A fuel injection system life prediction method and electronic equipment based on digital twin model

Abstract

The present invention proposes a rapid life prediction method and electronic device based on a digital twin model. First, a multidisciplinary joint simulation model consisting of a geometric model, a system model, a fluid-structure coupling model, and a life assessment model is established to evaluate the life of the fuel injection system based on pump-end pressure, device-end pressure, and fuel injection volume. Second, the multidisciplinary joint simulation model is reduced in order using a neural network to obtain a virtual prototype that can quickly respond to input data. Third, based on the data of the physical prototype, the virtual prototype is corrected, and the physical and virtual prototypes are mapped to complete the construction of the digital twin model. Finally, the pump-end pressure, device-end pressure, and fuel injection volume measured by the physical prototype are transmitted to the virtual prototype to complete the real-time prediction of the physical prototype's life. The present invention can predict the life of the fuel injection system in real time based on the real-time operating status of the fuel injection system.

Description

Technical Field

[0001] The present invention belongs to the field of fuel injection technology, specifically a life assessment technology based on a digital twin model designed for fuel injection systems, which is suitable for life prediction of fuel injection systems in the product development stage and life assessment in the after-sales service stage. Background Art

[0002] The fuel injection system is a core component of the engine, known as the "heart" of the engine. It is subjected to periodic high temperatures and high pressures in the combustion chamber during operation, and its working environment is extremely harsh. The product's condition has a significant impact on the normal operation of the ship and whether its emissions comply with regulatory requirements. When the product's condition fails to meet the ship's emission requirements, it must be replaced. Wear of the core components of the fuel injection system can lead to poor fuel spray atomization, which is the main cause of the deterioration of engine combustion conditions. Furthermore, because the delicate and precision parts of the fuel injection system are all subjected to high-speed reciprocating motion within the confined space within the fuel injection system, it is impossible to effectively monitor the working condition and wear of the internal parts of the fuel injection system by directly installing sensors. As a result, it is impossible to establish an accurate life prediction model for the fuel injection system to predict its life.

[0003] Since the life of the fuel injection system is related to the safe operation of the engine, in order to ensure the reliability of the fuel injection system's operation, during the product design phase, the product's service life can only be determined through long-term durability tests and continuous disassembly and inspection of the actual product, which greatly increases the product's development cycle; and during the product's service phase, the reliable operation of the equipment can only be guaranteed by setting shorter inspection and overhaul cycles, which increases the product's subsequent maintenance costs. Summary of the Invention

[0004] In order to more accurately predict the life of the fuel injection system, the present invention proposes a fuel injection system life prediction method and electronic equipment based on a digital twin model, establishes a digital twin model of the fuel injection system for life prediction of the fuel injection system, and solves the current problems of high cost and long product life design cycle of the fuel injection system, as well as short product maintenance cycle time interval and high maintenance cost.

[0005] The technical solution of the present invention is as follows

[0006] In a first aspect, the present invention provides a fuel injection system life prediction method based on a digital twin model, which is mainly achieved by the following steps:

[0007] S1. Construct a digital twin model of the fuel injection system, which consists of a real-time mapped physical prototype and a virtual prototype. The virtual prototype is a multidisciplinary joint simulation model composed of a geometric model, a system model, a fluid-structure interaction model, and a life assessment model, obtained through neural network order reduction.

[0008] S2. Use the virtual prototype simulation in S1 to obtain the wear amount of the fuel injection system under the working state.

[0009] S3. Obtain the actual wear of the physical prototype through measurement.

[0010] S4. Compare the measured values ​​of the physical prototype with the results of the virtual prototype simulation and modify the virtual prototype model of the fuel injection system.

[0011] S5. The pump-end pressure, device-end pressure, and fuel injection volume measured in real time by the physical prototype are transmitted to the virtual prototype of the fuel injection system, and a rapid prediction of the life of the physical prototype of the fuel injection system is completed.

[0012] According to an embodiment of the present invention, the method for establishing the virtual prototype in S1 is as follows:

[0013] S11. Build a 3D geometric model of the fuel injection system based on parametric modeling technology;

[0014] S12. Establish a system model based on system simulation analysis tools.

[0015] S13. Establish a fluid-structure coupling model based on structural analysis tools and fluid analysis tools.

[0016] S14. Establish a fuel injection system life prediction model based on Archard theory.

[0017] S15. Based on the joint simulation tool, realize the data connection of geometric model, system model, fluid-structure interaction model, and life assessment model, and build a life prediction joint simulation model.

[0018] S16. Based on the CNN-LSTM neural network, the fuel injection system joint simulation model is reduced to create a virtual prototype that can quickly respond to inputs.

[0019] Specifically, the calculation results of the joint simulation model under different working conditions and different geometric shapes are used as training data, the pump-end pressure, device-end pressure and fuel injection amount are used as input, and the wear amount is used as output. The CNN-LSTM neural network is used for training to realize the rapid calculation of the wear amount of the fuel injection system based on the pump-end pressure, device-end pressure and fuel injection amount, complete the order reduction of the joint simulation model of the fuel injection system, and establish a virtual prototype that can respond quickly according to the input.

[0020] According to an embodiment of the present invention, the method for establishing the three-dimensional geometric model of the fuel injection system in S11 is as follows:

[0021] S111. Using a three-dimensional modeling tool and based on parametric modeling technology, establish a parametric three-dimensional model of the fuel injection system that can be quickly modified based on input data, and complete the establishment of the original geometric model.

[0022] S112. Import the measurement data of the physical prototype of the fuel injection system into the geometric model as parameters to complete the correction of the geometric structure and ensure the consistency of the geometric model with the physical prototype structure.

[0023] According to an embodiment of the present invention, the system model establishment method in S12 is as follows:

[0024] S121. Based on the system modeling tool, complete the system modeling of the fuel injection system.

[0025] S122. Based on the geometric model, extract structure-related data and input it into the system model.

[0026] S123. The initial operating condition data measured by the physical prototype is transferred to the system model to complete the initial system modeling.

[0027] S124. Compare the pump-end pressure, device-end pressure, and fuel injection quantity calculated based on the system model with the measured data to correct the model.

[0028] According to an embodiment of the present invention, the fluid-structure coupling model modeling method in S13 is as follows:

[0029] S131. Based on structural analysis tools, complete the establishment of a fuel injection system structural model;

[0030] S132. Based on the fluid analysis tool, complete the establishment of the fuel injection system fluid model;

[0031] S133. Connect the structural model and the fluid model using the fluid-structure coupling tool to complete the construction of the fluid-structure coupling model;

[0032] S134. The oil inlet pressure, oil outlet pressure, and speed of the moving parts calculated by the system model are imported as boundaries into the fluid-structure coupling model to complete the calculation of the pump end pressure, the device end pressure, and the fuel injection amount;

[0033] S135. Compare the pump-end pressure and the device-end pressure calculated by the fluid-solid coupling model with the corresponding data calculated by the system model to complete the correction of the fluid-solid coupling model.

[0034] According to an embodiment of the present invention, the method for performing life prediction based on the life prediction model in S14 is as follows:

[0035] S141. Determine the maximum allowable wear based on fuel injection system experimental data and historical failure data.

[0036] S142. The contact pressure and sliding distance per unit cycle calculated by the fluid-structure coupling model, as well as the material parameters, are input into the life prediction model to calculate the wear of the fuel injection system per unit cycle, that is, to calculate the cumulative wear of the fuel injection system based on the life assessment model;

[0037] S143. When the accumulated wear of the fuel injection system reaches the maximum allowable wear, the product life is deemed to have expired and the life assessment is completed.

[0038] According to an embodiment of the present invention, the life prediction model in S14 is established based on Archard wear theory, and the formula is as follows:

[0039]

[0040] Where: dV is the wear volume; d p is the normal pressure between parts; d l is the relative sliding distance between parts; H is the material hardness; K is the wear coefficient;

[0041] The total wear of the fuel injection system is calculated as follows:

[0042]

[0043] Among them, ω is the total wear amount, P is the normal pressure of the contact surface, V is the relative slip velocity, and a, b, and c are material constants.

[0044] Based on the above theory, a life assessment model is established to calculate the cumulative wear of the fuel injection system, and the life assessment is completed based on the maximum allowable wear.

[0045] According to an embodiment of the present invention, the method for constructing the life prediction joint simulation model in S15 is as follows:

[0046] S151. Using multidisciplinary co-simulation tools, connect the geometric model, system model, fluid-structure interaction model, and life assessment model to establish a multidisciplinary co-simulation model.

[0047] S152. The pump-end pressure, device-end pressure, and fuel injection volume of the physical prototype are transferred to the multidisciplinary joint simulation model to complete the life prediction of the fuel injection system;

[0048] According to an embodiment of the present invention, the virtual prototype order reduction method of the digital twin model of the fuel injection system in S16 is as follows: the calculation results of the joint simulation model under different working conditions and different geometric shapes are used as training data, the pump-end pressure, the device-end pressure and the fuel injection amount are used as input, and the wear amount is used as output, and the CNN-LSTM neural network is used for training to realize the rapid calculation of the wear amount of the fuel injection system based on the pump-end pressure, the device-end pressure and the fuel injection amount, complete the order reduction of the joint simulation model of the fuel injection system, and establish a virtual prototype that can respond quickly according to the input.

[0049] In another aspect, the present invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, and when executed by the at least one processor, the computer program causes the electronic device to perform the fuel injection system life prediction method based on a digital twin model according to the first aspect above.

[0050] Compared with the prior art, the present invention has at least the following beneficial effects:

[0051] The fuel injection system life prediction method based on the digital twin model described in the present invention solves the problem that the fuel injection system cannot accurately predict the service life. By utilizing digital twin technology, the simulated data of the fuel injection system pump-end pressure, device-end pressure and injection amount are compared with the measured data, and the digital twin model is corrected. Therefore, the fuel injection system life prediction method based on the digital twin model proposed in the present invention can accurately predict the service life of the fuel injection system. At the same time, the model reduction technology is used to realize life prediction based on real-time measurement results.

[0052] The fuel injection system operates in a high-temperature, high-pressure environment. The product status has a significant impact on whether the ship's emissions are compliant. When the product status cannot meet the ship's emission requirements, it must be replaced. The method described in the present invention can accurately and quickly predict the life of the fuel injection system, thereby more accurately predicting the replacement time of the fuel injection system, reducing replacements caused by excessive redundancy in the change cycle settings, and reducing the cost of using the fuel injection system.

[0053] The invention is applicable to electronically controlled unit pumps, common rail systems, gas engines and dual-fuel engines.

[0054] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a schematic diagram of a digital twin model of a fuel injection system in one embodiment of the present application;

[0056] Figure 2 This is an example diagram of a parameterized model in one embodiment of the present application;

[0057] Figure 3 This is a flowchart of the joint simulation model life assessment in one embodiment of the present application. DETAILED DESCRIPTION

[0058] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of protection of the present application.

[0059] It should be understood that the various steps described in the method embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0060] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0061] like Figure 1 As shown, an exemplary embodiment of the present application provides a life prediction method for a fuel injection system based on a digital twin model, the method comprising the following steps:

[0062] S1. Construct a digital twin model of the fuel injection system. The digital twin model consists of a real-time mapped physical prototype and a virtual prototype. The virtual prototype is a multidisciplinary joint simulation model consisting of a geometric model, a system model, a fluid-structure interaction model, and a life assessment model, which is obtained through neural network order reduction.

[0063] S2. The pump-end pressure, device-end pressure, and fuel injection rate of the physical prototype are transferred to the virtual prototype in S1 to obtain the cumulative wear of the fuel injection system under the working state.

[0064] S3. Obtain the accumulated wear by measuring the mass difference of the physical prototype before and after operation.

[0065] S4. Compare the measured values ​​of the physical prototype with the results of the virtual prototype simulation and modify the virtual prototype model of the fuel injection system.

[0066] S5. Input the pump-end pressure, device-end pressure, and fuel injection quantity measured in real time by the physical prototype into the virtual prototype of the fuel injection system to complete the real-time prediction of the life of the physical prototype of the fuel injection system.

[0067] In one embodiment of the present application, the specific method of constructing the digital twin model is as follows:

[0068] S11. Geometric model in virtual prototype ( Figure 2 ) Using 3D modeling tools and based on parametric modeling technology, it can quickly modify the geometric model through parameters based on the measured physical prototype geometry data, ensuring the consistency of the geometric model with the physical prototype structure.

[0069] Specifically, in one embodiment of the present application, the method for establishing the three-dimensional geometric model of the fuel injection system in S11 is as follows:

[0070] S111. Using a three-dimensional modeling tool and based on parametric modeling technology, establish a parametric three-dimensional model of the fuel injection system that can be quickly modified based on input data, and complete the establishment of the original geometric model.

[0071] S112. Import the measurement data of the physical prototype of the fuel injection system into the geometric model as parameters to complete the correction of the geometric structure and ensure the consistency of the geometric model with the physical prototype structure.

[0072] S12. The system model in the virtual prototype is established based on the system modeling tool.

[0073] Parameters such as part mass, cavity volume, and material data from the geometric model are imported into the system model. Initial operating conditions, such as the physical prototype's oil inlet and outlet pressures, ambient temperature, and oil quality data, are then input to complete the system model. The system model is then used to calculate pump-end pressure, device-end pressure, fuel injection volume, SAC chamber pressure, accumulator chamber pressure, and the speed of each moving part. Finally, the pump-end pressure, device-end pressure, and fuel injection volume calculated using the system model are compared with the relevant data from the physical prototype to refine the system model.

[0074] Specifically, in one embodiment of the present application, the system model establishment method in S12 is as follows:

[0075] S121. Based on the system modeling tool, complete the system modeling of the fuel injection system.

[0076] S122. Based on the geometric model, extract structure-related data and input it into the system model.

[0077] S123. The initial operating condition data measured by the physical prototype is transferred to the system model to complete the initial system modeling.

[0078] S124. Compare the pump-end pressure, device-end pressure, and fuel injection quantity calculated based on the system model with the measured data to correct the model.

[0079] S13. The fluid-structure interaction model in the virtual prototype consists of a structural model and a fluid model connected by a fluid-structure interaction tool. By analyzing the operating conditions of the fuel injection system, key components and flow paths that affect lifespan are finely modeled. Other non-contact components or flow paths are set as rigid bodies or divided into coarser meshes to reduce the computational scale. After completing the fluid-structure interaction model preprocessing, the SAC chamber pressure, accumulator chamber pressure, and speed of each moving part calculated by the system model are used as boundary conditions of the fluid-structure interaction model. The fluid-structure interaction model is imported to calculate the pump-end pressure, device-end pressure, and injection volume. The calculated results are then compared with those calculated by the system model, and the fluid-structure interaction model is modified based on the comparison results. After the fluid-structure interaction model is modified, the pump-end pressure, device-end pressure, and injection volume are used as boundary conditions of the fluid-structure interaction model to complete the calculation of contact pressure and slip distance between parts.

[0080] Specifically, in one embodiment of the present application, the fluid-structure coupling model modeling method in S13 is as follows:

[0081] S131. Based on the structural analysis tool, complete the establishment of the fuel injection system structural model.

[0082] S132. Based on the fluid analysis tool, complete the establishment of the fluid model of the fuel injection system.

[0083] S133. Use the fluid-structure coupling tool to connect the structural model and the fluid model to complete the construction of the fluid-structure coupling model.

[0084] S134. The oil inlet pressure, oil outlet pressure, and speed of moving parts calculated by the system model are imported as boundaries into the fluid-structure coupling model to complete the calculation of the pump-end pressure, the device-end pressure, and the fuel injection amount.

[0085] S135. Compare the pump-end pressure and the device-end pressure calculated by the fluid-solid coupling model with the corresponding data calculated by the system model to complete the correction of the fluid-solid coupling model.

[0086] S14. The life prediction model in the virtual prototype is based on Archard wear theory, and its theoretical formula is as follows:

[0087]

[0088] Where: dV represents the wear volume; d pIt represents the normal pressure between parts; d l It represents the relative sliding distance between parts; H represents the material hardness; K represents the wear coefficient.

[0089] Integrating the above formula, the total wear of the parts can be obtained, which is as follows:

[0090]

[0091] ω is the total wear amount, P is the contact surface positive pressure, V is the relative slip velocity, a, b, c are material constants, and H is the material hardness.

[0092] Based on the above theory, a life assessment model is established. The contact pressure and relative sliding distance between parts calculated by the fluid-solid coupling model are transferred to the life assessment model to complete the calculation of the wear amount and cumulative wear amount per unit time of the fuel injection system. The maximum allowable wear amount is determined based on experimental data and historical failure data to complete the life assessment of the fuel injection system.

[0093] Specifically, in one embodiment of the present application, the method for performing lifespan prediction based on the lifespan prediction model in S14 is as follows:

[0094] S141. Determine the maximum allowable wear based on fuel injection system experimental data and historical failure data.

[0095] S142. The contact pressure and sliding distance per unit cycle calculated by the fluid-solid coupling model, as well as the material parameters, are input into the life prediction model to calculate the wear of the fuel injection system per unit cycle, that is, the cumulative wear of the fuel injection system is calculated based on the life assessment model.

[0096] S143. When the accumulated wear of the fuel injection system reaches the maximum allowable wear, the product life is deemed to have expired and the life assessment is completed.

[0097] S15. The co-simulation model in the virtual prototype is built based on a multidisciplinary co-simulation tool. The geometric model, system model, fluid-structure interaction model, and life assessment model are connected through the multidisciplinary co-simulation tool to achieve effective data transfer between models, making the model closer to the physical prototype. The life assessment process based on this model is shown in Figure 3 The geometric model maps the model geometry to the physical prototype, the system model maps the environment to the physical prototype, the fluid-structure interaction model calculates component contact pressure and relative slip distance based on measured pump-end pressure, device-end pressure, and fuel injection volume, and the life assessment model assesses the life of the fuel injection system based on calculated wear values. By passing the physical prototype's pump-end pressure, device-end pressure, and fuel injection volume into the multidisciplinary co-simulation model, the fuel injection system's life prediction can be completed.

[0098] S16. Because the computational efficiency of the multidisciplinary joint simulation model is too low to meet the requirements for real-time mapping between virtual and physical prototypes in the digital twin model, a neural network is used to reduce the order of the multidisciplinary joint simulation model. This neural network model uses the ReLU function as the activation function, uses Categories_cossentropy to calculate the model loss, and uses the Adam algorithm as the gradient descent optimizer. The combined model is constructed using a CNN-LSTM network. The model is trained using the calculation results of the joint simulation model under different operating conditions and different geometric shapes and the actual measurement results as training data, with pump-end pressure, device-end pressure, and fuel injection volume as input, and wear volume as output. The model can complete real-time calculation of wear and real-time assessment of life based on the measured fuel system pump-end pressure, device-end pressure, and fuel injection volume, completing the construction of a virtual prototype that meets the requirements.

[0099] It can be seen that the above life assessment method based on the digital twin model proposes to establish a digital twin model of the fuel injection system, map the virtual prototype and physical prototype of the fuel injection system, and conduct real-time analysis and prediction of the wear of the fuel injection system parts, so as to more accurately predict the life of the fuel injection system.

Claims

1. A fuel injection system life prediction method based on a digital twin model, characterized in that: The method comprises the following steps: S1. Construct a digital twin model of the fuel injection system. The digital twin model consists of a real-time mapped physical prototype and a virtual prototype. The virtual prototype is a multidisciplinary co-simulation model composed of a geometric model, a system model, a fluid-structure interaction model, and a life assessment model, and is obtained through neural network order reduction. Specifically, the model includes: S11. Build a 3D geometric model of the fuel injection system based on parametric modeling technology; S12. Establish a system model based on system simulation analysis tools; S121. Complete the system modeling of the fuel injection system using the system modeling tool; including: S122. Based on the geometric model, extract structure-related data and input it into the system model; S123. The initial operating condition data measured by the physical prototype is transferred to the system model to complete the initial system modeling; S124. Compare the pump-end pressure, device-end pressure, and fuel injection amount calculated based on the system model with the measured data and modify the model; S13. Establish a fluid-structure coupling model based on structural analysis tools and fluid analysis tools; S14. Establish a fuel injection system life prediction model based on Archard theory; S15. Connect the data of the geometric model, system model, fluid-structure interaction model, and life assessment model using a co-simulation tool to build a co-simulation model for life prediction; including: S151. Using multidisciplinary co-simulation tools, connect the geometric model, system model, fluid-structure interaction model, and life assessment model to establish a multidisciplinary co-simulation model. S152. The pump-end pressure, device-end pressure, and fuel injection volume of the physical prototype are transferred to the multidisciplinary joint simulation model to complete the life prediction of the fuel injection system; S16. Using a CNN-LSTM neural network, reduce the order of the co-simulation model of the fuel injection system to establish a virtual prototype capable of rapidly responding to inputs. Specifically, using the calculation results of the co-simulation model under different operating conditions and geometric shapes as training data, with pump-end pressure, device-end pressure, and fuel injection volume as inputs, and wear volume as output, the CNN-LSTM neural network is trained to rapidly calculate the wear volume of the fuel injection system based on the pump-end pressure, device-end pressure, and fuel injection volume. This reduces the order of the co-simulation model of the fuel injection system and establishes a virtual prototype capable of rapidly responding to inputs. S2. derive the wear of the fuel injection system under the working state by using the virtual prototype simulation in S1; S3. Obtain the actual wear amount of the physical prototype by measuring; S4. Compare the measured values ​​of the physical prototype with the results of the virtual prototype simulation and modify the virtual prototype model of the fuel injection system; S5. The pump-end pressure, device-end pressure, and fuel injection volume measured in real time by the physical prototype are transmitted to the virtual prototype model of the fuel injection system, and a rapid prediction of the life of the physical prototype of the fuel injection system is completed.

2. The fuel injection system life prediction method based on digital twin model according to claim 1 is characterized in that: The method for establishing the 3D geometric model of the fuel injection system in S11 is as follows: S111. Using a 3D modeling tool and parametric modeling technology, a parametric 3D model of the fuel injection system is established that can be quickly modified based on input data, completing the establishment of the original geometric model; S112. Import the measurement data of the physical prototype of the fuel injection system into the geometric model as parameters to complete the correction of the geometric structure.

3. The fuel injection system life prediction method based on digital twin model according to claim 1 is characterized in that: The modeling method of the fluid-structure coupling model in S13 is as follows: S131. Based on structural analysis tools, complete the establishment of a fuel injection system structural model; S132. Based on the fluid analysis tool, complete the establishment of the fuel injection system fluid model; S133. Connect the structural model and the fluid model using the fluid-structure coupling tool to complete the construction of the fluid-structure coupling model; S134. The oil inlet pressure, oil outlet pressure, and speed conditions of the moving parts calculated by the system model are imported as boundaries into the fluid-structure coupling model to complete the calculation of the pump end pressure, the device end pressure, and the fuel injection amount; S135. Compare the pump-end pressure and the device-end pressure calculated by the fluid-solid coupling model with the corresponding data calculated by the system model to complete the correction of the fluid-solid coupling model.

4. The fuel injection system life prediction method based on digital twin model according to claim 1 is characterized in that: The method for life prediction based on the life prediction model in S14 is as follows: S141. Determine the maximum allowable wear based on fuel injection system experimental data and historical failure data; S142. The contact pressure and sliding distance per unit cycle calculated by the fluid-structure coupling model, as well as the material parameters, are input into the life prediction model to calculate the wear of the fuel injection system per unit cycle, that is, to calculate the cumulative wear of the fuel injection system based on the life assessment model; S143. When the accumulated wear of the fuel injection system reaches the maximum allowable wear, the product life is deemed to have expired and the life assessment is completed.

5. The fuel injection system life prediction method based on digital twin model according to claim 4 is characterized in that: The life prediction model in S14 is based on Archard wear theory, and the formula is as follows: ， in: is the wear volume; is the normal pressure between parts; is the relative sliding distance between parts; H is the material hardness; K is the wear coefficient; The total wear of the fuel injection system is calculated as follows: ， in, is the total wear amount, is the positive pressure on the contact surface, is the relative slip velocity, a, b, c are material constants.

6. An electronic device comprising: at least one processor; and a memory communicatively connected to at least one processor, wherein the memory stores a computer program that can be executed by the at least one processor, and when the computer program is executed by the at least one processor, it is used to enable the electronic device to execute the fuel injection system life prediction method based on the digital twin model according to any one of claims 1 to 5.

Images