Fuel injector fault early warning method, device and equipment and storage medium

Abstract

The invention discloses an oil injector fault early warning method, device and equipment and a storage medium, and relates to the technical field of ship fault diagnosis. The fuel injector fault early warning method comprises the steps that current operation state data and historical operation state data of a fuel injector are obtained, and a fuel injector state estimation model based on the multivariate state estimation technology is constructed according to the historical operation state data; according to the current operation state data, whether the current operation condition of the oil injector is a steady state condition is judged, and if yes, the similarity of the current operation state data of the oil injector is determined according to the current operation state data and an oil injector state estimation model based on the multivariate state estimation technology; and the current dynamic threshold value is obtained, whether the running state of the oil injector breaks down or not is judged according to the similarity between the current dynamic threshold value and the current running state data of the oil injector, and whether the current dynamic threshold value is updated or not is judged. Early warning is carried out before the running state of the oil sprayer breaks down, and the equipment maintenance efficiency and reliability are improved.

Description

Technical Field

[0001] The present application relates to the technical field of ship fault diagnosis, and in particular to an injector fault early warning method, device, equipment and storage medium. Background Art

[0002] The high-pressure common rail technology for marine diesel engines is the third technological leap in the development of diesel engines. Compared with the traditional mechanical fuel system, the high-pressure common rail system has the characteristics of high injection pressure and good environmental protection. It also has the advantages of flexible adjustment of key indicators such as injection timing, circulating oil volume, and injection duration. Among them, the electronically controlled injector, as the core component of the high-pressure common rail system, plays a major role in controlling the injection timing and adjusting the injection duration. The performance of the electronically controlled injector will directly affect the combustion process in the diesel engine cylinder. If the electronically controlled injector fails, it will affect the circulating oil volume and atomization performance, making the combustion in the cylinder unable to meet the normal working requirements of the diesel engine. In severe cases, it will affect the operation of the diesel engine and cause it to shut down.

[0003] However, the existing diesel engine design does not yet have the online early warning function of the electronic fuel injector, so there is no early warning before the electronic fuel injector fails, resulting in low equipment maintenance efficiency, high maintenance costs, poor equipment reliability and other problems. Summary of the invention

[0004] Purpose of the invention: An embodiment of the present application provides an injector fault warning method, aiming to overcome the technical problem in the prior art that no early warning can be given before a current injector fault occurs, resulting in low equipment maintenance efficiency, high maintenance costs, and poor equipment reliability; another purpose of an embodiment of the present application is to provide an injector fault warning device; the third purpose of the present application is to provide an electronic device; the fourth purpose of the present application is to provide a computer-readable storage medium.

[0005] Technical solution: A fuel injector fault warning method according to an embodiment of the present application comprises:

[0006] Acquire current operating state data and historical operating state data of the injector, and construct an injector state estimation model based on multivariate state estimation technology according to the historical operating state data;

[0007] Determine whether the current operating condition of the injector is a steady-state condition according to the current operating state data, and if so, determine the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology;

[0008] A current dynamic threshold is obtained, and it is determined whether a fault occurs in the operating state of the injector according to the similarity between the current dynamic threshold and the current operating state data of the injector, and it is determined whether to update the current dynamic threshold.

[0009] In some embodiments, the step of constructing a fuel injector state estimation model based on a multivariate state estimation technique according to the historical operating state data includes:

[0010] Filter out historical steady-state operating condition data according to the historical operating status data;

[0011] A fuel injector state estimation model based on multivariate state estimation technology is established according to the historical steady-state operating condition data.

[0012] In some embodiments, the step of establishing a fuel injector state estimation model based on a multivariate state estimation technique according to the historical steady-state operating condition data includes:

[0013] Preprocessing the historical steady-state operating condition data to obtain a test matrix and a training matrix;

[0014] Generate a model observation matrix based on the training matrix;

[0015] The injector state estimation model based on the multivariate state estimation technology is established according to the test matrix and the model observation matrix.

[0016] In some embodiments, generating a model observation matrix based on the training matrix includes:

[0017] determining a health matrix based on the training matrix;

[0018] Nonlinear operator based on Euclidean distance calculation model;

[0019] Determining a model weight coefficient according to the nonlinear operator and the health matrix;

[0020] The model observation matrix is ​​generated according to the model weight coefficients.

[0021] In some embodiments, filtering out historical steady-state operating data according to the historical operating status data includes:

[0022] It is determined whether the historical operating status data is a steady-state operating condition according to the historical operating status data, non-steady-state operating condition data in the historical operating status data is eliminated, and steady-state operating condition data is retained.

[0023] In some embodiments, the determination of the steady-state operating condition includes:

[0024] Acquiring operating status data of the fuel injector; wherein the operating status data includes oil temperature data of the fuel injector and rail pressure data of the fuel injector;

[0025] It is determined whether the rail pressure of the injector changes according to the rail pressure data of the injector. If yes, it is further determined whether the oil temperature monotonicity of the injector changes. If yes, it is determined that the current working condition is a steady-state working condition.

[0026] In some embodiments, judging whether a fault occurs in the operating state of the fuel injector according to the similarity between the current dynamic threshold and the current operating state data of the fuel injector, and judging whether to update the current dynamic threshold, comprises:

[0027] comparing the similarity of the current operating state data of the injector with the current dynamic threshold;

[0028] If the similarity of the current operating state data of the injector is greater than the current dynamic threshold, it is determined that the current operating state data of the injector is normal, and it is determined whether to update the current dynamic threshold;

[0029] If the similarity of the current operating status data of the injector is less than or equal to the current dynamic threshold, it is determined that the current operating status data of the injector is abnormal, and a time series of the results of the judgment of whether the current operating status data of the injector is abnormal is obtained; and whether the operating status of the injector is faulty is determined based on the time series of the results of the judgment of whether the current operating status data of the injector is abnormal.

[0030] In some embodiments, the determining whether to update the current dynamic threshold comprises:

[0031] comparing the similarity of the current operating state data of the injector with a static threshold;

[0032] If the similarity of the current operating state data of the injector is greater than the static threshold, maintaining the current dynamic threshold;

[0033] If the similarity of the current operating state data of the injector is less than or equal to the static threshold, the current dynamic threshold is updated according to the similarity of the current operating state data of the injector.

[0034] In some embodiments, judging whether the operating state of the fuel injector is faulty according to the time series of the result of judging whether the current operating state data of the fuel injector is abnormal includes:

[0035] Determining the number of times the current operating state data of the injector is abnormal continuously according to the time series of the result of judging whether the current operating state data of the injector is abnormal;

[0036] It is also determined whether the number of times that the current operating state data of the injector is continuously abnormal exceeds a preset number. If it exceeds, it is determined that the operating state of the injector is faulty and an alarm message is sent.

[0037] In some embodiments, the determining the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology includes:

[0038] Inputting the current operating state data into the injector state estimation model based on the multivariate state estimation technology to obtain an estimated value of the current operating state data of the injector;

[0039] The similarity of the current operating state data of the fuel injector is calculated based on the estimated value of the current operating state data of the fuel injector and the current operating state data.

[0040] In some embodiments, the current operating state data includes at least one of: current rail pressure data of the fuel injector, current oil temperature data of the fuel injector, and current oil quantity data of the fuel injector;

[0041] The historical operating status data includes at least one of historical rail pressure data of the fuel injector, historical oil temperature data of the fuel injector, and historical oil quantity data of the fuel injector.

[0042] Accordingly, an injector fault warning device according to an embodiment of the present application comprises:

[0043] A first acquisition module, used for acquiring current operating state data and historical operating state data of the injector;

[0044] A model building module, used for building a fuel injector state estimation model based on a multivariate state estimation technology according to the historical operating state data;

[0045] A steady-state operating condition judgment module, used for judging whether the current operating condition of the injector is a steady-state operating condition according to the current operating state data;

[0046] A similarity determination module, used for determining the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology;

[0047] The second acquisition module is used to obtain the current dynamic threshold;

[0048] a fault judgment module, used for judging whether a fault occurs in the operating state of the fuel injector according to the similarity between the current dynamic threshold and the current operating state data of the fuel injector;

[0049] The threshold update judgment module is used to judge whether to update the current dynamic threshold.

[0050] Accordingly, an electronic device described in an embodiment of the present application includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the above-mentioned injector fault warning method when executing the computer program.

[0051] Accordingly, a computer-readable storage medium described in an embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, the above-mentioned injector fault warning method is implemented.

[0052] Beneficial effect: Compared with the prior art, the fuel injector fault warning method, device, equipment and storage medium of the embodiment of the present application include: obtaining the current operating state data and historical operating state data of the fuel injector, and constructing a fuel injector state estimation model based on the multivariate state estimation technology according to the historical operating state data; judging whether the current operating condition of the fuel injector is a steady-state condition according to the current operating state data, if so, determining the similarity of the current operating state data of the fuel injector according to the current operating state data and the fuel injector state estimation model based on the multivariate state estimation technology; obtaining the current dynamic threshold, judging whether the operating state of the fuel injector fails according to the similarity between the current dynamic threshold and the current operating state data of the fuel injector, and judging whether to update the current dynamic threshold. Therefore, the method can achieve: early warning before the operating state of the fuel injector fails, thereby improving equipment maintenance efficiency, improving equipment reliability, and reducing equipment maintenance costs. In addition, a state estimation model is constructed through the historical operating status data of the injector, and the similarity of the current operating status data is calculated based on the state estimation model. The dynamic threshold is combined to determine in real time whether the operating status of the injector has a fault. The combination of the state estimation model and the dynamic threshold can improve the accuracy, effectiveness and reliability of fault warning judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 is a structural schematic diagram of a direct current transmission system according to an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the overall process of the AC fault ride-through method at the receiving end of the power transmission system according to an embodiment of the present application;

[0056] Figure 3 It is a schematic diagram of a construction process of an injector state estimation model provided in an embodiment of the present application;

[0057] Figure 4 It is a flow chart of a method for early warning of a fuel injector failure provided in an embodiment of the present application;

[0058] Figure 5 It is a principle structure diagram of a fuel injector fault warning device provided in an embodiment of the present application;

[0059] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application.

[0060] Reference numerals:

[0061] 101 - first acquisition module; 102 - model building module; 103 - steady-state operating condition judgment module; 104 - similarity determination module; 105 - second acquisition module; 106 - fault judgment module; 107 - threshold value update judgment module; 100 - injector fault warning device. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0063] It should be understood that although the terms first, second, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the concepts of the present application. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0064] Those skilled in the art will appreciate that the drawings are only schematic diagrams of example embodiments and may not be to scale. The modules or processes in the drawings are not necessarily required to implement the present application and therefore cannot be used to limit the scope of protection of the present application.

[0065] Figure 1This is a flow chart of a method for early warning of a fuel injector fault provided in an embodiment of the present application. This method is applicable to a process of implementing an online early warning of a fuel injector fault in a marine diesel engine fault diagnosis platform. This method can be executed by a fuel injector fault early warning device, which can be implemented by software and / or hardware, and can be configured in a processor of a marine diesel engine fault diagnosis platform. Figure 1 , the injector fault warning method comprises the following steps:

[0066] Step 110: Acquire current operating state data and historical operating state data of the injector, and construct an injector state estimation model based on Multivariate State Estimation Technique (MSET) according to the historical operating state data.

[0067] The fuel injector may be an electronically controlled fuel injector, etc., and may be specifically configured according to actual conditions, and no specific limitation is made here.

[0068] Among them, the current operation status data can be obtained in real time through the operation status monitoring device of the injector, such as a sensor, etc. The historical operation status data can be directly obtained from the database, storage, etc., and there is no need to classify the historical operation status data (such as marking, labeling, etc.), and it can be used directly, so the data availability is high.

[0069] The operating status data of the injector may be rail pressure data, oil temperature data, oil quantity data, etc., which may be set according to actual conditions and are not specifically limited here.

[0070] Among them, by establishing an injector state estimation model based on MSET, it is helpful to accurately predict the similarity of the injector's current operating state data, which in turn helps to improve the accuracy and reliability of subsequent fault prediction.

[0071] As an implementation mode, optionally, the current operating status data includes at least one of: current rail pressure data of the injector, current oil temperature data of the injector, and current oil quantity data of the injector; the historical operating status data includes at least one of: historical rail pressure data of the injector, historical oil temperature data of the injector, and historical oil quantity data of the injector.

[0072] It should be noted that the specific data included in the operating status data of the injector can be set according to actual conditions and is not specifically limited here.

[0073] Step 120: determine whether the current operating condition of the injector is a steady-state condition based on the current operating state data; if so, determine the similarity of the current operating state data of the injector based on the current operating state data and an injector state estimation model based on a multivariate state estimation technique.

[0074] Among them, the similarity of the current operating state data of the fuel injector is related to the specific operating state data. For example, assuming that the current operating state data is the current oil quantity data of the fuel injector, the similarity of the current oil quantity data of the fuel injector can be determined based on the current oil quantity data of the fuel injector and the fuel injector state estimation model based on MSET. Assuming that the current operating state data is the current oil temperature data of the fuel injector, the similarity of the current oil temperature data of the fuel injector can be determined based on the current oil temperature data of the fuel injector and the fuel injector state estimation model based on MSET.

[0075] Specifically, after obtaining the current operating state data of the fuel injector, it is determined whether the current operating condition of the fuel injector is a steady state condition according to the current operating state data. If it is a steady state condition, the similarity of the current operating state data of the fuel injector is further calculated to perform subsequent fault judgment.

[0076] Step 130: Obtain the current dynamic threshold, determine whether the operating state of the injector is faulty based on the similarity between the current dynamic threshold and the current operating state data of the injector, and determine whether to update the current dynamic threshold.

[0077] In the technical solution of this embodiment, the working principle of the injector fault warning method is as follows: Figure 1First, the current operating state data and historical operating state data of the injector are obtained, and the injector state estimation model based on the multivariate state estimation technology is constructed according to the historical operating state data. Then, whether the current operating condition of the injector is a steady-state condition is determined according to the current operating state data. If so, the similarity of the current operating state data of the injector is determined according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology. Finally, the current dynamic threshold is obtained, and whether the operating state of the injector fails is determined according to the similarity between the current dynamic threshold and the current operating state data of the injector, and whether to update the current dynamic threshold. It can be seen that the injector state estimation model based on MSET is constructed through the historical operating state data of the injector, and the similarity of the current operating state data of the injector is determined according to the injector state estimation model based on MSET, and the operating state of the injector can be real-time online fault warning according to the similarity and the current dynamic threshold, so as to predict in advance whether the injector fails and improve the equipment maintenance efficiency and reliability. And by combining the injector state estimation model with the current dynamic threshold obtained in real time, real-time online warning of injector faults can be achieved, and by updating the current dynamic threshold in real time, the accuracy, effectiveness and reliability of the warning can be improved. In addition, by establishing the injector state estimation model based on the historical operating state data of the injector, on the one hand, the similarity of the injector's current operating state data can be accurately predicted by the injector state estimation model and the injector's current operating state data, thereby improving the accuracy of subsequent fault prediction. On the other hand, there is no need to classify the historical data, and it can be directly used for the construction of the injector state estimation model, with high data availability, which solves the problem of low data availability caused by complex working conditions and no labels of long-term monitoring data.

[0078] The technical solution of this embodiment provides a method for early warning of fuel injector failure, which includes: obtaining the current operating state data and historical operating state data of the fuel injector, and constructing a fuel injector state estimation model based on the multivariate state estimation technology according to the historical operating state data; judging whether the current operating condition of the fuel injector is a steady-state condition according to the current operating state data, and if so, determining the similarity of the current operating state data of the fuel injector according to the current operating state data and the fuel injector state estimation model based on the multivariate state estimation technology; obtaining the current dynamic threshold, judging whether the operating state of the fuel injector fails according to the similarity between the current dynamic threshold and the current operating state data of the fuel injector, and judging whether to update the current dynamic threshold. Therefore, this method can achieve: early warning before the operating state of the fuel injector fails, thereby improving equipment maintenance efficiency, improving equipment reliability, and reducing equipment maintenance costs. In addition, a state estimation model is constructed through the historical operating status data of the injector, and the similarity of the current operating status data is calculated based on the state estimation model. The dynamic threshold is combined to determine in real time whether the operating status of the injector has a fault. The combination of the state estimation model and the dynamic threshold can improve the accuracy, effectiveness and reliability of fault warning judgment.

[0079] Figure 2 is a flow chart of another injector fault warning method provided in an embodiment of the present application. Based on the above embodiment, optionally, refer to Figure 2 , the method comprises the following steps:

[0080] Step 210: Acquire current operating state data and historical operating state data of the injector, and filter out historical steady-state operating condition data according to the historical operating state data.

[0081] As an implementation mode, optionally, historical steady-state operating data is screened out based on historical operating status data, including: judging whether the historical operating status data is a steady-state operating condition based on the historical operating status data, eliminating non-steady-state operating condition data in the historical operating status data, and retaining the steady-state operating condition data.

[0082] The non-steady-state operating condition data is the variable operating condition stage data. The specific variable operating condition type can be set according to the actual situation and is not specifically limited here.

[0083] Step 220: Establish a fuel injector state estimation model based on multivariate state estimation technology according to historical steady-state operating condition data.

[0084] As an implementation mode, optionally, an injector state estimation model based on multivariate state estimation technology is established according to historical steady-state operating data, including: preprocessing the historical steady-state operating data to obtain a test matrix and a training matrix; generating a model observation matrix based on the training matrix; and establishing an injector state estimation model based on the multivariate state estimation technology according to the test matrix and the model observation matrix.

[0085] Among them, the preprocessing of the historical steady-state operating condition data includes: first, removing the missing data points and outliers in the historical steady-state operating condition data (for example, judging whether there are parameters that exceed the range and parameters that far exceed the alarm value in the data, and if so, removing them as outlier samples), and then performing standardization. The standardized data is used as sample data. A certain proportion of the sample data is randomly selected as training data, and the rest is used as test data. A training matrix is ​​obtained based on the training data, and a test matrix is ​​obtained based on the test data.

[0086] As an implementation mode, optionally, generating a model observation matrix based on a training matrix includes: determining a health matrix based on the training matrix; calculating a model nonlinear operator based on Euclidean distance; determining a model weight coefficient based on the nonlinear operator and the health matrix; and generating a model observation matrix based on the model weight coefficient.

[0087] The specific implementation method of determining the model weight coefficient according to the nonlinear operator and the health matrix can be: by introducing the system relative error calculation formula, the model weight coefficient can be obtained by combining the nonlinear operator and the health matrix.

[0088] Step 230: determine whether the current operating condition of the injector is a steady-state condition based on the current operating state data; if so, input the current operating state data into an injector state estimation model based on a multivariate state estimation technique to obtain an estimated value of the current operating state data of the injector.

[0089] Among them, by judging that the current operating condition is a steady-state condition according to the current operating status data and then making subsequent fault judgments according to the steady-state condition judgment method, it is beneficial to improve the accuracy of subsequent judgments, thereby improving the accuracy, effectiveness and reliability of fault warnings.

[0090] Step 240: Calculate the similarity of the current operating state data of the fuel injector based on the estimated value of the current operating state data of the fuel injector and the current operating state data.

[0091] For example, assuming that the current operating state data of the injector is the oil temperature of the injector, the oil temperature of the injector is input into the injector state estimation model based on MSET to obtain the estimated value (or model predicted value) of the injector oil temperature, and then the estimated value of the injector oil temperature and the injector oil temperature (i.e., the actual value) are input into the similarity calculation formula to obtain the similarity of the injector oil temperature. Similarly, assuming that the current operating state data of the injector is the oil quantity of the injector, the oil quantity of the injector is input into the injector state estimation model based on MSET to obtain the estimated value (or model predicted value) of the injector oil quantity, and then the estimated value of the injector oil quantity and the injector oil quantity are input into the similarity calculation formula to obtain the similarity of the injector oil quantity.

[0092] Among them, the calculation formula for the similarity of the current operating status data of the injector is:

[0093]

[0094] Among them, x i is the actual value of the i-th data point of the current operating status data of the injector, y i is the model predicted value (i.e., estimated value) of the i-th data point of the current operating status data of the injector, and n is a natural number.

[0095] Step 250 , determine whether the similarity of the current operating state data of the injector is greater than the current dynamic threshold. If so, execute step 260 ; otherwise, execute step 270 .

[0096] Different operating state data correspond to different dynamic thresholds. For example, when the current operating state data is the oil temperature of the injector, the current dynamic threshold corresponding to the current operating state data is different from the current dynamic threshold corresponding to the oil volume of the injector.

[0097] Specifically, by comparing the similarity of the current operating state data of the fuel injector with the current dynamic threshold, it can be determined whether the current operating state data is abnormal, and then whether the current operating state of the fuel injector is faulty. For example, when the current operating state data of the fuel injector is the oil temperature of the fuel injector, a sliding window length value is set (the specific value can be set according to the actual situation, and is not specifically limited here) to collect a section of the oil temperature data of the fuel injector, and then the oil temperature of the fuel injector is input into the fuel injector state estimation model based on MSET, and the estimated value of the oil temperature of the fuel injector can be calculated, and then the similarity of the oil temperature of the fuel injector can be calculated based on the estimated value of the oil temperature of the fuel injector and the oil temperature of the fuel injector, and then the similarity of the oil temperature of the fuel injector is compared with the current dynamic threshold corresponding to it to determine whether the oil temperature of the fuel injector is faulty, so as to predict whether the oil temperature is faulty in advance and issue an alarm, thereby improving equipment maintenance efficiency, improving equipment reliability, and reducing equipment maintenance costs. By combining the injector state estimation model with the current dynamic threshold of the injector oil temperature obtained in real time, real-time online warning of injector oil temperature failure can be achieved, and by updating the current dynamic threshold corresponding to the injector oil temperature in real time, the accuracy, effectiveness and reliability of the warning can be improved.

[0098] Similarly, when the current operating state data of the injector is the oil volume of the injector, the above method can be used to determine whether the oil volume of the injector is faulty, so as to predict whether the oil volume is faulty in advance and issue an alarm, thereby improving equipment maintenance efficiency, improving equipment reliability, and reducing equipment maintenance costs. By combining the injector state estimation model with the current dynamic threshold of the injector oil volume obtained in real time, real-time online warning of injector oil volume failure can be achieved, and by updating the current dynamic threshold corresponding to the injector oil volume in real time, the accuracy, effectiveness and reliability of the warning can be improved.

[0099] Step 260: Determine whether the current operating state data of the injector is abnormal, and determine whether to update the current dynamic threshold.

[0100] Specifically, the similarity of the current operating status data of the injector is compared with the current dynamic threshold. If the similarity of the current operating status data of the injector is greater than the current dynamic threshold, it can be judged that there is no abnormality in the current operating status data of the injector. Further, it is judged whether the current dynamic threshold needs to be updated to improve the accuracy, effectiveness and reliability of fault warning.

[0101] As an implementation mode, optionally, determining whether to update the current dynamic threshold includes: comparing the similarity of the current operating status data of the injector with the static threshold; if the similarity of the current operating status data of the injector is greater than the static threshold, maintaining the current dynamic threshold; if the similarity of the current operating status data of the injector is less than or equal to the static threshold, updating the current dynamic threshold according to the similarity of the current operating status data of the injector.

[0102] Among them, the initial dynamic threshold of the current dynamic threshold can be set as the initial similarity of each interval. For example, after judging that the current operating condition of the injector is a steady-state condition, the current operating state data of the injector collected in real time is input into the injector state estimation model based on MSET, and the similarity of the current operating state data is calculated, the sliding window length value is set, and the initial similarity calculated by the injector state estimation model based on MSET is obtained as the initial dynamic threshold of the current dynamic threshold.

[0103] The static threshold is greater than the initial dynamic threshold of the current dynamic threshold.

[0104] The current dynamic threshold may be set by adjusting the dynamic threshold at the previous sampling moment based on the mean and variance of the similarity at the current sampling moment and the mean and variance of the similarity at the previous sampling moment.

[0105] Specifically, when the similarity of the current operating state data of the fuel injector is greater than the current dynamic threshold, it means that the current operating state data is normal and the fuel injector is also normal, then the similarity of the current operating state data of the fuel injector (i.e., the operating state data collected at the current sampling moment) is compared with the static threshold to determine whether to update the current dynamic threshold. If the similarity of the current operating state data of the fuel injector is greater than the static threshold, the current dynamic threshold is kept unchanged. If the similarity of the current operating state data of the fuel injector is less than or equal to the static threshold, the similarity of the current operating state data of the fuel injector is used as the current dynamic threshold, and the current dynamic threshold is updated. Thus, after judging whether the current operating state of the fuel injector is abnormal at each sampling moment, if the current operating state is normal, the current dynamic threshold will be updated. By updating the current dynamic threshold in real time, the accuracy of fault prediction can be improved.

[0106] Step 270, determine whether the current operating state data of the injector is abnormal, and obtain a time series of the results of determining whether the current operating state data of the injector is abnormal; and determine whether the operating state of the injector is faulty based on the time series of the results of determining whether the current operating state data of the injector is abnormal.

[0107] The time series of the result of judging whether the current operating state data of the fuel injector is abnormal refers to the judgment result obtained by judging whether the current operating state data of the fuel injector is abnormal within a period of time (or a certain sampling time).

[0108] As an implementation mode, optionally, judging whether a fault occurs in the operating state of the injector based on a time series of a judgment result of whether the current operating state data of the injector is abnormal includes: determining the number of times the current operating state data of the injector is abnormal continuously appears according to the time series of a judgment result of whether the current operating state data of the injector is abnormal; and judging whether the number of times the current operating state data of the injector is abnormal continuously appears exceeds a preset number, and if so, judging that a fault occurs in the operating state of the injector, and sending an alarm message.

[0109] The specific value of the preset number of times can be set according to actual conditions and is not specifically limited here.

[0110] Specifically, the similarity of the current operating state data of the fuel injector is compared with the current dynamic threshold value. If the similarity of the current operating state data of the fuel injector is less than or equal to the current dynamic threshold value, it can be judged that the current operating state data of the fuel injector may be abnormal. In order to improve the accuracy of the judgment, further, the time series of the judgment result of whether the current operating state data of the fuel injector is abnormal is obtained, and the number of times the current operating state data is abnormal can be determined according to the time series of the judgment result. Then, the number of times the current operating state data is abnormal is compared with the preset number of times. If it is greater than the preset number of times, it can be judged that the operating state of the fuel injector may fail, and an alarm message is sent. In this way, real-time online early warning of the operating state of the fuel injector can be achieved, so that the fault can be predicted in advance before the fuel injector fails, thereby reducing the equipment maintenance cost and improving the equipment maintenance efficiency and reliability.

[0111] In the technical solution of this embodiment, the working principle of the injector fault warning method is as follows: Figure 2First, the current operating state data and historical operating state data of the injector are obtained, and the historical steady-state operating condition data are screened out according to the historical operating state data. Then, the injector state estimation model based on the multivariate state estimation technology is established according to the historical steady-state operating condition data. Secondly, whether the current operating condition of the injector is a steady-state condition is determined according to the current operating state data. If so, the current operating state data is input into the injector state estimation model based on the multivariate state estimation technology to obtain the estimated value of the current operating state data of the injector. The similarity of the current operating state data of the injector is calculated according to the estimated value of the current operating state data of the injector and the current operating state data. It is determined whether the similarity of the current operating state data of the injector is greater than the current dynamic threshold. If the similarity of the current operating state data of the injector is greater than the current dynamic threshold, it is determined that there is no abnormality in the current operating state data of the injector, and further it is determined whether to update the current dynamic threshold. If the similarity of the current operating state data of the injector is less than or equal to the current dynamic threshold, the current operating state data of the injector is judged to be abnormal, and the time series of the judgment result of whether the current operating state data of the injector is abnormal is obtained; and whether the operating state of the injector fails is judged according to the time series of the judgment result of whether the current operating state data of the injector is abnormal. It can be seen that the injector state estimation model based on MSET is constructed through the historical operating state data of the injector, and the similarity of the current operating state data of the injector is determined according to the injector state estimation model based on MSET, and the operating state of the injector can be real-time online fault warning according to the similarity and the current dynamic threshold, so as to predict in advance whether the injector fails and improve the equipment maintenance efficiency and reliability. And by combining the injector state estimation model with the current dynamic threshold obtained in real time, the real-time online warning of the injector fault can be realized, and by updating the current dynamic threshold in real time, the accuracy, effectiveness and reliability of the warning can be improved. In addition, by establishing an injector state estimation model based on the injector's historical operating state data, on the one hand, the injector state estimation model and the injector's current operating state data can accurately predict the similarity of the injector's current operating state data, thereby improving the accuracy of subsequent fault prediction. On the other hand, there is no need to classify the historical data, and it can be directly used to build the injector state estimation model, with high data availability, solving the problem of low data availability caused by complex working conditions and no labels of long-term monitoring data.

[0112] As a specific implementation method, optionally, the determination of the steady-state operating condition includes: obtaining operating status data of the injector; wherein the operating status data includes oil temperature data of the injector and rail pressure data of the injector; determining whether the rail pressure of the injector has changed based on the rail pressure data of the injector, and if so, further determining whether the monotonicity of the oil temperature of the injector has changed, and if so, determining that the current operating condition is a steady-state operating condition.

[0113] Specifically, first determine whether the rail pressure of the injector has changed. If the rail pressure has changed, it means that the current data is variable operating condition data, and then further determine whether the monotonicity of the oil temperature data has changed. If the monotonicity of the oil temperature has changed, it means that the temperature under the current variable operating condition has changed from an upward or downward trend to a stable (or constant value), and the current operating condition can be determined to be a steady-state condition, thereby improving the accuracy of the steady-state condition judgment, thereby avoiding misjudgment and causing inaccurate subsequent fault warning judgments.

[0114] For example, in the process of online warning of the fault of the fuel injector (such as when the fuel injector is assembled and used), it can be judged whether the current operating condition of the fuel injector is a steady-state condition according to the above-mentioned steady-state condition judgment method based on the current operating state data, so as to perform subsequent fault warning judgment. For example, assuming that the current operating state data is the rail pressure data and oil temperature data of the fuel injector, the rail pressure data and oil temperature data of the fuel injector can be judged whether the current operating condition of the fuel injector is a steady-state condition according to the above-mentioned steady-state condition judgment method.

[0115] For example, in the process of constructing the injector state estimation model based on MSET, it is possible to determine whether the historical operating condition of the injector is a steady-state condition according to the above-mentioned steady-state condition judgment method based on the historical operating state data, thereby screening out the historical steady-state condition data for subsequent modeling. For example, assuming that the historical operating state data is the rail pressure data and oil temperature data of the injector with a long period, the rail pressure data and oil temperature data of the injector with a long period can be used to determine whether the current operating condition of the injector is a steady-state condition according to the above-mentioned steady-state condition judgment method.

[0116] Figure 3 is a schematic diagram of a construction process of an injector state estimation model provided in an embodiment of the present application. Figure 3, obtain historical operating status data (such as long-term rail pressure and injector temperature monitoring data), determine whether the rail pressure has changed, if it has changed, determine that the current data is variable operating condition data, and further determine whether the temperature monotonicity of the injector has changed. If the temperature monotonicity of the injector has changed, determine that the current data is steady-state operating condition data, and eliminate the non-steady-state operating condition data (i.e., variable operating condition data), and retain the steady-state operating condition data. Then, remove data missing points and outliers. Secondly, perform data standardization. After standardization, a certain proportion of samples are randomly selected as training data, and the rest are test data. Then, screen parameters to determine the training matrix K. Calculate the health matrix D based on the training matrix K. Calculate the system nonlinear operator based on the Euclidean distance. Calculate the model weight coefficient W based on the system relative error. Then, generate the model observation matrix. Calculate the relative error of the model observation matrix to the test matrix, and calculate the relative error distribution. Then determine whether the equal error meets the requirements. If so, the construction of the injector state estimation model based on MSET is completed. Otherwise, return to the step of screening parameters to determine the training matrix K and repeat the execution until the requirements are met.

[0117] Exemplarily, taking the historical operating status data including the historical rail pressure data of the injector and the historical oil temperature data of the injector as an example, the construction process of the injector state estimation model based on MSET is as follows: First, based on the screened historical steady-state operating data, such as the historical rail pressure data and the historical oil temperature data, remove the data missing point samples. Then, determine whether there are out-of-range parameters and parameters that far exceed the alarm value in the data. If so, remove them as outliers to obtain sample data. Secondly, convert the sample data into dimensionless values ​​according to the data conversion formula. Exemplarily, the value range can be [0, 1]. Among them, the data conversion formula is:

[0118]

[0119] Among them, x z-score is the dimensionless numerical result after conversion; x i is the i-th data point; x min is the minimum value in the data set; x max is the maximum value in the data set.

[0120] Secondly, the standardized data of historical steady-state conditions with missing points and outliers removed are taken as the analysis object and divided into training data and test data according to a certain ratio (the specific ratio setting can be set according to actual conditions and is not specifically limited here).

[0121] Secondly, determine the training matrix K as:

[0122] K=[X (t1) ,X (t2),X (t3) ,…,X (tk) ]

[0123] Secondly, the health matrix D is calculated according to the health matrix calculation formula. The health matrix calculation formula is:

[0124]

[0125] Secondly, the nonlinear operator is calculated based on the Euclidean distance The calculation formula of the nonlinear operator is:

[0126]

[0127] Among them, x i and i are the actual value and the predicted value respectively.

[0128] Secondly, the system relative error calculation formula is introduced:

[0129] ε=|X obs -X est |=|X obs -D.W|

[0130] Among them, X obs is the system test matrix; X est Estimate vector for the system.

[0131] Secondly, according to the following formula, W=[w1,w2,…,w m ] Taking partial derivatives we get:

[0132] D T ·D·W=D T ·X obs

[0133] Then perform matrix operations on it and get:

[0134] W=(D T ·D) -1 ·(D T ·X obs )

[0135] The model weight coefficient W can be obtained by combining the nonlinear operator. The model weight coefficient calculation formula is:

[0136]

[0137] Finally, the prediction results of the MSET model are compared with the test data, and the relative error between the two is calculated by the following error formula. When the relative error meets the requirements, the injector state estimation model based on MSET is obtained. If the relative error does not meet the requirements, return to the above step of determining the training matrix and repeat it until the relative error meets the requirements.

[0138] The relative error calculation formula is as follows:

[0139]

[0140] Among them, δ i is the relative error, x i The calculation results of the model are: The actual results for the test data.

[0141] Figure 4 is a flow chart of a method for early warning of a fuel injector failure provided in an embodiment of the present application. Figure 4 When the injector is assembled and used, the health matrix, model weight coefficient and the existing injector temperature and rail pressure steady-state data of the injector are stored in the control system host computer. Real-time electronic control injector oil temperature and rail pressure data are collected. According to the above-mentioned steady-state condition judgment method, it is judged whether the current state is in a steady-state condition, and the real-time prediction of the injector fault is performed when it is judged to be a steady-state condition. The real-time collected injector oil temperature and oil quantity data are input into the injector state estimation model based on MSET, and the similarity between the model estimation value and the actual value is calculated according to the similarity calculation formula. Then, the sliding window length value is selected, and the initial dynamic threshold and static threshold of the model are set. Secondly, the relationship between the similarity and the dynamic threshold is judged. When the similarity is less than the current dynamic threshold, it is judged that the injector may be abnormal. When the similarity is continuously less than the dynamic threshold, it is judged that the injector may be abnormal, and an alarm message is sent. Then, the real-time collected injector oil quantity, oil temperature and rail pressure steady-state condition data are stored in the control system host computer. In this way, real-time online early warning of injector faults is achieved.

[0142] Correspondingly, an embodiment of the present application also provides an injector fault warning device. Figure 5 This is a principle structure diagram of a fuel injector fault warning device provided in an embodiment of the present application. Figure 5The injector fault warning device 100 includes: a first acquisition module 101, used to acquire the current operating state data and historical operating state data of the injector; a model construction module 102, used to construct an injector state estimation model based on the multivariate state estimation technology according to the historical operating state data; a steady-state operating condition judgment module 103, used to judge whether the current operating condition of the injector is a steady-state operating condition according to the current operating state data; a similarity determination module 104, used to determine the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology; a second acquisition module 105, used to acquire the current dynamic threshold; a fault judgment module 106, used to judge whether the operating state of the injector is faulty according to the similarity between the current dynamic threshold and the current operating state data of the injector; a threshold update judgment module 107, used to judge whether to update the current dynamic threshold.

[0143] The technical solution of this embodiment provides an injector fault warning device, which includes: a first acquisition module for acquiring the current operating state data and historical operating state data of the injector; a model construction module for constructing an injector state estimation model based on the multivariate state estimation technology according to the historical operating state data; a steady-state operating condition judgment module for judging whether the current operating condition of the injector is a steady-state operating condition according to the current operating state data; a similarity determination module for determining the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology; a second acquisition module for acquiring the current dynamic threshold; a fault judgment module for judging whether the operating state of the injector fails according to the similarity between the current dynamic threshold and the current operating state data of the injector; and a threshold update judgment module for judging whether to update the current dynamic threshold. Therefore, the device can achieve: early warning before the operating state of the injector fails, thereby improving equipment maintenance efficiency, improving equipment reliability, and reducing equipment maintenance costs. In addition, a state estimation model is constructed through the historical operating status data of the injector, and the similarity of the current operating status data is calculated based on the state estimation model. The dynamic threshold is combined to determine in real time whether the operating status of the injector has a fault. The combination of the state estimation model and the dynamic threshold can improve the accuracy, effectiveness and reliability of fault warning judgment.

[0144] In some embodiments, the model building module 102 includes: a data screening unit for screening out historical steady-state operating data according to historical operating status data; and a model building unit for building an injector state estimation model based on multivariate state estimation technology according to the historical steady-state operating data.

[0145] In some embodiments, the model building unit is also used to preprocess historical steady-state operating data to obtain a test matrix and a training matrix; generate a model observation matrix based on the training matrix; and establish an injector state estimation model based on multivariate state estimation technology based on the test matrix and the model observation matrix.

[0146] In some embodiments, the model building unit is also used to determine a health matrix based on the training matrix; calculate a model nonlinear operator based on the Euclidean distance; determine a model weight coefficient based on the nonlinear operator and the health matrix; and generate a model observation matrix based on the model weight coefficient.

[0147] In some embodiments, the data screening unit is further used to determine whether the historical operating status data is a steady-state condition based on the historical operating status data, eliminate non-steady-state condition data in the historical operating status data, and retain steady-state condition data.

[0148] In some embodiments, the steady-state operating condition judgment module 103 is also used to obtain operating status data of the injector; wherein the operating status data includes oil temperature data of the injector and rail pressure data of the injector; and judging whether the rail pressure of the injector changes according to the rail pressure data of the injector, and if so, further judging whether the monotonicity of the oil temperature of the injector changes, and if so, judging that the current operating condition is a steady-state operating condition.

[0149] In some embodiments, the fault judgment module 106 includes: a first comparison unit, used to compare the similarity of the current operating status data of the injector with the current dynamic threshold; a fault judgment unit, used to determine that the current operating status data of the injector is normal if the similarity is greater than the current dynamic threshold, and determine whether to update the current dynamic threshold; if the similarity of the current operating status data of the injector is less than or equal to the current dynamic threshold, determine that the current operating status data of the injector is abnormal, and obtain a time series of the judgment result of whether the current operating status data of the injector is abnormal; judge whether the operating status of the injector is faulty according to the time series of the judgment result of whether the current operating status data of the injector is abnormal.

[0150] In some embodiments, the threshold update judgment module 107 includes: a second comparison unit, used to compare the similarity of the current operating status data of the injector with the static threshold; a threshold update judgment unit, used to maintain the current dynamic threshold if the similarity of the current operating status data of the injector is greater than the static threshold; if the similarity of the current operating status data of the injector is less than or equal to the static threshold, update the current dynamic threshold according to the similarity of the current operating status data of the injector.

[0151] In some embodiments, the fault judgment unit is also used to determine the number of times the current operating status data of the injector has been continuously abnormal based on the time series of the result of judging whether the current operating status data of the injector is abnormal; and to judge whether the number of times the current operating status data of the injector has been continuously abnormal exceeds a preset number. If so, it is determined that the operating status of the injector has failed and an alarm message is sent.

[0152] In some embodiments, the similarity determination module 104 includes: an estimated value obtaining unit, which is used to input the current operating state data into the injector state estimation model based on the multivariate state estimation technology to obtain the estimated value of the current operating state data of the injector; and a similarity obtaining unit, which is used to calculate the similarity of the current operating state data of the injector based on the estimated value of the current operating state data of the injector and the current operating state data.

[0153] In some embodiments, the current operating status data includes at least one of current rail pressure data of the injector, current oil temperature data of the injector, and current oil quantity data of the injector; the historical operating status data includes at least one of historical rail pressure data of the injector, historical oil temperature data of the injector, and historical oil quantity data of the injector.

[0154] Accordingly, the present application also provides an electronic device, see Figure 6 , Figure 6 The structure diagram of the electronic device of the embodiment of the present application is illustrated. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned injector fault warning method are implemented. Since the injector fault warning method is described in detail above, it will not be repeated here.

[0155] Accordingly, the embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned injector failure warning method are implemented. Since the above-mentioned injector failure warning method is described in detail, it will not be repeated here.

[0156] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] The above is a detailed introduction to the injector fault warning method, device, equipment and storage medium provided in the embodiments of the present application, and the principles and implementation methods of the present application are explained by using specific examples. The description of the above embodiments is only used to help understand the technical solution and its core idea of ​​the present application; ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and these modifications or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiments of the present application.

Claims

1. A fuel injector fault warning method, characterized in that: include: Acquire current operating state data and historical operating state data of the injector, and construct an injector state estimation model based on multivariate state estimation technology according to the historical operating state data; Determine whether the current operating condition of the injector is a steady-state condition according to the current operating state data, and if so, determine the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology; A current dynamic threshold is obtained, and it is determined whether a fault occurs in the operating state of the injector according to the similarity between the current dynamic threshold and the current operating state data of the injector, and it is determined whether to update the current dynamic threshold.

2. The fuel injector failure warning method according to claim 1, characterized in that: The method of constructing a fuel injector state estimation model based on a multivariate state estimation technology according to the historical operating state data comprises: Filter out historical steady-state operating condition data according to the historical operating status data; A fuel injector state estimation model based on multivariate state estimation technology is established according to the historical steady-state operating condition data.

3. The fuel injector failure warning method according to claim 2, characterized in that: The method of establishing a fuel injector state estimation model based on a multivariate state estimation technology according to the historical steady-state operating condition data comprises: Preprocessing the historical steady-state operating condition data to obtain a test matrix and a training matrix; Generate a model observation matrix based on the training matrix; The injector state estimation model based on the multivariate state estimation technology is established according to the test matrix and the model observation matrix.

4. The fuel injector failure warning method according to claim 3, characterized in that: The generating a model observation matrix based on the training matrix comprises: determining a health matrix based on the training matrix; Nonlinear operator based on Euclidean distance calculation model; Determining a model weight coefficient according to the nonlinear operator and the health matrix; The model observation matrix is ​​generated according to the model weight coefficients.

5. The fuel injector failure warning method according to claim 2, characterized in that: The filtering out the historical steady-state operating condition data according to the historical operating status data includes: It is determined whether the historical operating status data is a steady-state operating condition according to the historical operating status data, non-steady-state operating condition data in the historical operating status data is eliminated, and steady-state operating condition data is retained.

6. The fuel injector failure warning method according to claim 1 or 5, characterized in that: The determination of the steady-state operating condition includes: Acquiring operating status data of the fuel injector; wherein the operating status data includes oil temperature data of the fuel injector and rail pressure data of the fuel injector; It is determined whether the rail pressure of the injector changes according to the rail pressure data of the injector. If yes, it is further determined whether the oil temperature monotonicity of the injector changes. If yes, it is determined that the current working condition is a steady-state working condition.

7. The fuel injector failure warning method according to claim 1, characterized in that: The step of judging whether a fault occurs in the operating state of the fuel injector according to the similarity between the current dynamic threshold value and the current operating state data of the fuel injector, and judging whether to update the current dynamic threshold value, comprises: comparing the similarity of the current operating state data of the injector with the current dynamic threshold; If the similarity of the current operating state data of the injector is greater than the current dynamic threshold, it is determined that the current operating state data of the injector is normal, and it is determined whether to update the current dynamic threshold; If the similarity of the current operating status data of the injector is less than or equal to the current dynamic threshold, it is determined that the current operating status data of the injector is abnormal, and a time series of the results of the judgment of whether the current operating status data of the injector is abnormal is obtained; and whether the operating status of the injector is faulty is determined based on the time series of the results of the judgment of whether the current operating status data of the injector is abnormal.

8. The fuel injector failure warning method according to claim 7, characterized in that: The determining whether to update the current dynamic threshold comprises: comparing the similarity of the current operating state data of the injector with a static threshold; If the similarity of the current operating state data of the injector is greater than the static threshold, maintaining the current dynamic threshold; If the similarity of the current operating state data of the injector is less than or equal to the static threshold, the current dynamic threshold is updated according to the similarity of the current operating state data of the injector.

9. The fuel injector failure warning method according to claim 7, characterized in that: The step of judging whether a fault occurs in the operating state of the fuel injector according to the time series of the result of judging whether the current operating state data of the fuel injector is abnormal comprises: Determining the number of times the current operating state data of the injector is abnormal continuously according to the time series of the result of judging whether the current operating state data of the injector is abnormal; It is also determined whether the number of times that the current operating state data of the injector is continuously abnormal exceeds a preset number. If it exceeds, it is determined that the operating state of the injector is faulty and an alarm message is sent.

10. The fuel injector failure warning method according to claim 1, characterized in that: Determining the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology includes: Inputting the current operating state data into the injector state estimation model based on the multivariate state estimation technology to obtain an estimated value of the current operating state data of the injector; The similarity of the current operating state data of the fuel injector is calculated based on the estimated value of the current operating state data of the fuel injector and the current operating state data.

11. The fuel injector failure warning method according to claim 1, characterized in that: The current operating state data includes at least one of: current rail pressure data of the fuel injector, current oil temperature data of the fuel injector, and current oil quantity data of the fuel injector; The historical operating status data includes at least one of historical rail pressure data of the fuel injector, historical oil temperature data of the fuel injector, and historical oil quantity data of the fuel injector.

12. A fuel injector fault warning device, characterized in that: include: A first acquisition module, used for acquiring current operating state data and historical operating state data of the injector; A model building module, used for building a fuel injector state estimation model based on a multivariate state estimation technology according to the historical operating state data; A steady-state operating condition judgment module, used for judging whether the current operating condition of the injector is a steady-state operating condition according to the current operating state data; A similarity determination module, used for determining the similarity of the current operating state data of the injector according to the current operating state data and the injector state estimation model based on the multivariate state estimation technology; The second acquisition module is used to obtain the current dynamic threshold; a fault judgment module, used for judging whether a fault occurs in the operating state of the fuel injector according to the similarity between the current dynamic threshold and the current operating state data of the fuel injector; The threshold update judgment module is used to judge whether to update the current dynamic threshold.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the injector failure warning method according to any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the injector failure warning method according to any one of claims 1 to 11 is implemented.

Images