Engine troubleshooting system based on digital twinning technology

Abstract

The invention provides an engine troubleshooting system based on a digital twinning technology, which comprises the steps of constructing a digital simulation model of an engine based on the digital twinning technology, constructing a maintenance judgment model, and simulating engine operation and fault data through the digital simulation model for fault judgment training, and the maintenance judgment model evaluates fault judgment training. In the embodiment, the digital simulation model of the engine is constructed through the digital twinning technology, all detectable parameters of the engine are synchronously displayed by the digital simulation model for reference of maintenance personnel and judgment of the position of a fault part, and the maintenance judgment model evaluates the fault position judgment time, the maintenance time and the like of the maintenance personnel. And the troubleshooting maintenance level of maintenance personnel is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin, and in particular to an engine fault troubleshooting system based on digital twin technology. Background Art

[0002] In 2002, Professor Dr. Michael Grieves of the University of Michigan first proposed the technical concept of Digital Twin, which is to monitor the real-time state of an object through a digital model. Due to the relatively low level of digital technology at that time, this technology did not develop in depth. With the improvement of technologies such as 3D modeling technology and big data technology, the concept of Digital Twin came back into people's sight in 2014. Simply put, digital twin is a virtual replica of a real physical system. A connection is established between the virtual body and the entity through data exchange, and through this connection, the real-time dynamics of the entity can be monitored.

[0003] In the field of engines, especially high-power density engines, due to their harsh application environment and the requirement to operate at high power for a long time, the service life and maintenance cycle of high-power density engines are much shorter than those in the civilian field. Even the service life and maintenance cycle of high-power density engines are calculated in motorcycle hours. In this case, relevant personnel need to have relatively high maintenance and fault diagnosis and exclusion capabilities to ensure the normal use of the engine in various environments. However, at the present stage, with the increase and replacement of various vehicles in our country, the rapidly increasing crew members of various types of vehicles do not have enough physical engines to train for various fault situations, and most of the maintenance experience is passed on orally, and there is still room for improvement in the comprehensive diagnosis and exclusion quality.

[0004] At the present stage, digital twin has been applied in the field of engines. For example, technologies such as CN117313313B and CN116971881B use digital twin technology to display the operating state of the engine in the engine field. In the above technologies, digital twin technology is mainly used only for display in the form of a smart screen. And the engine fault diagnosis method based on digital twin applied by Beijing Institute of Technology in CN116340848B can only diagnose components with sensor monitoring at the present stage, and the digital twin technology of components without sensors cannot be simulated, and the diagnosis of various engine faults cannot be realized. Summary of the Invention

[0005] In order to make up for the defects of the above digital twin technology in the field of engine fault diagnosis and exclusion, the present application proposes an engine fault troubleshooting system based on digital twin technology.

[0006] Its technical solution includes: The system includes an engine digital simulation model and a maintenance judgment model built based on digital twin technology. The digital simulation model simulates engine operation and fault data for fault diagnosis and troubleshooting training, and the maintenance judgment model evaluates the fault diagnosis and troubleshooting training. Among them, the process of building the digital simulation model includes: establishing a corresponding operation state model according to engine parameters; training a neural network based on historical fault data to form a fault simulation model; fitting the engine components in the operation state model with the engine components in the fault simulation model one by one to obtain the digital simulation model. Among them, the process of the maintenance judgment model evaluating the score of fault diagnosis and troubleshooting training includes: obtaining the diagnosis time and troubleshooting time of each type of fault in the historical fault data, forming a normal distribution curve according to the diagnosis time and troubleshooting time of the same type of fault respectively, obtaining the diagnosis threshold time and troubleshooting threshold time according to the normal distribution curve, and evaluating according to the diagnosis threshold time, troubleshooting threshold time and the fault diagnosis and troubleshooting training time.

[0007] On the basis of the above technology, further, the process of establishing a corresponding operation state model according to engine parameters includes building an explicit component model and a hidden component model. The explicit components include the components in the engine that directly obtain operation parameters, and the hidden components include the components that cannot obtain operation parameters but have had faults and are included in the historical fault data.

[0008] On the basis of the above technology, further, the engine parameters also include the sound data and vibration data in each operation state of the engine, and the historical fault data includes the sound and vibration data during engine operation in case of faults.

[0009] On the basis of the above technology, further, the diagnosis threshold time includes a qualified time and an excellent time. The qualified time is the time at the maximum value of the normal distribution curve, and the excellent time is the time at the first 10% node of the normal distribution curve.

[0010] On the basis of the above technology, further, the troubleshooting threshold time includes a qualified time and an excellent time. The qualified time is the time at the maximum value of the normal distribution curve, and the excellent time is the time at the first 10% node of the normal distribution curve.

[0011] On the basis of the above technology, further, after each fault diagnosis and troubleshooting training is completed, the historical fault data is collected and updated according to the fault diagnosis and troubleshooting training time.

[0012] On the basis of the above technology, further, the process of fitting the engine components in the operation state model with the engine components in the fault simulation model one by one includes fitting the explicit component model with the engine components in the fault simulation model one by one.

[0013] The engine fault troubleshooting system based on digital twin technology in this application constructs a digital simulation model of the engine based on digital twin technology. The engine components in the operating state model are fitted one by one with the engine components in the fault simulation model, so that the operating state model can simulate all monitorable parameters within the digital twin range. The fault simulation model can simulate the corresponding engine operating parameters according to different faulty components. The operating state model simulates the engine operating state based on the engine operating parameters given by the fault simulation model for maintenance personnel to judge and repair, improving the authenticity of the engine repair process. At the same time, it can score according to the performance of each vehicle group, select excellent maintenance experiences according to the scores to adjust the maintenance manual, and improve the fault judgment and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic flow chart of an embodiment of the present invention;

[0015] Figure 2 It is a schematic diagram of a normal distribution curve of an embodiment of the present invention;

[0016] Figure 3 It is a schematic diagram of a time curve of an embodiment of the present invention. SPECIFIC EMBODIMENTS

[0017] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0019] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected", and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations. In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application. It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations. It should also be understood that the term " / and" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0020] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0021] In one embodiment of the present application, the present application includes an engine fault troubleshooting system based on digital twin technology, which includes an engine digital simulation model and a maintenance judgment model constructed based on digital twin technology. The digital simulation model simulates the engine operation and fault data for fault diagnosis and troubleshooting training, and the maintenance judgment model evaluates the fault diagnosis and troubleshooting training. In this embodiment, the digital simulation model of the engine is constructed through digital twin technology, and all engine detectable parameters are synchronously displayed by the digital simulation model for maintenance personnel to refer to and judge the location of the faulty component. The maintenance judgment model evaluates the time for maintenance personnel to judge the fault location, maintenance time, etc., effectively improving the troubleshooting and maintenance level of maintenance personnel. In this embodiment, the process of constructing the digital simulation model includes: establishing a corresponding operating state model according to the engine parameters. Generally speaking, many components of existing engines are equipped with sensors for monitoring their own states, such as rotational speed, cylinder temperature, high-pressure fuel rail pressure, output power, etc. The parameters collected by the above sensors are the basis of the digital twin technology in this embodiment. The digital simulation model of the engine is constructed using the above sensor parameters to display the detectable component parameters of the engine in various operating states for maintenance personnel to refer to. During the simulation process of this embodiment, the parameters required for fault simulation are obtained based on the historical maintenance records of the physical engine. The recorded historical maintenance process is integrated into historical fault data, which records the faulty components of the engine and the operating data of the engine under fault conditions. The neural network is trained based on the historical fault data to form a fault simulation model. The fault simulation model can effectively simulate the operating parameters of the engine under different component fault conditions to achieve a realistic effect. In addition, since there are many engine components and only a small part of the components are detected by sensors, that is, the operating state model established based on digital twin technology can only display the operating states of some components. Therefore, it is necessary to fit the engine components in the operating state model with the engine components in the fault simulation model one by one to fully display the operating states of the engine components with detectable parameters, and at the same time, various component fault conditions can be fully simulated. The fitted model is used as the digital simulation model. This digital simulation model can fully display the parameters of all engine components with sensors, such as rotational speed, power, oil pressure, water temperature, oil temperature, lubricating oil state, transmission state, etc., and can also fully simulate the changes in the above displayable component parameters directly or indirectly affected after component faults.

[0022] Combined with Figure 2, the evaluation process of the maintenance judgment model in this embodiment for the fault diagnosis and exclusion training score includes: obtaining the diagnosis time and exclusion time of each type of fault in the historical fault data, forming normal distribution curves according to the diagnosis time and exclusion time of the same type of fault respectively, obtaining the diagnosis threshold time and the fault exclusion threshold time according to the normal distribution curves, and evaluating in combination with the fault diagnosis and exclusion training time. In this implementation plan, the maintenance judgment model aims to optimize the maintenance operation process and improve the maintenance operation efficiency. For this purpose, during the review process of the maintenance judgment model in this embodiment, the diagnosis time and exclusion time of each type of fault in the historical fault data are obtained, normal distribution curves are formed according to the diagnosis time and exclusion time of the same type of fault respectively, and by obtaining the maintenance time and maintenance process of the number of people in each time period, the relatively optimized maintenance process and relatively optimized maintenance operations are selected and incorporated into the training manual to improve the overall maintenance process. The relatively optimized maintenance process screening method in this implementation method includes using the maintenance process with the least time consumption during the fault exclusion process as the relatively optimized maintenance process; the relatively optimized maintenance operation screening method includes using the maintenance operation with the shortest time consumption under the same maintenance process as the optimized maintenance operation.

[0023] Based on the above-mentioned embodiment, further, the process of establishing the corresponding operating state model according to the engine parameters includes constructing an explicit component model and a hidden component model. The explicit components include the components that directly obtain the operating parameters in the engine, and the hidden components include the components that cannot obtain the operating parameters but have had faults and are included in the historical fault data. In this embodiment, the explicit components mainly refer to the components that can directly obtain parameters by sensors, such as the crankshaft, cylinder, water tank, transmission, etc. The hidden components refer to the components that cannot directly obtain the operating parameters, but have had faults and are included in the historical fault data, and can affect the engine. The digital simulation model simulation ability of this application includes the function of directly affecting the visualization parameters when the explicit components fail, and also includes the ability to indirectly affect the visualization parameters when the hidden components fail.

[0024] Based on the above-mentioned embodiment, further, the engine parameters also include the sound data and vibration data in each operating state of the engine, and the historical fault data includes the sound and vibration data during the operation of the engine under fault conditions. In this embodiment, in many cases, the sound and vibration states of the engine operation can be used as the basis for assisting in judging the source of the fault, such as cylinder scoring, surging, etc. Combining the sound data and vibration data can effectively improve the maintenance personnel's ability to judge the fault location.

[0025] Based on the above-mentioned one embodiment, further, the diagnostic threshold time includes a qualified time and an excellent time. The qualified time is the time at the maximum value of the normal distribution curve, and the excellent time is the time at the first 10% node of the normal distribution curve. Based on the above-mentioned one embodiment, further, the troubleshooting threshold time includes a qualified time and an excellent time. The qualified time is the time at the maximum value of the normal distribution curve, and the excellent time is the time at the first 10% node of the normal distribution curve. In this embodiment, setting the qualified time helps to evaluate the technical levels of all trainees, and setting the excellent time helps to screen out excellent trainees to extract experience.

[0026] Based on the above-mentioned one embodiment, further, after each fault diagnosis and troubleshooting training is completed, the historical fault data is collected and updated according to the fault diagnosis and troubleshooting training time. In this embodiment, collecting and updating the time data helps to determine whether the experience promotion and improvement in the diagnosis and repair process are reasonable. Combining Figure 3 The judgment process includes: obtaining the times of previous fault diagnosis and troubleshooting trainings in the same type of maintenance training as nodes, using the time used as the Y value, and the number of trainings as the X value to fit a two-dimensional curve. The fault diagnosis and troubleshooting training time includes the diagnostic threshold time and the troubleshooting threshold time. In this embodiment, the qualified time curve of the diagnostic threshold time, the excellent time curve of the diagnostic threshold time, the qualified time curve of the troubleshooting threshold time, and the excellent time curve of the troubleshooting threshold time are respectively fitted, and it is judged whether the time used for adjacent time nodes in each time curve is a decreasing trend. If so, it means that the experience promotion and improvement are reasonable, and if not, it means that the experience promotion this time is unreasonable. In this embodiment, the experience promotion for the qualified time curve can be used as basic experience. For example, if the qualified time curve of the diagnostic threshold time shows a decreasing trend in the time used, it means that the promotion of the diagnostic basic experience is reasonable and has a promoting effect on most maintenance personnel. If there is no decreasing trend in the time used, it means that the promotion of the diagnostic basic experience cannot take effect on most maintenance personnel, and this diagnostic experience is excluded. The experience promotion for the excellent time curve can be used as advanced experience. For example, if the excellent time curve of the diagnostic threshold time shows a decreasing trend in the time used, it means that the promotion of the diagnostic advanced experience is reasonable and has a further promoting effect on excellent maintenance personnel. If there is no decreasing trend in the time used, it means that the promotion of the diagnostic advanced experience cannot improve the level of excellent personnel, and this diagnostic experience is excluded.

[0027] Based on the above-mentioned one embodiment, further, the process of fitting the engine components in the operating state model with the engine components in the fault simulation model one by one includes fitting the explicit component model with the engine components in the fault simulation model one by one.

[0028] All or part of the processes in the method of the above embodiments can be implemented by a computer program to instruct relevant hardware. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the device / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0029] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0030] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0031] In the embodiments provided in this application, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device controller embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0032] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0033] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An engine fault troubleshooting system based on digital twin technology, characterized in that, It includes an engine digital simulation model and a maintenance judgment model built based on digital twin technology. The digital simulation model simulates engine operation and fault data for fault diagnosis and troubleshooting training, and the maintenance judgment model evaluates the fault diagnosis and troubleshooting training. Among them, the process of building the digital simulation model includes: establishing a corresponding operating state model according to engine parameters; training a neural network based on historical fault data to form a fault simulation model; fitting the engine components in the operating state model with the engine components in the fault simulation model one by one to obtain the digital simulation model. Among them, the process of the maintenance judgment model evaluating the score of fault diagnosis and troubleshooting training includes: obtaining the diagnosis time and troubleshooting time of each type of fault in the historical fault data, forming a normal distribution curve according to the diagnosis time and troubleshooting time of the same type of fault respectively, obtaining the diagnosis threshold time and troubleshooting threshold time according to the normal distribution curve, and evaluating according to the diagnosis threshold time, troubleshooting threshold time and the fault diagnosis and troubleshooting training time.

2. The system according to claim 1, characterized in that, The process of establishing a corresponding operating state model according to engine parameters includes building an explicit component model and a hidden component model. The explicit components include the components in the engine that directly obtain operating parameters, and the hidden components include the components that cannot obtain operating parameters but have had faults and are included in the historical fault data.

3. The system according to claim 1, wherein: The engine parameters also include the sound data and vibration data in each operating state of the engine, and the historical fault data includes the sound and vibration data during engine operation in case of faults.

4. The system according to claim 1, wherein The diagnosis threshold time includes a qualified time and an excellent time. The qualified time is the time at the maximum value of the normal distribution curve, and the excellent time is the time at the 10% node in front of the normal distribution curve.

5. The system according to claim 1, characterized in that, The troubleshooting threshold time includes a qualified time and an excellent time. The qualified time is the time at the maximum value of the normal distribution curve, and the excellent time is the time at the 10% node in front of the normal distribution curve.

6. The system according to claim 1, wherein: After each fault diagnosis and troubleshooting training is completed, the historical fault data is collected and updated according to the fault diagnosis and troubleshooting training time.

7. The system according to claim 2, wherein: The process of fitting the engine components in the operating state model with the engine components in the fault simulation model one by one includes fitting the explicit component model with the engine components in the fault simulation model one by one.

Images