Fuel injector leakage detection method and device, vehicle and computer readable storage medium

Abstract

The invention relates to an oil injector leakage detection method and device, a vehicle and a computer readable storage medium. The method comprises the steps that after an engine stops, the rail pressure of a high-pressure oil rail is adjusted to a fixed rail pressure value; acquiring rail pressure data acquired by a rail pressure sensor in a rail pressure maintaining stage; and based on a preset leakage detection rule, the rail pressure data are detected, and the leakage state of the oil injector is determined. The method can improve the leakage detection accuracy of the fuel injector.

Description

Technical Field

[0001] This application relates to the field of fuel injector technology, and in particular to a method, apparatus, vehicle, and computer-readable storage medium for detecting fuel injector dripping. Background Technology

[0002] In direct injection engines, the high-pressure common rail injector is the core component for achieving precise fuel injection, and its sealing performance directly determines combustion efficiency, emission levels, and engine life. Injector dripping refers to the continuous, minute leakage of high-pressure fuel into the combustion chamber after the injector solenoid valve is de-energized and closed, due to valve core wear, impurities, or other reasons. This fault is particularly insidious after the engine is shut down, but its long-term presence will lead to fuel dilution of engine oil, cylinder carbon buildup, difficulty starting in cold weather, pre-ignition knocking, and ultimately, serious mechanical damage such as connecting rod bending and piston melting. Therefore, a method for detecting injector dripping is needed.

[0003] In related technologies, injector leak detection uses a dependency inference method, which assumes that injector leaks will cause the fuel in that cylinder to be too rich, preventing the air-fuel mixture from igniting properly and thus causing misfires, thereby determining that there is an injector leak. However, this method cannot distinguish between injector leaks and misfires caused by other faults such as spark plug aging, ignition coil failure, or valve carbon buildup, resulting in low accuracy in injector leak detection. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, vehicle, computer-readable storage medium, and computer program product for detecting injector leaks that can improve the accuracy of injector leak detection, in order to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for detecting fuel injector dripping, including:

[0006] After the engine is stopped, adjust the high-pressure oil rail pressure to a fixed rail pressure value;

[0007] Acquire rail pressure data collected by the rail pressure sensor during the rail pressure holding stage;

[0008] Based on preset leak detection rules, the rail pressure data is detected to determine the leak status of the injector.

[0009] In one embodiment, the step of detecting the rail pressure data based on a preset drip detection rule to determine the dripping status of the injector includes:

[0010] Determine the calibration threshold based on the fixed rail pressure value;

[0011] If the rail pressure data is less than or equal to the calibration threshold, then the injector is in a dripping state.

[0012] If the rail pressure data is greater than the calibration threshold, then the dripping status of the injector is no dripping.

[0013] In one embodiment, after the method states that the injector is in a dripping state if the rail pressure data is less than or equal to the calibration threshold, the method further includes:

[0014] Obtain a preset threshold range; the preset threshold range is a preset threshold range used to characterize different leakage levels, determined based on actual vehicle operating data and the fixed rail pressure value.

[0015] The target rail pressure value for the rail pressure holding stage is determined based on the rail pressure data.

[0016] The target rail pressure value is compared with the preset threshold range to determine the dripping level of the injector.

[0017] In one embodiment, comparing the target rail pressure value with the preset threshold range to determine the dripping level of the injector includes:

[0018] If the target rail pressure value is within the first preset threshold range, then the dripping level of the injector is determined to be the first dripping level;

[0019] If the target rail pressure value is within the second preset threshold range, then the dripping level of the injector is determined to be the second dripping level;

[0020] If the target rail pressure value is within the third preset threshold range, then the dripping level of the injector is determined to be the third dripping level; the first preset threshold range is greater than the second preset threshold range, and the second preset threshold range is greater than the third preset threshold range.

[0021] In one embodiment, the method further includes:

[0022] Real-time acquisition of rail pressure and temperature data of the vehicle during operation;

[0023] The rail pressure change rate of the injector is determined based on the real-time rail pressure data.

[0024] The rail pressure change rate of the injector is corrected based on the real-time temperature data.

[0025] The safe driving distance of the vehicle is determined based on the corrected rail pressure change rate, the dripping status, and the real-time rail pressure data.

[0026] In one embodiment, the method further includes:

[0027] The steps described above are executed according to a preset cycle: adjusting the high-pressure oil rail pressure to a fixed rail pressure value after the engine stops, acquiring rail pressure data collected by the rail pressure sensor during the rail pressure holding stage, and determining the dripping status of the injector.

[0028] In one embodiment, the method further includes:

[0029] Predict the safe operating time of the injector and the vehicle malfunction of the corresponding vehicle based on the dripping status;

[0030] Based on the safe usage time and vehicle malfunction, corresponding warning information is generated;

[0031] The warning information is pushed to the after-sales terminal so that maintenance personnel can perform maintenance on the injector, and / or the after-sales terminal sends maintenance information to the vehicle user terminal.

[0032] Secondly, this application also provides an injector drip detection device, comprising:

[0033] The rail pressure adjustment module is used to adjust the high-pressure oil rail pressure to a fixed value after the engine is stopped.

[0034] The data acquisition module is used to acquire the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage;

[0035] The drip detection module is used to detect the rail pressure data based on preset drip detection rules to determine the dripping status of the injector.

[0036] Thirdly, this application also provides a vehicle, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] After the engine is stopped, adjust the high-pressure oil rail pressure to a fixed rail pressure value;

[0038] Acquire rail pressure data collected by the rail pressure sensor during the rail pressure holding stage;

[0039] Based on preset leak detection rules, the rail pressure data is detected to determine the leak status of the injector.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0041] After the engine is stopped, adjust the high-pressure oil rail pressure to a fixed rail pressure value;

[0042] Acquire rail pressure data collected by the rail pressure sensor during the rail pressure holding stage;

[0043] Based on preset leak detection rules, the rail pressure data is detected to determine the leak status of the injector.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0045] After the engine is stopped, adjust the high-pressure oil rail pressure to a fixed rail pressure value;

[0046] Acquire rail pressure data collected by the rail pressure sensor during the rail pressure holding stage;

[0047] Based on preset leak detection rules, the rail pressure data is detected to determine the leak status of the injector.

[0048] The aforementioned injector drip detection method, device, vehicle, computer-readable storage medium, and computer program product adjust the high-pressure fuel rail pressure to a fixed value after the engine is stopped. Under this condition, the rail pressure data collected by the rail pressure sensor during the rail pressure holding phase is acquired. Based on preset drip detection rules, the rail pressure data is detected to determine the injector drip status. This method sets a fixed rail pressure when the engine is stopped, which can reduce the aggravation of cavitation caused by the increase in rail pressure after shutdown. The rail pressure value during the pressure holding phase is used as a direct physical quantity criterion for the injector sealing performance, rather than indirect inference through combustion abnormalities. It also avoids interference from the wear caused by the injector operation on the drip detection, and can directly, accurately, and in real time identify the injector drip risk, thus improving the accuracy of drip detection. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a diagram illustrating the application environment of an injector dripping detection method in one embodiment.

[0051] Figure 2 This is a flowchart illustrating a fuel injector drip detection method in one embodiment;

[0052] Figure 3 This is a flowchart illustrating a method for identifying the level of leakage in one embodiment;

[0053] Figure 4 This is a system structure diagram of an injector dripping active early warning system in one embodiment;

[0054] Figure 5 This is a flowchart illustrating the injector drip detection method in another embodiment;

[0055] Figure 6 This is a structural block diagram of an injector drip detection device in one embodiment;

[0056] Figure 7 This is a diagram of the internal structure of a vehicle in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] Currently, fuel injector leak detection mainly relies on inference methods, and no mass-produced ECU system has a direct, dedicated leak diagnosis function. Existing technical solutions include engine misfire counter alarms and cold start vibration analysis. Engine misfire counter alarms state that fuel injector leaks can cause the fuel in that cylinder to be too rich, preventing the air-fuel mixture from igniting properly and thus causing misfires. However, misfires are a possible consequence of leaks, not a direct symptom. Misfires can also be caused by spark plug aging, ignition coil failure, valve carbon buildup, etc., resulting in a high misdiagnosis rate. Cold start vibration analysis shows that engine speed fluctuations and unstable combustion occur after a cold start. Leaking fuel is not fully atomized in a cold engine state and accumulates on the cylinder wall, resulting in concentrated combustion during startup and causing a violent impact. However, cold start vibration is affected by multiple factors such as ambient temperature, fuel quality, and carbon buildup, making it impossible to distinguish whether the problem is caused by fuel injector leaks or intake manifold carbon buildup.

[0059] However, neither engine misfire counter alarms nor cold start vibration analysis can identify leaks in real time while driving. After a customer complaint, the injector must be removed by after-sales service for a pressure holding test to determine the extent of the leak. This process is time-consuming, costly, inefficient, and does not allow for preventative maintenance. Therefore, to address the issue of accuracy in injector leak detection, a method to improve the accuracy of injector leak detection is proposed.

[0060] The injector dripping detection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, vehicle 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers. Vehicle 102 can be of different types of hybrid vehicles, and it is equipped with an engine fuel supply system and fuel injectors.

[0061] After the engine stops, vehicle 102 adjusts the high-pressure fuel rail pressure to a fixed value. During the pressure-holding phase, the rail pressure sensor on vehicle 102 collects rail pressure data and uploads it to a server. The server, based on preset leak detection rules, detects the rail pressure data to determine the injector's leak status. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0062] In one exemplary embodiment, such as Figure 2 As shown, a method for detecting fuel injector dripping is provided, including steps 202 to 206. Wherein:

[0063] Step 202: After the engine is stopped, adjust the high-pressure oil rail pressure to a fixed rail pressure value.

[0064] Understandably, the fuel injector is a crucial component in the engine's fuel supply system, responsible for atomizing fuel into fine droplets based on the characteristics of the air-fuel mixture and injecting them into specific areas of the combustion chamber. Due to different combustion characteristics, the operating pressure of the fuel injector varies. For example, the operating pressure of gasoline fuel injectors in passenger cars is typically within 40 MPa, while that of clean fuels is within 28 MPa. The high-pressure fuel rail pressure experiences significant instantaneous pressure fluctuations, such as 10–35 MPa. Therefore, relying solely on the rate of rail pressure change to identify injector leaks is insufficient. To ensure detection accuracy, after detecting engine shutdown in a hybrid vehicle, the high-pressure fuel rail pressure is first adjusted to a fixed value. This setting reduces the risk of cavitation caused by increased rail pressure after shutdown and protects the fuel injectors.

[0065] A fixed rail pressure can also be understood as a fixed low rail pressure. A fixed rail pressure refers to a set value that maintains the fuel rail pressure in the common rail system at a relatively low and stable level under specific operating conditions or control strategies. Adjusting the high-pressure fuel rail pressure to a fixed value after engine shutdown can be achieved by controlling the high-pressure fuel pump outlet throttle valve or the common rail pressure relief solenoid valve after the engine's main fuel supply is cut off, actively adjusting and stabilizing the rail pressure at a preset constant value. The specific method for adjusting the high-pressure fuel rail pressure is not limited here.

[0066] Step 204: Obtain the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage.

[0067] The rail pressure sensor can be a piezoelectric or silicon piezoresistive pressure sensor installed on the high-pressure common rail for real-time monitoring of fuel pressure. It can be used to directly acquire pressure time-series data during the rail pressure holding phase. The rail pressure sensor can be a high-pressure fuel rail sensor; for example, it is installed on the high-pressure common rail and samples at a set sampling frequency to obtain a rail pressure analog signal. The ECU (Electronic Control Unit) then converts this analog signal into a pressure signal in real time, thus obtaining the rail pressure value acquired by the sensor during the rail pressure holding phase. The rail pressure holding phase can be, but is not limited to, 60 seconds.

[0068] Under normal circumstances, after the engine stops, the rail pressure rises due to fuel heating, and it should not decrease after 60 seconds. If it decreases slowly, it indicates that fuel is continuously leaking into the cylinder, preventing proper pressure maintenance. In other words, after the engine stops, a properly functioning injector, when closed, has good sealing properties, effectively preventing fuel from leaking into the combustion chamber or other parts, thus maintaining relatively stable fuel pressure in the rail without significant pressure fluctuations. Therefore, collecting rail pressure data during the pressure maintenance phase for injector leak detection can identify injector leaks promptly and accurately.

[0069] For example, after the engine is stopped and the high-pressure oil rail pressure is adjusted to a fixed rail pressure value, the rail pressure data collected by the rail pressure sensor within 60 seconds is acquired. That is, after each engine shutdown, the rail pressure is first forcibly reduced to 3MPa, and then the rail pressure data collected by the rail pressure sensor within 60 seconds is acquired to perform pressure maintenance and leak detection. Here, 3MPa is the fixed rail pressure value.

[0070] Step 206: Based on the preset drip detection rules, the rail pressure data is detected to determine the drip status of the injector.

[0071] The preset drip detection rule can be to calculate the average of the acquired rail pressure data, compare the average with a calibrated threshold, and if the average is less than or equal to the calibrated threshold, the injector is considered to be dripping; if it is greater than the calibrated threshold, the injector is considered to be not dripping. Alternatively, it can select the rail pressure value with the highest value from the rail pressure data and compare it with the calibrated threshold to determine whether dripping has occurred. The aforementioned calibrated threshold is the reference rail pressure value for determining whether the injector is dripping.

[0072] The aforementioned injector dripping detection method adjusts the high-pressure fuel rail pressure to a fixed value after the engine is stopped. Under this condition, the rail pressure data collected by the rail pressure sensor during the rail pressure holding phase is obtained. Based on preset dripping detection rules, the rail pressure data is detected to determine the injector's dripping status. This method sets a fixed rail pressure when the engine is stopped, which can reduce the aggravation of cavitation caused by the increase in rail pressure after shutdown. The rail pressure value during the pressure holding phase is used as a direct physical quantity criterion for the injector's sealing performance, rather than indirect inference through combustion abnormalities. It also avoids interference from the wear caused by the injector's operation on the dripping detection. This method can directly, accurately, and in real time identify the risk of injector dripping, thus improving the accuracy of dripping detection.

[0073] The following provides a method for detecting the dripping state of an injector. Optionally, in an exemplary embodiment, the method for detecting rail pressure data based on a preset dripping detection rule to determine the dripping state of the injector includes: determining a calibration threshold based on a fixed rail pressure value; if the rail pressure data is less than or equal to the calibration threshold, the injector is considered to be dripping; if the rail pressure data is greater than the calibration threshold, the injector is considered to be not dripping.

[0074] The calibration threshold can be determined by using machine learning algorithms, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs) in deep learning, to mine and analyze injector operating data under different operating conditions, including different fixed rail pressures, different usage durations, and different environmental conditions. This data will automatically learn the complex nonlinear relationship between rail pressure and dripping, thereby determining the calibration threshold corresponding to the fixed rail pressure value. Alternatively, it can be determined by using a physical model or lookup table mapping relationship built into a preset dripping detection rule to convert the currently set fixed rail pressure value into the upper limit of pressure decay allowed during the corresponding pressure holding period.

[0075] In one embodiment, the calibration threshold is a reference rail pressure value used to determine whether the injector is leaking. A mapping relationship between a fixed rail pressure value and the calibration threshold is pre-calibrated. During injector leak detection, the mapping relationship between the fixed rail pressure value and the calibration threshold is first determined using the fixed rail pressure value, thus identifying the calibration threshold corresponding to the current fixed rail pressure value. When the collected rail pressure data is less than or equal to the calibration threshold, the injector is determined to be leaking; when the collected rail pressure data is greater than the calibration threshold, the injector is determined to be not leaking. It is understood that "the collected rail pressure data is less than or equal to the calibration threshold" can mean either the average value of the collected rail pressure data is less than or equal to the calibration threshold, or the maximum value of the collected rail pressure data is less than or equal to the calibration threshold; this embodiment does not impose a specific limitation. Similarly, "the collected rail pressure data is greater than the calibration threshold" can mean either the average value of the collected rail pressure data is greater than the calibration threshold, or the maximum value of the collected rail pressure data is greater than the calibration threshold.

[0076] In another embodiment, the calibration threshold is the rail pressure attenuation amount used to determine whether the injector is dripping. A mapping relationship between a fixed rail pressure value and the calibration threshold is pre-calibrated. During injector drip detection, the mapping relationship between the fixed rail pressure value and the calibration threshold is first determined by finding the fixed rail pressure value, thus identifying the calibration threshold corresponding to the current fixed rail pressure value. Then, feature extraction is performed on the rail pressure data sequence to calculate the actual pressure attenuation amount during the pressure holding period. Specifically, the first rail pressure value corresponding to the initial moment and the second rail pressure value corresponding to the end moment are obtained from the time series data. The first rail pressure value is subtracted from the second rail pressure value to determine the actual pressure attenuation amount. When the actual pressure attenuation amount is greater than or equal to the calibration threshold, the injector is determined to be dripping; when the actual pressure attenuation amount is less than the calibration threshold, the injector is determined to be not dripping.

[0077] In the above embodiments, a calibration threshold is determined based on a fixed rail pressure value. The calibration threshold is the reference rail pressure value for determining whether the injector is leaking. If the rail pressure data is less than or equal to the calibration threshold, it is determined that a leak has occurred. If the rail pressure data is greater than the calibration threshold, it is determined that no leak has occurred. This can avoid interference caused by other faults such as misfires on the combustion chamber side, thereby improving the accuracy of injector leak detection.

[0078] In the following embodiments, the calibration threshold is used as the reference rail pressure value for determining whether the injector is leaking.

[0079] Understandably, during engine monitoring, if a cylinder experiences continuous misfires, the ECU will react quickly, recording this fault information as a specific fault code and illuminating the malfunction indicator lamp. When the vehicle is cold-started, if the ECU detects engine speed fluctuations exceeding a preset range, it indicates unstable combustion, potentially due to uneven fuel injection or inaccurate ignition timing. The ECU will record this combustion instability in detail. When engineers notice obvious abnormalities such as shaking or difficulty starting, they will read the fault code, rule out the cause, and manually remove the fuel injectors for pressure testing. Once a fuel injector leak is confirmed, engineers will replace it promptly. However, the entire process from fault occurrence to final repair takes an average of 3-7 days. During this time, because the fault is not resolved promptly, the vehicle is forced to operate with a leaking fuel injector. This abnormal operating state can cause serious damage to the engine.

[0080] In other words, current fuel injection leak detection methods only identify whether a leak has occurred. By the time a leak is detected, the situation may already be quite serious. In this case, the engine may have already worn down, and related components throughout the vehicle may have suffered mechanical damage. Repairing this issue is costly and time-consuming. Therefore, by identifying different levels of leaks and providing timely warnings, fuel injector leaks can be identified promptly, reducing repair costs and shortening the repair time.

[0081] In one exemplary embodiment, such as Figure 3 As shown, a method for identifying dripping levels is provided, including the following steps:

[0082] Step 302: Obtain the preset threshold range; the preset threshold range is a preset threshold range used to characterize different leakage levels, determined based on the actual vehicle operation data and the fixed rail pressure value.

[0083] The preset threshold range is determined by cluster analysis and quantile extraction of the rail pressure attenuation corresponding to the same fixed rail pressure value under massive real vehicle data to determine the critical point of each level.

[0084] Step 304: Determine the target rail pressure value for the rail pressure holding stage based on the rail pressure data.

[0085] The target rail pressure value can be the rail pressure value with the largest value in the rail pressure data corresponding to the pressure holding stage, or it can be the average of all rail pressure values ​​in the rail pressure data corresponding to the pressure holding stage.

[0086] Step 306: Compare the target rail pressure value with the preset threshold range to determine the dripping level of the injector.

[0087] The preset threshold range can include a first preset threshold range, a second preset threshold range, and a third preset threshold range. Different preset threshold ranges correspond to different degrees of leakage (or the degree of leakage). Taking a fixed rail pressure of 3 MPa and a calibration threshold of 2.9 MPa as an example, if the rail pressure data is less than or equal to the calibration threshold, the injector is considered to be leaking. At this point, the injector's leaking state has been determined to be leaking, meaning the target rail pressure value is less than or equal to 2.9 MPa. Next, the injector's leakage level needs to be further determined. For example, the first preset threshold range is set to a rail pressure value between 2.9 and 2.5 MPa, corresponding to slight leakage; the second preset threshold range is set to a rail pressure value between 2.5 and 2.0 MPa, corresponding to moderate leakage; and the third preset threshold range is set to a rail pressure value less than 2 MPa, corresponding to severe leakage.

[0088] Further, in an exemplary embodiment, comparing the target rail pressure value with a preset threshold range to determine the injector's dripping level includes: if the target rail pressure value is within a first preset threshold range, then the injector's dripping level is determined to be a first dripping level; if the target rail pressure value is within a second preset threshold range, then the injector's dripping level is determined to be a second dripping level; if the target rail pressure value is within a third preset threshold range, then the injector's dripping level is determined to be a third dripping level; the first preset threshold range is greater than the second preset threshold range, and the second preset threshold range is greater than the third preset threshold range.

[0089] The first level of leakage can also be called a minor leak, the second level of leakage can also be called a moderate leak, and the third level of leakage can also be called a serious leak. A serious leak can be specifically manifested as obvious cold start shaking and misfire shaking of the engine.

[0090] For example, through real-vehicle big data testing, it was determined that a normal injector exhibits minimal rail pressure fluctuations within 60 seconds of engine shutdown. If an injector exhibiting a dripping failure mode has rail pressure data collected within 60 seconds that is less than or equal to the calibrated threshold (MPa), it is considered an injector dripping. The calibrated threshold is the baseline rail pressure value used to determine whether an injector is dripping. Further, if the target rail pressure value is within the range of 2.9~2.5 MPa, it is considered a minor leak; if the target rail pressure value is within the range of 2.5~2.0 MPa, it is considered a moderate leak; and if the target rail pressure value is less than 2 MPa, it is considered a severe leak. Furthermore, identifying the injector's dripping level allows for timely warnings to the user, from initial detection to early warning of a leak, and ultimately to warnings of a severe leak. This enables users to take appropriate measures promptly, improving the user experience.

[0091] In the above method, a preset threshold range is jointly calibrated based on real vehicle operation data and fixed rail pressure values. When a leak is detected in the injector, the leak situation is further classified into different levels. This allows for corresponding measures to be taken for different levels of leaks and timely warnings to be issued, improving the accuracy of injector leak detection. In addition, the process from the detection of a leak to the issuance of a timely warning and the occurrence of a serious leak can provide timely warnings to users, enabling them to take appropriate measures in a timely manner and improving the user experience.

[0092] Based on the identified drip level, the safe driving distance of the vehicle corresponding to the drip level can be determined. In one embodiment, the injector drip detection method further includes:

[0093] The system acquires real-time rail pressure and temperature data of the vehicle while it is in motion; it determines the rail pressure change rate of the injector based on the real-time rail pressure data; it corrects the rail pressure change rate of the injector based on the real-time temperature data; and it determines the safe driving distance of the vehicle based on the corrected rail pressure change rate, leakage status, and real-time rail pressure data.

[0094] The real-time temperature data can be continuously collected by a fuel temperature sensor or a common rail wall temperature sensor during vehicle operation. The real-time rail pressure data can be determined by the continuous time-series signal output by the high-pressure fuel pressure sensor in the common rail system. The rail pressure change rate can be the instantaneous change in rail pressure per unit time, characterizing the leakage rate of the high-pressure fuel system under the current operating conditions.

[0095] The corrected rail pressure change rate can be a rail pressure change rate corrected by a physical model driven by real-time temperature data or by a lookup table method. For example, the corrected rail pressure change rate can be determined by calling a built-in temperature-correction coefficient mapping table. The correction coefficient is determined by the real-time temperature data, and the original rail pressure change rate is corrected by scalar multiplication or nonlinear function mapping. For instance, the corresponding correction coefficient is retrieved from the current real-time temperature data, and the original rail pressure change rate is determined by scalar multiplication or nonlinear function mapping.

[0096] The safe driving distance can be defined as the maximum mileage threshold predicted by the system that allows continued driving without causing serious mechanical damage, under the constraints of the current dripping state, the corrected rail pressure change rate, and real-time rail pressure data. The safe driving distance can be determined, but is not limited to, calculations using a multi-parameter coupled model. This involves integrating the corrected rail pressure change rate to estimate the total future leakage mass, mapping it to the critical oil dilution concentration, and then combining this with the current vehicle speed and fuel consumption to calculate the remaining safe mileage. In the case of a confirmed dripping situation, the safe driving distance corresponding to each dripping level can be further determined based on the actual dripping level, the corrected rail pressure change rate, and real-time rail pressure data, which can reduce the safe driving distance.

[0097] In the above embodiments, by correcting the rail pressure change rate of the injector based on real-time temperature data, and determining the safe driving distance of the vehicle based on the corrected rail pressure change rate, dripping status, and real-time rail pressure data, the user experience is improved, and the vehicle can be repaired in a timely manner, reducing maintenance costs.

[0098] Furthermore, the above-mentioned injector dripping detection scheme can continuously monitor the leakage threshold and achieve accurate after-sales early warning. In an exemplary embodiment, the above-mentioned injector dripping detection method further includes: performing the following steps according to a preset cycle: adjusting the high-pressure fuel rail pressure to a fixed rail pressure value after the engine is stopped, and obtaining the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage to determine the dripping status of the injector.

[0099] The preset period can be the time used to trigger the repetitive drip detection process.

[0100] For example, a high-pressure fuel rail sensor installed on the high-pressure common rail collects analog rail pressure signals in real time. The ECU converts these analog rail pressure signals into pressure signals in real time to obtain rail pressure data. Real-time temperature data collected by a temperature sensor and real-time engine speed are also acquired. These converted data streams are transmitted to a Tbox module via CAN communication. The Tbox module then uploads data packets including timestamps, real-time rail pressure, real-time engine speed, and real-time temperature to a cloud platform or other server at preset time intervals. On the cloud platform, the process is repeated periodically after engine shutdown, adjusting the high-pressure fuel rail pressure to a fixed value and acquiring rail pressure data collected by the rail pressure sensor during the rail pressure holding phase to determine the injector's dripping status. If dripping is confirmed, a target rail pressure value for the rail pressure holding phase can be further determined based on the rail pressure data. The target rail pressure value is then compared with a preset threshold range to determine the injector's dripping level.

[0101] For each cycle of leak detection, corresponding early warning information can be generated and pushed to the after-sales terminal so that maintenance personnel can perform maintenance on the injector, and / or the after-sales terminal can send maintenance information to the vehicle user terminal.

[0102] To allow sufficient time for after-sales service to schedule parts replacements with customers, thus preventing engine damage or improving user experience, one embodiment of the above-mentioned injector leak detection method further includes:

[0103] Predict the safe operating time of the injector and the corresponding vehicle malfunction based on the dripping status; generate corresponding early warning information based on the safe operating time and vehicle malfunction; push the early warning information to the after-sales terminal so that maintenance personnel can perform maintenance on the injector, and / or, the after-sales terminal sends maintenance information to the vehicle user terminal.

[0104] The safe operating time can be a threshold of time or mileage at which the injector can continue to operate without causing derivative failures, based on the current leak status prediction. Both safe operating time and vehicle failure can be based on a trained prediction model, with the leak status as input and the prediction output as the model result. Alternatively, the safe operating time can be obtained by looking up the initial leakage rate from a table based on the leak level and inputting it into a thermo-mechanical degradation model. Vehicle failure can be determined by matching a pre-set fault propagation tree to the leak level, performing Monte Carlo simulations based on current operating data, and outputting high-probability fault types and expected occurrence points. The warning information can include data such as safe operating time, vehicle failure prediction, and handling suggestions.

[0105] In the above embodiments, by pushing early warning information to the after-sales terminal so that maintenance personnel can perform maintenance on the injectors, and / or by sending maintenance information to the vehicle user terminal, it is possible to avoid the problem being detected only after the engine is damaged or the vehicle breaks down, and proactive interaction with the user can be achieved through cloud data collaboration.

[0106] In an exemplary embodiment, an active early warning system for injector dripping corresponding to an injector dripping detection method is provided. The system structure diagram of the active early warning system for injector dripping is shown below. Figure 4 As shown, the system includes a high-pressure fuel rail sensor, an ECU module, a communication module, a cloud platform, and a user terminal. The high-pressure fuel rail sensor is installed on the common fuel rail and samples the pressure within the common fuel rail 100 times per second, outputting an analog signal voltage between 0V and 5V. The ECU module converts the analog signal output by the high-pressure fuel rail sensor into a pressure signal in real time and transmits the data stream to the communication module (e.g., a Tbox module) via CAN communication. The communication module uploads a data packet (containing timestamp, rail pressure, engine speed, and temperature) to the cloud platform every 5 minutes. The cloud platform stores the acquired data and executes the aforementioned injector drip detection method every 30 minutes, i.e., running the model algorithm every 30 minutes: if (t_stop: 60s≤t≤120s & threshold≤P≤threshold)→trigger_warning = true; the model identifies the "drip pattern"; obtains the corresponding drip level, and then generates the corresponding warning information to be sent to the user terminal. The specific implementation can be achieved using the methods defined above, and will not be elaborated upon here.

[0107] In the above embodiments, a fixed low rail pressure is set when the engine is stopped to reduce the increase in rail pressure after shutdown, which exacerbates cavitation. Data analysis is performed during this rail pressure holding phase, which can directly, accurately, and in real time identify the risk of injector leakage, avoiding the situation where a passive response is only made after a serious fault occurs, such as misfire or vibration. The cloud actively pushes information to engineers or after-sales front-end, notifying engineers in advance to pay attention to the parts, thereby avoiding engine damage and improving the user experience.

[0108] In one exemplary embodiment, a fuel injector drip detection method is provided, such as... Figure 5 As shown, it includes the following steps:

[0109] Step 502: After the engine stops, adjust the high-pressure oil rail pressure to a fixed rail pressure value and obtain the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage.

[0110] Step 504: Based on the preset drip detection rules, the rail pressure data is detected to determine the drip status of the injector.

[0111] Step 506: Obtain the preset threshold range; the preset threshold range is a preset threshold range used to characterize different leakage levels, determined based on the actual vehicle operation data and the fixed rail pressure value.

[0112] Step 508: Determine the target rail pressure value for the rail pressure holding stage based on the rail pressure data.

[0113] Step 510: Compare the target rail pressure value with the preset threshold range to determine the dripping level of the injector, generate warning information corresponding to the dripping level, and push the warning information.

[0114] It should be noted that the specific implementation method of this example can be achieved through the methods described above, and will not be repeated here. It should also be noted that any of the above-mentioned injector leak detection methods can be executed via the cloud. This involves proactively issuing warnings based on the analysis of collected fuel rail pressure big data and cloud-based collaborative injector leak detection. A fixed low rail pressure is set when the engine is off, and data analysis is performed within 60 seconds of this threshold rail pressure. This allows for direct, accurate, and real-time identification of injector leak risks, which are then proactively pushed to engineers or after-sales personnel via the cloud, notifying them to pay attention to the parts in advance, thereby preventing engine damage and improving user experience. In addition, any of the above-mentioned injector leak detection methods can also be implemented on the vehicle side, i.e., by adding an internal diagnostic module to the ECU to identify leaks and trigger a warning upon the next engine start. This is suitable for vehicles without a TBox.

[0115] In practical applications, the aforementioned injector leak detection uses rail pressure big data as a direct diagnostic basis for injector leaks, breaking through the reliance on indirect inference based on "misfire / vibration" and constructing a new intelligent diagnostic system of "perception-analysis-early warning-closed loop". In the methanol project's vehicle road durability test, the measured early warning accuracy rate was 100%, successfully identifying multiple injector leak incidents.

[0116] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0117] Based on the same inventive concept, this application also provides an injector dripping detection device for implementing the injector dripping detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more injector dripping detection device embodiments provided below can be found in the limitations of the injector dripping detection method described above, and will not be repeated here.

[0118] In one exemplary embodiment, such as Figure 6 As shown, a fuel injector drip detection device is provided, comprising: a rail pressure adjustment module 602, a data acquisition module 604, and a drip detection module 606, wherein:

[0119] The rail pressure adjustment module 602 is used to adjust the high-pressure oil rail pressure to a fixed rail pressure value after the engine is stopped.

[0120] The data acquisition module 604 is used to acquire the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage.

[0121] The drip detection module 606 is used to detect rail pressure data based on preset drip detection rules to determine the dripping status of the injector.

[0122] The aforementioned injector drip detection device adjusts the high-pressure fuel rail pressure to a fixed value after the engine is stopped. Under these conditions, it acquires rail pressure data collected by the rail pressure sensor during the rail pressure holding phase. Based on preset drip detection rules, it detects the rail pressure data to determine the injector's drip status. This method, by setting a fixed rail pressure after the engine is stopped, can reduce the aggravation of cavitation caused by the increase in rail pressure after shutdown. It uses the rail pressure value during the pressure holding phase as a direct physical quantity criterion for the injector's sealing performance, rather than inferring indirectly through abnormal combustion, and avoids interference from wear caused by injector operation on drip detection. It can directly, accurately, and in real time identify the risk of injector dripping, thus improving the accuracy of drip detection.

[0123] In an exemplary embodiment, the drip detection module 606 is used to determine a calibration threshold based on a fixed rail pressure value; if the rail pressure data is less than or equal to the calibration threshold, the drip state of the injector is dripping; if the rail pressure data is greater than the calibration threshold, the drip state of the injector is not dripping.

[0124] In an exemplary embodiment, the drip detection module 606 is used to obtain a preset threshold range; the preset threshold range is a preset threshold range used to characterize different drip levels, determined based on actual vehicle operating data and fixed rail pressure values.

[0125] Determine the target rail pressure value for the rail pressure holding stage based on rail pressure data;

[0126] The target rail pressure value is compared with the preset threshold range to determine the drip level of the injector.

[0127] In an exemplary embodiment, the drip detection module 606 is used to determine the drip level of the injector as the first drip level if the target rail pressure value is within the first preset threshold range.

[0128] If the target rail pressure value is within the second preset threshold range, then the dripping level of the injector is determined to be the second dripping level;

[0129] If the target rail pressure value is within the third preset threshold range, the dripping level of the injector is determined to be the third dripping level; the first preset threshold range is greater than the second preset threshold range, and the second preset threshold range is greater than the third preset threshold range.

[0130] In an exemplary embodiment, the injector drip detection device further includes a correction module and a safe driving distance determination module. The correction module is used to acquire real-time rail pressure data and real-time temperature data of the vehicle during driving; determine the rail pressure change rate of the injector based on the real-time rail pressure data; and correct the rail pressure change rate of the injector based on the real-time temperature data.

[0131] The safe driving distance determination module determines the safe driving distance of the vehicle based on the corrected rail pressure change rate, leakage status, and real-time rail pressure data.

[0132] In an exemplary embodiment, the injector drip detection device further includes the step of adjusting the high-pressure fuel rail pressure to a fixed rail pressure value after the engine is stopped according to a preset cycle, and obtaining the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage to determine the drip status of the injector.

[0133] In an exemplary embodiment, the injector drip detection device further includes an early warning module, which predicts the safe operating time of the injector and the vehicle malfunction corresponding to the injector based on the dripping status; generates corresponding early warning information based on the safe operating time and the vehicle malfunction; pushes the early warning information to the after-sales terminal so that maintenance personnel can perform maintenance on the injector; and / or, the after-sales terminal sends maintenance information to the vehicle user terminal.

[0134] Each module in the aforementioned fuel injector drip detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the vehicle's processor in hardware form or independent of it, or stored in the vehicle's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0135] In one exemplary embodiment, a vehicle is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown, the vehicle includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The vehicle's processor provides computing and control capabilities. The vehicle's memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The vehicle's input / output interface is used for exchanging information between the processor and external devices. The vehicle's communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a fuel injector leak detection method. The vehicle's display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the vehicle can be a touch layer covering the display screen, or buttons, trackballs or touchpads set on the vehicle body, or external keyboards, touchpads or mice, etc.

[0136] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the vehicle to which the present application is applied. A specific vehicle may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting fuel injector dripping, characterized in that, The method includes: After the engine is stopped, adjust the high-pressure oil rail pressure to a fixed rail pressure value; Acquire rail pressure data collected by the rail pressure sensor during the rail pressure holding stage; Based on preset leak detection rules, the rail pressure data is detected to determine the leak status of the injector.

2. The method according to claim 1, characterized in that, The step of detecting the rail pressure data based on preset leak detection rules to determine the leak status of the injector includes: Determine the calibration threshold based on the fixed rail pressure value; If the rail pressure data is less than or equal to the calibration threshold, then the injector is in a dripping state. If the rail pressure data is greater than the calibration threshold, then the dripping status of the injector is no dripping.

3. The method according to claim 2, characterized in that, After the method states that if the rail pressure data is less than or equal to the calibration threshold, and the injector is in a dripping state, the method further includes: Obtain a preset threshold range; the preset threshold range is a preset threshold range used to characterize different leakage levels, determined based on actual vehicle operating data and the fixed rail pressure value. The target rail pressure value for the rail pressure holding stage is determined based on the rail pressure data. The target rail pressure value is compared with the preset threshold range to determine the dripping level of the injector.

4. The method according to claim 3, characterized in that, The step of comparing the target rail pressure value with the preset threshold range to determine the dripping level of the injector includes: If the target rail pressure value is within the first preset threshold range, then the dripping level of the injector is determined to be the first dripping level; If the target rail pressure value is within the second preset threshold range, then the dripping level of the injector is determined to be the second dripping level; If the target rail pressure value is within the third preset threshold range, then the dripping level of the injector is determined to be the third dripping level; the first preset threshold range is greater than the second preset threshold range, and the second preset threshold range is greater than the third preset threshold range.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Real-time acquisition of rail pressure and temperature data of the vehicle during operation; The rail pressure change rate of the injector is determined based on the real-time rail pressure data. The rail pressure change rate of the injector is corrected based on the real-time temperature data. The safe driving distance of the vehicle is determined based on the corrected rail pressure change rate, the dripping status, and the real-time rail pressure data.

6. The method according to claim 5, characterized in that, The method further includes: The steps described above are executed according to a preset cycle: adjusting the high-pressure oil rail pressure to a fixed rail pressure value after the engine stops, acquiring rail pressure data collected by the rail pressure sensor during the rail pressure holding stage, and determining the dripping status of the injector.

7. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Predict the safe operating time of the injector and the vehicle malfunction of the corresponding vehicle based on the dripping status; Based on the safe usage time and vehicle malfunction, corresponding warning information is generated; The warning information is pushed to the after-sales terminal so that maintenance personnel can perform maintenance on the injector, and / or the after-sales terminal sends maintenance information to the vehicle user terminal.

8. A fuel injector drip detection device, characterized in that, The device includes: The rail pressure adjustment module is used to adjust the high-pressure oil rail pressure to a fixed value after the engine is stopped. The data acquisition module is used to acquire the rail pressure data collected by the rail pressure sensor during the rail pressure holding stage; The drip detection module is used to detect the rail pressure data based on preset drip detection rules to determine the dripping status of the injector.

9. A vehicle comprising a memory and a processor, said memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images