A method, apparatus and medium for fuel injection correction based on engine injectors

Abstract

This specification discloses an injection correction method, device, and medium based on engine injectors, relating to the field of injector monitoring technology. The method includes: acquiring engine parameters and real-time operating data of the engine injector; determining a current injector aging prediction model that matches the engine parameters based on the engine parameters and a preset model correspondence table, the injector aging prediction model being used to predict the aging degree of the engine injector; determining current injector aging estimation parameters, which are injection delay durations, using the current injector aging prediction model and real-time operating data; generating an advance angle correction value based on the current injector aging estimation parameters, thereby correcting the real-time advance angle of the engine injector to generate a corrected advance angle, and then correcting the injection time of the engine injector based on the corrected advance angle.

Description

Technical Field

[0001] This specification relates to the field of fuel injector monitoring technology, and in particular to a fuel injection correction method, device and medium based on engine fuel injectors. Background Technology

[0002] During diesel engine operation, as the running time increases, the aging of various components is inevitable, including the engine injectors, a critical component of the fuel system. During use, the aging of the engine injectors causes changes in their opening timing. This opening delay deviation affects the accuracy of fuel injection control, leading to a deterioration in engine fuel consumption and emissions.

[0003] Typically, statistical methods are used to correct injection errors caused by injector aging. However, because the degree of injector aging is not quantified, and actual injector aging is closely related to injector specifications and actual usage, statistical samples cannot accurately represent the aging patterns of injectors, resulting in a lack of specificity in injection correction. Therefore, existing technologies do not quantify the impact of injector aging when correcting injectors, leading to insufficient accuracy in injection correction. Summary of the Invention

[0004] This specification provides one or more embodiments of an injection correction method, device, and medium based on engine injectors, to solve the following technical problem: the prior art does not quantify the impact of injector aging when correcting injectors, thus resulting in the accuracy of injection correction failing to meet requirements.

[0005] One or more embodiments of this specification employ the following technical solutions:

[0006] This specification provides one or more embodiments of a fuel injection correction method based on an engine injector. The method includes: acquiring engine parameters and real-time operating data of the engine injector, wherein the real-time operating data includes: engine speed, fuel injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; determining a current injector aging prediction model matching the engine parameters based on the engine parameters and a preset model correspondence table, wherein the injector aging prediction model is used to predict the aging degree of the engine injector; determining a current injector aging estimation parameter based on the current injector aging prediction model and the real-time operating data, wherein the current injector aging estimation parameter is the injection delay duration; generating an advance angle correction value based on the current injector aging estimation parameter, thereby correcting the real-time advance angle of the engine injector to generate a corrected advance angle, and correcting the injection time of the engine injector based on the corrected advance angle.

[0007] Further, based on the current injector aging estimation parameters, an advance angle correction value is generated, specifically including: determining the current aging state of the engine injector based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector, wherein the current aging state includes normal aging state, aging state to be corrected, and fault aging state; when the current aging state of the engine injector is the aging state to be corrected, an advance angle correction value is generated based on the current injector aging estimation parameters of the engine injector.

[0008] Furthermore, based on the current injector aging estimation parameters, an advance angle correction value is generated, specifically including: obtaining the current engine speed of the engine injector; and generating the advance angle correction value using the current injector aging estimation parameters and the current engine speed.

[0009] Furthermore, the real-time advance angle of the engine injector is corrected using the advance angle correction value to generate a corrected advance angle. Specifically, this includes: determining the current advance angle of the engine injector; and adding the advance angle correction value to the current advance angle to correct the real-time advance angle of the engine injector and generate a corrected advance angle.

[0010] Further, before determining the current injector aging prediction model matching the engine parameters based on the engine injector and a preset model correspondence table, the method further includes: acquiring historical injection operation characteristic data for different engine types, wherein the engine type is related to engine displacement; inputting the historical injection operation characteristic data under the same specified engine type into multiple training machine models in a pre-generated reference model library for model training, obtaining a model evaluation index for each training machine model, wherein the model evaluation index includes any one or more of goodness of fit, mean square error, and error distribution; sorting the multiple training machine models according to the model evaluation index of each training machine model, determining the specified training machine model at the top, wherein the performance of the specified training machine model is better than other training machine models except the specified training machine model; establishing a correspondence between the specified training machine model and the specified engine type to construct a correspondence table between engine type and machine training model.

[0011] Furthermore, before inputting historical fuel injection operation feature data under the same specified engine type into multiple training machine models in a pre-generated reference model library, the method further includes: constructing an initial model library, wherein the model library includes various machine models, including support vector machine models, gradient descent tree models, BP neural network models, and time-delay neural network models; acquiring historical operation feature data of engine injectors with arbitrary parameters, wherein the historical operation feature data includes: engine speed, fuel injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; performing data cleaning, noise reduction, and filtering on the historical operation feature data to generate a model dataset, which is then used to train each machine model in the model library to obtain a trained machine model; and updating the trained machine model in the initial model library to generate a reference model library.

[0012] Further, based on the engine parameters of the engine injector and a preset model correspondence table, a current injector aging prediction model matching the engine parameters is determined. Specifically, this includes: determining the current engine type of the engine injector based on its engine parameters; searching for a correspondence in the engine type-machine training model correspondence table based on the engine type to determine the current machine training model corresponding to the current engine type; acquiring historical injection operation feature data corresponding to the current engine type; and using the historical injection operation feature data to perform secondary training on the current machine training model to obtain a current injector aging prediction model matching the engine parameters.

[0013] Further, before determining the current aging state of the engine injector based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector, the method further includes: obtaining the maximum fuel supply and maximum injection pressure of the fuel system corresponding to the engine injector; determining the upper limit of the aging threshold corresponding to the engine injector using the maximum fuel supply and maximum injection pressure; obtaining multiple historical injection delay durations of a specified engine injector under normal operating conditions, wherein the specified engine injector has the same specifications as the engine injector; determining the maximum historical injection delay duration and the minimum historical injection delay duration among the multiple historical injection delay durations; generating a lower limit of the aging threshold based on the average of the maximum historical injection delay duration and the minimum historical injection delay duration; and generating the aging threshold corresponding to the engine injector using the upper limit of the aging threshold and the lower limit of the aging threshold.

[0014] This specification provides one or more embodiments of an injection correction device based on an engine injector, comprising:

[0015] At least one processor; and,

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions executable by the at least one processor. These instructions, when executed by the at least one processor, enable the at least one processor to: acquire engine parameters and real-time operating data of the engine injectors, wherein the real-time operating data includes: engine speed, fuel injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; determine a current injector aging prediction model matching the engine parameters based on the engine parameters and a preset model correspondence table, wherein the injector aging prediction model is used to predict the aging degree of the engine injectors; determine current injector aging estimation parameters for the engine injectors using the current injector aging prediction model and the real-time operating data, wherein the current injector aging estimation parameters are injection delay durations; generate an advance angle correction value based on the current injector aging estimation parameters, thereby correcting the real-time advance angle of the engine injectors using the advance angle correction value, generating a corrected advance angle, and correcting the injection time of the engine injectors based on the corrected advance angle.

[0018] This specification provides one or more embodiments of a non-volatile computer storage medium storing computer-executable instructions, which are configured to: acquire engine parameters and real-time operating data of an engine injector, wherein the real-time operating data includes: engine speed, injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; determine a current injector aging prediction model matching the engine parameters based on the engine parameters and a preset model correspondence table, wherein the injector aging prediction model is used to predict the aging degree of the engine injector; determine a current injector aging estimation parameter for the engine injector using the current injector aging prediction model and the real-time operating data, wherein the current injector aging estimation parameter is the injection delay duration; generate an advance angle correction value based on the current injector aging estimation parameter, thereby correcting the real-time advance angle of the engine injector using the advance angle correction value, generating a corrected advance angle, and correcting the injection time of the engine injector based on the corrected advance angle.

[0019] The above-mentioned at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: Through the above technical solutions, by matching the engine parameters of the engine injector with the corresponding machine model and selecting the matching current injector aging prediction model, the matching degree between the model and the injector is guaranteed, which can improve the pertinence and accuracy of aging degree estimation. Compared with traditional strategies, the accuracy and timeliness of estimation are improved; by quantifying the aging degree of the injector through the injection delay duration, the aging degree is displayed intuitively, and more accurate values ​​of aging degree are provided for injection correction; based on the current injector aging estimation parameters, an advance angle correction value is generated, and the advance angle is optimized through the advance angle correction value to achieve injection optimization. The influence of aging degree is considered, and the aging degree is quantified into a delay duration. The advance angle is optimized through the injection delay duration, ensuring the accuracy of injection correction. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0021] Figure 1 A schematic flowchart illustrating an injection correction method based on an engine injector, provided as an embodiment of this specification.

[0022] Figure 2 This is a flowchart illustrating a method for estimating the aging state of an engine injector provided in the embodiments of this specification.

[0023] Figure 3 This is a schematic diagram of a fuel injection correction device based on an engine injector, provided as an embodiment of this specification. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0025] During diesel engine operation, as the running time increases, the aging of various components is inevitable, including the engine injectors, a critical component of the fuel system. During use, the aging of the engine injectors causes changes in their opening timing. This opening delay deviation affects the accuracy of fuel injection control, leading to a deterioration in engine fuel consumption and emissions.

[0026] Typically, statistical methods are used to correct injection errors caused by injector aging. However, because the degree of injector aging is not quantified, and actual injector aging is closely related to injector specifications and actual usage, statistical samples cannot accurately represent the aging patterns of injectors, resulting in a lack of specificity in injection correction. Therefore, existing technologies do not quantify the impact of injector aging when correcting injectors, leading to insufficient accuracy in injection correction.

[0027] This specification provides an injection correction method based on engine injectors. It should be noted that the execution subject in this specification embodiment can be a server or any device with data processing capabilities. Figure 1 This is a flowchart illustrating an injection correction method based on an engine injector, as provided in the embodiments of this specification. Figure 1 As shown, the main steps include the following:

[0028] Step S101: Obtain engine parameters and real-time operating data of the engine injectors.

[0029] In one embodiment of this specification, engine parameters and real-time operating data of the engine injector are acquired. The real-time operating data includes: engine speed, fuel injection quantity, exhaust gas flow rate, cooled-down temperature, cooled-down pressure, coolant temperature, oil temperature, oil pressure, and nitrogen oxide content; the engine parameters of the engine injector include engine displacement and power.

[0030] Step S102: Based on the engine parameters of the engine injectors and the preset model correspondence table, determine the current injector aging prediction model that matches the engine parameters.

[0031] In one embodiment of this specification, the selection of the model type and the optimization of the model's hyperparameters also need to consider the engine displacement and power, as well as the maximum fuel supply, maximum injection pressure, and high-pressure fuel line length of the fuel system, because their impact on the model and hyperparameters cannot be ignored. Based on the engine parameters of the engine injectors and a preset model correspondence table, a current injector aging prediction model matching the engine parameters is determined, wherein the injector aging prediction model is used to predict the degree of aging of the engine injectors.

[0032] An initial model library is constructed, which includes various machine learning models, including support vector machines, gradient descent trees, backpropagation (BP) neural networks, and time-delay neural networks. Historical operating characteristic data of engine injectors with arbitrary parameters is obtained, including engine speed, injection quantity, exhaust gas flow rate, post-cooling temperature, post-cooling pressure, coolant temperature, oil temperature, oil pressure, and nitrogen oxide content. This historical operating characteristic data is then cleaned, denoised, and filtered to generate a model dataset. This dataset is used to train each machine learning model in the initial model library, resulting in a trained machine learning model. Finally, this trained machine learning model is updated within the initial model library to generate a reference model library.

[0033] In one embodiment of this specification, to improve the timeliness of wear estimation, multiple machine models are integrated by constructing a model library. First, an initial model library is constructed, including support vector machine (SVM) models, gradient descent tree (TDD) models, backpropagation (BP) neural network (BP) models, and time-delay neural network (TDN) models. These models are merely examples, and other machine models may also be included. For example, commonly used BP neural network models, time-series neural network (TDN) models, deep learning time-series neural network (LSTM) models, the simplified LSTM-based GRU model, the tree-based regression model GBDT and its upgraded version XGBoost, and the support vector machine-based SVM model can be selected.

[0034] Secondly, historical operating characteristic data corresponding to the injectors of engines with arbitrary parameters is obtained. Here, "arbitrary parameters" refers to the historical operating characteristic data of injectors corresponding to any engine type, and the historical operating characteristic data is generated over a large number of historical operating cycles. These historical operating cycles can be operating cycles during the experimental phase or operating cycles during actual historical operation. The operating characteristic data includes engine speed, injection quantity, exhaust gas flow rate, cooled-down temperature, cooled-down pressure, coolant temperature, oil temperature, oil pressure, and nitrogen oxide content. Next, to improve the model training effect, the collected historical operating characteristic data needs to be preprocessed, including data cleaning, noise reduction, and filtering. Feature transformation can also be performed to generate a model dataset. The data in the model dataset is used to train each machine model, resulting in a trained machine model. In the initial model library, the trained machine models replace the initial machine models, updating the trained machine models and generating a reference model library.

[0035] Before determining the current injector aging prediction model matching the engine parameters based on the engine injector and a pre-defined model correspondence table, the method further includes: acquiring historical injection operation characteristic data for different engine types, wherein the engine type is related to engine displacement; inputting the historical injection operation characteristic data under the same specified engine type into multiple training machine models in a pre-generated reference model library for model training, obtaining a model evaluation index for each training machine model, wherein the model evaluation index includes any one or more of good fit, mean square error, and error distribution; ranking the multiple training machine models according to the model evaluation index of each training machine model, determining the specified training machine model at the top, wherein the performance of the specified training machine model is better than other training machine models except the specified training machine model; establishing a correspondence between the specified training machine model and the specified engine type to construct a correspondence table between engine type and machine training model.

[0036] In one embodiment of this specification, historical fuel injection operation characteristic data for different engine types are acquired. Here, engine type is related to engine displacement; for example, engines with a displacement of 10L or more are considered large engines, engines with a displacement greater than 4L and less than 10L are considered medium engines, and engines with a displacement not greater than 4L are considered small engines. Multiple historical fuel injection operation characteristic data of the injectors for each engine type are input into multiple training machine models in a pre-generated reference model library for model training. Model evaluation metrics are obtained for each training machine model, including goodness of fit, mean squared error (MSE), and any one or more of the error distribution. A higher goodness of fit, a lower MSE, and a smaller variance (normal distribution variance) of the error distribution indicate a better model. Based on the model evaluation metrics of each training machine model, the multiple training machine models are ranked, and the optimal training machine model at the top is designated as the model corresponding to each engine type, establishing a correspondence between the designated training machine model and the designated engine type. The model corresponding to each engine type is determined in the above manner to construct a correspondence table between engine type and machine training model. For example, the TDN model corresponds to large engines with a displacement of 10L and above, while the LSTM model corresponds to small engines with a displacement of 4L and below.

[0037] Based on the engine parameters of the engine injector and a preset model correspondence table, a current injector aging prediction model matching the engine parameters is determined. Specifically, this includes: determining the current engine type of the engine injector based on its engine parameters; searching for a correspondence between the engine type and the machine training model in the engine type-machine training model correspondence table to determine the current machine training model corresponding to the current engine type; obtaining historical injection operation feature data corresponding to the current engine type; and using this historical injection operation feature data to perform secondary training on the current machine training model to obtain a current injector aging prediction model matching the engine parameters.

[0038] In one embodiment of this specification, the current engine type of the engine injector is determined based on its engine parameters. Then, a lookup is performed in the engine type-machine training model correspondence table to determine the current machine training model corresponding to the current engine type. By using the engine parameters of the engine injector, a matching current injector aging prediction model is determined. Selecting a matching current injector aging prediction model ensures a high degree of matching between the model and the injector, improving the specificity and accuracy of aging estimation. Compared with traditional strategies, this improves the accuracy and timeliness of estimation, better meeting the time requirements of state estimation. Determining the machine model matching the injector to be monitored through a correspondence lookup improves the model matching degree and can further enhance the model's prediction accuracy. Historical injection operation feature data corresponding to the current engine type is obtained, and the current machine training model is retrained using this historical injection operation feature data to obtain a current injector aging prediction model that matches the engine parameters. The data in the reference model library is trained using any type of historical data. To further ensure the accuracy of the model, a second training is performed using historical data corresponding to the engine type to ensure that the current model can accurately predict aging estimates under the current type.

[0039] Step S103: Determine the current injector aging estimation parameters of the engine injector using the current injector aging prediction model and real-time operating data.

[0040] In one embodiment of this specification, the real-time operating data of the engine injectors undergoes data preprocessing, including data cleaning, noise reduction, filtering, and feature transformation. This data is then input into the current injector aging prediction model to obtain the current injector aging estimation parameters. These parameters are the injection delay duration. By quantifying the injector aging degree using the injection delay duration, the degree of aging is visually displayed, providing a more accurate numerical value for injection correction.

[0041] Figure 2 This is a flowchart illustrating a method for estimating the aging condition of an engine injector provided in the embodiments of this specification. Figure 2 In this context, the engine type of the engine injector is a large engine, and its corresponding model is the trained TDN model. The TDN model is integrated into the ECU. After the data is collected, preprocessing operations such as data cleaning, data noise reduction, data filtering, and feature transformation are performed before inputting it into the TDN model. The model outputs the injection delay time.

[0042] Step S104: Based on the current injector aging estimation parameters, generate an advance angle correction value, so as to correct the real-time advance angle of the engine injector through the advance angle correction value, generate a corrected advance angle, and correct the injection time of the engine injector based on the corrected advance angle.

[0043] Based on the current injector aging estimation parameters, an advance angle correction value is generated. Specifically, this includes: determining the current aging state of the engine injector based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector. The current aging state includes normal aging state, aging state to be corrected, and fault aging state. When the current aging state of the engine injector is the aging state to be corrected, an advance angle correction value is generated based on the current injector aging estimation parameters of the engine injector.

[0044] In one embodiment of this specification, the current aging state of the engine injector is determined based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector. The current aging state includes normal aging state, aging state requiring correction, and faulty aging state. The aging threshold here includes an upper limit and a lower limit. When the current injector aging estimation parameters are less than the lower limit, it is determined to be a normal aging state, meaning the impact of aging is negligible. When the current injector aging estimation parameters are greater than the upper limit, it is determined to be excessive aging, i.e., a faulty aging state, and an error is reported to prompt component replacement. When the current injector aging estimation parameters are neither less than the lower limit nor greater than the upper limit, it is determined to be an aging state requiring correction, meaning the impact of aging needs to be corrected. Based on the current injector aging estimation parameters of the engine injector, an advance angle correction value is generated.

[0045] Before determining the current aging state of the engine injector based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector, the method further includes: obtaining the maximum fuel supply and maximum injection pressure of the fuel system corresponding to the engine injector; determining the upper limit of the aging threshold corresponding to the engine injector using the maximum fuel supply and maximum injection pressure; obtaining multiple historical injection delay durations of a specified engine injector under normal operating conditions, wherein the specified engine injector has the same specifications as the engine injector; determining the maximum and minimum historical injection delay durations among the multiple historical injection delay durations; generating a lower limit of the aging threshold based on the average of the maximum and minimum historical injection delay durations; and generating the aging threshold corresponding to the engine injector using the upper and lower limits of the aging threshold.

[0046] In one embodiment of this specification, the effects of aging on different injectors vary. To accurately correct the aging of injectors of different specifications, it is necessary to set a corresponding aging threshold for each injector. The maximum fuel supply and maximum injection pressure of the fuel system corresponding to the engine injector are obtained. Based on the maximum fuel supply and maximum injection pressure, the upper limit of the aging threshold corresponding to the engine injector is determined. Here, the upper limit of the aging threshold is the upper limit of the injection delay duration, and the calculation method can be determined according to existing methods. A designated engine injector with the same specifications as the current engine injector is determined, and multiple historical injection delay durations of the designated engine injector under normal operating conditions are obtained. At this time, the operating states corresponding to the multiple historical injection delay durations are all normal operation. Among the multiple historical injection delay durations, the maximum historical injection delay duration and the minimum historical injection delay duration are determined. The lower limit of the aging threshold is generated based on the average of the maximum and minimum historical injection delay durations. The aging threshold corresponding to the engine injector is generated using the upper limit of the aging threshold and the lower limit of the aging threshold.

[0047] Based on the current injector aging estimation parameters, an advance angle correction value is generated, specifically including: obtaining the current engine speed of the engine injector; and generating the advance angle correction value using the current injector aging estimation parameters and the current engine speed.

[0048] In one embodiment of this specification, the current engine speed of the engine injector is obtained; using the current injector aging estimation parameters and the current engine speed, an advance angle correction value is generated, and the calculation formula for the advance angle correction value c is as follows: Where t is the current injector aging estimation parameter obtained from the model estimation, i.e. the current time delay, and n is the current engine speed.

[0049] The real-time advance angle of the engine injector is corrected using this advance angle correction value to generate a corrected advance angle. Specifically, this involves: determining the current advance angle of the engine injector; and adding the advance angle correction value to the current advance angle to correct the real-time advance angle of the engine injector, thus generating the corrected advance angle. In other words, the corrected advance angle is obtained by summing the current advance angle and the advance angle correction value.

[0050] The above technical solution matches the engine parameters of the fuel injector with the corresponding machine model and selects the matching current fuel injector aging prediction model, ensuring the matching degree between the model and the fuel injector. This improves the pertinence and accuracy of aging degree estimation, enhancing the accuracy and timeliness of estimation compared to traditional strategies. The aging degree of the fuel injector is quantified by the injection delay duration, providing a direct visual representation of the aging degree and further offering precise numerical values ​​for injection correction. Based on the current fuel injector aging estimation parameters, an advance angle correction value is generated to optimize the advance angle, thus achieving injection optimization. This approach considers the impact of aging degree and quantifies it as a delay duration, optimizing the advance angle through the injection delay duration to ensure the accuracy of injection correction.

[0051] This specification also provides an injection correction device based on an engine injector, such as... Figure 3 As shown, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: acquire engine parameters and real-time operating data of the engine injector, wherein the real-time operating data includes: engine speed, fuel injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; and, based on the engine parameters of the engine injector and a preset model correspondence table, determine the engine parameters that match the engine parameters. The system includes a current injector aging prediction model, which is used to predict the aging degree of the engine injectors. Based on this model and real-time operating data, the system determines the current injector aging estimation parameters, where the current injector aging estimation parameters are the injection delay duration. According to these parameters, an advance angle correction value is generated to correct the real-time advance angle of the engine injectors, generating a corrected advance angle. This corrected advance angle is then used to correct the injection timing of the engine injectors.

[0052] This specification also provides a non-volatile computer storage medium storing computer-executable instructions. These instructions are configured to: acquire engine parameters and real-time operating data of an engine injector, wherein the real-time operating data includes: engine speed, fuel injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; determine a current injector aging prediction model matching the engine parameters based on the engine parameters and a preset model correspondence table, wherein the injector aging prediction model is used to predict the aging degree of the engine injector; determine current injector aging estimation parameters based on the current injector aging prediction model and the real-time operating data, wherein the current injector aging estimation parameters are injection delay durations; generate an advance angle correction value based on the current injector aging estimation parameters, thereby correcting the real-time advance angle of the engine injector to generate a corrected advance angle, and then correct the injection time of the engine injector based on the corrected advance angle.

[0053] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0054] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0055] The devices, media, and methods provided in the embodiments of this specification are one-to-one correspondences. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0056] Those skilled in the art will understand that embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0057] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0058] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0059] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0060] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0061] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0062] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0063] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0064] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for fuel injection correction based on engine injectors, characterized in that, The method includes: The engine parameters and real-time operating data of the engine injectors are acquired, wherein the real-time operating data includes: engine speed, injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content. Based on the engine parameters of the engine injector and a preset model correspondence table, a current injector aging prediction model that matches the engine parameters is determined, wherein the injector aging prediction model is used to predict the degree of aging of the engine injector. The current injector aging prediction model and the real-time operating data are used to determine the current injector aging estimation parameters of the engine injector, wherein the current injector aging estimation parameters are the injection delay duration. Based on the current injector aging estimation parameters, an advance angle correction value is generated to correct the real-time advance angle of the engine injector. A corrected advance angle is generated to correct the injection timing of the engine injector based on the corrected advance angle.

2. The method for fuel injection correction based on engine injectors according to claim 1, characterized in that, Based on the current injector aging estimation parameters, an advance angle correction value is generated, specifically including: Based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector, the current aging state of the engine injector is determined, wherein the current aging state includes normal aging state, aging state to be corrected and faulty aging state. When the current aging state of the engine injector is an aging state to be corrected, an advance angle correction value is generated based on the current injector aging estimation parameters of the engine injector.

3. The method for fuel injection correction based on engine injectors according to claim 2, characterized in that, Based on the current injector aging estimation parameters, an advance angle correction value is generated, specifically including: Obtain the current engine speed of the engine injector; An advance angle correction value is generated using the current injector aging estimation parameters and the current engine speed.

4. The method for fuel injection correction based on engine injectors according to claim 3, characterized in that, The real-time advance angle of the engine injector is corrected using the advance angle correction value to generate a corrected advance angle, specifically including: Determine the current advance angle of the engine injector; Based on the current advance angle, the advance angle correction value is added to correct the real-time advance angle of the engine injector, thereby generating a corrected advance angle.

5. The method for fuel injection correction based on engine injectors according to claim 1, characterized in that, Before determining the current injector aging prediction model that matches the engine parameters based on the engine injector and a preset model correspondence table, the method further includes: Acquire historical fuel injection operation characteristic data for different engine types, wherein the engine type is related to engine displacement; Historical fuel injection operation characteristic data under the same specified engine type are input into multiple training machine models in a pre-generated reference model library for model training, and model evaluation indexes are obtained for each training machine model. The model evaluation indexes include any one or more of the following: good fit, mean square error, and error distribution. Based on the model evaluation metrics of each training machine model, the multiple training machine models are ranked to determine the designated training machine model that ranks first, wherein the performance of the designated training machine model is better than that of other training machine models. Establish a correspondence between the specified training machine model and the specified engine type to construct a correspondence table between engine type and machine training model.

6. The method for fuel injection correction based on engine injectors according to claim 5, characterized in that, Before inputting historical fuel injection operation characteristic data for the same specified engine type into multiple training machine models in a pre-generated reference model library, the method further includes: Construct an initial model library, which includes various machine models, including support vector machine models, gradient descent tree models, backpropagation neural network models, and time-delay neural network models. Acquire historical operating characteristic data of engine injectors with arbitrary parameters, wherein the historical operating characteristic data includes: engine speed, injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content; The historical operational feature data is cleaned, denoised, and filtered to generate a model dataset, which is then used to train each machine model in the model library to obtain a trained machine model. In the initial model library, the trained machine model is updated to generate a reference model library.

7. The method for fuel injection correction based on engine injectors according to claim 6, characterized in that, Based on the engine parameters of the engine injectors and a preset model correspondence table, a current injector aging prediction model matching the engine parameters is determined, specifically including: Based on the engine parameters of the engine injector, the current engine type of the engine injector is determined. Based on the engine type, a correspondence is searched in the correspondence table between engine type and machine training model to determine the current machine training model corresponding to the current engine type. Obtain historical fuel injection operation feature data corresponding to the current engine type, and use the historical fuel injection operation feature data to perform secondary training on the current machine training model to obtain a current injector aging prediction model that matches the engine parameters.

8. The method for fuel injection correction based on engine injectors according to claim 2, characterized in that, Before determining the current aging state of the engine injector based on the current injector aging estimation parameters and the pre-acquired aging threshold corresponding to the engine injector, the method further includes: Obtain the maximum fuel supply and maximum injection pressure of the fuel system corresponding to the engine injector; The upper limit of the aging threshold corresponding to the engine injector is determined by the maximum fuel supply and the maximum fuel injection pressure. Obtain multiple historical injection delay durations of a specified engine injector under normal operating conditions, wherein the specified engine injector has the same specifications as the engine injector. Among the multiple historical fuel injection delay durations, the maximum historical fuel injection delay duration and the minimum historical fuel injection delay duration are determined; The lower limit of the aging threshold is generated based on the average of the maximum historical injection delay duration and the minimum historical injection delay duration. The aging threshold corresponding to the engine injector is generated by using the upper limit of the aging threshold and the lower limit of the aging threshold.

9. A fuel injection correction device based on an engine injector, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: The engine parameters and real-time operating data of the engine injectors are acquired, wherein the real-time operating data includes: engine speed, injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content. Based on the engine parameters of the engine injector and a preset model correspondence table, a current injector aging prediction model that matches the engine parameters is determined, wherein the injector aging prediction model is used to predict the degree of aging of the engine injector. The current injector aging prediction model and the real-time operating data are used to determine the current injector aging estimation parameters of the engine injector, wherein the current injector aging estimation parameters are the injection delay duration. Based on the current injector aging estimation parameters, an advance angle correction value is generated to correct the real-time advance angle of the engine injector. A corrected advance angle is generated to correct the injection timing of the engine injector based on the corrected advance angle.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: The engine parameters and real-time operating data of the engine injectors are acquired, wherein the real-time operating data includes: engine speed, injection quantity, exhaust gas flow rate, after-cooling temperature, after-cooling pressure, water temperature, oil temperature, oil pressure, and nitrogen oxide content. Based on the engine parameters of the engine injector and a preset model correspondence table, a current injector aging prediction model that matches the engine parameters is determined, wherein the injector aging prediction model is used to predict the degree of aging of the engine injector. The current injector aging prediction model and the real-time operating data are used to determine the current injector aging estimation parameters of the engine injector, wherein the current injector aging estimation parameters are the injection delay duration. Based on the current injector aging estimation parameters, an advance angle correction value is generated to correct the real-time advance angle of the engine injector. A corrected advance angle is generated to correct the injection timing of the engine injector based on the corrected advance angle.

Images