Fault diagnosis method and device for engine lubrication system, medium and program product

Abstract

The invention provides an engine lubrication system fault diagnosis method and device, a medium and a product, and relates to the technical field of engine detection, and the method comprises the steps: obtaining the actual operation data of each of a plurality of key function parts in an engine lubrication system; monitoring whether the actual operation data of each of the plurality of key function parts has data exception or not; screening out a target functional component with data exception from the plurality of key functional components; and performing fault diagnosis on the engine lubrication system based on the actual operation data of the target functional part, and generating a fault part and a fault mode as a first diagnosis result. According to the method, by monitoring the actual operation data of the key functional parts of the engine lubrication system, necessary data support is provided for diagnostic analysis, abnormity can be found in time, and an accurate diagnostic result is given.

Description

TECHNICAL FIELD

[0001] The present disclosure belongs to the technical field of engine detection, and particularly relates to an engine lubrication system fault diagnosis method, device, medium and program product. BACKGROUND

[0002] The engine lubrication system is one of the key systems to ensure the normal operation of the engine.

[0003] At present, the fault diagnosis of the engine lubrication system of a commercial vehicle mainly relies on the monitoring of the main oil passage oil pressure. Once a fault occurs, the maintenance personnel reads the fault code through an OBD diagnostic instrument, and then performs manual inspection and maintenance. In some related technologies, the fault diagnosis of the engine lubrication system involves the monitoring of the main oil passage oil temperature and the like.

[0004] The above method has the following shortcomings: the first shortcoming is that the monitoring points are too few, the monitoring scheme is incomplete, and the running state of each component of the lubrication system cannot be comprehensively evaluated. The second shortcoming is that the fault diagnosis precision is too low, and the maintenance personnel's troubleshooting experience is excessively relied on, early warning cannot be realized, and a major fault may occur, causing irreparable economic losses to the user. The third shortcoming is that due to the lack of a systematic diagnosis model and data interaction, the automation and intelligentization of fault diagnosis cannot be realized. SUMMARY

[0005] The present disclosure provides an engine lubrication system fault diagnosis method, device and medium, and aims to at least partially solve the technical problem of low fault diagnosis precision caused by too few monitoring points in the related art.

[0006] At least one embodiment of the present disclosure provides an engine lubrication system fault diagnosis method applied to a vehicle terminal, comprising:

[0007] Obtaining actual running data of each of a plurality of key functional components in an engine lubrication system;

[0008] Monitoring whether the actual running data of each of the plurality of key functional components is abnormal;

[0009] Selecting a target functional component with data abnormality from the plurality of key functional components; and

[0010] Performing fault diagnosis on the engine lubrication system based on the actual running data of the target functional component, generating a fault position and a fault mode as a first diagnosis result.

[0011] In the method provided by at least one embodiment of the present disclosure, the key functional components include a main oil passage, an oil pump, an oil cooler and an oil pan; and

[0012] The actual operation data of the main oil passage includes main oil passage oil pressure;

[0013] The actual operation data of the oil pump includes oil pressure after the oil pump and oil temperature after the oil pump;

[0014] The actual operation data of the oil cooler includes oil pressure after the oil cooler; and,

[0015] The actual operation data of the oil sump includes oil level of the oil sump.

[0016] In the method provided by at least one embodiment of the present disclosure, the engine lubrication system is diagnosed based on the actual operation data of the target functional component to generate a fault position and a fault mode, including:

[0017] Obtaining engine operation data;

[0018] Identifying whether the engine operation data has data anomaly;

[0019] If yes, generating a first fault position and a first fault mode based on the engine operation data and the actual operation data of the target functional component through a pre-set first fault diagnosis model;

[0020] If no, generating a second fault position and a second fault mode based on the actual operation data of the target functional component through a pre-set second fault diagnosis model.

[0021] In the method provided by at least one embodiment of the present disclosure, the engine lubrication system is diagnosed based on the actual operation data of the target functional component to generate a fault position and a fault mode, including:

[0022] Obtaining engine operation data and vehicle operation data of a vehicle in which the engine lubrication system is located;

[0023] Identifying whether the vehicle operation data has data anomaly;

[0024] If yes, generating a third fault position and a third fault mode based on the vehicle operation data, the engine operation data and the actual operation data of the target functional component through a pre-set third fault diagnosis model when the engine operation data has data anomaly, and generating a fourth fault position and a fourth fault mode based on the vehicle operation data and the actual operation data of the target functional component through a pre-set fourth fault diagnosis model when the engine operation data has no anomaly;

[0025] If not, when the engine operation data has data abnormality, a first fault location and a first fault mode are generated based on the engine operation data and actual operation data of the target functional component by a pre-set first fault diagnosis model, and when the engine operation data has no abnormality, a second fault location and a second fault mode are generated based on the actual operation data of the target functional component by a pre-set second fault diagnosis model.

[0026] In the method provided in at least one embodiment of the present disclosure, the engine operation data includes engine speed and engine oil consumption, the vehicle operation data includes vehicle acceleration and slope, and the monitoring whether the actual operation data of each of the plurality of key functional components has data abnormality comprises:

[0027] For the actual operation data of each of the plurality of key functional components, initialization analysis is performed, wherein the initialization analysis is configured to identify whether the actual operation data exceeds a calibration range of the key functional component in normal operation under a current working condition;

[0028] When the actual operation data exceeds the calibration range, it is determined that the actual operation data has data abnormality;

[0029] When the actual operation data does not exceed the calibration range, it is determined that the actual operation data has no data abnormality.

[0030] In the method provided in at least one embodiment of the present disclosure, the vehicle terminal is built-in with a local potential risk diagnosis model and a local fault diagnosis model, the local fault diagnosis model includes the first fault diagnosis model, the second fault diagnosis model, the third fault diagnosis model and the fourth fault diagnosis model, and the filtering of the target functional component having data abnormality from the plurality of key functional components comprises:

[0031] The actual operation data of each of the key functional components having data abnormality is tracked for a set time respectively, and the frequency of data abnormality of the related key functional component within the set time is counted;

[0032] In response to the frequency being less than a first set value, it is determined that the key functional component has no abnormality at the current time;

[0033] In response to the frequency being greater than or equal to the first set value and less than a second set value, it is determined that the key functional component has occasional or intermittent abnormality, and a trigger signal of the local potential risk diagnosis model is generated, wherein the local potential risk diagnosis model is configured to pre-judge engine operation risk based on the actual operation data of the key functional component having occasional or intermittent abnormality, and generate an engine operation risk pre-judgment probability;

[0034] In response to the frequency being greater than or equal to a second set value, it is determined that the key functional component has a persistent abnormality, and a trigger signal for generating the local fault diagnosis model is generated, wherein the first set value is less than the second set value, and the local fault diagnosis model is configured to generate the first diagnosis result based on the actual operation data of the target functional component for fault diagnosis of the engine lubrication system.

[0035] In the method provided by at least one embodiment of the present disclosure, the first fault location and the first fault mode are generated based on the engine operation data and the actual operation data of the target functional component through a pre-set first fault diagnosis model, which includes: extracting the feature parameters of the engine operation data and the actual operation data of the target functional component, respectively, matching the feature parameters with the standard parameters of different fault locations and different fault modes stored in the local fault mode database built in the vehicle terminal through the matching algorithm of the first fault diagnosis model, and determining the first fault location and the first fault mode based on the matching result; and,

[0036] The second fault location and the second fault mode are generated based on the actual operation data of the target functional component through a pre-set second fault diagnosis model, which includes: extracting the feature parameters of the actual operation data of the target functional component, matching the feature parameters with the standard parameters of different fault locations and different fault modes stored in the local fault mode database built in the vehicle terminal through the matching algorithm of the second fault diagnosis model, and determining the second fault location and the second fault mode based on the matching result.

[0037] The method provided by at least one embodiment of the present disclosure further includes:

[0038] Timing to acquire the cloud platform fault mode database, the cloud platform potential risk diagnosis model and the cloud platform fault diagnosis model of the cloud platform in communication with the vehicle terminal;

[0039] Updating the local fault mode database based on the cloud platform fault mode database;

[0040] Updating the local potential risk diagnosis model based on the cloud platform potential risk diagnosis model;

[0041] Updating the local fault diagnosis model based on the cloud platform fault diagnosis model; and,

[0042] Uploading the first diagnosis result obtained in this fault diagnosis and the corresponding feature parameters to the cloud platform for secondary diagnosis evaluation and iterative update of the cloud platform fault diagnosis model, or feeding back to the user terminal in communication with the cloud platform.

[0043] The method provided by at least one embodiment of the present disclosure further includes:

[0044] Based on the whole vehicle operation data, the engine operation data and the actual operation data of the target functional component, a prediction probability of vehicle failure is generated, and a warning signal is generated when the prediction probability of vehicle failure exceeds a set threshold.

[0045] The method provided by at least one embodiment of the present disclosure further includes:

[0046] When the first diagnostic result is an unknown fault, the actual operation data of the target functional component is uploaded to a cloud platform for the cloud platform to call a big data analysis model built-in the cloud platform to perform secondary diagnosis;

[0047] In response to receiving a secondary diagnostic result fed back by the cloud platform, the secondary diagnostic result and the corresponding feature parameters are updated to the local fault mode database.

[0048] At least one embodiment of the present disclosure also provides an engine lubrication system fault diagnosis device, applied to a vehicle terminal, including:

[0049] A data acquisition unit configured to acquire actual operation data of each of a plurality of key functional components in an engine lubrication system;

[0050] A preprocessing unit configured to monitor whether the actual operation data of each of the plurality of key functional components is abnormal;

[0051] A screening unit configured to screen a target functional component with data abnormality from the plurality of key functional components; and,

[0052] A fault diagnosis unit configured to perform fault diagnosis on the engine lubrication system based on the actual operation data of the target functional component, to generate a fault position and a fault mode as a first diagnostic result.

[0053] At least one embodiment of the present disclosure also provides a storage medium, which stores a program or instructions, and the program or instructions implement the steps of the method provided by any one of the embodiments of the present disclosure when executed by a processor.

[0054] At least one embodiment of the present disclosure also provides a program product, including a program or instructions, and the program or instructions implement the steps of the method provided by any one of the embodiments of the present disclosure when executed by a processor.

[0055] Compared with the related art, the engine lubrication system fault diagnosis method, device, medium and program product provided by the embodiments of the present disclosure can significantly improve the accuracy and efficiency of fault diagnosis. First, by monitoring the actual operation data of the necessary and complete key functional components of the engine lubrication system in real time, necessary data support is provided for diagnosis analysis, abnormalities can be found in time, and accurate diagnosis results can be given. Secondly, the type and location (key functional components) of the fault can be accurately judged, clear guidance is provided for maintenance personnel, rapid diagnosis of fault modes is realized, diagnosis time and misjudgment rate are reduced, the occurrence of major engine failures is avoided, and rapid repair of engine failures is realized, thereby solving the technical problem of low fault diagnosis accuracy caused by too few monitoring points in the related art.

[0056] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0058] Figure 1 A flowchart of an engine lubrication system fault diagnosis method provided by at least one embodiment of the present disclosure is provided.

[0059] Figure 2 A composition schematic diagram of an engine lubrication system provided by at least one embodiment of the present disclosure is provided.

[0060] Figure 3 A flowchart of another engine lubrication system fault diagnosis method provided by at least one embodiment of the present disclosure is provided.

[0061] Figure 4 A flowchart of still another engine lubrication system fault diagnosis method provided by at least one embodiment of the present disclosure is provided.

[0062] Figure 5 A diagnosis information interaction process schematic diagram of an engine lubrication system fault diagnosis method instance provided by at least one embodiment of the present disclosure is provided.

[0063] Figure 6 A principle schematic diagram of an engine lubrication system fault diagnosis method instance provided by at least one embodiment of the present disclosure is provided.

[0064] Figure 7 A structural block diagram of an engine lubrication system fault diagnosis device provided by at least one embodiment of the present disclosure is provided.

[0065] Figure 8 A schematic diagram of a program product according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0066] The present disclosure will be further described by way of illustration with reference to the following drawings and embodiments. It is specifically pointed out that the following embodiments are merely for illustrative purposes and are not intended to limit the scope of the present disclosure. Similarly, the following embodiments are only part of the embodiments of the present disclosure, and all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present disclosure.

[0067] The terms "first", "second", and "third" in the embodiments of the present disclosure are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", and "third" can explicitly or implicitly include at least one of the features.

[0068] In the description of the present disclosure, the meaning of "a plurality of" is at least two, such as two or three, unless otherwise explicitly and specifically limited.

[0069] In the present disclosure, the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the present specification, the illustrative representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the skilled person in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0070] In the embodiments of the present disclosure, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or components inherent to the process, method, product or device.

[0071] As used herein, "program product" is a software product that mainly realizes its solution through a computer program, and is not limited to running on a certain type of electronic device or electronic device.

[0072] As used herein, "electronic device" includes, but is not limited to, devices that are configured to receive / send communication signals over a wired line (e.g., a telephone line, a digital cable, or a direct cable connection, and / or another data connection / network) and / or that are configured to receive / send communication signals wirelessly (e.g., over a satellite or cellular network, a wireless local area network (WLAN), a digital television network, a satellite network, or an AM-FM radio transmitter, and / or another communication terminal). Devices that are configured to communicate wirelessly can be referred to as "wireless communication terminals," "wireless terminals," or "mobile terminals." Examples of mobile terminals include, but are not limited to, satellite or cellular phones; Personal Communication System (PCS) terminals that can combine a cellular radiotelephone with data processing, facsimile, and data communications capabilities; PDA's that can include a wireless telephonic, pager, Internet / intranet access, Web browser, organizer, calendar, and / or global positioning system (GPS) receiver; and conventional laptop and / or palmtop receivers or other electronic devices that include a wireless telephonic transceiver.

[0073] The term "engine controller" in the embodiments of the present disclosure, abbreviated as ECU.

[0074] The term "vehicle control unit" in the embodiments of the present disclosure, abbreviated as VCU, coordinates the high voltage on the battery control system of the vehicle and coordinates the power generation of the range extending system.

[0075] The term "on-board diagnostic system" in the embodiments of the present disclosure, abbreviated as OBD, is an electronic system installed on the engine for monitoring and managing engine emissions.

[0076] The term "lubrication system" in the embodiments of the present disclosure refers to a system that circulates clean, appropriate amount and appropriate temperature of lubricating oil to the parts of the engine that need lubrication or oil cooling. The lubrication system is generally composed of oil sump, filter, oil pump, oil cooler, oil filter, safety valve, pressure regulating valve and other components.

[0077] Figure 1 A flowchart of an engine lubrication system fault diagnosis method provided for at least one embodiment of the present disclosure. The method is applied to a vehicle terminal, which can be an engine controller ECU or a vehicle controller VCU. As shown in Figure 1 The flowchart can include the following steps S10-S40.

[0078] Step S10: Obtain the actual operation data of each of a plurality of key functional components in the engine lubrication system.

[0079] Step S20: Monitor whether the actual operation data of each of the plurality of key functional components is abnormal.

[0080] Step S30: screening a target functional component with data anomaly from the plurality of key functional components.

[0081] Step S40: performing fault diagnosis on the engine lubrication system based on the actual operation data of the target functional component, to generate a fault position and a fault mode as a first diagnosis result.

[0082] It should be noted that, in addition to the conventional monitoring of the main oil passage oil pressure data, the above method adds detection points to other key functional components of the engine lubrication system except the main oil passage, for obtaining actual operation data of each of the plurality of key functional components. Through the actual operation data collected by the above added detection points, more accurate fault diagnosis of the mechanical components in the engine lubrication system can be achieved.

[0083] Some embodiments of the present disclosure also provide a device, a medium (storage medium) and a program product corresponding to the above method.

[0084] The method provided by at least one embodiment of the present disclosure is suitable for any application scenario that needs to diagnose the fault of the engine lubrication system of a vehicle, and embodiments of the present disclosure do not limit this. For example, the method can be applied to various types of vehicles, including but not limited to cars, trucks, buses, engineering machinery and agricultural machinery, etc. In these vehicles, the health status of the engine lubrication system is crucial to ensure the normal operation of the engine and prolong the service life. Through the method of the present disclosure, comprehensive and accurate fault diagnosis of the engine lubrication system can be achieved, helping maintenance personnel to quickly locate and solve potential problems, thereby improving the maintenance efficiency and accuracy. In addition, the method can also be combined with other vehicle management systems or diagnostic tools to realize a more intelligent and automated fault diagnosis process, and provide more convenient and efficient maintenance services for vehicle users.

[0085] Compared with related art, the method proposed by the present disclosure can significantly improve the accuracy and efficiency of fault diagnosis. First, by monitoring the actual operation data of the necessary and complete key functional components of the engine lubrication system in real time, the method provides necessary data support for diagnostic analysis, and can timely find anomalies and give accurate diagnosis results. Secondly, the method can accurately determine the type and location (key functional component) of the fault, provide clear guidance for maintenance personnel, realize rapid diagnosis of fault mode, reduce diagnosis time and misdiagnosis rate, and is conducive to avoiding the occurrence of major engine failures and rapid repair of engine failures, solving the technical problem of low fault diagnosis accuracy caused by too few monitoring points in related art.

[0086] For step S10, the key functional components include but are not limited to the main oil gallery, the oil pump, the oil cooler, and the oil sump, and may further include the oil strainer, the oil filter, the pressure regulating valve, etc. The actual operation data can be real-time operation data or non-real-time operation data, and the embodiments of the present disclosure do not make any limitation in this regard. The locations of the monitoring points on the oil pump, the oil cooler, and the oil sump can be found in the following description. Figure 2 The main function of the oil strainer is to filter impurities in the oil to ensure the cleanliness of the oil. The actual operation data thereof can include the clogging state of the oil strainer, which can be indirectly evaluated by monitoring the change in the oil flow or pressure. The oil filter is used for further purifying the oil, and the actual operation data thereof can cover the service life and clogging degree of the filter, which are usually judged by the cumulative working time or the change in the oil pressure. The pressure regulating valve is responsible for regulating the pressure of the oil system to ensure that it fluctuates within a reasonable range. The actual operation data thereof can include the set pressure of the pressure regulating valve and the actual working pressure, which can be directly obtained by a pressure sensor.

[0087] For step S20, the monitoring point data added by step S10 can achieve more accurate monitoring of the mechanical components in the lubrication system, such as the oil strainer, the oil pump, the oil cooler, the oil filter, and the pressure regulating valve. These data can not only reflect the working state of each component, but also timely discover potential fault risks. For example, when the oil strainer is clogged, the oil flow decreases and the pressure changes abnormally, and the system can quickly capture this signal and issue a warning. Similarly, the performance degradation of the oil pump, the heat dissipation efficiency reduction of the oil cooler, the clogging of the oil filter, and the misadjustment of the pressure regulating valve can all be accurately identified by the newly added monitoring point data.

[0088] For step S30, the target functional components with data anomalies are selected from the multiple key functional components based on the monitoring results of step 20. Based on the preset abnormal data judgment criteria, such as values exceeding the normal range, abnormal fluctuations, or unexpected change trends, the system can automatically identify and mark the target functional components that may have faults or performance degradation, thereby improving the efficiency of diagnosis.

[0089] For step S40, the system first compares the actual operating data of the target functional component with the preset normal operating parameter range, and then performs in-depth analysis through an advanced algorithm model. If the actual operating data deviates from the normal range, the system will further determine the specific location and mode of the fault. For example, if the actual flow data of the oil pump is significantly lower than the standard value, the system may diagnose that the oil pump is blocked or severely worn, causing insufficient oil supply; if the pressure of the oil filter changes abnormally, it may be that the filter is blocked or failed. In addition, the system also considers the mutual influence between multiple components to more accurately determine the root cause of the fault. Through this step, technicians can quickly obtain detailed fault diagnosis reports to provide strong support for subsequent maintenance or replacement work.

[0090] Figure 2 A schematic diagram of an engine lubrication system is provided for at least one embodiment of the present disclosure. As shown in Figure 2 , the actual operating data of the main oil gallery includes the main oil gallery oil pressure (also referred to as the main oil gallery oil pressure), which is obtained through a pressure temperature sensor arranged in the main oil gallery. The actual operating data of the oil pump includes the oil pressure after the oil pump (also referred to as the oil pressure after the oil pump) and the oil temperature after the oil pump (also referred to as the oil temperature after the oil pump), which are obtained through a pressure temperature sensor added after the oil pump. The actual operating data of the oil cooler includes the oil pressure after the oil cooler (also referred to as the oil pressure after the oil cooler), which is obtained through a pressure sensor added after the oil cooler. The actual operating data of the oil sump includes the oil level of the oil sump, which is obtained through an oil level sensor added in the oil sump.

[0091] Figure 3 A flowchart of another engine lubrication system fault diagnosis method is provided for at least one embodiment of the present disclosure. Based on Figure 1 , as shown in Figure 3 , in order to improve the diagnosis accuracy, step S40 is refined into the following sub-steps S401-S404.

[0092] Sub-step S401: Obtain engine operating data.

[0093] Sub-step S402: Identify whether the engine operating data has data anomalies.

[0094] Sub-step S403: If yes, generate a first fault location and a first fault mode based on the engine operating data and the actual operating data of the target functional component through a pre-set first fault diagnosis model.

[0095] Sub-step S404: If no, generate a second fault location and a second fault mode based on the actual operating data of the target functional component through a pre-set second fault diagnosis model.

[0096] It should be noted that the first fault diagnosis model and the second fault diagnosis model are not necessarily different, but can be the same model according to actual conditions, or different diagnosis logic or algorithms according to different fault types. Moreover, the first fault diagnosis model and the second fault diagnosis model are not fixed, but can be iteratively updated.

[0097] Among them, the engine operating data includes but is not limited to engine speed and other key parameters, which can comprehensively reflect the working state of the engine and the performance of the lubricating system. After obtaining these data, the system will combine the actual operating data of the target functional component, such as the oil pressure after the oil pump and the oil pressure after the oil filter, for comprehensive analysis. Through deep mining and comparison of these data, the system can more accurately identify possible fault points in the engine lubricating system, such as performance decline of the oil pump, blockage or failure of the filter, etc. At the same time, the system will also infer the mode of the fault according to the specific performance of the fault, such as insufficient oil supply, poor oil circulation, etc., thereby providing more detailed fault diagnosis information for technicians. This step of refinement makes the entire fault diagnosis process more scientific and accurate, providing a more reliable basis for subsequent maintenance or replacement work.

[0098] In some embodiments, the engine operating data is configured to include engine speed, engine oil consumption, and engine output torque. These data not only intuitively reflect the current working state of the engine, but are also crucial for evaluating the efficiency of the lubricating system. Changes in engine speed can reveal the response capability of the lubricating system under different working conditions of the engine, while monitoring of engine oil consumption helps to find additional oil consumption caused by poor lubrication. The size and stability of the engine output torque are also directly related to the performance of the lubricating system. If the lubricating system fails, such as insufficient oil supply or oil quality decline, it may cause the engine output torque to decrease or the fluctuation to increase, thereby affecting the power performance and driving experience of the vehicle. By comprehensively analyzing these data, the system can more comprehensively evaluate the health status of the engine lubricating system, further improving the accuracy and efficiency of fault diagnosis.

[0099] Figure 4 A flowchart of another engine lubricating system fault diagnosis method provided by at least one embodiment of the present disclosure is shown in FIG. 4. Based on the method shown in FIG. 3, as shown in FIG. 4, in order to further improve the diagnosis accuracy, step S40 is refined into the following sub-steps S401* to S404*. Figure 1 Figure 4 Sub-step S401*: Obtain engine operating data and vehicle operating data of the vehicle in which the engine lubricating system is located.

[0100] Sub-step S401*: Obtain engine operating data and vehicle operating data of the vehicle in which the engine lubricating system is located.

[0101] Sub-step S402*: Identify whether there is data anomaly in the vehicle operating data.​

[0102] Sub-step S403*: If yes, when the engine operation data has data abnormalities, generating a third fault location and a third fault mode based on the vehicle operation data, the engine operation data, and the actual operation data of the target functional component through a pre-set third fault diagnosis model, and when the engine operation data has no abnormalities, generating a fourth fault location and a fourth fault mode based on the vehicle operation data and the actual operation data of the target functional component through a pre-set fourth fault diagnosis model.

[0103] Sub-step S404*: If no, when the engine operation data has data abnormalities, generating a first fault location and a first fault mode based on the engine operation data and the actual operation data of the target functional component through a pre-set first fault diagnosis model, and when the engine operation data has no abnormalities, generating a second fault location and a second fault mode based on the actual operation data of the target functional component through a pre-set second fault diagnosis model.

[0104] It should be noted that the first fault diagnosis model, the second fault diagnosis model, the third fault diagnosis model, and the fourth fault diagnosis model are not necessarily different, but can be the same model according to the actual situation, or different diagnosis logic or algorithms according to the different fault types. Moreover, the first fault diagnosis model, the second fault diagnosis model, the third fault diagnosis model, and the fourth fault diagnosis model are not fixed, but can be iteratively updated.

[0105] The vehicle operation data includes but is not limited to vehicle speed, mileage, engine temperature, coolant temperature, etc., which can reflect the overall operation state of the vehicle and the working environment of the engine. After obtaining these data, the system will combine the engine operation data and the actual operation data of the target functional component for more comprehensive and in-depth analysis. By considering the vehicle operation data, the system can more accurately evaluate the performance of the engine lubrication system under different working conditions, and thus more accurately locate the fault location and infer the fault mode. For example, after high-speed driving or long-time continuous work, the engine lubrication system may fail due to excessive load or increased wear, and the vehicle operation data can help the system better understand and predict the occurrence of such failures. The addition of this step further improves the accuracy and comprehensiveness of fault diagnosis, providing more rich diagnostic information and maintenance recommendations for technicians. Through algorithm analysis and continuous algorithm iteration of the diagnosis model, more accurate and visual failure locations and failure modes are provided for users and maintenance personnel, which is beneficial to improve the convenience of fault solving.

[0106] In some embodiments, in order to adapt to the complex and variable actual driving environment, the vehicle running data is configured to include vehicle acceleration and slope. Among them, the vehicle acceleration can reflect the acceleration performance of the vehicle in the driving process and the driving habit of the driver, which is particularly crucial for evaluating the performance of the engine lubrication system in the sudden acceleration working condition. And the slope data can help the system understand the current terrain environment of the vehicle, such as driving on an uphill, downhill or flat road. These information is of great significance to judge the working state of the engine lubrication system under the influence of different gravity. By including vehicle acceleration and slope in the consideration of vehicle running data, the system can more comprehensively analyze the performance of the engine lubrication system under different driving conditions and terrain environments, thereby further improving the accuracy and pertinence of fault diagnosis. This improvement enables the system to better adapt to the complex and variable actual driving environment, providing more accurate and reliable fault diagnosis services for vehicle owners and maintenance personnel.

[0107] In some embodiments, in order to improve the diagnostic efficiency of the method, step S20 is refined to include the following sub-steps S201-S203.

[0108] Sub-step S201: For the actual running data of each of the plurality of key functional components, perform initialization analysis, wherein the initialization analysis is configured to identify whether the actual running data is outside the calibration range (factory data or initial calibration data) of the normal operation of the key functional component under the current working condition.

[0109] Sub-step S202: When the actual running data is outside the calibration range, it is determined that the actual running data has data anomaly.

[0110] Sub-step S203: When the actual running data is not outside the calibration range, it is determined that the actual running data has no data anomaly.

[0111] The purpose of the initialization analysis is to quickly and clearly determine whether there is data anomaly through preliminary analysis of the monitoring data. Through sub-steps S201-S203, the running state of the key functional component can be efficiently evaluated. This refined step provides necessary data for the final fault diagnosis, not only improves the response speed of fault diagnosis, but also ensures the accuracy and efficiency of the diagnosis process, providing a strong guarantee for the stable operation of the engine lubrication system.

[0112] In some embodiments, the vehicle terminal is built-in with a local potential risk diagnosis model and a local fault diagnosis model, and the local fault diagnosis model includes the first, second, third and fourth fault diagnosis models. In order to accurately monitor and determine the abnormality of the running state of the key functional component, step S30 is refined to include the following sub-steps S301-S304.

[0113] Sub-step S301: Continuously track the actual operation data of each actual operation data with data anomaly for a set time, and count the frequency of data anomaly of the related key functional components within the set time.

[0114] Sub-step S302: In response to the frequency being less than a first set value, it is determined that the key functional component is currently normal.

[0115] Sub-step S303: In response to the frequency being greater than or equal to the first set value and less than a second set value, it is determined that the key functional component has occasional or intermittent anomalies, and a trigger signal of a local potential risk diagnosis model is generated, wherein the local potential risk diagnosis model is configured to predict engine operation risk based on actual operation data of the key functional component with occasional or intermittent anomalies, and generate an engine operation risk prediction probability.

[0116] Sub-step S304: In response to the frequency being greater than or equal to the second set value, it is determined that the key functional component has persistent anomalies, and a trigger signal of a local fault diagnosis model is generated, wherein the first set value is less than the second set value, the local fault diagnosis model is configured to diagnose faults of the engine lubrication system based on actual operation data of the target functional component, and generate a first diagnosis result (step S40).

[0117] The precise monitoring and anomaly determination of the operation state of the key functional components of the engine are achieved through sub-step S301 to sub-step S304. In the initial analysis process of the data, when the detected data exceeds the calibration value, in order to avoid false positives, the fault alarm mechanism is not directly triggered, but the data is first tracked for a period of time. The frequency of abnormal data is determined to be normal, occasional or continuous, and then it is determined to be no anomaly, occasional or intermittent anomaly, or confirmed persistent anomaly (fault), and the subsequent alarm is triggered.

[0118] In some embodiments, in order to predict the probability of engine failure, the method further includes the following step S50.

[0119] Step S50: Running the potential risk diagnosis model to generate an engine operation risk prediction probability as a second diagnosis result.

[0120] The potential risk diagnosis model is configured to comprehensively analyze the running state of the engine based on the historical running data of the engine, the monitoring data of the key functional components and the first diagnosis result of the fault diagnosis model, predict the possibility of failure of the engine in a future period of time, and quantify it as an engine running risk prediction probability. The introduction of this step can realize early warning of potential engine failure, provide more ample time for the operator to prepare for maintenance, and further reduce the loss caused by engine downtime due to failure. At the same time, combined with the first diagnosis result, the potential risk diagnosis model can provide a more comprehensive engine health status evaluation, and provide strong support for the maintenance decision of the engine.

[0121] In some embodiments, on the basis of sub-steps S301-S304, in order to further ensure the stable operation of the engine, step S30 further includes sub-step S305.

[0122] Sub-step S305: generating a corresponding maintenance suggestion or alarm signal according to the engine running risk prediction probability or the first diagnosis result.

[0123] If the engine running risk prediction probability is high, the operator is prompted to perform maintenance inspection on the engine in advance to avoid the occurrence of potential failure. If the first diagnosis result indicates that the engine lubrication system has a fault, an alarm signal is immediately triggered, and a detailed fault diagnosis report is generated to enable the maintenance personnel to quickly locate and repair the fault, thereby effectively ensuring the safe and reliable operation of the engine.

[0124] In some embodiments, in order to accurately identify the fault position and the fault mode, the first fault position and the first fault mode in step S403 or step S404* are configured to be obtained through the following sub-steps S403a-S403b.

[0125] Sub-step S403a: extracting feature parameters in the engine running data and the actual running data of the target functional component, respectively.

[0126] Sub-step S403b: matching the above-mentioned feature parameters with standard parameters of different fault positions and different fault modes stored in the local fault mode database built in the vehicle terminal through a matching algorithm of the first fault diagnosis model, and determining the first fault position and the first fault mode based on the matching result.

[0127] The characteristic parameters include fluctuation amplitude, duration, and change trend. Through sub-steps S403a-S403b, the specific location and fault mode of the problem in the engine lubrication system can be accurately identified. The implementation of this process relies on in-depth analysis of the engine operation data and the actual operation data of the target functional component. The extraction of characteristic parameters is a key step, which requires screening key information related to fault diagnosis from a large amount of data. Subsequently, by comparing these characteristic parameters with the standard parameters in the local fault mode database, the possible fault location and fault mode can be quickly located, providing accurate guidance for subsequent maintenance work. This method not only improves the accuracy and efficiency of fault diagnosis, but also greatly reduces the risk of engine damage caused by misdiagnosis or missed diagnosis.

[0128] In some embodiments, the second fault location and the second fault mode in step S404 or step S404* are configured to be obtained through the following sub-steps S404a-S404b.

[0129] Sub-step S404a: Extracting characteristic parameters in the actual operation data of the target functional component.

[0130] Sub-step S404b: Matching the above characteristic parameters with the standard parameters of different fault locations and different fault modes stored in the local fault mode database built in the vehicle terminal through the matching algorithm of the second fault diagnosis model, and determining the fault location and fault mode based on the matching result.

[0131] The characteristic parameters include at least one of the frequency of data anomalies, fluctuation amplitude, duration, and change trend. Through sub-steps S404a-S404b, the running state of the target functional component can be comprehensively and accurately evaluated. For example, the fluctuation amplitude can reflect the stability of the target functional component during operation, the duration can reveal the persistence of the fault phenomenon, and the change trend can predict the development trend of the fault. These characteristic parameters together constitute an important basis for fault diagnosis, making the diagnosis result more reliable. In addition, by continuously updating and optimizing the local fault mode database, the accuracy and adaptability of fault diagnosis can be further improved, ensuring the stable operation of the engine lubrication system.

[0132] In some embodiments, the third fault location and the third fault mode in step S403* are configured to be obtained through the following sub-steps S403a*-S403b*.

[0133] Sub-step S403a*: Extracting characteristic parameters of the vehicle operation data, the engine operation data, and the actual operation data of the target functional component.

[0134] Sub-step S403b*: The above feature parameters are matched with the standard parameters of different fault parts and different fault modes stored in the local fault mode database built-in in the vehicle terminal through the matching algorithm of the third fault diagnosis model, and the third fault part and the third fault mode are determined based on the matching result.

[0135] Among them, in order to improve the efficiency and accuracy of fault diagnosis, artificial intelligence technology such as machine learning or deep learning algorithm can be introduced to intelligently analyze and process the extracted feature parameters. These algorithms can automatically identify patterns and anomalies in data, further assist in determining fault parts and fault modes, reduce manual intervention, and improve the automation level of diagnosis. At the same time, combined with cloud platform big data technology, remote fault diagnosis and early warning can be realized, providing more convenient and efficient services for vehicle maintenance and maintenance.

[0136] In some embodiments, the fourth fault part and the fourth fault mode in step S403* are configured to be obtained through the following sub-steps S404a-S404b.

[0137] Sub-step S403c*: Extract the feature parameters of the whole vehicle operation data and the actual operation data of the target functional component.

[0138] Sub-step S403d*: The above feature parameters are matched with the standard parameters of different fault parts and different fault modes stored in the local fault mode database built-in in the vehicle terminal through the matching algorithm of the fourth fault diagnosis model, and the fourth fault part and the fourth fault mode are determined based on the matching result.

[0139] Among them, in order to further improve the intelligence and accuracy of engine lubrication system fault diagnosis, neural network models in deep learning can be introduced, especially convolutional neural networks (CNN) or recurrent neural networks (RNN), to perform deeper learning and analysis on the extracted feature parameters. These neural network models can automatically learn and extract complex features in data, further improving the accuracy of fault diagnosis.

[0140] In some embodiments, to improve the intelligent level of fault diagnosis, the method further comprises the following steps S01-S05.

[0141] Step S01: Obtain the cloud platform fault mode database (referred to as cloud database), cloud platform potential risk diagnosis model and cloud platform fault diagnosis model of the cloud platform communicating with the vehicle terminal in a timely manner;

[0142] Step S02: Update the local fault mode database based on the cloud platform fault mode database.

[0143] Step S03: updating the local potential risk diagnosis model based on the cloud platform potential risk diagnosis model.

[0144] Step S04: updating the local fault diagnosis model based on the cloud platform fault diagnosis model.

[0145] Step S05: uploading the first diagnosis result obtained by the current fault diagnosis and the corresponding feature parameters to the cloud platform for secondary diagnosis evaluation and iterative updating of the cloud platform fault diagnosis model, or feeding back to the user terminal in communication with the cloud platform.

[0146] Wherein, through steps S01-S03, a closed-loop fault diagnosis system can be constructed to realize real-time updating of fault data and continuous optimization of diagnosis model. Specifically, step S01 ensures the timeliness and comprehensiveness of local database information by regularly obtaining the fault mode database of the cloud platform; step S02 updates the local database based on the cloud platform data to improve the accuracy and coverage of local diagnosis; step S03 uploads the local diagnosis result and its feature parameters to the cloud platform, which not only helps the cloud platform to perform secondary diagnosis evaluation to improve the reliability of diagnosis, but also provides rich data support for iterative updating of the fault diagnosis model. The initialization analysis, fault diagnosis and fault mode judgment stages are completed by the diagnosis analysis in the ECU, and the cloud platform fault mode database is shared with the ECU. The main basis for ECU algorithm diagnosis is the fault mode database, and the main logic of the diagnosis method is to match the detected abnormal data with the running data of different fault modes in the fault mode database to determine the fault mode. This mode of collaborative work between the cloud platform and the local greatly improves the intelligent level of engine lubrication system fault diagnosis. In the cloud platform, the technical engineers perform secondary diagnosis evaluation and improve the fault mode and fault data, and then iterate the system fault diagnosis method to finally update and upload the fault mode database. This method also has self-adaptive learning ability, which can continuously optimize the diagnosis model to adapt to the needs of different vehicle models and working conditions, further improve the accuracy and reliability of diagnosis, and solve the technical problem of low fault diagnosis precision caused by too few monitoring points.

[0147] In some embodiments, in order to realize the early prediction of potential faults of the vehicle, the method further includes the following step S60.

[0148] Step S60: generating a prediction probability of vehicle fault based on the whole vehicle running data, the engine running data and the actual running data of the target functional component, and generating a warning signal when the prediction probability of vehicle fault exceeds a set threshold.

[0149] The early prediction of potential vehicle faults can be achieved through step S60. Specifically, the vehicle operation data, engine operation data, and actual operation data of the target functional component (such as the lubrication system) are comprehensively analyzed, and the possibility of fault occurrence, i.e., the prediction probability, is calculated using advanced algorithm models. When the prediction probability exceeds the preset safety threshold, the system automatically triggers the early warning mechanism and generates a warning signal. This function not only improves the predictability of vehicle maintenance and reduces the occurrence of sudden failures, but also helps the vehicle owner or maintenance personnel to take appropriate measures in a timely manner to avoid the expansion of faults and ensure the safety and reliability of vehicle operation.

[0150] In some embodiments, the method further comprises steps S70-S80.

[0151] Step S70: When the first diagnosis result is an unknown fault, the actual operation data of the target functional component is uploaded to the cloud platform for the cloud platform to call the big data analysis model built-in the cloud platform for secondary diagnosis.

[0152] Step S80: In response to receiving the secondary diagnosis result fed back by the cloud platform, the secondary diagnosis result and its corresponding characteristic parameters are updated to the local fault mode database.

[0153] Through steps S70-S80, in-depth and accurate identification of unknown faults is achieved. With the powerful computing power of the cloud platform big data analysis model and the comprehensive fault mode database, the actual operation data of the target functional component can be analyzed more deeply, and more accurate diagnosis results can be provided. This fault diagnosis method that integrates the cloud platform and the local platform not only significantly improves the accuracy and efficiency of diagnosis, but also ensures the continuous updating and optimization of the fault mode database, providing a strong guarantee for the long-term stable operation of the vehicle.

[0154] Figure 5 The diagnostic information interaction process diagram of the engine lubrication system fault diagnosis method example provided by at least one embodiment of the present disclosure is shown in FIG. 1. As shown in FIG. 1, the diagnostic information interaction process of the engine lubrication system fault diagnosis method example provided by at least one embodiment of the present disclosure includes the following steps. Figure 5As shown, the diagnostic information interaction process involves information interaction between the ECU and the VCU or instrument panel (also known as intelligent instrument), interaction of man-machine fault information and troubleshooting results, information interaction between the diagnostic method and the cloud platform and the fault mode database, and information interaction between the ECU and other analysis platforms. The interaction between the ECU and other analysis platforms is realized through the vehicle networking system. The basic function of the vehicle networking system is data sharing of engine operation data, and finally realizes storage of background data, data interaction of the fault mode database, and data interaction with other analysis platforms. Here, the other analysis system mentioned can be a cloud platform, which has the functions of remote fault diagnosis analysis and algorithm iteration; or an engine component reliability analysis platform, which has the functions of remote detection, query, and collection of vehicle operation data, and can further evaluate and analyze the operation of engine components with the aid of big data, and evaluate subsequent new product development schemes. The functions of other analysis platforms can be various and are not limited to the above-mentioned two functions, but the realization of their functions mainly relies on big data of engine operation.

[0155] Figure 6 The principle schematic diagram of an engine lubrication system fault diagnosis method example provided for at least one embodiment of the present disclosure is shown. The method mainly designs four processes of initialization analysis, failure mode diagnosis, diagnostic information interaction, and database information storage. The initialization analysis process quickly determines whether there is data anomaly through preliminary analysis of the monitored data, and triggers potential risk hazard diagnosis and fault failure diagnosis algorithms according to the characteristics of abnormal data. The failure mode diagnosis process determines the diagnosis result and the fault position through specific algorithm analysis. The diagnostic information interaction process realizes information interaction between the engine ECU and the VCU or instrument panel, interaction of man-machine fault information and troubleshooting results, information interaction between the diagnostic algorithm and the cloud platform and the failure mode database, and information interaction between the ECU and other analysis platforms. The database information storage process completes the historical data storage of fault data, which is convenient for subsequent historical fault query, failure analysis and algorithm iteration. Through the feedback interaction of fault information, the continuous iteration of the algorithm in the local fault diagnosis model is realized, the diagnosis accuracy is continuously improved, and the failure position and failure mode are fed back through the instrument panel to accelerate the solution of the fault problem; at the same time, the monitoring and analysis of abnormal data can realize the identification and elimination of early hidden risks, avoid the occurrence of larger faults, and reduce the economic loss of users.

[0156] Figure 7 The structural block diagram of an engine lubrication system fault diagnosis device provided for at least one embodiment of the present disclosure is shown. The device is applied to a vehicle terminal, such as Figure 7 As shown, the engine lubrication system fault diagnosis device 1 comprises a data acquisition unit 10, a preprocessing unit 20, a screening unit 30, and a fault diagnosis unit 40.

[0157] The data acquisition unit 10 is configured to acquire actual operation data of each of a plurality of key functional components in the engine lubrication system.

[0158] The preprocessing unit 20 is configured to identify whether the actual operation data of each of the plurality of key functional components is abnormal.

[0159] The screening unit 30 is configured to screen a target functional component with abnormal data from the plurality of key functional components.

[0160] The fault diagnosis unit 40 is configured to perform fault diagnosis on the engine lubrication system based on the actual operation data of the target functional component, and generate a fault position and a fault mode as a first diagnosis result.

[0161] The specific manners in which the units in the device embodiments perform operations have been described in detail in the embodiments of the method, and will not be described in detail here.

[0162] In some embodiments, the data acquisition unit 10 includes a pressure and temperature sensor arranged at a main oil passage, a pressure and temperature sensor arranged after an oil pump, a pressure sensor arranged after an oil cooler, an oil level sensor arranged in an oil pan, and a data collector.

[0163] The pressure and temperature sensor arranged at the main oil passage is used to acquire a main oil passage pressure and a main oil passage temperature.

[0164] The pressure and temperature sensor arranged after the oil pump is used to acquire an oil pump post pressure and an oil pump post temperature.

[0165] The pressure sensor arranged after the oil cooler is used to acquire an oil cooler post pressure.

[0166] The oil level sensor arranged in the oil pan is used to acquire an oil pan oil level.

[0167] The data collector is used to transmit the main oil passage pressure, the main oil passage temperature, the oil pump post pressure, the oil pump post temperature, the oil cooler post pressure, and the oil pan oil level to an ECU.

[0168] The preprocessing unit 20, the screening unit 30, and the fault diagnosis unit 40 can be implemented in a software module or hardware.

[0169] The embodiments of the present disclosure further provide a storage medium storing a program or instructions, which, when executed by a processor, implement the steps of the above method embodiments.

[0170] The embodiments of the present disclosure further provide a program product, such as a computer program product, which includes a computer program and a storage medium storing the computer program. Figure 8As shown, the program product comprises one or more processors 21 and a memory 22, Figure 8 The processor 21 is taken as an example in the description.

[0171] The controller can further comprise an input device 23 and an output device 24.

[0172] The processor 21, the memory 22, the input device 23 and the output device 24 can be connected by a bus or other means, Figure 8 The connection by the bus is taken as an example in the description.

[0173] The processor 21 can be a central processing unit (CPU), and the processor 21 can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination thereof, and the general-purpose processor can be a microprocessor or any conventional processor.

[0174] The memory 22 is a non-transitory computer readable storage medium, which can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the method in the embodiments of the present disclosure. The processor 21 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 22, that is, implements the steps of the above method embodiments.

[0175] The memory 22 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application program required by a function; the data storage area can store data created according to the use of the processing device of the server operation, etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device or other non-transitory solid-state memory device. In some embodiments, the memory 22 can optionally include a memory remotely arranged with respect to the processor 21, and these remote memories can be connected to the network connection device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0176] The input device 23 can receive inputted digital or character information, and generate key signal inputs related to user settings and function controls of the processing device of the server. The output device 24 can include a display device such as a display screen.

[0177] One or more modules are stored in the memory 22, which, when executed by the one or more processors 21, perform the method as shown. Figure 1

[0178] Those skilled in the art can understand that all or part of the processes in the above-mentioned method embodiments can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the above-mentioned method embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory (FM), a hard disk drive (HDD), or a solid-state drive (SSD), etc. The storage medium can also include a combination of the above-mentioned types of memories.

[0179] Although the embodiments of the present disclosure are described in conjunction with the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present disclosure, and such modifications and changes fall within the scope defined by the appended claims.

[0180] Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present disclosure, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present disclosure.​

Claims

1. A method for diagnosing engine lubrication system faults, applied to vehicle terminals, characterized in that, include: Acquire the actual operating data of each of the multiple key functional components in the engine lubrication system; Monitor whether there are any data anomalies in the actual operating data of each of the multiple key functional components; Select the target functional components with abnormal data from the multiple key functional components; as well as, Based on the actual operating data of the target functional components, the engine lubrication system is diagnosed to generate fault locations and fault modes, which serve as the first diagnostic result.

2. The method according to claim 1, characterized in that, The key functional components include the main oil passage, oil pump, oil cooler, and oil pan; and... The actual operating data of the main oil passage includes the main oil passage oil pressure; The actual operating data of the oil pump includes the oil pressure and oil temperature after the oil pump. The actual operating data of the oil cooler includes the oil pressure after the oil cooler; and... The actual operating data of the oil pan includes the oil level in the oil pan.

3. The method according to claim 1, characterized in that, The process of diagnosing faults in the engine lubrication system based on the actual operating data of the target functional components, and generating fault locations and fault modes, includes: Acquire engine operating data; Identify whether there are any data anomalies in the engine operating data; If so, based on the engine operating data and the actual operating data of the target functional component, a first fault location and a first fault mode are generated through a pre-set first fault diagnosis model; and, If not, a second fault location and a second fault mode are generated based on the actual operating data of the target functional component through a pre-set second fault diagnosis model.

4. The method according to claim 1, characterized in that, The process of diagnosing faults in the engine lubrication system based on the actual operating data of the target functional components, and generating fault locations and fault modes, includes: Acquire engine operating data and vehicle operating data of the vehicle in which the engine lubrication system is located; Identify whether there are any data anomalies in the vehicle operation data; If the engine operating data is abnormal, a third fault location and a third fault mode are generated based on the vehicle operating data, the engine operating data, and the actual operating data of the target functional component using a pre-set third fault diagnosis model; and if the engine operating data is not abnormal, a fourth fault location and a fourth fault mode are generated based on the vehicle operating data and the actual operating data of the target functional component using a pre-set fourth fault diagnosis model; and, If not, when there is an anomaly in the engine operating data, a first fault location and a first fault mode are generated based on the engine operating data and the actual operating data of the target functional component through a pre-set first fault diagnosis model; and when there is no anomaly in the engine operating data, a second fault location and a second fault mode are generated based on the actual operating data of the target functional component through a pre-set second fault diagnosis model.

5. The method according to claim 4, characterized in that, The engine operating data includes engine speed and engine fuel consumption; the vehicle operating data includes vehicle acceleration and gradient; and the monitoring of whether there are any data anomalies in the actual operating data of each of the multiple key functional components includes: For the actual operating data of each of the multiple key functional components, an initialization analysis is performed, wherein the initialization analysis is configured to identify whether the actual operating data exceeds the calibration range of the key functional component under the current operating conditions. When the actual operating data exceeds the calibration range, it is determined that the actual operating data is abnormal; and, If the actual operating data does not exceed the calibration range, it is determined that there is no data anomaly in the actual operating data.

6. The method according to claim 4, characterized in that, The vehicle terminal has a built-in local potential risk diagnosis model and a local fault diagnosis model. The local fault diagnosis model includes a first fault diagnosis model, a second fault diagnosis model, a third fault diagnosis model, and a fourth fault diagnosis model. Furthermore, the step of selecting target functional components with data anomalies from the multiple key functional components includes: For each actual operating data point with data anomalies, continuous tracking is performed for a set period of time, and the frequency of data anomalies occurring in the relevant key functional components within the set period of time is statistically analyzed. If the frequency is less than a first preset value, it is determined that the critical functional component is currently without abnormality. In response to the frequency being greater than or equal to a first preset value and less than a second preset value, it is determined that the key functional component has an occasional or intermittent anomaly, and a trigger signal for the local potential risk diagnosis model is generated. The local potential risk diagnosis model is configured to predict engine operating risks based on the actual operating data of the key functional component with the occasional or intermittent anomaly, and generate an engine operating risk prediction probability; and... In response to the frequency being greater than or equal to a second preset value, it is determined that the key functional component has a persistent abnormality, and a trigger signal for the local fault diagnosis model is generated, wherein the first preset value is less than the second preset value, and the local fault diagnosis model is configured to perform fault diagnosis on the engine lubrication system based on the actual operating data of the target functional component, and generate the first diagnostic result.

7. The method according to claim 3 or 4, characterized in that, The step of generating a first fault location and a first fault mode based on the engine operating data and the actual operating data of the target functional component using a pre-set first fault diagnosis model includes: extracting feature parameters from the engine operating data and the actual operating data of the target functional component respectively; matching the feature parameters with standard parameters of different fault locations and different fault modes stored in the local fault mode database built into the vehicle terminal using the matching algorithm of the first fault diagnosis model; and determining the first fault location and the first fault mode based on the matching results. The process of generating a second fault location and a second fault mode based on the actual operating data of the target functional component through a pre-set second fault diagnosis model includes: extracting feature parameters from the actual operating data of the target functional component; matching the feature parameters with standard parameters of different fault locations and different fault modes stored in the local fault mode database built into the vehicle terminal using the matching algorithm of the second fault diagnosis model; and determining the second fault location and the second fault mode based on the matching results.

8. The method according to claim 6, characterized in that, Also includes: Periodically acquire the cloud platform fault mode database, cloud platform potential risk diagnosis model and cloud platform fault diagnosis model of the cloud platform that communicates with the vehicle terminal; The local fault mode database is updated based on the cloud platform fault mode database; The local potential risk diagnosis model is updated based on the cloud platform potential risk diagnosis model. The local fault diagnosis model is updated based on the cloud platform fault diagnosis model; and... The first diagnostic result obtained from this fault diagnosis and its corresponding characteristic parameters are uploaded to the cloud platform for secondary diagnostic evaluation and iterative updates of the cloud platform's fault diagnosis model, or for feedback to the user terminal communicating with the cloud platform.

9. The method according to any one of claims 1-4, characterized in that, Also includes: Based on the vehicle's operating data, engine operating data, and the actual operating data of the target functional components, a predicted probability of vehicle malfunction is generated, and a warning signal is generated when the predicted probability of vehicle malfunction exceeds a set threshold.

10. The method according to any one of claims 1-4, characterized in that, Also includes: When the first diagnostic result indicates an unknown fault, the actual operating data of the target functional component is uploaded to the cloud platform so that the cloud platform can call its built-in big data analysis model for secondary diagnosis; and, In response to receiving the secondary diagnostic results from the cloud platform, the secondary diagnostic results and their corresponding characteristic parameters are updated to the local fault mode database.

11. A fault diagnosis device for an engine lubrication system, applied to a vehicle terminal, characterized in that, include: The data acquisition unit is configured to acquire the actual operating data of each of the multiple key functional components in the engine lubrication system; The preprocessing unit is configured to monitor whether there are any data anomalies in the actual operating data of each of the plurality of key functional components; The filtering unit is configured to filter out target functional components with data anomalies from the plurality of key functional components; as well as, The fault diagnosis unit is configured to perform fault diagnosis on the engine lubrication system based on the actual operating data of the target functional component, and generate fault location and fault mode as the first diagnostic result.

12. A storage medium, characterized in that, The storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 10.

13. A program product comprising a program or instructions, characterized in that, When the program or instructions are executed by a processor, they implement the steps of the method as described in any one of claims 1 to 10.

Images