Engine carbon deposit identification and cleaning method and device, electronic equipment and storage medium

Abstract

This application relates to the field of vehicle technology and discloses a method, device, electronic device, and storage medium for identifying and cleaning engine carbon deposits. The method includes: acquiring a first rail pressure signal from the engine; performing preprocessing on the first rail pressure signal to obtain a second rail pressure signal; extracting dynamic features from the second rail pressure signal to determine the degree of carbon deposit based at least on the dynamic features and a preset network model; and performing corresponding carbon deposit cleaning actions based on the degree of carbon deposit. This application extracts dynamic features from the first rail pressure signal, and can accurately determine the degree of carbon deposit by combining these dynamic features with a preset network model. It then triggers differentiated carbon cleaning strategies (such as pulse high-pressure fuel injection, injector vibration carbon cleaning, and oxygen-rich combustion) based on the degree of carbon deposit, effectively overcoming the shortcomings of existing technologies in early warning, graded diagnosis, intelligent carbon cleaning, and engineering deployment.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, apparatus, electronic device, and storage medium for identifying and cleaning engine carbon deposits. Background Technology

[0002] Due to the high-pressure environment, the physicochemical properties of carbon deposits in injectors of current high-pressure gasoline engines (rail pressure ≥ 500 bar) undergo significant changes. Compared to carbon deposits in traditional gasoline engine injectors, these deposits are harder, have stronger adhesion, and are more prone to clogging the injection orifices, making traditional diagnostic methods inadequate. Existing technologies largely rely on statistical characteristics such as average rail pressure or amplitude fluctuations, or indirectly infer the carbon deposit status through fuel injection quantity compensation. These methods suffer from diagnostic lag, insufficient accuracy, and inability to distinguish carbon deposit levels. Especially in systems with rail pressures above 500 bar, the impact of carbon deposits on the dynamic response of the needle valve is more subtle (e.g., phase delay, waveform distortion), and traditional methods easily miss early-stage light to moderate carbon deposits. Furthermore, existing solutions lack intelligent carbon removal strategies tailored to the characteristics of high-rail-pressure carbon deposits. Carbon removal largely relies on manual operation or additives, lacking a closed-loop feedback mechanism and the ability to dynamically adjust parameters based on the degree of carbon deposit buildup, resulting in low maintenance efficiency and uncontrollable effectiveness. In addition, most models do not take into account the resource limitations of the vehicle's electronic control unit (ECU), resulting in a large number of parameters and high inference latency, making them difficult to implement in engineering.

[0003] It is worth noting that there are fundamental structural differences between gasoline engine injectors and diesel engine injectors operating at pressures above 500 bar. Gasoline engine injectors typically use multi-hole fan-shaped nozzles (6-10 holes, orifice diameter 0.10-0.15 mm), with a short needle valve stroke (0.05-0.1 mm) and fast response, aiming to achieve uniform fuel atomization and avoid carbon buildup on the wet walls. Diesel engine injectors, on the other hand, use fewer-hole conical nozzles (4-8 holes, orifice diameter 0.12-0.18 mm), with a long needle valve stroke (0.1-0.3 mm) and a thicker, heavier structure to withstand ultra-high pressures exceeding 1800 bar and resist wear caused by carbon buildup. Due to differences in fuel characteristics and combustion methods, gasoline engine carbon buildup is mostly soft gum and hydrocarbon polymers, which easily clog the nozzle edges, thus affecting the dynamic response of the needle valve. Diesel engine carbon buildup, however, is hard carbon deposits, mainly causing wear on the needle valve guide surface. Existing technologies often fail to differentiate between fuel types, and their diagnostic and carbon removal solutions are mostly developed based on diesel engines or general models, making it difficult to adapt to the structural characteristics and carbon buildup behavior of gasoline engine injectors. Summary of the Invention

[0004] The purpose of this invention is to provide an engine carbon deposit identification and cleaning method, device, electronic device and storage medium, so as to at least solve the problems of low efficiency and poor controllability of existing engine carbon cleaning strategies, thereby improving carbon cleaning efficiency and ensuring the user's driving experience.

[0005] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for identifying and cleaning engine carbon deposits, comprising at least:

[0006] Acquire the first rail pressure signal of the engine;

[0007] Perform a preprocessing operation on the first rail pressure signal to obtain the second rail pressure signal;

[0008] Extract the dynamic features of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic features and a preset network model;

[0009] Perform the corresponding carbon buildup cleaning action based on the carbon buildup level.

[0010] Optionally, the preprocessing operation on the first rail pressure signal to obtain the second rail pressure signal specifically includes:

[0011] Remove high-frequency noise from the first rail pressure signal to obtain the first process signal;

[0012] The first process signal is normalized to obtain the second rail pressure signal.

[0013] Optionally, the step of extracting the dynamic features of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic features and a preset network model specifically includes:

[0014] Extract the phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value from the second rail pressure signal;

[0015] The phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are input into the preset network model to determine the carbon deposition level.

[0016] Optionally, performing the corresponding carbon deposit cleaning action based on the carbon deposit level specifically includes:

[0017] If the carbon buildup level is mild, the carbon buildup cleaning action will not be triggered.

[0018] If the carbon buildup level is medium, then when the engine is not in a power demand condition, the rail pressure is increased, and the fuel injector is controlled to inject fuel at a preset frequency to complete the carbon buildup cleaning action.

[0019] If the carbon buildup level is severe, then when the engine is not operating under power demand conditions, the rail pressure is increased, fuel injector vibration is added, and the air-fuel ratio is adjusted to complete the carbon buildup cleaning action.

[0020] Secondly, the present invention also provides an engine carbon deposit identification and cleaning device, comprising at least:

[0021] The signal acquisition module is used to acquire the engine's first rail pressure signal;

[0022] The preprocessing module is used to perform preprocessing operations on the first rail pressure signal to obtain the second rail pressure signal;

[0023] The grade determination module is used to extract the dynamic features of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic features and a preset network model;

[0024] The carbon buildup cleaning module is used to perform corresponding carbon buildup cleaning actions based on the carbon buildup level.

[0025] Optionally, the preprocessing module is specifically used for:

[0026] Remove high-frequency noise from the first rail pressure signal to obtain a first process signal; and perform normalization processing on the first process signal to obtain a second rail pressure signal.

[0027] Optionally, the level determination module is specifically used for:

[0028] The phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are extracted from the second rail pressure signal; and the phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are input into the preset network model to determine the carbon deposition level.

[0029] Optionally, the carbon deposit cleaning module is specifically used for:

[0030] When the carbon buildup level is light, the carbon cleaning action is not triggered; and when the carbon buildup level is moderate, the rail pressure is increased when the engine is in a non-power demand condition, and the fuel injector is controlled to inject fuel at a preset frequency to complete the carbon cleaning action; and when the carbon buildup level is heavy, the rail pressure is increased when the engine is in a non-power demand condition, fuel injector vibration is added, and the air-fuel ratio is adjusted to complete the carbon cleaning action.

[0031] Thirdly, the present invention also provides an electronic device, including a memory and a processor, the memory storing a computer program executable on the processor, wherein the processor executes the program to implement the steps in the engine carbon deposit identification and cleaning method according to any one of the first aspects.

[0032] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the engine carbon deposit identification and cleaning method according to any one of the first aspects.

[0033] The technical solution provided by the embodiments of the present invention firstly acquires the first rail pressure signal of the engine; secondly, performs a preprocessing operation on the first rail pressure signal to obtain a second rail pressure signal; then, extracts the dynamic features of the second rail pressure signal to determine the carbon deposit level based at least on the dynamic features and a preset network model; finally, performs the corresponding carbon deposit cleaning action based on the carbon deposit level.

[0034] Therefore, this invention extracts dynamic features based on the first rail pressure signal. These dynamic features, combined with a preset network model, accurately determine the degree of carbon buildup and trigger differentiated carbon removal strategies (such as pulse high-pressure injection, injector vibration carbon removal, and oxygen-enriched combustion) according to the degree of buildup. This forms a closed-loop control system of "identification-decision-execution," effectively overcoming the shortcomings of existing technologies in early warning, graded diagnosis, intelligent carbon removal, and engineering deployment. Compared to traditional methods, this method can provide early warning 1-2 maintenance cycles earlier, preventing combustion instability, power loss, and excessive emissions caused by carbon buildup deterioration, thereby significantly improving engine reliability and durability. Attached Figure Description

[0035] Figure 1 This is a flowchart of an engine carbon deposit identification and cleaning method provided in an embodiment of the present invention;

[0036] Figure 2 This is a network model architecture diagram provided in an embodiment of the present invention;

[0037] Figure 3 This is a flowchart of another engine carbon deposit identification and cleaning method provided in an embodiment of the present invention;

[0038] Figure 4 This is a flowchart of another engine carbon deposit identification and cleaning method provided in an embodiment of the present invention;

[0039] Figure 5 This is a schematic diagram of the structure of an engine carbon deposit identification and cleaning device provided in an embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0043] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0044] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0045] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0046] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0047] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0048] Figure 1 This is a flowchart of an engine carbon deposit identification and cleaning method provided by an embodiment of the present invention. This embodiment is applicable to at least various engine carbon deposit cleaning scenarios. The engine carbon deposit identification and cleaning method can be, but is not limited to, executed by the engine carbon deposit identification and cleaning device in this embodiment of the present invention. This execution entity can be implemented in software and / or hardware. Figure 1 As shown, this engine carbon deposit identification and cleaning method includes at least the following steps:

[0049] S1. Acquire the first rail pressure signal of the engine.

[0050] The first rail pressure signal can be the rail pressure signal of the high-pressure common rail system, which can be acquired in real time using an engine rail pressure sensor at a sampling rate of ≥10kHz (12kHz recommended). The sampling window is locked at 2.5ms before and after each injection command trigger, forming a 60-point timing waveform (12kHz × 0.005s = 60). This sampling window covers the rail pressure fluctuations at the moment the injector needle valve opens and closes, ensuring the capture of dynamic response distortion characteristics of the needle valve. The sensor output is an analog voltage signal, which is converted into a digital signal by the ECU's analog-to-digital converter for subsequent processing.

[0051] S2. Perform preprocessing operations on the first rail pressure signal to obtain the second rail pressure signal.

[0052] Preprocessing can include filtering and normalization.

[0053] S3. Extract the dynamic characteristics of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic characteristics and the preset network model.

[0054] Among them, dynamic characteristics include at least one of phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value. Figure 2 This is a network model architecture diagram provided in an embodiment of the present invention. See also: Figure 2 The preset network model can be a lightweight LSTM neural network model, GRU, Transformer, Bi-LSTM or other temporal neural networks, or a fusion model combining physical modeling and machine learning. Taking a lightweight LSTM neural network model as an example, the model structure provided in this embodiment includes:

[0055] Input layer (60 points × 1 channel) → 1D CNN layer (16 filters, 3 convolutional kernels, ReLU activation) → MaxPooling layer (pooling size 2) → LSTM layer (32 units, return_sequences=False) → Dropout layer (0.2) → Dense layer (16 units, ReLU) → Output layer (3 units, Softmax activation). The model has only 7015 parameters, which meets the requirements for vehicle ECU deployment.

[0056] Furthermore, the training data during the training process comes from bench tests. By controlling the degree of carbon buildup in the injectors (0%, 30%, and 70% simulated carbon buildup), the start-stop rail pressure waveform of the injector needle valve is collected and labeled with the level, and the degree of carbon buildup in the injectors is output.

[0057] S4. Perform the corresponding carbon buildup cleaning action based on the carbon buildup level.

[0058] The degree of carbon buildup is categorized into three levels: light (0%-30%), moderate (30%-70%), and heavy (greater than 70%). Carbon cleaning processes include at least high-pressure fuel injection and injector vibration.

[0059] The technical solution provided in this embodiment firstly acquires the first rail pressure signal of the engine; secondly, performs preprocessing operations on the first rail pressure signal to obtain the second rail pressure signal; then, extracts the dynamic features of the second rail pressure signal to determine the carbon deposit level based at least on the dynamic features and a preset network model; finally, performs the corresponding carbon deposit cleaning action based on the carbon deposit level.

[0060] Therefore, this embodiment extracts dynamic features based on the first rail pressure signal. These dynamic features, combined with a preset network model, accurately determine the degree of carbon buildup. Based on this degree, differentiated carbon removal strategies (such as pulse high-pressure injection, injector vibration carbon removal, and oxygen-rich combustion) are triggered, forming a closed-loop control of "identification-decision-execution." This effectively compensates for the shortcomings of existing technologies in early warning, graded diagnosis, intelligent carbon removal, and engineering deployment. Compared to traditional methods, this method can provide early warning 1-2 maintenance cycles earlier, preventing combustion instability, power loss, and excessive emissions caused by carbon buildup deterioration, thereby significantly improving engine reliability and durability.

[0061] Based on the above embodiments or implementation methods Figure 3 This is a flowchart of another engine carbon deposit identification and cleaning method provided in an embodiment of the present invention. Figure 4 This is a flowchart of another engine carbon deposit identification and cleaning method provided in this embodiment of the invention. This embodiment is based on the above embodiment and includes additional steps. Figure 3 and Figure 4 As shown, this engine carbon deposit identification and cleaning method includes at least the following steps:

[0062] S1. Acquire the first rail pressure signal of the engine.

[0063] S21. Remove high-frequency noise from the first rail pressure signal to obtain the first process signal.

[0064] High-frequency noise can be removed by using a first-order low-pass filter (cutoff frequency 8kHz).

[0065] S22. Normalize the first process signal to obtain the second rail pressure signal.

[0066] The purpose of normalization can be to eliminate the influence of dimensions.

[0067] S31. Extract the phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value from the second rail pressure signal.

[0068] Among them, phase delay represents the time difference between the rising edge of the injection command and the falling edge of the rail pressure response, used to reflect the hysteresis of needle valve opening. Waveform similarity represents the Pearson correlation coefficient with a standard carbon-free waveform, used to quantify the degree of waveform distortion; high-frequency energy proportion represents the proportion of energy in the 1~5kHz frequency band in the Fast Fourier Transform (used to reflect the suppression of high-frequency fluctuations by carbon deposits). Peak-to-peak value represents the maximum difference in rail pressure at the moment of injection opening and closing, used to reflect the resistance to needle valve movement. The above feature set directly maps the influence of carbon deposits on the dynamic response of the needle valve, avoiding the lag of traditional statistical features.

[0069] S32. Input phase delay, waveform similarity, high-frequency energy ratio and peak-to-peak value into the preset network model to determine the carbon deposition level.

[0070] S41. If the carbon buildup level is mild, the carbon buildup cleaning action will not be triggered.

[0071] When the level is "mild" (0~30%), only the status is recorded and carbon removal is not triggered.

[0072] S42. If the carbon buildup level is medium, then when the engine is not in a power demand condition, the rail pressure is increased, and the fuel injector is controlled to inject fuel at a preset frequency to complete the carbon buildup cleaning action.

[0073] When the level is "moderate" (30~70%), the ECU briefly increases the rail pressure by 50 bar under non-power demand conditions of the engine (such as idling or coasting), and at the same time controls the injector to inject high-frequency pulse fuel at a frequency of 100Hz (i.e., the preset frequency) for 2 seconds, using high-pressure fuel impact to peel off carbon deposits at the edge of the nozzle.

[0074] S43. If the carbon buildup level is severe, then when the engine is not operating under power demand conditions, increase the rail pressure, add injector vibration, and adjust the air-fuel ratio to complete the carbon buildup cleaning action.

[0075] When the level is "severe" (>70%), the ECU increases the rail pressure by 50 bar and adds injector vibration to clean carbon. The needle valve makes a small opening and closing action of 0.1 mm stroke (frequency 20 Hz, lasting 1 second) before closing, using hydraulic impact to peel off highly adhesive carbon deposits, and simultaneously adjusts the air-fuel ratio to λ=1.1, increasing the combustion temperature to promote carbon deposit oxidation.

[0076] Understandably, all carbon removal actions are performed under the monitoring of ECU safety policies (such as automatic termination when knocking, exhaust temperature, or oxygen sensor signals are abnormal) to ensure engine operation safety.

[0077] In a specific implementation scenario, after the carbon deposit cleaning process is completed, this embodiment also provides a closed-loop feedback method:

[0078] If the rail pressure timing waveform under the same operating conditions is collected again, the waveform similarity recovery rate before and after carbon removal is compared (recovery rate = (similarity after carbon removal - similarity before carbon removal) / similarity before carbon removal × 100%). If the recovery rate is ≥80%, carbon removal is recorded as successful, and the model weights are updated; if the recovery rate is <20%, the carbon removal intensity is increased (rail pressure increased by 100 bar, pulse time extended), or a maintenance reminder is triggered (recovery rate is below 20% for three consecutive times); and an incremental learning method is adopted, updating only the neuron weights in the LSTM model related to the current carbon buildup level. Specifically, the system freezes the neuron weights in the LSTM layer that are not related to the current carbon buildup level, and only fine-tunes the fully connected layers and some LSTM units involved in the current classification, with the learning rate set to 0.001, and each update not exceeding 10 epochs to avoid catastrophic forgetting. This closed-loop mechanism enables the system to have self-learning capabilities and improves maintenance reliability. It is understandable that, in addition to waveform similarity, phase difference change rate, high-frequency energy recovery rate, and injection response time reduction rate can also be used as evaluation indicators for carbon removal effect.

[0079] In another specific implementation scenario, the technical solution provided in this embodiment is as follows:

[0080] During the operation of a high-pressure gasoline direct injection engine, the system collects 60 pressure data points within 2.5 milliseconds before and after each injection event by sampling the rail pressure sensor signal at high frequency, forming a complete rail pressure timing waveform at the start and stop. After preprocessing, this waveform is input into a lightweight LSTM model. The model automatically determines the current carbon deposit level by combining the dynamic response characteristics of the needle valve. When moderate carbon deposit is identified, the ECU automatically triggers a pulsed high-pressure injection strategy under non-power demand conditions, briefly increasing the rail pressure and impacting the carbon deposits at the edge of the injection nozzle with high-frequency injection action. At the same time, the changes in the rail pressure waveform during the carbon cleaning process are monitored in real time. If the waveform similarity recovery rate after carbon cleaning exceeds 85%, the carbon cleaning is considered successful and recorded in the vehicle health record. If the standard is not met, the carbon cleaning intensity is automatically increased or maintenance is prompted. The entire process does not require manual intervention, and all algorithms and strategies are deployed in the vehicle ECU, without relying on external communication or cloud support, ensuring data security and independent system operation.

[0081] Therefore, this embodiment extracts dynamic features based on the first rail pressure signal. These dynamic features, combined with a preset network model, accurately determine the degree of carbon buildup. Based on this degree, differentiated carbon removal strategies (such as pulse high-pressure injection, injector vibration carbon removal, and oxygen-rich combustion) are triggered, forming a closed-loop control of "identification-decision-execution." This effectively compensates for the shortcomings of existing technologies in early warning, graded diagnosis, intelligent carbon removal, and engineering deployment. Compared to traditional methods, this method can provide early warning 1-2 maintenance cycles earlier, preventing combustion instability, power loss, and excessive emissions caused by carbon buildup deterioration, thereby significantly improving engine reliability and durability.

[0082] Figure 5 This is a schematic diagram of the structure of an engine carbon deposit identification and cleaning device provided in an embodiment of the present invention. This embodiment is applicable to at least various engine carbon deposit cleaning scenarios, and the engine carbon deposit identification and cleaning device can be implemented using software and / or hardware. Figure 5 As shown, the engine carbon deposit identification and cleaning device includes at least:

[0083] The signal acquisition module 110 is used to acquire the first rail pressure signal of the engine.

[0084] The preprocessing module 120 is used to perform preprocessing operations on the first rail pressure signal to obtain the second rail pressure signal.

[0085] The grade determination module 130 is used to extract the dynamic characteristics of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic characteristics and a preset network model.

[0086] The carbon deposit cleaning module 140 is used to perform corresponding carbon deposit cleaning actions based on the degree of carbon deposit.

[0087] Optionally, the preprocessing module 120 is specifically used for:

[0088] Remove high-frequency noise from the first rail pressure signal to obtain a first process signal; and perform normalization processing on the first process signal to obtain a second rail pressure signal.

[0089] Optionally, the level determination module 130 is specifically used for:

[0090] The phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are extracted from the second rail pressure signal; and the phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are input into a preset network model to determine the carbon deposition level.

[0091] Optionally, the carbon deposit cleaning module 140 is specifically used for:

[0092] When the carbon buildup level is light, the carbon cleaning action is not triggered; when the carbon buildup level is moderate and the engine is in a non-power demand condition, the rail pressure is increased, and the fuel injector is controlled to inject fuel at a preset frequency to complete the carbon cleaning action; and when the carbon buildup level is heavy, when the engine is in a non-power demand condition, the rail pressure is increased, fuel injector vibration is added, and the air-fuel ratio is adjusted to complete the carbon cleaning action.

[0093] The technical solution provided in this embodiment firstly acquires the first rail pressure signal of the engine through a signal acquisition module; secondly, it performs preprocessing operations on the first rail pressure signal through a preprocessing module to obtain a second rail pressure signal; then, it extracts the dynamic features of the second rail pressure signal through a level determination module to determine the carbon deposit level based on the dynamic features and a preset network model; finally, it performs the corresponding carbon deposit cleaning action based on the carbon deposit level through a carbon deposit cleaning module.

[0094] Therefore, this embodiment extracts dynamic features based on the first rail pressure signal. These dynamic features, combined with a preset network model, accurately determine the degree of carbon buildup. Based on this degree, differentiated carbon removal strategies (such as pulse high-pressure injection, injector vibration carbon removal, and oxygen-rich combustion) are triggered, forming a closed-loop control of "identification-decision-execution." This effectively compensates for the shortcomings of existing technologies in early warning, graded diagnosis, intelligent carbon removal, and engineering deployment. Compared to traditional methods, this method can provide early warning 1-2 maintenance cycles earlier, preventing combustion instability, power loss, and excessive emissions caused by carbon buildup deterioration, thereby significantly improving engine reliability and durability.

[0095] This embodiment provides an electronic device. Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. See also: Figure 6 The electronic device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above-described engine carbon deposit identification and cleaning methods are performed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other via a communication bus and / or other forms of connection mechanisms (not shown). The memory 1002 stores a processor-executable computer program. When the electronic device 1000 is running, the processor 1001 executes the computer program to perform the engine carbon deposit identification and cleaning method in any optional implementation of the above embodiments, to at least achieve the following functions: acquiring a first rail pressure signal of the engine; performing preprocessing operations on the first rail pressure signal to obtain a second rail pressure signal; extracting dynamic features of the second rail pressure signal to determine the carbon deposit level based at least on the dynamic features and a preset network model; and performing corresponding carbon deposit cleaning actions based on the carbon deposit level.

[0096] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the engine carbon deposit identification and cleaning method provided in all embodiments of this application: acquiring a first rail pressure signal of the engine; performing a preprocessing operation on the first rail pressure signal to obtain a second rail pressure signal; extracting dynamic features of the second rail pressure signal to determine the carbon deposit level based at least on the dynamic features and a preset network model; and performing corresponding carbon deposit cleaning actions based on the carbon deposit level.

[0097] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0098] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0099] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0100] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying and cleaning engine carbon deposits, characterized in that, At least including: Acquire the first rail pressure signal of the engine; Perform a preprocessing operation on the first rail pressure signal to obtain the second rail pressure signal; Extract the dynamic features of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic features and a preset network model; Perform the corresponding carbon buildup cleaning action based on the carbon buildup level.

2. The engine carbon deposit identification and cleaning method according to claim 1, characterized in that, The preprocessing operation on the first rail pressure signal to obtain the second rail pressure signal specifically includes: Remove high-frequency noise from the first rail pressure signal to obtain the first process signal; The first process signal is normalized to obtain the second rail pressure signal.

3. The engine carbon deposit identification and cleaning method according to claim 1, characterized in that, The step of extracting the dynamic features of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic features and a preset network model specifically includes: Extract the phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value from the second rail pressure signal; The phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are input into the preset network model to determine the carbon deposition level.

4. The engine carbon deposit identification and cleaning method according to claim 1, characterized in that, The specific steps of performing the corresponding carbon deposit cleaning action based on the carbon deposit level include: If the carbon buildup level is mild, the carbon buildup cleaning action will not be triggered. If the carbon buildup level is medium, then when the engine is not in a power demand condition, the rail pressure is increased, and the fuel injector is controlled to inject fuel at a preset frequency to complete the carbon buildup cleaning action. If the carbon buildup level is severe, then when the engine is not operating under power demand conditions, the rail pressure is increased, fuel injector vibration is added, and the air-fuel ratio is adjusted to complete the carbon buildup cleaning action.

5. An engine carbon deposit identification and cleaning device, characterized in that, At least including: The signal acquisition module is used to acquire the engine's first rail pressure signal; The preprocessing module is used to perform preprocessing operations on the first rail pressure signal to obtain the second rail pressure signal; The grade determination module is used to extract the dynamic features of the second rail pressure signal to determine the carbon deposition level based at least on the dynamic features and a preset network model; The carbon buildup cleaning module is used to perform corresponding carbon buildup cleaning actions based on the carbon buildup level.

6. The engine carbon deposit identification and cleaning device according to claim 5, characterized in that, The preprocessing module is specifically used for: Remove high-frequency noise from the first rail pressure signal to obtain a first process signal; and perform normalization processing on the first process signal to obtain a second rail pressure signal.

7. The engine carbon deposit identification and cleaning device according to claim 5, characterized in that, The level determination module is specifically used for: The phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are extracted from the second rail pressure signal; and the phase delay, waveform similarity, high-frequency energy ratio, and peak-to-peak value are input into the preset network model to determine the carbon deposition level.

8. The engine carbon deposit identification and cleaning device according to claim 5, characterized in that, The carbon deposit cleaning module is specifically used for: When the carbon buildup level is light, the carbon cleaning action is not triggered; and when the carbon buildup level is moderate, the rail pressure is increased when the engine is in a non-power demand condition, and the fuel injector is controlled to inject fuel at a preset frequency to complete the carbon cleaning action; and when the carbon buildup level is heavy, the rail pressure is increased when the engine is in a non-power demand condition, fuel injector vibration is added, and the air-fuel ratio is adjusted to complete the carbon cleaning action.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the engine carbon deposit identification and cleaning method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the engine carbon deposit identification and cleaning method according to any one of claims 1 to 4.

Images