CN115758867A - Fuel injection system service life prediction method based on digital twin model and electronic equipment - Google Patents
Fuel injection system service life prediction method based on digital twin model and electronic equipment Download PDFInfo
- Publication number
- CN115758867A CN115758867A CN202211374821.2A CN202211374821A CN115758867A CN 115758867 A CN115758867 A CN 115758867A CN 202211374821 A CN202211374821 A CN 202211374821A CN 115758867 A CN115758867 A CN 115758867A
- Authority
- CN
- China
- Prior art keywords
- model
- fuel injection
- injection system
- service life
- end pressure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention provides a service life rapid prediction method based on a digital twin model and electronic equipment, wherein a multidisciplinary joint simulation model consisting of a geometric model, a system model, a fluid-solid coupling model and a service life evaluation model is established, so that the service life of a fuel injection system is evaluated based on pump end pressure, device end pressure and fuel injection quantity; secondly, reducing the order of the multidisciplinary joint simulation model through a neural network to obtain a virtual prototype capable of quickly responding to input data; thirdly, finishing the correction of the virtual prototype based on the data of the physical prototype, realizing the mapping of the physical prototype and the virtual prototype and finishing the construction of the digital twin model; and finally, transmitting the actually measured pump end pressure, device end pressure and fuel injection quantity of the physical prototype into the virtual prototype to complete the real-time prediction of the service life of the physical prototype. The invention can predict the service life of the fuel injection system in real time based on the real-time running state of the fuel injection system.
Description
Technical Field
The invention belongs to the technical field of fuel injection, in particular relates to a service life evaluation technology based on a digital twin model, which is designed for a fuel injection system and is suitable for service life prediction of the fuel injection system in a product development stage and service life evaluation in an after-sales service stage.
Background
The fuel injection system is a core component of the engine, is called as the heart of the engine, bears the periodic high temperature and high pressure of a combustion chamber when in work, has very bad working environment, has important influence on whether a ship normally works and whether the emission meets the requirements of regulations, and needs to be replaced when the product state cannot meet the requirements of the emission of the ship. The fuel injection system has the advantages that poor fuel injection atomization can be caused when core components of the fuel injection system are abraded, the main reason for worsening the combustion condition of an engine is caused, and due to the fact that vulnerable precise parts of the fuel injection system do high-speed reciprocating motion in a closed space inside the fuel injection system, working states of the parts inside the fuel injection system and abrasion conditions of the parts cannot be effectively monitored through a directly-installed sensor, the fuel injection system cannot establish an accurate service life prediction model to predict the service life of the parts.
Because the service life of the fuel injection system is related to the safe operation of the engine, in order to ensure the operation reliability of the fuel injection system, the service life of the product can be judged only by carrying out long-time endurance test and continuously carrying out physical overhaul at the product design stage, and the development cycle of the product is greatly prolonged; and the reliable operation of equipment can only be ensured by setting a short overhaul period and an overhaul period in the service stage of the product, so that the later maintenance cost of the product is increased.
Disclosure of Invention
In order to accurately predict the service life of a fuel injection system, the invention provides a service life prediction method of the fuel injection system based on a digital twin model and electronic equipment.
The technical scheme of the invention is as follows
The invention provides a method for predicting the service life of a fuel injection system based on a digital twin model in a first aspect, which is mainly realized by the following steps:
s1, constructing a digital twin model of the fuel injection system, wherein the model is composed of a physical prototype and a virtual prototype which are mapped in real time, and the virtual prototype is obtained by reducing the order through a neural network and is a multidisciplinary combined simulation model composed of a geometric model, a system model, a fluid-solid coupling model and a life evaluation model.
And S2, simulating by using the virtual prototype in the S1 to obtain the abrasion loss of the fuel injection system in the working state.
And S3, obtaining the actual abrasion loss of the physical prototype through measurement.
And S4, comparing the measured value of the physical prototype with the simulation result of the virtual prototype, and correcting the virtual prototype model of the fuel injection system.
And S5, transmitting the pump end pressure, the device end pressure and the fuel injection quantity measured in real time by the physical prototype into a virtual prototype of the fuel injection system, and finishing the rapid prediction of the service life of the physical prototype of the fuel injection system.
According to the embodiment of the invention, the method for establishing the virtual prototype in the S1 comprises the following steps:
s11, establishing a three-dimensional geometric model of the fuel injection system based on a parametric modeling technology;
and S12, establishing a system model based on a system simulation analysis tool.
And S13, establishing a fluid-solid coupling model based on a structural analysis tool and a fluid analysis tool.
And S14, establishing a service life prediction model of the fuel injection system based on the Archard theory.
And S15, realizing data connection of a geometric model, a system model, a fluid-solid coupling model and a service life evaluation model based on a joint simulation tool, and constructing a service life prediction joint simulation model.
And S16, reducing the order of the fuel injection system combined simulation model based on the CNN-LSTM neural network, and establishing a virtual prototype which can quickly correspond according to input.
Specifically, the calculation results of the combined 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 quantity are used as input, the abrasion loss is used as output, the CNN-LSTM neural network is used for training, the abrasion loss of the fuel injection system is quickly calculated based on the pump end pressure, the device end pressure and the fuel injection quantity, the reduction of the combined simulation model of the fuel injection system is completed, and a virtual prototype capable of quickly responding according to the input is established.
According to the embodiment of the invention, the method for establishing the three-dimensional geometrical model of the fuel injection system in S11 comprises the following steps:
and S111, establishing a fuel injection system parameterized three-dimensional model based on input data by using a three-dimensional modeling tool and a parameterized modeling technology, and completing establishment of an original geometric model.
And S112, importing the metering data of the physical prototype of the fuel injection system as parameters into the geometric model to finish the correction of the geometric structure and ensure the structural consistency of the geometric model and the physical prototype.
According to the embodiment of the present invention, the system model establishing method in S12 is as follows:
and S121, completing system model modeling of the fuel injection system based on a system modeling tool.
And S122, extracting structure-related data and transmitting the structure-related data into a system model based on the geometric model.
And S123, transmitting the actually measured initial working condition data of the physical prototype into a system model to complete the modeling of the initial system model.
And S124, comparing the pump end pressure, the device end pressure and the fuel injection quantity calculated based on the system model with the actually measured data, and correcting the model.
According to the embodiment of the invention, the fluid-solid coupling model modeling method in S13 is as follows:
s131, establishing a structural model of the fuel injection system based on a structural analysis tool;
s132, establishing a fluid model of the fuel injection system based on a fluid analysis tool;
s133, connecting the structural model and the fluid model through a fluid-solid coupling tool to complete the construction of the fluid-solid coupling model;
s134, introducing conditions such as oil inlet pressure, oil outlet pressure and the speed of a moving part obtained through calculation of a system model into a fluid-solid coupling model as a boundary to complete calculation of pump end pressure, device end pressure and fuel injection quantity;
and S135, comparing the pump end pressure and the device end pressure calculated by the fluid-solid coupling model with corresponding data calculated by the system model to finish the correction of the fluid-solid coupling model.
According to the embodiment of the present invention, the method for predicting the life based on the life prediction model in S14 is as follows:
and S141, determining the maximum allowable abrasion loss based on the experimental data and the historical failure data of the fuel injection system.
S142, transmitting the contact pressure and the sliding distance in the unit period calculated by the fluid-solid coupling model and the material parameters into the service life prediction model, and calculating the wear of the fuel injection system in the unit period, namely calculating the accumulated wear of the fuel injection system based on the service life evaluation model;
and S143, when the accumulated abrasion loss of the fuel injection system reaches the maximum allowable abrasion loss, determining that the service life of the product is due, and finishing service life evaluation.
According to the embodiment of the invention, the life prediction model in S14 is established based on the archer wear theory, and the formula is as follows:
wherein: dV is the wear volume; d is a radical of p Is the normal pressure between the parts; d is a radical of l Is the relative sliding distance between the parts; h is the material hardness; k is the wear coefficient;
the total wear rate of the fuel injection system is formulated as:
wherein omega is total abrasion loss, P is positive pressure of contact surface, V is relative slip speed, and a, b and c are material constants.
Based on the above theory, a life evaluation model is established, the accumulated wear amount of the fuel injection system is calculated, and life evaluation is completed based on the maximum allowable wear amount.
According to the embodiment of the invention, the method for constructing the life prediction combined simulation model in the step S15 is as follows:
s151, connecting a geometric model, a system model, a fluid-solid coupling model and a service life evaluation model based on a multidisciplinary joint simulation tool to establish a multidisciplinary joint simulation model;
s152, transmitting the pump end pressure, the device end pressure and the fuel injection quantity of the physical prototype into a multidisciplinary combined simulation model to complete the service life prediction of the fuel injection system;
according to the embodiment of the invention, the fuel injection system digital twin model virtual prototype reduction method in S16 is as follows: the calculation results of the combined simulation models 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 quantity are used as input, the abrasion quantity is used as output, the CNN-LSTM neural network is used for training, the calculation of the abrasion quantity of the fuel injection system is rapidly completed based on the pump end pressure, the device end pressure and the fuel injection quantity, the reduction of the combined simulation model of the fuel injection system is completed, and a virtual prototype capable of rapidly responding according to the input is established.
The present invention also provides in another aspect an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program, when executed by the at least one processor, is operable to cause the electronic device to perform the digital twin model based fuel injection system life prediction method according to the first aspect above.
Compared with the prior art, the invention has at least the following beneficial effects:
the service life prediction method of the fuel injection system based on the digital twin model solves the problem that the service life of the fuel injection system cannot be accurately predicted, and realizes the correction of the digital twin model by utilizing the digital twin technology and comparing simulation data and actual measurement data of the pump end pressure, the device end pressure and the fuel injection quantity of the fuel injection system, so that the service life of the fuel injection system can be accurately predicted by the service life prediction method of the fuel injection system based on the digital twin model, and meanwhile, the service life prediction based on a real-time measurement result is realized by using the model order reduction technology.
The method can accurately and rapidly predict the service life of the fuel injection system, thereby predicting the replacement time of the fuel injection system more accurately, reducing the replacement caused by too much redundancy set in the change period and reducing the use cost of the fuel injection system.
The invention is suitable for the electric control monoblock pump, the common rail system, the gas engine and the dual-fuel engine.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
FIG. 1 is a schematic illustration of a digital twin model of a fuel injection system according to an embodiment of the present application;
FIG. 2 is an exemplary diagram of a parameterized model in an embodiment of the present application;
FIG. 3 is a flowchart illustrating life evaluation of a joint simulation model according to an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for 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 illustration purposes only and are not intended to limit the scope of the present application.
It should be understood that the various steps recited in the method embodiments of the present application may be performed in a different order and/or in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present application is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "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"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
As shown in FIG. 1, an exemplary embodiment of the present application provides a life prediction method of a fuel injection system based on a digital twin model, the method comprising the steps of:
s1, constructing a digital twin model of the fuel injection system, wherein the digital twin model is formed by a physical prototype and a virtual prototype which are mapped in real time, and the virtual prototype is obtained by reducing the order of a neural network through a multidisciplinary combined simulation model formed by a geometric model, a system model, a fluid-solid coupling model and a life evaluation model.
S2, transmitting the pump end pressure, the device end pressure and the fuel injection quantity of the physical prototype into the virtual prototype in the S1 to obtain the accumulated abrasion quantity of the fuel injection system in the working state.
And S3, acquiring the accumulated abrasion loss by measuring the mass difference before and after the physical prototype works.
And S4, comparing the measured value of the physical prototype with the simulation result of the virtual prototype, and correcting the virtual prototype model of the fuel injection system.
And S5, inputting the pump end pressure, the device end pressure and the fuel injection quantity measured by the physical prototype in real time into the virtual prototype of the fuel injection system to complete the real-time prediction of the service life of the physical prototype of the fuel injection system.
In an embodiment of the present application, a specific method for constructing the digital twin model is as follows:
s11, a geometric model (shown in figure 2) in the virtual prototype is built by using a three-dimensional modeling tool based on a parameterized modeling technology, and the geometric model can be corrected quickly through parameters based on actually measured geometric data of the physical prototype, so that the structural consistency of the geometric model and the physical prototype is ensured.
Specifically, in an embodiment of the present application, the method for establishing the three-dimensional geometric model of the fuel injection system in S11 is as follows:
and S111, establishing a fuel injection system parameterized three-dimensional model based on input data by using a three-dimensional modeling tool and a parameterized modeling technology, and completing establishment of an original geometric model.
And S112, importing the metering data of the physical prototype of the fuel injection system into the geometric model as parameters to finish the correction of the geometric structure and ensure the structural consistency of the geometric model and the physical prototype.
And S12, establishing a system model in the virtual prototype based on a system modeling tool.
Importing parameters such as part mass, inner cavity volume, material data and the like in the geometric model into the system model, and inputting initial working conditions such as oil inlet pressure, oil outlet pressure, environment temperature, oil product data and the like of the physical prototype to complete the establishment of the system model; and the calculation of pump end pressure, device end pressure, fuel injection quantity, SAC (sample consensus) cavity pressure, pressure accumulation cavity pressure and the speed of each moving part can be realized based on a system model. And finally, comparing the pump end pressure, the device end pressure, the fuel injection quantity and the related data of the physical prototype obtained by the calculation of the system model, and correcting the system model.
Specifically, in an embodiment of the present application, the system model establishing method in S12 is as follows:
and S121, completing system model modeling of the fuel injection system based on a system modeling tool.
And S122, extracting structure-related data and transmitting the structure-related data into a system model based on the geometric model.
And S123, transmitting the actually measured initial working condition data of the physical prototype into the system model to complete the modeling of the initial system model.
And S124, comparing the pump end pressure, the device end pressure and the fuel injection quantity calculated based on the system model with the actually measured data, and correcting the model.
S13, a fluid-solid coupling model in the virtual prototype is formed by a structure model and a fluid model which are connected through a fluid-solid coupling tool. The working condition of the fuel injection system is analyzed, key parts and flow passages influencing the service life are subjected to fine modeling, and other non-contact parts or flow passages are subjected to calculation scale reduction by setting as rigid bodies or dividing into thicker grids; after the fluid-solid coupling model pretreatment is completed, introducing the SAC cavity pressure, the pressure storage cavity pressure and the speed of each moving part calculated by the system model into the fluid-solid coupling model as boundary conditions of the fluid-solid coupling model, comparing the calculated pump end pressure, the calculated device end pressure and the calculated oil injection quantity with the calculated result of the system model, and correcting the fluid-solid coupling model based on the comparison result; and after the fluid-solid coupling model is corrected, the pump end pressure, the device end pressure and the fuel injection quantity are used as boundary conditions of the fluid-solid coupling model, and the calculation of the contact pressure and the sliding distance between the parts is completed.
Specifically, in an embodiment of the present application, the fluid-solid coupling model modeling method in S13 is as follows:
and S131, based on a structural analysis tool, completing the establishment of a structural model of the fuel injection system.
And S132, establishing a fluid model of the fuel injection system based on a fluid analysis tool.
And S133, connecting the structural model and the fluid model through a fluid-solid coupling tool to complete the construction of the fluid-solid coupling model.
S134, introducing conditions such as oil inlet pressure, oil outlet pressure and the speed of the moving part obtained through calculation of the system model into a fluid-solid coupling model as a boundary, and finishing calculation of pump end pressure, device end pressure and fuel injection quantity.
And S135, comparing the pump end pressure and the device end pressure calculated by the fluid-solid coupling model with corresponding data calculated by the system model to finish the correction of the fluid-solid coupling model.
S14, constructing a service life prediction model in the virtual prototype based on the Archard wear theory, wherein the theoretical formula is as follows:
wherein: dV denotes the wear volume; d p Normal pressure between the parts is indicated; d l The relative sliding distance between the parts is shown; h represents the hardness of the material; k denotes the wear coefficient.
By integrating the above equation, the total wear rate of the part can be obtained, which is as follows:
omega is total abrasion loss, P is positive pressure of a contact surface, V is relative slip speed, a, b and c are material constants, and H is material hardness.
Establishing a life evaluation model based on the theory, transmitting the contact pressure and the relative slip distance between the parts calculated by the fluid-solid coupling model into the life evaluation model, completing the calculation of the abrasion loss and the accumulated abrasion loss of the fuel injection system in unit time, and completing the life evaluation of the fuel injection system based on the maximum allowable abrasion loss determined by the experimental data and the historical failure data.
Specifically, in an embodiment of the present application, the method for predicting the life based on the life prediction model in S14 includes:
and S141, determining the maximum allowable abrasion loss based on the experimental data and the historical failure data of the fuel injection system.
And S142, transmitting the contact pressure and the sliding distance in the unit period calculated by the fluid-solid coupling model and the material parameters into the service life prediction model, and calculating the wear of the fuel injection system in the unit period, namely calculating the accumulated wear of the fuel injection system based on the service life evaluation model.
And S143, when the accumulated abrasion loss of the fuel injection system reaches the maximum allowable abrasion loss, determining that the service life of the product is due, and finishing service life evaluation.
S15, constructing a combined simulation model in the virtual prototype based on a multidisciplinary combined simulation tool, connecting a geometric model, a system model, a fluid-solid coupling model and a life evaluation model through the multidisciplinary combined simulation tool, realizing effective transmission of data among models, enabling the models to be closer to a physical prototype, wherein the life evaluation flow based on the models is shown in a figure 3, the geometric model realizes mapping of the model geometry and the physical prototype, the system model realizes mapping of an environment and the physical prototype, the fluid-solid coupling model realizes calculation of part contact pressure and relative sliding distance based on actually measured pump end pressure, device end pressure and fuel injection quantity, and the life evaluation model realizes life evaluation of a fuel injection system based on a calculated wear value. And (3) transmitting the pump end pressure, the device end pressure and the fuel injection quantity of the physical prototype into the multidisciplinary combined simulation model, so that the service life prediction of the fuel injection system can be completed.
And S16, because the calculation efficiency of the multidisciplinary joint simulation model is too low, the requirement of real-time mapping of a virtual prototype and a real prototype in the digital twin model cannot be met, and therefore the multidisciplinary joint simulation model is reduced by using a neural network. The neural network model uses a ReLU function as an activation function, uses Categories _ cosentcopy to calculate model loss, simultaneously uses an Adam algorithm as a gradient descent optimizer, uses a CNN-LSTM network to complete the construction of a combined model, uses the calculation results and the real object measurement results of combined simulation models with different working conditions and different geometric shapes as training data, uses pump end pressure, device end pressure and fuel injection quantity as input, uses abrasion quantity as output, trains the model, realizes the real-time calculation of abrasion and the real-time evaluation of service life of the model based on the actually measured pump end pressure, device end pressure and fuel injection quantity of a fuel system, and completes the construction of a virtual prototype meeting requirements.
Therefore, by adopting the service life evaluation method based on the digital twin model, the service life of the fuel injection system can be more accurately predicted by establishing the digital twin model of the fuel injection system, and mapping the virtual prototype and the physical prototype of the fuel injection system to analyze and predict the wear condition of the parts of the fuel injection system in real time.
Claims (10)
1. A method for digital twin model based fuel injection system life prediction, the method comprising the steps of:
s1, constructing a digital twin model of a fuel injection system, wherein the digital twin model is composed of a physical prototype and a virtual prototype which are mapped in real time, the virtual prototype is a multidisciplinary combined simulation model which is composed of a geometric model, a system model, a fluid-solid coupling model and a life evaluation model, and the digital twin model is obtained by reducing the order through a neural network;
s2, simulating by using the virtual prototype in the S1 to obtain the abrasion loss of the fuel injection system in the working state;
s3, obtaining the actual abrasion loss of the physical prototype through measurement;
s4, comparing the measured value of the physical prototype with the simulation result of the virtual prototype, and correcting the virtual prototype model of the fuel injection system;
and S5, transmitting the pump end pressure, the device end pressure and the fuel injection quantity measured in real time by the physical prototype into a virtual prototype model of the fuel injection system, and finishing the rapid prediction of the service life of the physical prototype of the fuel injection system.
2. The digital twins model-based fuel injection system life prediction method as claimed in claim 1, wherein the virtual prototype in S1 is established as follows:
s11, establishing a three-dimensional geometric model of the fuel injection system based on a parametric modeling technology;
and S12, establishing a system model based on a system simulation analysis tool.
S13, establishing a fluid-solid coupling model based on a structural analysis tool and a fluid analysis tool;
and S14, establishing a service life prediction model of the fuel injection system based on the Archard theory.
S15, realizing data connection of a geometric model, a system model, a fluid-solid coupling model and a service life evaluation model based on a combined simulation tool, and constructing a service life prediction combined simulation model;
and S16, reducing the order of the fuel injection system combined simulation model based on the CNN-LSTM neural network, and establishing a virtual prototype capable of quickly responding according to input.
3. The method for predicting the life of a fuel injection system based on the digital twin model according to claim 1, wherein the method for establishing the three-dimensional geometric model of the fuel injection system in S11 is as follows:
s111, establishing a fuel injection system parameterized three-dimensional model based on input data by using a three-dimensional modeling tool and a parameterized modeling technology, and completing establishment of an original geometric model;
and S112, importing the metering data of the physical prototype of the fuel injection system into the geometric model as parameters to finish the correction of the geometric structure.
4. The digital twin model-based fuel injection system life prediction method according to claim 1, characterized in that the system model establishment method in S12 is as follows:
s121, based on a system modeling tool, completing system model modeling of the fuel injection system;
s122, extracting structure related data and transmitting the structure related data into a system model based on the geometric model;
s123, transmitting the actually measured initial working condition data of the physical prototype into a system model to complete modeling of the initial system model;
and S124, comparing the pump end pressure, the device end pressure and the fuel injection quantity calculated based on the system model with the actually measured data, and correcting the model.
5. The digital twin model-based fuel injection system life prediction method according to claim 1, characterized in that the fluid-solid coupling model modeling method in S13 is as follows:
s131, establishing a structural model of the fuel injection system based on a structural analysis tool;
s132, establishing a fluid model of the fuel injection system based on a fluid analysis tool;
s133, connecting the structural model and the fluid model through a fluid-solid coupling tool to complete the construction of the fluid-solid coupling model;
s134, introducing conditions such as oil inlet pressure, oil outlet pressure and the speed of a moving part obtained through calculation of a system model into a fluid-solid coupling model as a boundary to complete calculation of pump end pressure, device end pressure and fuel injection quantity;
and S135, comparing the pump end pressure and the device end pressure calculated by the fluid-solid coupling model with corresponding data calculated by the system model to finish the correction of the fluid-solid coupling model.
6. The method for predicting the life of a fuel injection system based on a digital twin model according to claim 1, wherein the method for predicting the life based on the life prediction model in S14 is as follows:
and S141, determining the maximum allowable abrasion loss based on the experimental data and the historical failure data of the fuel injection system.
S142, transmitting the contact pressure and the sliding distance in the unit period calculated by the fluid-solid coupling model and the material parameters into the service life prediction model, and calculating the wear of the fuel injection system in the unit period, namely calculating the accumulated wear of the fuel injection system based on the service life evaluation model;
and S143, when the accumulated abrasion loss of the fuel injection system reaches the maximum allowable abrasion loss, determining that the service life of the product is due, and finishing service life evaluation.
7. The digital twin model-based fuel injection system life prediction method according to claim 6, characterized in that the life prediction model in S14 is established based on Archard' S wear theory, and the formula is as follows:
wherein: dV is the wear volume; d p Is the normal pressure between the parts; d l Is the relative sliding distance between the parts; h is the material hardness; k is the wear coefficient;
the total wear rate of the fuel injection system is formulated as:
wherein omega is total abrasion loss, P is positive pressure of contact surface, V is relative slip speed, and a, b and c are material constants.
8. The method for predicting the life of a fuel injection system based on a digital twin model according to claim 1, wherein the multidisciplinary joint simulation model establishing method in S15 is as follows:
s151, connecting a geometric model, a system model, a fluid-solid coupling model and a service life evaluation model based on a multidisciplinary joint simulation tool to establish a multidisciplinary joint simulation model;
s152, transmitting the pump end pressure, the device end pressure and the fuel injection quantity of the physical prototype into a multidisciplinary combined simulation model to complete the service life prediction of the fuel injection system.
9. The method for predicting the service life of the fuel injection system based on the digital twin model as claimed in claim 1, wherein the step of reducing the virtual prototype of the digital twin model of the fuel injection system in S16 is as follows:
the calculation results of the combined simulation models 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 quantity are used as input, the abrasion quantity is used as output, the CNN-LSTM neural network is used for training, the calculation of the abrasion quantity of the fuel injection system is rapidly completed based on the pump end pressure, the device end pressure and the fuel injection quantity, the reduction of the combined simulation model of the fuel injection system is completed, and a virtual prototype capable of rapidly responding according to the input is established.
10. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program, when executed by the at least one processor, for causing the electronic device to perform a digital twin model based fuel injection system life prediction method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211374821.2A CN115758867A (en) | 2022-11-04 | 2022-11-04 | Fuel injection system service life prediction method based on digital twin model and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211374821.2A CN115758867A (en) | 2022-11-04 | 2022-11-04 | Fuel injection system service life prediction method based on digital twin model and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115758867A true CN115758867A (en) | 2023-03-07 |
Family
ID=85356262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211374821.2A Pending CN115758867A (en) | 2022-11-04 | 2022-11-04 | Fuel injection system service life prediction method based on digital twin model and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115758867A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454530A (en) * | 2023-12-26 | 2024-01-26 | 天津天汽模志通车身科技有限公司 | Digital twinning-based automobile body part modeling and detecting method and system |
-
2022
- 2022-11-04 CN CN202211374821.2A patent/CN115758867A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117454530A (en) * | 2023-12-26 | 2024-01-26 | 天津天汽模志通车身科技有限公司 | Digital twinning-based automobile body part modeling and detecting method and system |
| CN117454530B (en) * | 2023-12-26 | 2024-03-26 | 天津天汽模志通车身科技有限公司 | Digital twinning-based automobile body part modeling and detecting method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106404403B (en) | Method and system for analysis of a turbomachine | |
| CN112507452A (en) | Digital twin modeling method for reliability of turbine blade of aircraft engine | |
| WO2018044507A1 (en) | Machine learning-aided model-based method for estimating gas turbine component life | |
| WO2013191593A1 (en) | Method and system for determining life consumption of a mechanical part | |
| CN103983453A (en) | Differentiating method of fault diagnosis of executing mechanism of aeroengine and sensor | |
| CN115758867A (en) | Fuel injection system service life prediction method based on digital twin model and electronic equipment | |
| CN107145641A (en) | Blade vibration fatigue Probabilistic Life Prediction method | |
| CN111881495A (en) | Prestress steel structure safety assessment method based on digital twinning | |
| CN111310314B (en) | Method and system for determining service life of electromechanical device based on artificial intelligence | |
| CN112364567A (en) | Residual life prediction method based on consistency check of similarity of degraded tracks | |
| CN112861425A (en) | Method for detecting performance state of double-shaft gas turbine by combining mechanism and neural network | |
| CN107657083A (en) | A kind of intellectual water meter is in Line synthesis error calibration method | |
| CN115081484A (en) | Aircraft engine sensor fault diagnosis method based on CRJ-OSELM algorithm | |
| CN115114822A (en) | Method and system for estimating residual service life of underwater throttle valve based on digital twinning | |
| CN114154360B (en) | Multi-physical field probability digital twin modeling method for high-pressure internal gear pump | |
| CN111222095A (en) | Gross error discrimination method, device and system in dam deformation monitoring | |
| CN113343482A (en) | Vehicle power system monitoring and management method based on digital twins | |
| CN112966399A (en) | Pulse tube refrigerator working condition prediction method and system based on machine learning | |
| CN110083933A (en) | A kind of corrosion pipeline Bayes's degradation analysis method considering stochastic effects | |
| CN114936494A (en) | Data physical fusion driven high-temperature component reliability evaluation method and system | |
| CN110288265B (en) | Multi-element key quality characteristic coupling analysis method based on modularization | |
| CN115640652B (en) | Method for predicting residual life of axial plunger pump | |
| CN112130468A (en) | Device and method for simulating temperature of outer surface of high-pressure rotor of nuclear turbine | |
| CN112365022A (en) | Engine bearing fault prediction method based on multiple stages | |
| Li et al. | Simulation of Reliability Prediction Based on Multiple Factors for Spinning Machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |