Desorption diagnostic method and related device

Abstract

This application provides a purge diagnosis method and related apparatus. The method includes: upon receiving a diagnostic instruction, using a pressure detection module to obtain purge pressure data, the purge pressure data indicating the amplitude of pressure fluctuations near one end of a switch valve located in a pipeline between the canister and the fuel tank; based on the purge pressure data, determining whether a diagnosis result of the purge diagnosis system meets an alarm condition; and, when the diagnosis result of the purge diagnosis system meets the alarm condition, generating an alarm message and transmitting it to a predetermined user device. This application utilizes the purge pressure data indicating the amplitude of pressure fluctuations near one end of the switch valve located in the pipeline between the canister and the fuel tank to determine whether the diagnosis result of the purge diagnosis system meets the alarm condition, resulting in a highly reliable diagnostic result.

Description

Technical Field

[0001] The present application relates to the field of engine control technology, and in particular to a desorption diagnosis method and related devices. Background Art

[0002] With the implementation of the National VI standard and the gradual improvement of automobile environmental protection requirements, the control of fuel evaporation emissions has become a key link in the design of vehicle fuel systems. In order to reduce the emission of oil and gas into the atmosphere due to saturation of the carbon canister, desorption and flushing of the carbon canister is currently a commonly used solution.

[0003] An engine charcoal canister typically includes an adsorption port, a desorption port, and a vent. The adsorption port is connected to the fuel tank, while the desorption port is connected to the engine's intake manifold. The connection between the desorption port and the intake manifold is controlled by a canister solenoid valve. The vent connects the interior of the canister to the atmosphere, allowing gasoline vapor from the fuel tank to enter the canister through the adsorption port. The existing canister desorption process is as follows: When the canister solenoid valve, controlled by the engine ECU, opens, the canister enters the desorption mode. Specifically, under the negative pressure of the engine intake manifold, air flows into the canister through the vent, removing fuel molecules adsorbed on the activated carbon and reducing the fuel content in the canister. The fuel then enters the engine through the oil and gas pipeline to participate in combustion.

[0004] The relevant desorption process is to perform desorption diagnosis by detecting the pressure change of the intake manifold. When the carbon canister desorption flow rate is small, it will cause misdiagnosis. Summary of the Invention

[0005] The purpose of this application is to provide a desorption diagnostic method, a desorption diagnostic device, a desorption diagnostic system, an electronic device and a computer-readable storage medium, which uses desorption pressure data indicating the pressure fluctuation amplitude of the switch valve near one end of the carbon canister to determine whether the diagnostic result of the desorption diagnostic system meets the alarm condition, and the reliability of the diagnostic result is high.

[0006] The purpose of this application is achieved by the following technical solutions:

[0007] In a first aspect, the present application provides a desorption diagnostic method, comprising:

[0008] After receiving the diagnostic instruction, the pressure detection module is used to obtain desorption pressure data, wherein the desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near the carbon canister, wherein the switch valve is provided in the pipeline between the carbon canister and the fuel tank;

[0009] Based on the desorption pressure data, determining whether a diagnosis result of the desorption diagnosis system meets an alarm condition;

[0010] When the diagnosis result of the desorption diagnosis system meets the alarm condition, an alarm message is generated and sent to a preset user device.

[0011] The beneficial effects of this technical solution are: the pressure fluctuation amplitude is used to judge the diagnostic results, and even when the desorption flow of the carbon canister is small, the desorption status of the carbon canister can be objectively reflected; the desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near one end of the carbon canister, and whether a section of the pipeline from the switch valve to the carbon canister is normal during the desorption process can be detected, avoiding only detecting the intake manifold during the relevant desorption process, and whether the pipeline between the switch valve and the carbon canister is intact can be known in real time, avoiding failure of the pipeline between the switch valve and the carbon canister affecting the desorption of the carbon canister.

[0012] In summary, based on the desorption pressure data used to indicate the pressure fluctuation amplitude of the switch valve near one end of the carbon canister, it is judged whether the diagnostic result of the desorption diagnostic system meets the alarm conditions. When the desorption flow rate of the carbon canister is small, it can also objectively reflect the desorption status of the carbon canister, avoid false fault reports, and improve the reliability of the diagnostic results. The diagnostic results can indicate the integrity of the pipeline from the switch valve to the carbon canister, which is different from the existing method that only focuses on the pressure changes of the intake manifold, and the diagnostic results are more comprehensive.

[0013] In some optional implementations, before obtaining the diagnostic instruction, the method further includes:

[0014] Get the desorption interval time between the last desorption diagnosis and the current time;

[0015] When the desorption interval is not less than a predetermined interval, obtaining engine operation information;

[0016] Based on the operating information of the engine, obtaining the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction, wherein the desorption strategy includes a desorption time of the carbon canister by the engine;

[0017] The method of obtaining desorption pressure data by using the pressure detection module includes:

[0018] Based on the desorption strategy, controlling the engine to maintain a stable operating condition to desorb the carbon canister;

[0019] The switch valve is controlled to remain in a closed state, and the desorption pressure data is acquired by using the pressure detection module.

[0020] The beneficial effects of this technical solution are: the diagnostic instructions are obtained at the same time as the desorption strategy is obtained, and there are no other conditions restricting the acquisition of the diagnostic instructions, which improves the response speed of the desorption diagnosis to the desorption diagnosis; the desorption strategy is obtained based on the engine operating information, and different engine operating information can correspond to different desorption strategies, which improves the desorption effect; the desorption strategy and the diagnostic instructions are obtained based on the same information (engine operating information), avoiding deviations and mismatches between the desorption strategy and the diagnostic instructions caused by different information sources.

[0021] In some optional embodiments, when the desorption interval is not less than a predetermined interval, obtaining the engine operation information includes:

[0022] Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses;

[0023] When the similarity is lower than a preset similarity, shortening the predetermined interval;

[0024] The shortened predetermined interval is compared with the desorption interval, and when the desorption interval is not less than the predetermined interval, the operation information of the engine is acquired.

[0025] The beneficial effects of this technical solution are: the similarity is calculated based on historical desorption pressure data, which can scientifically reflect the desorption effect on the carbon canister during the desorption process. Even if the diagnosis result obtained based on the desorption pressure data does not meet the alarm condition, the change trend of the desorption effect can be obtained from the similarity between the historical desorption pressure data, and when the similarity is lower than the preset similarity, the predetermined interval time is shortened, thereby increasing the frequency of desorption and desorption diagnosis, and avoiding missed desorption diagnosis; calculating the similarity between the two most recent desorption pressure data, on the one hand, reduces the amount of calculation data for similarity calculation and improves the efficiency of similarity calculation; on the other hand, the two most recent desorption pressure data can better reflect the recent vehicle condition of the motor vehicle, reducing the noise influence of historical data with a longer interval time on the similarity calculation and the comparison of similarity with the preset similarity, and avoiding noise interference of longer historical data on the similarity calculation.

[0026] In some optional embodiments, the process of obtaining the desorption strategy includes:

[0027] Inputting the engine operation information into a desorption strategy model to obtain a desorption strategy corresponding to the engine operation information;

[0028] The training process of the desorption strategy model includes:

[0029] Acquire a training set, the training set including a plurality of training data, each of the training data including sample operating information of the engine in a real environment and labeled data of the corresponding desorption strategy;

[0030] For each training data in the training set, perform the following processing:

[0031] Inputting the sample operating information of the engine into a preset first deep learning model to obtain prediction data of the desorption strategy corresponding to the training data;

[0032] Updating model parameters of the first deep learning model based on the predicted data and the labeled data of the desorption strategy corresponding to the training data;

[0033] Detect whether a preset training end condition is met; if so, use the trained first deep learning model as the desorption strategy model; if not, continue training the first deep learning model using the next training data.

[0034] The beneficial effect of this technical solution is that: through design, establishing an appropriate number of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input layers and output layers, a preset first deep learning model can be obtained. Through learning and tuning of the first deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as much as possible. The desorption strategy model trained in this way can predict the corresponding output data based on any input data. It has a wide range of applications, and the calculation results are highly accurate and reliable.

[0035] In some optional embodiments, the process of determining whether the diagnosis result of the desorption diagnosis system meets the alarm condition includes:

[0036] If the pressure fluctuation amplitude indicated by the desorption pressure data is not greater than a preset pressure fluctuation threshold, determining that the diagnosis result of the desorption diagnosis system meets the alarm condition; otherwise, determining that the diagnosis result of the desorption diagnosis system does not meet the alarm condition; and / or,

[0037] The engine operating information is obtained, and the engine operating information and the desorption pressure data are input into a desorption diagnostic model to obtain a diagnostic result corresponding to the engine operating information and the desorption pressure data, wherein the diagnostic result is used to indicate whether an alarm condition is met.

[0038] This technical solution offers the following benefits: Using a pressure fluctuation threshold to determine whether the desorption diagnostic system's diagnostic results meet alarm conditions simplifies the process for obtaining diagnostic results and provides the fastest response time for desorption diagnosis. Using a desorption diagnostic model to obtain diagnostic results takes into account both the impact of engine operating information on canister desorption efficiency and the desorption pressure data's indication of desorption effectiveness, resulting in a highly intelligent approach. Both inputs are then automatically output by the desorption diagnostic model, resulting in high diagnostic efficiency.

[0039] In a second aspect, the present application further provides a desorption diagnostic device, comprising:

[0040] a pressure differential acquisition module, configured to, upon receiving a diagnostic instruction, use the pressure detection module to acquire desorption pressure data, the desorption pressure data being used to indicate a pressure fluctuation amplitude of a switch valve near one end of the carbon canister, the switch valve being disposed in a pipeline between the carbon canister and the fuel tank;

[0041] a condition judgment module, configured to judge whether a diagnosis result of the desorption diagnosis system meets an alarm condition based on the desorption pressure data;

[0042] The diagnosis alarm module is used to generate an alarm message and send it to a preset user device when the diagnosis result of the desorption diagnosis system meets the alarm condition.

[0043] In some optional embodiments, before obtaining the diagnostic instruction, the desorption diagnostic device further includes:

[0044] The duration acquisition module is used to obtain the desorption interval time between the last desorption diagnosis and the current moment;

[0045] an operating information acquisition module, configured to acquire engine operating information when the desorption interval is not less than a predetermined interval;

[0046] a measurement acquisition module, configured to acquire the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction based on the operating information of the engine, wherein the desorption strategy includes a desorption time of the carbon canister by the engine;

[0047] The pressure difference acquisition module includes:

[0048] a desorption control unit, configured to control the engine to maintain a stable operating condition based on the desorption strategy so as to desorb the carbon canister;

[0049] The pressure acquisition unit is used to control the switch valve to remain in a closed state and to acquire the desorption pressure data using the pressure detection module.

[0050] In some optional embodiments, when the desorption interval is not less than a predetermined interval, obtaining the engine operation information includes:

[0051] Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses;

[0052] When the similarity is lower than a preset similarity, shortening the predetermined interval;

[0053] The shortened predetermined interval is compared with the desorption interval, and when the desorption interval is not less than the predetermined interval, the operation information of the engine is acquired.

[0054] In some optional embodiments, the process of obtaining the desorption strategy includes:

[0055] Inputting the engine operation information into a desorption strategy model to obtain a desorption strategy corresponding to the engine operation information;

[0056] The training process of the desorption strategy model includes:

[0057] Acquire a training set, the training set including a plurality of training data, each of the training data including sample operating information of the engine in a real environment and labeled data of the corresponding desorption strategy;

[0058] For each training data in the training set, perform the following processing:

[0059] Inputting the sample operating information of the engine into a preset first deep learning model to obtain prediction data of the desorption strategy corresponding to the training data;

[0060] Updating model parameters of the first deep learning model based on the predicted data and the labeled data of the desorption strategy corresponding to the training data;

[0061] Detect whether a preset training end condition is met; if so, use the trained first deep learning model as the desorption strategy model; if not, continue training the first deep learning model using the next training data.

[0062] In some optional embodiments, the process of determining whether the diagnosis result of the desorption diagnosis system meets the alarm condition includes:

[0063] If the pressure fluctuation amplitude indicated by the desorption pressure data is not greater than a preset pressure fluctuation threshold, determining that the diagnosis result of the desorption diagnosis system meets the alarm condition; otherwise, determining that the diagnosis result of the desorption diagnosis system does not meet the alarm condition; and / or,

[0064] The engine operating information is obtained, and the engine operating information and the desorption pressure data are input into a desorption diagnostic model to obtain a diagnostic result corresponding to the engine operating information and the desorption pressure data, wherein the diagnostic result is used to indicate whether an alarm condition is met.

[0065] In a third aspect, the present application further provides a desorption diagnostic system, the desorption diagnostic system comprising a switch valve, a pressure detection module, and the desorption diagnostic device according to the second aspect;

[0066] The switch valve is provided on the pipeline between the carbon canister and the fuel tank, and is used to connect and close the carbon canister and the fuel tank;

[0067] The pressure detection module is connected to both ends of the switch valve and is used to obtain the pressure fluctuation amplitude of the switch valve at one end close to the carbon canister.

[0068] In some optional embodiments, the pressure detection module includes a first pressure sensor and a second pressure sensor, and the first pressure sensor and the second pressure sensor are respectively arranged at two ends of the switch valve; or,

[0069] The pressure detection module includes a pressure differential sensor, and the pressure differential sensor is communicated with both ends of the switch valve respectively.

[0070] In a fourth aspect, the present application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0071] In a fifth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The present application is further described below with reference to the accompanying drawings and examples.

[0073] Figure 1 A schematic flow chart of a desorption diagnostic method provided in the present application is shown.

[0074] Figure 2 A schematic diagram of a process for obtaining a desorption strategy provided in this application is shown.

[0075] Figure 3 A schematic diagram of a process for obtaining desorption pressure data provided by the present application is shown.

[0076] Figure 4 A schematic diagram of a process for obtaining engine operating information provided by the present application is shown.

[0077] Figure 5 A schematic structural diagram of a desorption diagnostic device provided in this application is shown.

[0078] Figure 6 Shown is a structural block diagram of a desorption diagnostic system provided by the present application.

[0079] Figure 7 A schematic structural diagram of an electronic device provided in this application is shown.

[0080] Figure 8 Shown is a structural block diagram of a program product provided by this application. DETAILED DESCRIPTION

[0081] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0082] It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0083] In this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0084] The first, second, etc. descriptions appearing in the embodiments of this application are only for illustration and distinction of the description objects. There is no order, nor does it indicate any special limitation on the number of devices in the embodiments of this application, and cannot constitute any limitation on the embodiments of this application.

[0085] First, a brief description is given of one of the application fields (motor vehicle desorption field) of the embodiment of the present application.

[0086] Desorption is the reverse process of adsorption. It is an operational process in which the adsorbed components are precipitated from the saturated adsorbent, allowing the adsorbent to be regenerated. That is, the adsorbed substance is desorbed under certain conditions. Specifically for motor vehicles, engine fuel (diesel or gasoline) is volatile. If there is no charcoal canister, the engine fuel will evaporate directly into the atmosphere, causing air pollution. A charcoal canister can be added between the engine and the atmosphere. Although the activated carbon in the charcoal canister will absorb the gaseous fuel that evaporates from the fuel supply system, the amount of gaseous fuel that the activated carbon can adsorb has a limit. Because the vacuum at the intake manifold end is lower than that at the charcoal canister end when the engine is running, the fuel absorbed in the activated carbon can be recovered into the engine intake duct based on the pressure difference between the charcoal canister and the engine, and sent to the engine combustion chamber to be used as fuel. The fuel tank is a container for fuel and a special container for storing hydraulic oil or hydraulic fluid in the hydraulic system.

[0087] The switch valve is an executive element of the electronic control system of a motor vehicle, and is used to receive a control signal sent by the vehicle control module (MCU, Electronic Control Unit, engine control unit) to execute the conduction or cutoff of the two ends of the switch valve. The switch valve can also be provided with a pressure protection function. When the pressure acting on the switch valve reaches the opening pressure, the switch valve opens and the fuel vapor is discharged through the valve seat. For example, the switch valve is a fuel tank isolation valve (i.e., FTIV valve). In the embodiment of the present application, the full name of the fuel tank isolation valve (i.e., FTIV valve) is Fuel Tank Isolation Valve, which seals the evaporated oil and gas in the fuel tank in the fuel tank. The oil and gas in the fuel tank can be released into the charcoal canister and enter the engine through the charcoal canister for combustion.

[0088] Under normal circumstances, the fuel tank isolation valve remains closed. It opens only when a refueling request is made, the tank pressure exceeds a certain threshold, or there is a significant negative pressure inside the tank. Fuel tank isolation valve opening is activated, releasing fuel vapors into the charcoal canister. Additionally, fuel tank leak diagnosis can trigger a request to open the fuel tank isolation valve.

[0089] In the embodiments of the present application, negative pressure refers to a gas state with a gas pressure lower than normal pressure (i.e., one atmospheric pressure). For example, a miniature vacuum pump can form a negative pressure of 0.04 MPa at the exhaust end, which means that 40% of the gas in the closed container can be extracted, and the remaining 60% has a pressure difference of 100*(1-0.6)=40KPA with respect to the external atmospheric pressure (i.e., its negative pressure value is: -40Kpa), which is displayed as -0.04Mpa on a commonly used vacuum gauge, assuming that the local atmospheric pressure is 0.1Mpa. The embodiments of the present application do not limit the pressure of the negative pressure environment, and it can be, for example, 80Kpa, 93KPa, 94Kpa, or 99Kpa.

[0090] Similarly, in the embodiments of the present application, positive pressure refers to a gas state with a gas pressure higher than normal pressure (i.e., one atmospheric pressure as commonly known). For example, a micro vacuum pump (which can be used for both pumping and inflating) can form a positive pressure of 0.1 MPa (relative pressure) at the exhaust end, which means that it can form a gas pressure 0.1 MPa higher than atmospheric pressure. A positive pressure environment refers to an environment in which the air pressure is positive. The embodiments of the present application do not limit the pressure of the positive pressure environment, which can be, for example, 102 KPa, 105 KPa, 106 KPa, or 130 KPa.

[0091] (Method Example)

[0092] See also Figure 1 , Figure 1 A schematic flow chart of a desorption diagnostic method provided in the present application is shown.

[0093] The desorption diagnostic method comprises:

[0094] Step S101: After receiving the diagnostic instruction, the pressure detection module is used to obtain desorption pressure data. The desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near the carbon canister. The switch valve is set in the pipeline between the carbon canister and the fuel tank.

[0095] Step S102: Based on the desorption pressure data, determining whether the diagnosis result of the desorption diagnosis system meets the alarm condition;

[0096] Step S103: When the diagnosis result of the desorption diagnosis system meets the alarm condition, an alarm message is generated and sent to a preset user device.

[0097] Therefore, the pressure fluctuation amplitude is used to judge the diagnosis result, and the desorption status of the carbon canister can be objectively reflected even when the desorption flow rate of the carbon canister is small; the desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near one end of the carbon canister, and whether a section of the pipeline from the switch valve to the carbon canister is normal can be detected during the desorption process, avoiding only detecting the intake manifold during the relevant desorption process, and knowing in real time whether the pipeline between the switch valve and the carbon canister is intact, avoiding failure of the pipeline between the switch valve and the carbon canister affecting the desorption of the carbon canister.

[0098] In summary, based on the desorption pressure data used to indicate the pressure fluctuation amplitude of the switch valve near one end of the carbon canister, it is judged whether the diagnostic result of the desorption diagnostic system meets the alarm conditions. When the desorption flow rate of the carbon canister is small, it can also objectively reflect the desorption status of the carbon canister, avoid false fault reports, and improve the reliability of the diagnostic results. The diagnostic results can indicate the integrity of the pipeline from the switch valve to the carbon canister, which is different from the existing method that only focuses on the pressure changes of the intake manifold, and the diagnostic results are more comprehensive.

[0099] The desorption pressure data indicates the amplitude of pressure fluctuations near the canister end of the on-off valve. This can be the ratio of the pressure rise or fall over a fixed time period, or the difference in pressure rise or fall detected by the pressure detection module over a fixed time period. Examples include a 7% rise per minute, a 3% fall per second, a 0.03 kPa rise per minute, and a 0.003 kPa rise per minute. Desorption pressure data can also be presented as a pressure-time curve, with the horizontal axis representing time and the vertical axis representing the pressure change at each corresponding time point.

[0100] The diagnostic result can be expressed using at least one of Chinese characters, letters, numbers and special symbols, such as "A001", "B001", "low desorption efficiency", "normal desorption", "abnormal desorption" or "#01" or any one or a combination thereof.

[0101] In a specific application, "A001", "low desorption efficiency", and "normal desorption" are used to indicate that the desorption condition is normal and the diagnosis result does not meet the alarm condition.

[0102] In another specific application, "B001", "very low desorption efficiency", "abnormal desorption", and "#01" are used to indicate that the desorption condition is abnormal and the diagnosis result meets the alarm condition.

[0103] This embodiment does not limit the preset user equipment, and the user equipment can be a central console of a motor vehicle, a smart phone, a tablet, a computer, etc.

[0104] In a specific application, when the user device is a center console of a motor vehicle and the diagnosis result of the desorption diagnosis system meets the alarm condition, after the center console receives the alarm information, the center console fault light indicating the desorption fault will flash to alarm.

[0105] In another specific application, when the user device is a smart phone and the diagnosis result of the desorption diagnosis system meets the alarm condition, after the alarm information is received by the smart phone, the smart phone displays a pop-up window to remind the user of the desorption fault.

[0106] See also Figure 2 and Figure 3 , Figure 2 A schematic diagram of a process for obtaining a desorption strategy provided by the present application is shown. Figure 3 A schematic diagram of a process for obtaining desorption pressure data provided by the present application is shown.

[0107] In some optional implementations, before step S101, the method may further include:

[0108] Step S104: obtaining the desorption interval between the last desorption diagnosis and the current moment;

[0109] Step S105: when the desorption interval is not less than the predetermined interval, obtaining engine operation information;

[0110] Step S106: Based on the engine operation information, the diagnostic instruction and the desorption strategy corresponding to the diagnostic instruction are obtained. The desorption strategy includes the desorption time of the carbon canister by the engine.

[0111] Step S101 may include:

[0112] Step S201: Based on the desorption strategy, controlling the engine to maintain a stable operating condition to desorb the carbon canister;

[0113] Step S202: controlling the switch valve to remain in a closed state, and using the pressure detection module to obtain the desorption pressure data.

[0114] Therefore, the diagnostic instructions are obtained at the same time as the desorption strategy is obtained, and there are no other conditions restricting the acquisition of the diagnostic instructions, which improves the response speed of the desorption diagnosis to the desorption diagnosis; the desorption strategy is obtained based on the engine operating information, and different engine operating information can correspond to different desorption strategies, which improves the desorption effect; the desorption strategy and the diagnostic instructions are obtained based on the same information (engine operating information), avoiding deviations and mismatches between the desorption strategy and the diagnostic instructions caused by different information sources.

[0115] Among them, the desorption interval length between the last desorption diagnosis and the current moment can refer to the length of time from the start moment of the last desorption diagnosis to the current moment. Since the duration of the last desorption diagnosis does not need to be considered, the amount of calculation when obtaining the desorption interval length is small, which reduces the pressure of data processing and improves the efficiency of obtaining desorption strategies and diagnostic instructions.

[0116] The desorption interval between the last desorption diagnosis and the current moment can also refer to the length of time from the end of the last desorption diagnosis to the current moment. When the desorption interval between the last desorption diagnosis and the current moment refers to the length of time from the end of the last desorption diagnosis to the current moment, excluding the duration of the last desorption process from the desorption interval can more objectively reflect the time interval without desorption diagnosis.

[0117] The embodiments of the present application do not limit the engine operating information. The engine operating information may be one or a combination of the actual engine speed data, the engine continuous operating time data, and the engine running distance data. The stable engine operating condition can be understood as the engine idling or stable speed.

[0118] The desorption strategy can be the desorption time of desorbing the carbon canister by using the engine negative pressure. The desorption time corresponding to a desorption strategy can be continuous, such as continuous desorption for 10 minutes, 2 minutes, and 30 seconds, or it can be discontinuous, such as desorption for 30 seconds after pausing for 1 minute within 10 minutes, and pausing for 1 second every 10 seconds of desorption within 1 minute.

[0119] The pressure detection module may include a first pressure sensor and a second pressure sensor, each disposed at either end of the on-off valve. For example, the first pressure sensor may be disposed on one side of the on-off valve closest to the fuel tank, while the second pressure sensor may be disposed on the other side of the on-off valve. When the on-off valve remains closed, the pressure value acquired by the first pressure sensor may be considered relatively fixed. The pressure value acquired by the second pressure sensor may fluctuate during normal desorption conditions. The second pressure sensor and the first pressure sensor are used to acquire the pressure difference at different times to obtain desorption pressure data. Since the pressure acquired by the first pressure sensor is used to acquire the desorption pressure data, the desorption status of the canister can be objectively reflected even when the desorption flow rate of the canister is low. Alternatively, the first pressure sensor may be disposed within the fuel tank. However, due to the volatility of the fuel within the tank, the pressure value acquired by the first pressure sensor when disposed within the tank is relatively unstable.

[0120] Alternatively, the pressure detection module may also include a differential pressure sensor, each connected to the two ends of the on-off valve. The differential pressure sensor measures the pressure difference across the on-off valve at different times to generate desorption pressure data. This objectively reflects the desorption status of the canister even when the canister's desorption flow rate is low. Compared to a pressure detection module consisting of a first pressure sensor and a second pressure sensor, the differential pressure sensor occupies less space, has a lower failure rate, and improves the stability of desorption diagnosis.

[0121] See also Figure 4 , Figure 4 A schematic diagram of a process for obtaining engine operating information provided by the present application is shown.

[0122] In some optional implementations, step S105 may include:

[0123] Step S301: obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses;

[0124] Step S302: when the similarity is lower than a preset similarity, shortening the predetermined interval;

[0125] Step S303: comparing the shortened predetermined interval with the desorption interval, and obtaining the engine operation information when the desorption interval is not less than the predetermined interval.

[0126] Therefore, the similarity is calculated based on the historical desorption pressure data, which can scientifically reflect the desorption effect on the carbon canister during the desorption process. Even if the diagnosis result obtained based on the desorption pressure data does not meet the alarm condition, the change trend of the desorption effect can be obtained from the similarity between the historical desorption pressure data, and when the similarity is lower than the preset similarity, the predetermined interval time is shortened, thereby increasing the frequency of desorption and desorption diagnosis, and avoiding missed desorption diagnosis; calculating the similarity between the two most recent desorption pressure data, on the one hand, reduces the amount of calculation data for the similarity calculation and improves the efficiency of the similarity calculation; on the other hand, the two most recent desorption pressure data can better reflect the recent vehicle condition of the motor vehicle, reducing the noise influence of historical data with a longer interval on the similarity calculation and the comparison of the similarity with the preset similarity, and avoiding the noise interference of longer historical data on the similarity calculation.

[0127] This embodiment does not limit the method for obtaining engine operating information. For example, if the operating information is engine speed, the engine speed signal can be obtained based on the ignition pulse, or it can be calculated by measuring the crankshaft speed using a signal disk mounted on the engine crankshaft. For example, if the operating information is engine distance traveled, the engine distance traveled can be calculated based on the engine speed and operating time.

[0128] This embodiment does not limit the preset similarity, which may be 0.98, 80%, or 95%, for example.

[0129] This embodiment does not limit the method for obtaining similarity. In a specific application, when the desorption pressure data of the two most recent desorption diagnoses are pressure-time curves, the similarity between the two can be obtained based on each point of the curve, the shape of the curve (Hausdorff distance calculation), and the segmentation of the curve (such as the one-way distance method). When the similarity between the two is lower than a preset similarity (such as 0.98 or 0.95), it can be considered that the similarity between the desorption pressure data of the two most recent desorption diagnoses is low and the desorption condition is unstable, thereby shortening the predetermined interval and increasing the frequency of desorption and desorption diagnosis.

[0130] In another specific application, similarity can also be determined using the Pearson Correlation Coefficient method. Desorption pressure data from the two most recent desorption diagnoses can be obtained and then compared using the Pearson Correlation Coefficient method to determine a linear correlation between the two. For example, if the Pearson coefficient is 0.85, the desorption pressure data from the two desorption diagnoses can be considered highly correlated, with a similarity of 0.85.

[0131] In another specific application, the desorption pressure data of the two most recent desorption diagnoses are input into the similarity model to obtain the similarity corresponding to the desorption pressure data of the two most recent desorption diagnoses.

[0132] The training process of the similarity model may include: obtaining a similarity training set, the similarity training set including a plurality of similarity training data pairs and their corresponding labeled similarities, and training a preset second deep learning model using the similarity training set to obtain the similarity model.

[0133] The similarity training set is used to train a preset second deep learning model, including: for multiple similarity training data in the similarity training set, each similarity training data includes a first sample object and a second sample object, inputting any similarity training data into the preset second deep learning model to obtain a predicted similarity corresponding to the sample similarity training data; based on the corresponding predicted similarity and labeled similarity with the sample similarity training data, updating the model parameters of the second deep learning model; detecting whether a preset training end condition is met, if so, stopping training, and using the trained second deep learning model as the similarity model, if not, repeating the above training process to continue training the second deep learning model.

[0134] The first sample object and the second sample object respectively include sample desorption pressure data. Because the similarity model can be trained with a large amount of training data, it can predict corresponding output data for different input data, has a wide range of applications, and a high level of intelligence. By designing, establishing an appropriate number of neuron computing nodes and a multi-layered computing hierarchy, and selecting appropriate input and output layers, a preset second deep learning model can be obtained. Through learning and tuning of this preset second deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, it can be as close to the actual correlation relationship as possible. The similarity model thus trained can obtain the similarity between each historical measurement data and the second measurement data based on the similarity between the two, and the calculation results are highly accurate and reliable.

[0135] In some optional implementations, the present application may adopt the above-mentioned training process to train a similarity model. In other optional implementations, the present application may adopt a pre-trained similarity model.

[0136] In some optional implementations, for example, data mining can be performed on historical data to obtain training data. Of course, the first sample object and the second sample object can also be automatically generated using the generative network of the GAN model.

[0137] The GAN model, or Generative Adversarial Network, consists of a generator and a discriminator. The generator takes random samples from the latent space as input, and its output is required to closely mimic real samples from the training set. The discriminator receives real samples or the output of the generator, with the goal of distinguishing the generator output from real samples as closely as possible. The generator, in turn, is tasked with deceiving the discriminator as much as possible. The two networks compete against each other, constantly adjusting their parameters with the ultimate goal of making it impossible for the discriminator to determine whether the generator output is realistic.

[0138] The predicted similarity can be expressed in numbers or percentages. When expressed in numbers, the predicted similarity is, for example, 60, 80, or 90; when expressed in percentages, the predicted similarity is, for example, 50%, 70%, or 90%. The higher the number, the higher the predicted similarity.

[0139] The present application does not limit the preset similarity threshold, which may be 70%, 80% or 90%.

[0140] This application does not limit the preset training end conditions. For example, it can be that the number of training times reaches a preset number (the preset number is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10,000 times, etc.), or it can be that all the training data in the training set complete one or more trainings, or it can be that the total loss value obtained from this training is not greater than the preset loss value.

[0141] In some optional embodiments, the process of obtaining the desorption strategy may include:

[0142] Inputting the engine operation information into a desorption strategy model to obtain a desorption strategy corresponding to the engine operation information;

[0143] The training process of the desorption strategy model includes:

[0144] Acquire a training set, the training set including a plurality of training data, each of the training data including sample operating information of the engine in a real environment and labeled data of the corresponding desorption strategy;

[0145] For each training data in the training set, perform the following processing:

[0146] Inputting the sample operating information of the engine into a preset first deep learning model to obtain prediction data of the desorption strategy corresponding to the training data;

[0147] Updating model parameters of the first deep learning model based on the predicted data and the labeled data of the desorption strategy corresponding to the training data;

[0148] Detect whether a preset training end condition is met; if so, use the trained first deep learning model as the desorption strategy model; if not, continue training the first deep learning model using the next training data.

[0149] Therefore, by designing, establishing an appropriate number of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input and output layers, the preset first deep learning model can be obtained. Through the learning and tuning of the first deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as much as possible. The desorption strategy model trained in this way can predict the corresponding output data based on any input data. It has a wide range of applications, and the calculation results are highly accurate and reliable.

[0150] In some optional implementations, the embodiments of the present application may train a desorption strategy model, and in other optional implementations, the embodiments of the present application may adopt a pre-trained desorption strategy model.

[0151] In some optional implementations, for example, data mining can be performed on historical data to obtain multiple training data in the training set and their corresponding labeled data of the desorption strategy. The multiple training data in the training set can also be automatically generated using the generative network of the GAN model.

[0152] The embodiment of the present application does not limit the method for obtaining the labeled data. For example, manual labeling, automatic labeling, or semi-automatic labeling can be used.

[0153] The embodiment of the present application does not limit the training process of the desorption strategy model. For example, it can adopt the above-mentioned supervised learning training method, or can adopt the semi-supervised learning training method, or can adopt the unsupervised learning training method.

[0154] The embodiments of the present application do not limit the preset training end conditions. For example, it can be that the number of training times reaches a preset number (the preset number of times is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10,000 times, etc.), or it can be that all the training data in the training set complete one or more trainings, or it can be that the total loss value obtained from this training is not greater than the preset loss value.

[0155] In other optional embodiments, the step of obtaining the desorption strategy corresponding to the diagnostic instruction may include: inputting the obtained engine operating information into a preset desorption strategy calculation formula, and calculating the desorption strategy corresponding to the obtained engine operating information. The present application does not limit the preset desorption strategy calculation formula, which may be, for example, a univariate polynomial or a multivariate polynomial, or, for example, a linear polynomial or a nonlinear polynomial. Using the desorption strategy calculation formula and the independent variable (engine operating information), the dependent variable (the predicted desorption strategy corresponding to the engine operating information) is calculated. The calculation process based on the calculation formula consumes less computing resources, takes less computing time, and has higher computing efficiency.

[0156] In some optional embodiments, the process of determining whether the diagnosis result of the desorption diagnosis system meets the alarm condition may include:

[0157] If the pressure fluctuation amplitude indicated by the desorption pressure data is not greater than a preset pressure fluctuation threshold, determining that the diagnosis result of the desorption diagnosis system meets the alarm condition; otherwise, determining that the diagnosis result of the desorption diagnosis system does not meet the alarm condition; and / or,

[0158] The engine operating information is obtained, and the engine operating information and the desorption pressure data are input into a desorption diagnostic model to obtain a diagnostic result corresponding to the engine operating information and the desorption pressure data, wherein the diagnostic result is used to indicate whether an alarm condition is met.

[0159] Therefore, the pressure fluctuation threshold is used to determine whether the diagnostic results of the desorption diagnostic system meet the alarm conditions. The process of obtaining the diagnostic results is simple and the response speed of the desorption diagnosis can be obtained as quickly as possible. The desorption diagnostic model is used to obtain the diagnostic results, which takes into account both the impact of the engine's operating information on the canister's desorption efficiency and the indication of the desorption pressure data on the desorption effect, and has a high level of intelligence. Both are input into the desorption diagnostic model, and the desorption diagnostic model is used to (automatically) output the diagnostic results, which has a high diagnostic efficiency.

[0160] The present application does not limit the method for obtaining the desorption diagnostic model. In some embodiments, the present application can train the desorption diagnostic model. In other embodiments, the present application can use a pre-trained desorption diagnostic model.

[0161] In some optional embodiments, the desorption diagnosis model may be trained using the following training process: obtaining a desorption diagnosis training set, wherein each training data in the desorption diagnosis training set includes operating information and desorption pressure data of an engine used for training, and labeled data of a diagnosis result corresponding to the training data;

[0162] For each training data in the desorption diagnosis training set, the following processing is performed:

[0163] Inputting the engine operating information and desorption pressure data in the training data into a preset third deep learning model to obtain prediction data of the diagnosis result corresponding to the training data;

[0164] Updating model parameters of the third deep learning model based on the predicted data and the labeled data of the diagnosis result corresponding to the training data;

[0165] Detect whether a preset training end condition is met; if so, use the trained third deep learning model as the desorption strategy model; if not, continue training the third deep learning model using the next training data.

[0166] By designing, establishing an appropriate number of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input and output layers, a preset third deep learning model can be obtained. Through learning and tuning of the preset third deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as much as possible. The desorption diagnosis model trained in this way can realize the function of obtaining diagnostic results, and the calculation results are highly accurate and reliable.

[0167] In some embodiments, the present application may adopt the above-mentioned training process to train a desorption diagnosis model. In other embodiments, the present application may adopt a pre-trained desorption diagnosis model.

[0168] This application does not limit the method of obtaining the labeled data. For example, manual labeling, automatic labeling, or semi-automatic labeling can be used.

[0169] The present application does not limit the training process of the desorption diagnosis model. For example, it can adopt the above-mentioned supervised learning training method, or can adopt the semi-supervised learning training method, or can adopt the unsupervised learning training method.

[0170] This application does not limit the preset training end conditions. For example, it can be that the number of training times reaches a preset number (the preset number is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10,000 times, etc.), or it can be that the training data in the desorption diagnosis training set completes one or more training times, or it can be that the total loss value obtained in this training is not greater than the preset loss value.

[0171] This embodiment does not limit the pressure fluctuation threshold, which can be expressed, for example, by the magnitude of the pressure fluctuation or by the ratio of the pressure increase or decrease, such as 10 kPa, 120 kPa, or 10%.

[0172] In some optional embodiments, the method may further include the following steps:

[0173] The switch valve is controlled to maintain a conducting state, and an air pump is used to pump air into the charcoal canister or the fuel tank to generate a pressure difference between the charcoal canister and the fuel tank. The air pump is arranged between the switch valve and the charcoal canister, and a pressure detection module is connected to an end of the air pump close to the charcoal canister and an end of the switch valve close to the fuel tank, respectively.

[0174] Using a pressure detection module to obtain pressure data, the pressure data is used to indicate the pressure difference between the two opposite ends of the switch valve and the air pump;

[0175] According to the pressure data value, it is determined whether there are leaks in the pipelines at both ends of the switch valve and the air pump.

[0176] Therefore, the air pump and the switch valve are combined to detect the pressure changes between the charcoal canister and the fuel tank in a sealed state to detect whether there is leakage between the two. The operation is simple and convenient; the pressure detection module used for desorption diagnosis is reused for leakage detection of the charcoal canister and the fuel tank, providing users with more options without significantly increasing the space occupied.

[0177] This embodiment does not limit the size of the diagnostic pressure threshold. The diagnostic pressure threshold is expressed as a pressure value, such as 20 kPa, 90 kPa, or 110 kPa.

[0178] In a specific application, the switch valve can be controlled to remain in an on state, and an air pump can be used to pump air into the charcoal canister, so that the charcoal canister is in a positive pressure environment and the fuel tank is in a negative pressure environment. Then, a pressure detection module is used to obtain pressure data, which is used to indicate the pressure difference between the two opposite ends of the switch valve and the air pump. When the pressure difference between the two ends is not lower than the diagnostic pressure threshold, the switch valve is controlled to close and the air pump stops pumping air.

[0179] The pressure detection module is used to obtain pressure data after the switch valve is closed, and based on the pressure data after the switch valve is closed, it is determined whether there is leakage in the pipelines at both ends of the switch valve and the air pump.

[0180] For example, when there is a leak in the pipeline of the switch valve or air pump near one end of the fuel tank, the pressure difference between the two ends indicated by the pressure data will be larger than the normal situation (no leakage); when there is a leak in the pipeline of the switch valve or air pump near one end of the charcoal canister, the pressure difference between the two ends indicated by the pressure data will be smaller than the normal situation (no leakage).

[0181] In another specific application, the switch valve can be controlled to remain in an on state, and an air pump can be used to pump air into the fuel tank, so that the fuel tank is in a positive pressure environment and the carbon canister is in a negative pressure environment. Then, a pressure detection module can be used to obtain pressure data, which is used to indicate the pressure difference between the two opposite ends of the switch valve and the air pump. When the pressure difference between the two ends is not lower than a diagnostic pressure threshold, the switch valve is controlled to close and the air pump stops pumping air.

[0182] The pressure detection module is used to obtain pressure data after the switch valve is closed, and based on the pressure data after the switch valve is closed, it is determined whether there is leakage in the pipelines at both ends of the switch valve and the air pump.

[0183] For example, when there is a leak in the pipeline of the switch valve or air pump near one end of the charcoal canister, the pressure difference between the two ends indicated by the pressure data will be larger than the normal situation (no leakage); when there is a leak in the pipeline of the switch valve or air pump near one end of the fuel tank, the pressure difference between the two ends indicated by the pressure data will be smaller than the normal situation (no leakage).

[0184] In a specific application scenario, the desorption diagnostic method may include:

[0185] Get the desorption interval time between the last desorption diagnosis and the current time;

[0186] Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses;

[0187] When the similarity is lower than a preset similarity, shortening the predetermined interval;

[0188] comparing the shortened predetermined interval with the desorption interval, and acquiring the engine operation information when the desorption interval is not less than the predetermined interval;

[0189] Based on the operating information of the engine, obtaining the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction, wherein the desorption strategy includes a desorption time of the carbon canister by the engine;

[0190] After receiving the diagnostic instruction, the engine is controlled to maintain a stable operating condition based on the desorption strategy to desorb the carbon canister;

[0191] controlling the switch valve to remain in a closed state and using the pressure detection module to obtain the desorption pressure data, wherein the desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near one end of the carbon canister, wherein the switch valve is provided on the pipeline between the carbon canister and the fuel tank;

[0192] If the pressure fluctuation amplitude indicated by the desorption pressure data is not greater than a preset pressure fluctuation threshold, determining that the diagnosis result of the desorption diagnosis system meets the alarm condition; otherwise, determining that the diagnosis result of the desorption diagnosis system does not meet the alarm condition;

[0193] When the diagnosis result of the desorption diagnosis system meets the alarm condition, an alarm message is generated and sent to a preset user device.

[0194] In another specific application scenario, the desorption diagnostic method may include:

[0195] Get the desorption interval time between the last desorption diagnosis and the current time;

[0196] Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses;

[0197] When the similarity is lower than a preset similarity, shortening the predetermined interval;

[0198] comparing the shortened predetermined interval with the desorption interval, and acquiring the engine operation information when the desorption interval is not less than the predetermined interval;

[0199] Based on the operating information of the engine, obtaining the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction, wherein the desorption strategy includes a desorption time of the carbon canister by the engine;

[0200] After receiving the diagnostic instruction, the engine is controlled to maintain a stable operating condition based on the desorption strategy to desorb the carbon canister;

[0201] controlling the switch valve to remain in a closed state and using the pressure detection module to obtain the desorption pressure data, wherein the desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near one end of the carbon canister, wherein the switch valve is provided on the pipeline between the carbon canister and the fuel tank;

[0202] acquiring engine operating information, and inputting the engine operating information and the desorption pressure data into a desorption diagnostic model to obtain a diagnostic result corresponding to the engine operating information and the desorption pressure data, wherein the diagnostic result is used to indicate whether an alarm condition is met;

[0203] When the diagnosis result of the desorption diagnosis system meets the alarm condition, an alarm message is generated and sent to a preset user device.

[0204] The acquisition process of the above-mentioned desorption strategy may include:

[0205] Inputting the engine operation information into a desorption strategy model to obtain a desorption strategy corresponding to the engine operation information;

[0206] The training process of the desorption strategy model includes:

[0207] Acquire a training set, the training set including a plurality of training data, each of the training data including sample operating information of the engine in a real environment and labeled data of the corresponding desorption strategy;

[0208] For each training data in the training set, perform the following processing:

[0209] Inputting the sample operating information of the engine into a preset first deep learning model to obtain prediction data of the desorption strategy corresponding to the training data;

[0210] Updating model parameters of the first deep learning model based on the predicted data and the labeled data of the desorption strategy corresponding to the training data;

[0211] Detect whether a preset training end condition is met; if so, use the trained first deep learning model as the desorption strategy model; if not, continue training the first deep learning model using the next training data.

[0212] (Device Example)

[0213] See also Figure 5 , Figure 5 A schematic structural diagram of a desorption diagnostic device provided in this application is shown.

[0214] The embodiment of the present application also provides a desorption diagnostic device, the specific implementation of which is consistent with the implementation method and the technical effect achieved in the above method embodiment, and some contents will not be repeated here.

[0215] The desorption diagnostic device comprises:

[0216] A pressure differential acquisition module 101 is configured to, upon receiving a diagnostic instruction, use a pressure detection module to acquire desorption pressure data, the desorption pressure data being used to indicate a pressure fluctuation amplitude of a switch valve located on a pipeline between the canister and the fuel tank, the switch valve being disposed near one end of the canister;

[0217] A condition judgment module 102 is configured to judge whether a diagnosis result of the desorption diagnosis system meets an alarm condition based on the desorption pressure data;

[0218] The diagnosis alarm module 103 is configured to generate an alarm message and send the alarm message to a preset user device when the diagnosis result of the desorption diagnosis system meets the alarm condition.

[0219] In some optional embodiments, before obtaining the diagnostic instruction, the desorption diagnostic device further includes:

[0220] The duration acquisition module is used to obtain the desorption interval time between the last desorption diagnosis and the current moment;

[0221] an operating information acquisition module, configured to acquire engine operating information when the desorption interval is not less than a predetermined interval;

[0222] a measurement acquisition module, configured to acquire the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction based on the operating information of the engine, wherein the desorption strategy includes a desorption time of the carbon canister by the engine;

[0223] The pressure difference acquisition module includes:

[0224] a desorption control unit, configured to control the engine to maintain a stable operating condition based on the desorption strategy so as to desorb the carbon canister;

[0225] The pressure acquisition unit is used to control the switch valve to remain in a closed state and to acquire the desorption pressure data using the pressure detection module.

[0226] In some optional embodiments, when the desorption interval is not less than a predetermined interval, obtaining the engine operation information includes:

[0227] Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses;

[0228] When the similarity is lower than a preset similarity, shortening the predetermined interval;

[0229] The shortened predetermined interval is compared with the desorption interval, and when the desorption interval is not less than the predetermined interval, the operation information of the engine is acquired.

[0230] In some optional embodiments, the process of obtaining the desorption strategy includes:

[0231] Inputting the engine operation information into a desorption strategy model to obtain a desorption strategy corresponding to the engine operation information;

[0232] The training process of the desorption strategy model includes:

[0233] Acquire a training set, the training set including a plurality of training data, each of the training data including sample operating information of the engine in a real environment and labeled data of the corresponding desorption strategy;

[0234] For each training data in the training set, perform the following processing:

[0235] Inputting the sample operating information of the engine into a preset first deep learning model to obtain prediction data of the desorption strategy corresponding to the training data;

[0236] Updating model parameters of the first deep learning model based on the predicted data and the labeled data of the desorption strategy corresponding to the training data;

[0237] Detect whether a preset training end condition is met; if so, use the trained first deep learning model as the desorption strategy model; if not, continue training the first deep learning model using the next training data.

[0238] In some optional embodiments, the process of determining whether the diagnosis result of the desorption diagnosis system meets the alarm condition includes:

[0239] If the pressure fluctuation amplitude indicated by the desorption pressure data is not greater than a preset pressure fluctuation threshold, determining that the diagnosis result of the desorption diagnosis system meets the alarm condition; otherwise, determining that the diagnosis result of the desorption diagnosis system does not meet the alarm condition; and / or,

[0240] The engine operating information is obtained, and the engine operating information and the desorption pressure data are input into a desorption diagnostic model to obtain a diagnostic result corresponding to the engine operating information and the desorption pressure data, wherein the diagnostic result is used to indicate whether an alarm condition is met.

[0241] (System Example)

[0242] See also Figure 6 , Figure 6 The structure block diagram of a desorption diagnosis system provided by the present application is shown. The specific implementation method is consistent with the implementation method and the technical effect achieved in the above method embodiment, and some contents are not repeated here.

[0243] The embodiment of the present application further provides a desorption diagnostic system 300 , which includes a switch valve 301 , a pressure detection module 303 , and a desorption diagnostic device 302 as described in the device embodiment;

[0244] The switch valve 301 is provided on the pipeline between the carbon canister and the fuel tank, and is used to connect and close the carbon canister and the fuel tank;

[0245] The pressure detection module 303 is connected to both ends of the switch valve 301 and is used to obtain the pressure fluctuation amplitude of the switch valve 301 at one end close to the carbon canister.

[0246] In some optional embodiments, the pressure detection module 303 may include a first pressure sensor and a second pressure sensor, wherein the first pressure sensor and the second pressure sensor are respectively disposed at both ends of the switch valve 301; or,

[0247] The pressure detection module 303 includes a pressure difference sensor, which is connected to both ends of the switch valve 301 respectively.

[0248] In some optional embodiments, the desorption diagnostic system 300 further includes an air pump, which is disposed between the switch valve 301 and the carbon canister.

[0249] In a specific application, the pressure detection module 303 is connected to the end of the air pump close to the carbon canister and the end of the switch valve 301 close to the fuel tank. Thus, the pressure detection module 303 can obtain pressure data between the two opposite ports of the air pump and the switch valve 301.

[0250] (Equipment Example)

[0251] See also Figure 7 , Figure 7 FIG2 shows a schematic diagram of the structure of an electronic device 200 provided by the present application. The electronic device 200 includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0252] The memory 210 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 211 and / or a cache memory 212 , and may further include a read-only memory (ROM) 213 .

[0253] Among them, the memory 210 also stores a computer program, which can be executed by the processor 220, so that the processor 220 implements the steps of any of the above methods. Its specific implementation method is consistent with the implementation method and the technical effect achieved in the above method embodiment, and some contents will not be repeated here.

[0254] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0255] Accordingly, the processor 220 may execute the aforementioned computer program and the utility 214 .

[0256] Bus 230 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0257] The electronic device 200 may also communicate with one or more external devices 240, such as a keyboard, pointing device, Bluetooth device, etc., and may also communicate with one or more devices capable of interacting with the electronic device 200, and / or any device that enables the electronic device 200 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication may be performed via an input / output interface 250. Furthermore, the electronic device 200 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device 200, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0258] (Medium Example)

[0259] The embodiment of the present application also provides a computer-readable storage medium, the specific implementation of which is consistent with the implementation method and the technical effect achieved in the above method embodiment, and some contents will not be repeated here.

[0260] The computer-readable storage medium is used to store a computer program; when the computer program is executed, the steps of the above method in the embodiment of the present application are implemented.

[0261] See also Figure 8 , Figure 8The present application provides a block diagram of a program product for implementing any of the above methods. The program product may utilize a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. The program product may utilize any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0262] A computer-readable storage medium may include a data signal transmitted in baseband or as part of a carrier wave, carrying readable program code. This transmitted data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which can transmit, transmit, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof. The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a standalone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0263] It should be noted that, in the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b and c can be single or multiple. It is worth noting that "at least one" can also be interpreted as "one or more items".

[0264] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0265] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are configured to distinguish similar objects, and are not necessarily configured to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

Claims

1. A desorption diagnostic method, characterized in that: The method comprises: After receiving the diagnostic instruction, the pressure detection module is used to obtain desorption pressure data, wherein the desorption pressure data is used to indicate the pressure fluctuation amplitude of the switch valve near the carbon canister, wherein the switch valve is provided in the pipeline between the carbon canister and the fuel tank; Based on the desorption pressure data, determining whether a diagnosis result of a desorption diagnosis system meets an alarm condition; When the diagnosis result of the desorption diagnosis system meets the alarm condition, an alarm message is generated and sent to a preset user device; Before obtaining the diagnostic instruction, the method further includes: Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses; When the similarity is lower than a preset similarity, shortening the predetermined interval; comparing the shortened predetermined interval with the desorption interval, and acquiring engine operation information when the desorption interval is not less than the predetermined interval; acquiring the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction based on the operating information of the engine; The desorption interval is the desorption interval between the last desorption diagnosis and the current moment.

2. The desorption diagnostic method according to claim 1, characterized in that: Before obtaining the diagnostic instruction, the method further includes: The desorption strategy includes the desorption time of the carbon canister by the engine; The method of obtaining desorption pressure data by using the pressure detection module includes: Based on the desorption strategy, controlling the engine to maintain a stable operating condition to desorb the carbon canister; The switch valve is controlled to remain in a closed state, and the desorption pressure data is acquired by using the pressure detection module.

3. The desorption diagnostic method according to claim 2, characterized in that: The process of obtaining the desorption strategy includes: Inputting the engine operation information into a desorption strategy model to obtain a desorption strategy corresponding to the engine operation information; The training process of the desorption strategy model includes: Acquire a training set, the training set including a plurality of training data, each of the training data including sample operating information of the engine in a real environment and labeled data of the corresponding desorption strategy; For each training data in the training set, perform the following processing: Inputting the sample operating information of the engine into a preset first deep learning model to obtain prediction data of the desorption strategy corresponding to the training data; Updating model parameters of the first deep learning model based on the predicted data and the labeled data of the desorption strategy corresponding to the training data; Detect whether a preset training end condition is met; if so, use the trained first deep learning model as the desorption strategy model; if not, continue training the first deep learning model using the next training data.

4. The desorption diagnostic method according to claim 1, characterized in that: The process of determining whether the diagnosis result of the desorption diagnosis system meets the alarm condition includes: If the pressure fluctuation amplitude indicated by the desorption pressure data is not greater than a preset pressure fluctuation threshold, determining that the diagnosis result of the desorption diagnosis system meets the alarm condition; otherwise, determining that the diagnosis result of the desorption diagnosis system does not meet the alarm condition; and / or, The engine operating information is obtained, and the engine operating information and the desorption pressure data are input into a desorption diagnostic model to obtain a diagnostic result corresponding to the engine operating information and the desorption pressure data, wherein the diagnostic result is used to indicate whether an alarm condition is met.

5. A desorption diagnostic device, characterized in that: The desorption diagnostic device comprises: a pressure differential acquisition module, configured to, upon receiving a diagnostic instruction, use the pressure detection module to acquire desorption pressure data, the desorption pressure data being used to indicate a pressure fluctuation amplitude of a switch valve near one end of the carbon canister, the switch valve being disposed in a pipeline between the carbon canister and the fuel tank; a condition judgment module, configured to judge whether a diagnosis result of a desorption diagnosis system meets an alarm condition based on the desorption pressure data; a diagnosis alarm module, configured to generate an alarm message and send it to a preset user device when the diagnosis result of the desorption diagnosis system meets the alarm condition; Before obtaining the diagnostic instruction, Obtaining the desorption pressure data of the two most recent desorption diagnoses, and calculating the similarity between the desorption pressure data of the two most recent desorption diagnoses; When the similarity is lower than a preset similarity, shortening the predetermined interval; comparing the shortened predetermined interval with the desorption interval, and acquiring engine operation information when the desorption interval is not less than the predetermined interval; acquiring the diagnostic instruction and a desorption strategy corresponding to the diagnostic instruction based on the engine operating information; The desorption interval is the desorption interval between the last desorption diagnosis and the current moment.

6. A desorption diagnostic system, characterized in that: The desorption diagnostic system comprises a switch valve, a pressure detection module and the desorption diagnostic device according to claim 5; The switch valve is provided on the pipeline between the carbon canister and the fuel tank, and is used to connect and close the carbon canister and the fuel tank; The pressure detection module is connected to both ends of the switch valve and is used to obtain the pressure fluctuation amplitude of the switch valve at one end close to the carbon canister.

7. The desorption diagnostic system according to claim 6, characterized in that: The pressure detection module includes a first pressure sensor and a second pressure sensor, wherein the first pressure sensor and the second pressure sensor are respectively arranged at two ends of the switch valve; or, The pressure detection module includes a pressure differential sensor, and the pressure differential sensor is communicated with both ends of the switch valve respectively.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 4 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images