for the opening of a vehicle carbon canister control valve is used to implement any one of claims 1 to 7, wherein the system is deployed in a carbon canister electronic valve central control unit, and the carbon canister electronic valve central control unit is communicatively connected with the carbon canister solenoid valve, comprising: An operating condition receiving module, the operating condition receiving module is used to receive engine operating conditions, wherein the engine operating conditions include engine torque, engine speed, engine power and engine monitoring temperature; A prediction configuration module, the prediction configuration module is used to integrate and configure the fuel vapor flow prediction unit according to the service life of the engine to obtain a fuel vapor flow prediction model; a flow prediction module, the flow prediction module being used to input the engine torque, the engine speed, the engine power and the engine monitoring temperature into the fuel vapor flow prediction model to obtain an expected fuel vapor flow; The opening control module is used to associate the opening according to the expected flow rate of fuel vapor, obtain the expected valve opening, and control the carbon canister solenoid valve.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing a digital control method for the opening of a vehicle carbon canister control valve as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the digital control method for the opening of a vehicle carbon canister control valve as described in any one of claims 1 to 7 is implemented.

Images