Fault diagnosis method and device for diaphragm type urea pump, electronic equipment and medium

Abstract

The invention relates to a fault diagnosis method and device for a diaphragm type urea pump, electronic equipment and a medium, and belongs to the technical field of engine exhaust aftertreatment. The method comprises the steps that obtained operation data of the diaphragm type urea pump are input into a trained prediction model, and a urea pressure prediction value output by the prediction model is obtained; the prediction model is obtained based on historical operation data and urea injection pressure training corresponding to the historical operation data; and based on the urea pressure predicted value and the urea pressure measured value, fault diagnosis is carried out on the diaphragm type urea pump. According to the fault diagnosis method of the diaphragm type urea pump, the urea pressure prediction value is obtained through accurate prediction of the prediction model, and accurate judgment of the fault is achieved through comparison of the model prediction value and the measured value.

Description

Technical Field

[0001] The present invention relates to the technical field of engine exhaust aftertreatment, and in particular to a fault diagnosis method, device, electronic equipment and medium for a diaphragm type urea pump. Background Art

[0002] In the current market, there are many cases of insufficient urea injection due to blockage of the filter screen of the urea injection system. After blockage, the pressure of the urea pump will drop. However, due to the large differences in urea injection pressure under different working conditions and vehicles, the traditional fault diagnosis method is limited by the characteristics of the diaphragm pump and may have false alarms or leaks. The existing urea pump pressure failure is diagnosed by table lookup. The corresponding relationship table of urea injection volume and urea pressure is obtained through experiments. During vehicle operation, the theoretical urea pressure value under the current injection volume is obtained by looking up the table according to the current injection volume to determine whether the urea injection system is working properly.

[0003] Due to the characteristics of the diaphragm pump, the urea injection pressure is not a constant value even at a stable injection volume. When the injection volume is constant, its working pressure also presents a sinusoidal distribution characteristic. The urea pressure value obtained by the table lookup method is poorly consistent with the transient urea pressure. At the same time, simply looking up the table cannot take into account the effects of exhaust back pressure, exhaust temperature, ambient temperature, previous working status and other factors on urea injection pressure.

[0004] Under the same injection volume, the distribution range of the outer envelope pressure is relatively wide, making it difficult to ensure the robustness of the traditional urea pressure low fault diagnosis method (for example, if the measured pressure value under a certain injection volume is lower than the limit value, it is considered a fault). Urea pressure is affected by many factors, and the pressure may not increase with the increase of injection volume, and the urea pressure may be different under the same injection volume, which increases the difficulty of traditional diagnosis. Summary of the invention

[0005] In view of this, it is necessary to provide a fault diagnosis method, device, electronic equipment and medium for a diaphragm urea pump to solve the problem of how to improve the accuracy of fault diagnosis of a diaphragm urea pump.

[0006] In order to solve the above problems, the present invention provides a fault diagnosis method for a diaphragm type urea pump, comprising: The acquired operation data of the diaphragm urea pump is input into a trained prediction model to obtain a urea pressure prediction value output by the prediction model; the prediction model is trained based on historical operation data and the urea injection pressure corresponding to the historical operation data; Based on the predicted urea pressure value and the measured urea pressure value, a fault diagnosis is performed on the diaphragm urea pump.

[0007] In a possible implementation, the performing fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value includes: The predicted urea pressure value and the measured urea pressure value are fused based on an extended Kalman filter method to obtain a fused value; Based on the ratio of the measured urea pressure value to the fusion value, a fault diagnosis is performed on the diaphragm urea pump.

[0008] In a possible implementation, the performing fault diagnosis on the diaphragm urea pump based on the ratio of the measured urea pressure value to the fusion value includes: When the ratio is less than a first preset value, the fault is diagnosed as filter blockage; When the ratio is greater than a second preset value, the fault is diagnosed as nozzle blockage; The first preset value is smaller than the second preset value.

[0009] In a possible implementation, before performing fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value, the method further includes: The NOx concentration measured by the NOx sensor determines the conversion efficiency of the SCR system; When the conversion efficiency is higher than a third preset value, the actual measured value of the urea pressure is obtained.

[0010] In a possible implementation, the prediction model is trained in the following manner: The historical operation data is used as a model input, and the urea injection pressure is used as an output, and the Transformer model is trained to obtain the prediction model.

[0011] In a possible implementation, the expression of the fusion value is as follows:

[0012]

[0013] in, represents the fusion value, represents the corrected urea pressure prediction value, represents the Kalman gain, Indicates the measured value of urea pressure, represents the weight parameter of the linear link, represents the predicted value of urea pressure, is the correction parameter of the linear link, Indicates time.

[0014] In a possible implementation, the operation data includes: Ambient temperature, exhaust flow, urea injection amount and SCR inlet temperature.

[0015] The present invention also provides a fault diagnosis device for a diaphragm type urea pump, comprising: A prediction module, used for inputting the acquired operation data of the diaphragm urea pump into a trained prediction model to obtain a urea pressure prediction value output by the prediction model; the prediction model is obtained by training based on historical operation data and the urea injection pressure corresponding to the historical operation data; The diagnosis module is used to perform fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value.

[0016] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the fault diagnosis method of the diaphragm urea pump described in any of the above implementations.

[0017] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the fault diagnosis method for the diaphragm type urea pump described in any of the above implementations is implemented.

[0018] The beneficial effects of the present invention are as follows: the fault diagnosis method, device, electronic device and medium of the diaphragm urea pump provided by the present invention obtain a prediction model based on historical operation data and corresponding urea injection pressure training, so as to accurately predict the working pressure of the urea pump through the operation data of the diaphragm urea pump and the prediction model to obtain a urea pressure prediction value, and perform fault diagnosis on the diaphragm urea pump in combination with the urea pressure prediction value and the urea pressure actual measurement value. For example, it can be judged whether the diaphragm urea pump has a fault through the difference between the urea pressure prediction value and the urea pressure actual measurement value, the urea pressure prediction value is accurately predicted through the prediction model, and the fault is accurately judged by comparing the model prediction value with the actual measurement value. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1One of the method flow charts of an embodiment of the fault diagnosis method of the diaphragm type urea pump provided by the present invention; Figure 2 A second method flow chart of an embodiment of a method for diaphragm type urea pump fault diagnosis provided by the present invention; Figure 3 A schematic structural diagram of an embodiment of a fault diagnosis system for a diaphragm type urea pump provided by the present invention; Figure 4 A schematic structural diagram of an embodiment of a fault diagnosis device for a diaphragm type urea pump provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0023] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0024] Figure 1 One of the method flow charts of an embodiment of the fault diagnosis method of the diaphragm type urea pump provided by the present invention is as follows Figure 1 As shown in the figure, the fault diagnosis method of the diaphragm urea pump includes: S101, inputting the acquired operation data of the diaphragm urea pump into a trained prediction model to obtain a urea pressure prediction value output by the prediction model; the prediction model is obtained by training based on historical operation data and the urea injection pressure corresponding to the historical operation data; S102: Perform fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value.

[0025] Compared with the prior art, the fault diagnosis method of the diaphragm urea pump provided in the embodiment of the present invention obtains a prediction model based on historical operating data and corresponding urea injection pressure training, so as to accurately predict the working pressure of the urea pump through the operating data of the diaphragm urea pump and the prediction model to obtain a urea pressure prediction value, and perform fault diagnosis on the diaphragm urea pump in combination with the urea pressure prediction value and the urea pressure measured value. For example, it can be judged whether the diaphragm urea pump has a fault through the difference between the urea pressure prediction value and the urea pressure measured value, the urea pressure prediction value is accurately predicted through the prediction model, and the fault is accurately judged by comparing the model prediction value with the measured value.

[0026] In some embodiments of the present invention, the operating data includes: Ambient temperature, exhaust flow, urea injection amount and SCR inlet temperature.

[0027] In some embodiments of the present invention, the prediction model is trained in the following manner: The historical operation data is used as a model input, and the urea injection pressure is used as an output, and the Transformer model is trained to obtain the prediction model.

[0028] The operating data includes: ambient temperature, exhaust flow, urea injection amount and SCR inlet temperature. The machine learning model can be trained using the ambient temperature, exhaust flow, urea injection amount, SCR inlet temperature and the corresponding urea injection pressure in the historical operating data of the vehicle that is running normally and without any faults.

[0029] The machine learning model used in the embodiment of the present invention is a Transformer model, which includes an encoding layer, a multi-head attention layer, an FNN layer and a SoftMax layer.

[0030] The vehicle information is input into the encoding layer for position encoding, and then encoded and decoded by the multi-head attention module and processed by the FNN layer and SoftMax layer to obtain the urea pressure value predicted by the model. By considering the impact of vehicle operating conditions on the working pressure of the injection system, the time series data takes into account the historical operating status, making the prediction of the working pressure of the urea pump more accurate and reasonable.

[0031] The fault diagnosis method for a diaphragm urea pump provided in an embodiment of the present invention adopts a Transformer-based machine learning model to predict the working pressure of the urea pump through operating data such as urea injection amount, ambient temperature, SCR temperature and exhaust flow rate, and adopts a data fusion algorithm to fuse the fault-free measured working pressure with the pressure predicted by the machine learning model, and introduces the working pressure difference caused by factors such as installation layout and manufacturing deviation, so as to achieve model prediction values ​​that vary from vehicle to vehicle and from working condition to working condition, and diagnose faults more reasonably and accurately.

[0032] In some embodiments of the present invention, the fault diagnosis of the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value includes: The predicted urea pressure value and the measured urea pressure value are fused based on an extended Kalman filter method to obtain a fused value; Based on the ratio of the measured urea pressure value to the fusion value, a fault diagnosis is performed on the diaphragm urea pump.

[0033] In some embodiments of the present invention, the expression of the fusion value is as follows:

[0034]

[0035] in, represents the fusion value, represents the corrected urea pressure prediction value, represents the Kalman gain, Indicates the measured value of urea pressure, represents the weight parameter of the linear link, represents the predicted value of urea pressure, is the correction parameter of the linear link, Indicates time.

[0036] The predicted value of urea pressure and the measured value of urea pressure are fused by the extended Kalman filter (EKF) method to obtain a fused value.

[0037] Optionally, the NOx emissions of the current SCR system are added as an enabling condition during fusion, because normal system emissions mean that the injection system is working well. At this time, the sensor measured pressure can represent the normal allowable level of the vehicle. The fusion of the measured value and the model can take into account the differences in the vehicle due to manufacturing deviations, installation layout and other factors, which further improves the prediction of the urea pump working pressure specific to each vehicle.

[0038] The specific fusion process is as follows:

[0039]

[0040]

[0041]

[0042]

[0043] in, represents the prediction result of the Transformer model (i.e., the predicted value of urea pressure), is the predicted value corrected by Kalman filter fusion (i.e. fusion value), is the predicted value before Kalman filter fusion correction, is the Kalman gain, is the actual value of the urea pressure sensor at time t (i.e. the measured value of urea pressure), is the weight parameter of the linear link, is the correction parameter of the linear link, is the actual process noise, is the noise of the prediction process, is the prior covariance matrix, is the posterior covariance matrix at time t, is the posterior covariance matrix of the previous moment before moment t.

[0044] The fault diagnosis method for a diaphragm urea pump provided in an embodiment of the present invention adopts a fusion algorithm to fuse the measured urea pressure under normal working conditions with the predicted pressure of a machine learning model, and to fuse the working pressure changes caused by factors such as installation layout and manufacturing deviation into the pressure value predicted based on the working condition.

[0045] In some embodiments of the present invention, the fault diagnosis of the diaphragm urea pump based on the ratio of the measured urea pressure value to the fusion value includes: When the ratio is less than a first preset value, the fault is diagnosed as filter blockage; When the ratio is greater than a second preset value, the fault is diagnosed as nozzle blockage; The first preset value is smaller than the second preset value.

[0046] The ratio of the measured urea pressure value to the fusion value is calculated. When the ratio is less than a first preset value (eg, 0.5), the fault is diagnosed as filter blockage, and the filter maintenance reminder is activated.

[0047] When the ratio is greater than a second preset value (eg, 1.5), the fault is diagnosed as nozzle blockage, and the nozzle cleaning maintenance reminder is activated.

[0048] In addition, when the engine is running in regeneration mode, the working pressure predicted by the model will deviate greatly from the actual working pressure, so it is necessary to avoid fault identification in regeneration mode. At the same time, when the system is working well and the SCR conversion efficiency is normal, there is no need to determine whether the injection system has a fault.

[0049] The fault diagnosis method of the diaphragm urea pump provided in the embodiment of the present invention determines whether the urea working pressure is normal by comparing the fused predicted urea pressure value with the measured value, which is more accurate than the traditional judgment method of setting a fixed threshold.

[0050] In some embodiments of the present invention, before performing fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value, the method further includes: The NOx concentration measured by the NOx sensor determines the conversion efficiency of the SCR system; When the conversion efficiency is higher than a third preset value, the actual measured value of the urea pressure is obtained.

[0051] Based on the NOx concentration measured by the NOx sensor, the conversion efficiency of the current SCR system can be calculated.

[0052] When the conversion efficiency of the SCR system is higher than the third preset value, it is considered that the entire SCR system is in good condition, which also indicates that the urea injection is normal. At this time, the urea injection pressure measured by the pressure sensor is considered to be the pressure of the normal operation of the urea pump. Therefore, the pressure prediction value obtained by deep learning can be Kalman fused with the actual measurement result of the urea pressure sensor.

[0053] When the conversion efficiency of the SCR system is lower than the third preset value, it is considered that there may be faults in some aspects of the SCR system. At this time, the actual measured value of the urea injection pressure is no longer integrated with the machine learning model to avoid the impact of fault data on the prediction results, making the prediction results more accurate. Finally, the predicted pressure is compared with the actual measured pressure of the sensor to diagnose whether the system has a fault.

[0054] The fault diagnosis method for the diaphragm urea pump provided in the embodiment of the present invention sets a system working state judgment through fault discrimination. When the SCR conversion efficiency is normal and the vehicle is operating under regeneration and other working conditions, fault diagnosis is not enabled, which can improve the reliability of diagnosis.

[0055] Figure 2 The second method flow chart of an embodiment of the fault diagnosis method of the diaphragm urea pump provided by the present invention is as follows: Figure 2 As shown, the fault diagnosis method of the diaphragm type urea pump provided by the present invention includes: S201, obtaining historical vehicle operation data and corresponding urea injection system operating pressure and fault form; S202, extracting features from the operating data and matching the features with the working pressure and the fault form; S203, performing machine learning calculations based on operating data characteristics and work pressure; S204, combining the current operating working pressure with the operating data characteristics and the working pressure machine learning calculation results to predict the working pressure of the current system in a normal state; S205: Make a fault warning judgment based on the predicted working pressure and the measured working pressure.

[0056] Figure 3 A schematic diagram of the structure of an embodiment of a fault diagnosis system for a diaphragm type urea pump provided by the present invention is shown in FIG. Figure 3 As shown, the fault diagnosis system of the diaphragm urea pump provided by the present invention includes a machine learning module, a fusion module and a fault reminder module.

[0057] The fault diagnosis system and method of the diaphragm urea pump provided by the present invention are described in detail below in conjunction with specific application scenarios.

[0058] The fault diagnosis method of the diaphragm urea pump provided by the present invention first collects the operation data of the urea injection system under different working / fault modes, associates the collected data with the urea working pressure and the system status, and then trains the machine learning model based on Transformer to obtain the model parameters. The current working pressure of the urea injection system is predicted based on the trained machine learning model and the vehicle operation data, and finally the measured urea pump pressure is compared with the predicted value to issue a fault reminder.

[0059] The specific method is as follows: Operation data selection. The model training selects vehicles with no faults in historical operation, vehicles with blocked urea pump filters, and vehicles with blocked nozzles, and obtains operation data collected by the vehicle remote terminal Tbox, including ambient temperature, exhaust flow, urea injection volume, SCR inlet temperature, urea injection pressure, front / rear NOx sensor status, front / rear NOx sensor concentration, engine combustion mode and other data information. After the model is integrated into the ECU, the prediction process directly obtains the above vehicle operation information in the ECU.

[0060] Machine learning module: The machine learning model is trained using the ambient temperature, exhaust flow, urea injection amount, SCR inlet temperature, and urea injection pressure of the vehicle information in the historical operation data that is running normally and without fault. The machine learning model used here is the Transformer-based urea pressure model. The Transformer model includes an encoding layer, a multi-head attention layer, an FNN layer, and a SoftMax layer.

[0061] The vehicle information is input into the encoding layer for position encoding, and then encoded and decoded by the multi-head attention module and processed by the FNN layer and SoftMax layer to obtain the urea pressure value predicted by the model. The impact of the vehicle operating conditions on the working pressure of the injection system is taken into account here, and the time series data takes into account the historical operating status, which makes the prediction of the urea pump working pressure more accurate and reasonable.

[0062] Fusion module: The machine learning pressure model value and the measured pressure model value are fused through the extended Kalman filter. The NOx emission of the current SCR system is added as an enabling condition. Because normal system emissions mean that the injection system is working well, the sensor measured pressure can represent the normal allowable level of the vehicle. The fusion of measurement values ​​and models can take into account the differences caused by manufacturing deviations, installation layout and other factors in the vehicle, and the prediction of the urea pump working pressure for each vehicle is further improved.

[0063]

[0064]

[0065]

[0066]

[0067]

[0068] in, Represents the prediction result of the Transformer model, is the predicted value after Kalman filter fusion correction, is the predicted value before Kalman filter fusion correction, is the Kalman gain, is the actual value of the urea pressure sensor at time t, is the weight parameter of the linear link, is the correction parameter of the linear link, is the actual process noise, is the noise of the prediction process, is the prior covariance matrix, is the posterior covariance matrix at time t, is the posterior covariance matrix of the previous moment before moment t.

[0069] Fault reminder module: Calculate the ratio of the measured urea pump pressure to the fusion urea model pressure. When the ratio is less than 0.5, the filter maintenance reminder is activated. When the ratio is greater than 1.5, the nozzle cleaning maintenance reminder is activated. When the engine is running in regeneration mode, the working pressure predicted by the model will have a large deviation from the actual pressure, so it is necessary to avoid fault identification in regeneration mode. At the same time, when the system is working well and the SCR conversion efficiency is normal, there is no need to determine whether the injection system has a fault.

[0070] The fault diagnosis method of the diaphragm urea pump provided by the embodiment of the present invention obtains urea pressure and operation history data of different vehicle operation states including urea pump fault state, extracts features from the historical data, performs deep machine learning on the historical data, predicts the system pressure that a normal system should show under the current operation state according to the deep learning result and the current operation information, and calculates the current SCR system conversion efficiency based on the NOx concentration measured by the NOx sensor. When the SCR efficiency is higher than the set value, it is considered that the entire SCR system is in good condition, which also indicates that the urea injection is normal. At this time, it is considered that the urea injection pressure measured by the pressure sensor is the pressure of the normal operation of the urea pump. At this time, the deep learning predicted pressure and the actual measured result of the urea pressure sensor are Kalman fused. When the SCR conversion efficiency is lower than the set threshold, it is considered that some aspects of the system may have faults. At this time, the actual measured value of the urea injection pressure is no longer fused with the machine learning model, so as to avoid the fault data from affecting the prediction result, so that the prediction result is more accurate. Finally, the predicted pressure is compared with the actual measured pressure of the sensor to diagnose whether the system has a fault.

[0071] By adopting a machine learning model to predict the working pressure of the urea pump according to the vehicle operating conditions, the data fusion algorithm will fuse the fault-free measured working pressure with the pressure predicted by the machine learning model, and introduce the working pressure differences caused by factors such as installation layout and manufacturing deviations. This can achieve model prediction values ​​that vary from vehicle to vehicle and from working condition to condition, and enable more reasonable and accurate fault diagnosis.

[0072] The AI ​​urea pressure model is used to predict the working pressure of the urea pump, and accurate judgment of filter blockage and nozzle blockage is achieved by comparing model prediction with actual measurement.

[0073] In order to better implement the fault diagnosis method of the diaphragm urea pump in the embodiment of the present invention, based on the fault diagnosis method of the diaphragm urea pump, the embodiment of the present invention further provides a fault diagnosis device of the diaphragm urea pump. Figure 4 A schematic diagram of the structure of an embodiment of a fault diagnosis device for a diaphragm type urea pump provided by the present invention is shown in FIG. Figure 4As shown, the fault diagnosis device 400 of the diaphragm type urea pump includes: The prediction module 410 is used to input the acquired operation data of the diaphragm urea pump into a trained prediction model to obtain a urea pressure prediction value output by the prediction model; the prediction model is obtained by training based on historical operation data and the urea injection pressure corresponding to the historical operation data; The diagnosis module 420 is used to perform fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value.

[0074] The fault diagnosis device 400 for a diaphragm urea pump provided in the above embodiment can implement the technical solution described in the above embodiment of the fault diagnosis method for a diaphragm urea pump. The specific implementation principles of the above modules or units can refer to the corresponding contents in the embodiment of the fault diagnosis method for a diaphragm urea pump, which will not be repeated here.

[0075] Optionally, the diagnosis module 420 is specifically configured to: The predicted urea pressure value and the measured urea pressure value are fused based on an extended Kalman filter method to obtain a fused value; Based on the ratio of the measured urea pressure value to the fusion value, a fault diagnosis is performed on the diaphragm urea pump.

[0076] Optionally, the diagnosis module 420 is further specifically configured to: When the ratio is less than a first preset value, the fault is diagnosed as filter blockage; When the ratio is greater than a second preset value, the fault is diagnosed as nozzle blockage; The first preset value is smaller than the second preset value.

[0077] Optionally, the method further includes: a determination module, configured to: The NOx concentration measured by the NOx sensor determines the conversion efficiency of the SCR system; When the conversion efficiency is higher than a third preset value, the actual measured value of the urea pressure is obtained.

[0078] Optionally, the prediction model is trained in the following manner: The historical operation data is used as a model input, and the urea injection pressure is used as an output, and the Transformer model is trained to obtain the prediction model.

[0079] Optionally, the expression of the fusion value is as follows:

[0080]

[0081] in, represents the fusion value, represents the corrected urea pressure prediction value, represents the Kalman gain, Indicates the measured value of urea pressure, represents the weight parameter of the linear link, represents the predicted value of urea pressure, is the correction parameter of the linear link, Indicates time.

[0082] Optionally, the operation data includes: Ambient temperature, exhaust flow, urea injection amount and SCR inlet temperature.

[0083] like Figure 5 As shown, the present invention also provides an electronic device 500. The electronic device 500 includes a processor 501, a memory 502 and a display 503. Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0084] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run program codes or process data stored in the memory 502, such as the fault diagnosis method of the diaphragm urea pump in the present invention.

[0085] In some embodiments, the processor 501 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 501 may be local or remote. In some embodiments, the processor 501 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0086] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500.

[0087] Furthermore, the memory 502 may include both an internal storage unit of the electronic device 500 and an external storage device. The memory 502 is used to store application software installed in the electronic device 500 and various data.

[0088] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an organic light-emitting diode (OLED) touch device, etc. The display 503 is used to display information on the electronic device 500 and to display a visual user interface. The components 501-503 of the electronic device 500 communicate with each other via a system bus.

[0089] In one embodiment, when the processor 501 executes the fault diagnosis program of the diaphragm urea pump in the memory 502, the following steps may be implemented: The acquired operation data of the diaphragm urea pump is input into a trained prediction model to obtain a urea pressure prediction value output by the prediction model; the prediction model is trained based on historical operation data and the urea injection pressure corresponding to the historical operation data; Based on the predicted urea pressure value and the measured urea pressure value, a fault diagnosis is performed on the diaphragm urea pump.

[0090] It should be understood that: when the processor 501 executes the fault diagnosis program of the diaphragm urea pump in the memory 502, in addition to the above functions, other functions can also be realized. For details, please refer to the description of the corresponding method embodiment above.

[0091] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 500 mentioned, and the electronic device 500 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 500 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0092] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, which is used to store a computer-readable program or instruction. When the program or instruction is executed by a processor, the steps or functions in the fault diagnosis method of the diaphragm urea pump provided in the above-mentioned method embodiments can be implemented. Those skilled in the art can understand that the implementation of all or part of the process of the above-mentioned embodiment method can be completed by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a disk, an optical disk, a read-only storage memory or a random access memory, etc.

[0093] The fault diagnosis method, device, electronic device and medium of the diaphragm urea pump provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A fault diagnosis method for a diaphragm urea pump, characterized in that: include: Inputting the acquired operating data of the diaphragm type urea pump into the trained prediction model to obtain a urea pressure prediction value output by the prediction model; The prediction model is obtained by training based on historical operation data and the urea injection pressure corresponding to the historical operation data; Based on the predicted urea pressure value and the measured urea pressure value, a fault diagnosis is performed on the diaphragm urea pump.

2. The fault diagnosis method of the diaphragm type urea pump according to claim 1, characterized in that: The method of performing fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value includes: The predicted urea pressure value and the measured urea pressure value are fused based on an extended Kalman filter method to obtain a fused value; Based on the ratio of the measured urea pressure value to the fusion value, a fault diagnosis is performed on the diaphragm urea pump.

3. The fault diagnosis method of the diaphragm type urea pump according to claim 2, characterized in that: The method of performing fault diagnosis on the diaphragm urea pump based on the ratio of the measured urea pressure value to the fusion value includes: When the ratio is less than a first preset value, the fault is diagnosed as filter blockage; When the ratio is greater than a second preset value, the fault is diagnosed as nozzle blockage; The first preset value is smaller than the second preset value.

4. The fault diagnosis method of a diaphragm type urea pump according to claim 1, characterized in that: Before performing fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value, the method further includes: The NOx concentration measured by the NOx sensor determines the conversion efficiency of the SCR system; When the conversion efficiency is higher than a third preset value, the actual measured value of the urea pressure is obtained.

5. The fault diagnosis method of a diaphragm type urea pump according to claim 1, characterized in that: The prediction model is trained in the following way: The historical operation data is used as a model input, and the urea injection pressure is used as an output, and the Transformer model is trained to obtain the prediction model.

6. The fault diagnosis method of a diaphragm type urea pump according to claim 1, characterized in that: The expression of the fusion value is as follows: in, represents the fusion value, represents the corrected urea pressure prediction value, represents the Kalman gain, Indicates the measured value of urea pressure, represents the weight parameter of the linear link, Represents the predicted value of urea pressure, is the correction parameter of the linear link, Indicates time.

7. The fault diagnosis method of a diaphragm type urea pump according to claim 1, characterized in that: The operation data includes: Ambient temperature, exhaust flow, urea injection amount and SCR inlet temperature.

8. A fault diagnosis device for a diaphragm urea pump, characterized in that: include: A prediction module, used for inputting the acquired operation data of the diaphragm urea pump into a trained prediction model to obtain a urea pressure prediction value output by the prediction model; The prediction model is obtained by training based on historical operation data and the urea injection pressure corresponding to the historical operation data; The diagnosis module is used to perform fault diagnosis on the diaphragm urea pump based on the predicted urea pressure value and the measured urea pressure value.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory, and is used to execute the program stored in the memory to implement the fault diagnosis method of the diaphragm type urea pump according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the fault diagnosis method for a diaphragm type urea pump according to any one of claims 1 to 7 is implemented.

Images