Fast reflector fault diagnosis method based on digital twinning
By building a digital twin of the fast reflector and using a deep learning fault diagnosis model, the rapid and accurate diagnosis of fast reflector failures is achieved, solving the problems of time-consuming and low accuracy in traditional methods, and reducing maintenance costs and risks.
Patent Information
- Application Number
- CN202411964659.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-04-25
AI Technical Summary
Traditional fault diagnosis methods take a long time and have low accuracy, making it difficult to effectively solve the fault diagnosis problem of fast reflectors in extreme environments.
The rapid reflector fault diagnosis method based on digital twins is used to build a digital twin by obtaining entity information data, monitoring the operating status in real time and using deep learning fault diagnosis models for analysis, identifying potential or existing faults and providing repair measures.
It improves the efficiency and accuracy of fault diagnosis, solves the problems of time-consuming and low accuracy in traditional methods, realizes accurate diagnosis and predictive maintenance, and reduces maintenance costs and risks.
Smart Images
Figure CN119884871A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of fault diagnosis, and in particular relates to a fast reflector fault diagnosis method based on digital twins. Background Art
[0002] With the rapid development of laser communications, astronomical observations, adaptive optical systems, laser weapons and other fields, the demand for beam control accuracy is growing. As a key component in these systems, fast reflectors usually work under extreme or complex environmental conditions, such as large temperature changes and strong vibration interference. These environmental factors pose severe challenges to the performance and stability of fast reflectors. Therefore, fault diagnosis technology has become an important part of ensuring the stable operation of fast reflectors. Traditional fault diagnosis methods often rely on manual experience or simple test tools, and there are problems such as time-consuming and labor-intensive diagnostic process and poor diagnostic accuracy. Summary of the invention
[0003] The purpose of the present invention is to provide a rapid mirror fault diagnosis method based on digital twins to solve the technical problems of long time consumption and low accuracy existing in traditional fault diagnosis methods.
[0004] To achieve the above object, the present invention adopts the following technical solution:
[0005] A rapid reflector fault diagnosis method based on digital twins, comprising: acquiring information data of a rapid reflector entity, and constructing a rapid reflector digital twin based on the information data of the rapid reflector entity; monitoring the operation status of the rapid reflector entity in real time and collecting real-time data and sending it to the rapid reflector digital twin; in the rapid reflector digital twin, using a deep learning-based fault diagnosis model to analyze the real-time data, and to identify potential or existing faults in the entity operation, and determine the cause of the fault; and providing fault repair measures according to the cause of the fault.
[0006] A rapid reflector fault diagnosis system based on digital twins, comprising: a construction unit, used to obtain information data of a rapid reflector entity, and to construct a rapid reflector digital twin based on the information data of the rapid reflector entity; a monitoring unit, used to monitor the operating status of the rapid reflector entity in real time and collect real-time data and send it to the rapid reflector digital twin; an analysis and judgment unit, used to analyze the real-time data in the rapid reflector digital twin using a deep learning-based fault diagnosis model, and to judge and identify potential or existing faults in the entity operation, and determine the cause of the fault; and a result unit, used to provide fault repair measures according to the cause of the fault.
[0007] A computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the above-mentioned digital twin-based rapid reflector fault diagnosis method when running.
[0008] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the digital twin-based rapid reflector fault diagnosis method through the computer program.
[0009] In the present invention, information data of a rapid reflector entity is obtained, and a rapid reflector digital twin is constructed based on the information data of the rapid reflector entity; the operation status of the rapid reflector entity is monitored in real time and real-time data is collected and sent to the rapid reflector digital twin; in the rapid reflector digital twin, a deep learning-based fault diagnosis model is used to analyze the real-time data, and potential or existing faults in the entity operation are judged and identified to determine the cause of the fault; fault repair measures are given according to the cause of the fault, thereby achieving the improvement of fault diagnosis efficiency and the improvement of fault diagnosis accuracy by establishing a rapid reflector digital twin and a fault diagnosis model, and solving the technical problems of long time consumption and low accuracy in traditional fault diagnosis methods. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 It is a flowchart of a rapid reflector fault diagnosis method based on digital twin in an embodiment of the present invention;
[0011] Figure 2 It is a schematic diagram of an implementation flow of a rapid reflector fault diagnosis method based on digital twin in an embodiment of the present invention;
[0012] Figure 3 is a structural schematic diagram of a rapid reflector fault diagnosis system based on digital twin in an embodiment of the present invention;
[0013] Figure 4 It is a structural schematic diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION
[0014] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and claims. It should be noted that the drawings are all in very simplified form and are not in precise proportions, and are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.
[0015] It should be noted that, in order to clearly explain the content of the present invention, the present invention specifically cites multiple embodiments to further illustrate different implementations of the present invention, wherein the multiple embodiments are enumerated rather than exhaustive. In addition, for the sake of brevity of explanation, the contents mentioned in the previous embodiments are often omitted in the subsequent embodiments. Therefore, the contents not mentioned in the subsequent embodiments can refer to the previous embodiments accordingly.
[0016] Example 1
[0017] A fast mirror fault diagnosis method based on digital twin, such as Figure 1 As shown, the method includes:
[0018] S102, acquiring information data of a rapid reflector entity, and constructing a rapid reflector digital twin based on the information data of the rapid reflector entity;
[0019] S104, monitoring the operating status of the rapid reflector entity in real time and collecting real-time data to send to the rapid reflector digital twin;
[0020] S106, in the fast mirror digital twin, using a deep learning-based fault diagnosis model to analyze real-time data, and identify potential or existing faults in the entity operation to determine the cause of the fault;
[0021] S108, providing fault repair measures according to the cause of the fault.
[0022] Digital twin fault diagnosis firstly realizes real-time monitoring of the operating status of the fast reflector, timely discovers potential faults, and prevents faults from occurring. Secondly, it has accurate fault diagnosis capabilities, combines data analysis and model analysis, deeply summarizes the mechanism of fault occurrence, traces back to the root cause of the fault, and provides targeted solutions. Therefore, by accurately constructing a digital twin fault diagnosis model for the fast reflector, it is possible to provide solutions for different fast reflector faults, and achieve the purpose of accurate diagnosis, predictive maintenance, and cost reduction and efficiency improvement.
[0023] As an optional implementation, after providing the fault repair measures, it also includes: verifying the repair measures in the fast reflector digital twin.
[0024] As an optional implementation, after providing fault repair measures, it also includes: after repairing the rapid reflector entity according to the repair measures, the operating status of the repaired rapid reflector entity is fed back to the rapid reflector digital twin, and the fault diagnosis model is iteratively optimized.
[0025] Specifically, the rapid mirror fault diagnosis method based on digital twin is not limited to the following when implemented: Figure 2 As shown, the following steps are included:
[0026] S1, obtaining relevant information of the fast reflector entity, including the reflector, driving elements, sensors, etc.;
[0027] S2, building a digital twin of the fast reflector, including structural model, electrical model, and motion model;
[0028] S3, real-time data monitoring and collection, real-time monitoring of the operating status of the fast reflector entity and updating the data to the digital twin;
[0029] S4, fault diagnosis and analysis, analyzes real-time data based on deep learning models in the digital twin to identify fault modes and causes;
[0030] S5, generate maintenance suggestions, put forward fault maintenance suggestions and handle the fault according to the fault details provided by the digital twin model;
[0031] S6, closed-loop feedback and optimization, feeds back the actual fault handling results and the physical operating status of the fast reflector to the digital twin model and iteratively optimizes the model.
[0032] As an optional implementation manner, obtaining information data of the fast reflector entity includes: obtaining reflector surface parameters, drive element parameters, angle sensor parameters, overall structure parameters and control parameters.
[0033] It is not limited to systematically collecting relevant information about the fast reflector entity, covering key parameters such as reflector surface type, drive component performance, angle sensor performance, etc. The specific data collected is not limited to include:
[0034] Mirror surface parameters, including but not limited to mirror material, effective working surface diameter, reflectivity, surface finish, surface deviation, laser damage threshold, etc.;
[0035] Driver element parameters, including but not limited to driving force, travel range, bandwidth, response speed, resolution, power consumption and efficiency;
[0036] Angle sensor parameters, including but not limited to measurement range, resolution, accuracy, response time, supply voltage and current, operating temperature range, repeatability, etc.;
[0037] Overall structural parameters, including but not limited to overall size, weight, materials, etc.;
[0038] Control parameters include, but are not limited to, control algorithms and related parameters in specific control algorithms.
[0039] As an optional implementation manner, constructing a digital twin of a fast reflector includes: constructing a structural model, an electrical model, a motion model, and a fault diagnosis model of the fast reflector entity.
[0040] Specifically, the establishment of the structural model of the rapid reflector entity is not limited to drawing the structural model of the rapid reflector in proportion according to the collected structural and material related information, and leaving an interface for interaction with other model data;
[0041] The establishment of the electrical model of the fast reflector entity is not limited to selecting electronic components and establishing electrical connections to form the electrical model of the fast reflector according to the received electrical related information, and leaving an interface for interacting with other model data;
[0042] The establishment of the motion model of the fast reflector entity is not limited to connecting the structural model and the electrical model of the fast reflector through a data interface. In combination with the collected control parameter related information, the motion model of the fast reflector entity is established based on the finite element method to achieve the reproduction of the actual motion state of the fast reflector entity.
[0043] Establishment of a fault diagnosis model for a fast reflector entity is not limited to establishing a fault diagnosis model based on deep learning, which is used to analyze the output data of the motion model to realize the fault diagnosis function.
[0044] As an optional implementation, a fault diagnosis model is constructed, including: constructing a fault signal processing layer, performing batch normalization processing by combining a single-dimensional convolution layer and a pooling layer; constructing a fault signal diagnosis layer, analyzing and calculating the input feature information by combining long and short-term memory units of multiple residual network structures, and establishing a connection between the motion state and the fault phenomenon; constructing a fault signal classification layer, classifying the fault signal based on an extreme learning machine, and determining the fault category and cause; constructing a maintenance method output layer, and determining the maintenance measures based on the least squares calculation method according to the feature information output by the fault signal classification layer.
[0045] Specifically, the fault diagnosis model based on deep learning mainly includes the following structure:
[0046] The fault signal processing layer mainly realizes batch normalization processing by combining the single-dimensional convolution layer and the pooling layer, which can extract feature information while avoiding overfitting.
[0047] The fault signal diagnosis layer mainly analyzes and calculates the input feature information through the combination of long and short-term memory units of multiple residual network structures, and establishes the connection between the motion state and the fault phenomenon;
[0048] The fault signal classification layer mainly classifies the fault signal based on the extreme learning machine method to determine the fault type and cause;
[0049] The maintenance method output layer mainly gives the final maintenance method based on the feature information output by the fault classification layer and the least squares calculation method.
[0050] As an optional implementation, the long short-term memory units of the multiple residual network structures include four structures: a forget gate, an input gate, a memory gate and an output gate.
[0051] The fault signal diagnosis layer of the long short-term memory unit based on the residual network structure mainly includes four structures: forget gate, input gate, memory gate and output gate.
[0052] The preferred model of the forget gate in the fault signal diagnosis layer of the long short-term memory unit based on the residual network structure is not limited to the following formula:
[0053] f t =σ(W f [h t-1 ,x t ]+b f ) (1)
[0054] Among them, f t is the output of the forget gate at time t, h t-1 is the hidden state of the previous memory unit, x t is the current input, σ is the sigmoid function, W f and b f Used as a linear transformation before the sigmoid function.
[0055] The input gate in the fault signal diagnosis layer of the long short-term memory unit based on the residual network structure mainly determines how much new information is added to the memory unit, which mainly includes two steps: calculating the memory decay coefficient i t and calculate the learned memory content D t , the preferred model is shown as follows:
[0056]
[0057] The memory gate can be updated using the outputs of the forget gate and the input gate. The preferred update model is shown below:
[0058] C t =f t C t-1 +i t D t (3)
[0059] Determine the output o based on the hidden state of the memory unit t , multiply it by the memory unit processed by the tanh function, and finally get the output information of the output gate. The preferred model is shown in the following formula:
[0060]
[0061] As an optional implementation, the fault diagnosis model is iteratively optimized, including: taking the fault diagnosis evaluation function as a standard, the fault diagnosis model is iteratively optimized.
[0062] As an optional implementation, the fault diagnosis model is iteratively optimized based on the fault diagnosis evaluation function, including: when the error value calculated by the fault diagnosis evaluation function is within a preset range, stopping the iteration to obtain an optimized fault diagnosis model.
[0063] In the iterative optimization of the relevant model parameters, it is necessary to use the designed fault diagnosis evaluation function as the standard for iterative optimization. The preferred evaluation function is shown in the following formula:
[0064]
[0065] Among them, a is the accuracy of fault diagnosis, and b is the recall rate of fault diagnosis. When the error value calculated by the digital twin fault diagnosis method using the evaluation function is within the set allowable range, the iteration is considered to be completed.
[0066] In the embodiment of the present application, by establishing a digital twin of the rapid reflector and a fault diagnosis model, the fault diagnosis efficiency is improved while the fault diagnosis accuracy is improved, thereby successfully achieving cost reduction and efficiency improvement; by using the fault warning function in the digital twin rapid reflector diagnosis method, the maintenance cost and risk of the rapid reflector in actual use can be reduced, effectively avoiding the losses caused by sudden failure of the rapid reflector in actual application.
[0067] Example 2
[0068] A fast mirror fault diagnosis system based on digital twin, such as Figure 3 As shown, the system includes:
[0069] A construction unit 302 is used to obtain information data of a rapid reflector entity, and to construct a rapid reflector digital twin based on the information data of the rapid reflector entity;
[0070] A monitoring unit 304 is used to monitor the operating status of the fast reflector entity in real time and collect real-time data and send it to the fast reflector digital twin;
[0071] An analysis and judgment unit 306 is used to analyze real-time data in the fast reflector digital twin using a deep learning-based fault diagnosis model, and to identify potential or existing faults in the entity operation and determine the cause of the fault;
[0072] The result unit 308 is used to provide fault repair measures according to the cause of the fault.
[0073] Optionally, the above-mentioned rapid reflector fault diagnosis system based on digital twin also includes a verification unit, which is used to verify the repair measures in the rapid reflector digital twin after the fault repair measures are given.
[0074] Optionally, the above-mentioned rapid reflector fault diagnosis system based on digital twin also includes an iterative optimization unit, which is used to, after giving fault repair measures, repair the rapid reflector entity according to the repair measures, and then feed back the operating status of the repaired rapid reflector entity to the rapid reflector digital twin, so as to iteratively optimize the fault diagnosis model.
[0075] Optionally, the construction unit 302 constructs a digital twin of the rapid reflector, including: constructing a structural model, an electrical model, a motion model, and a fault diagnosis model of the rapid reflector entity.
[0076] Optionally, the construction unit 302 constructs a fault diagnosis model, including: constructing a fault signal processing layer, performing batch normalization processing by combining a single-dimensional convolution layer and a pooling layer; constructing a fault signal diagnosis layer, analyzing and calculating the input feature information through the combination of long and short-term memory units of multiple residual network structures, and establishing a connection between the motion state and the fault phenomenon; constructing a fault signal classification layer, classifying the fault signal based on an extreme learning machine, and determining the fault category and cause; constructing a maintenance method output layer, and determining the maintenance measures based on the least squares calculation method according to the feature information output by the fault signal classification layer.
[0077] Optionally, the above-mentioned construction unit 302 has multiple long short-term memory units of residual network structure, including four structures: a forget gate, an input gate, a memory gate and an output gate.
[0078] Optionally, the iterative optimization unit performs iterative optimization on the fault diagnosis model, including: performing iterative optimization on the fault diagnosis model based on a fault diagnosis evaluation function as a standard.
[0079] Optionally, the iterative optimization unit iteratively optimizes the fault diagnosis model based on the fault diagnosis evaluation function, including: when the error value calculated by the fault diagnosis evaluation function is within a preset range, stopping the iteration to obtain an optimized fault diagnosis model.
[0080] Optionally, the construction unit 302 obtains information data of the fast reflector entity, including: obtaining reflector surface parameters, drive element parameters, angle sensor parameters, overall structure parameters and control parameters.
[0081] In the embodiment of the present application, by establishing a digital twin of the rapid reflector and a fault diagnosis model, the fault diagnosis efficiency is improved while the fault diagnosis accuracy is improved, thereby successfully achieving cost reduction and efficiency improvement; by using the fault warning function in the digital twin rapid reflector diagnosis method, the maintenance cost and risk of the rapid reflector in actual use can be reduced, effectively avoiding the losses caused by sudden failure of the rapid reflector in actual application.
[0082] Example 3
[0083] Another aspect of the embodiments of the present invention further provides an electronic device for implementing the above-mentioned fast reflector fault diagnosis method based on digital twin, such as Figure 4 As shown, the electronic device is not limited to being a terminal device or server in the system. The electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a rapid mirror fault diagnosis method based on digital twins at the logical level. Of course, in addition to software implementations, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0084] The network interface, processor and memory can be connected to each other through a bus system. The above bus can be divided into an address bus, a data bus, a control bus, etc.
[0085] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor.
[0086] The processor is used to execute the program stored in the memory and specifically perform the steps in any of the above method embodiments. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit of the processor or the instructions in the form of software.
[0087] Example 4
[0088] Another aspect of the embodiments of the present invention provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional embodiments of the above-mentioned fast reflector fault diagnosis method based on digital twins. The computer program is configured to execute the steps of any of the above-mentioned method embodiments when running.
[0089] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-readable storage media containing computer-usable program code.
[0090] In addition, for the above-mentioned specific implementation of the system, since it is basically similar to the method implementation, the description is relatively simple, and the relevant parts can be referred to the partial description of the method implementation. Moreover, it should be noted that in each module of the system of the present application, the components therein are logically divided according to the functions to be implemented, but the present application is not limited thereto, and the components can be re-divided or combined as needed.
[0091] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between it and other embodiments.
[0092] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the specific order or sequential order shown in the process depicted in the drawings is not necessarily required to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0093] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A fast reflector fault diagnosis method based on digital twin, characterized in that: include: Acquire information data of a rapid reflector entity, and construct a rapid reflector digital twin based on the information data of the rapid reflector entity; Monitor the running status of the fast reflector entity in real time and collect real-time data to send to the fast reflector digital twin; In the fast mirror digital twin, a deep learning-based fault diagnosis model is used to analyze real-time data, identify potential or existing faults in the entity operation, and determine the cause of the fault; Provide fault repair measures based on the cause of the fault.
2. The fast reflector fault diagnosis method based on digital twin according to claim 1, characterized in that: After giving the fault repair measures, it also includes: Verification of maintenance measures in the digital twin of the fast-reflector.
3. The fast reflector fault diagnosis method based on digital twin according to claim 1, characterized in that: After giving the fault repair measures, it also includes: After the rapid reflector entity is repaired according to the maintenance measures, the operating status of the repaired rapid reflector entity is fed back to the rapid reflector digital twin, and the fault diagnosis model is iteratively optimized.
4. The fast reflector fault diagnosis method based on digital twin according to claim 1, characterized in that: Build a fast mirror digital twin, including: Construct the structural model, electrical model, motion model and fault diagnosis model of the fast reflector entity.
5. The fast reflector fault diagnosis method based on digital twin according to claim 4, characterized in that: Build a fault diagnosis model, including: Construct a fault signal processing layer and perform batch normalization by combining a single-dimensional convolution layer and a pooling layer; Construct a fault signal diagnosis layer, analyze and calculate the input feature information through the combination of long and short-term memory units of multiple residual network structures, and establish the connection between the motion state and the fault phenomenon; Construct a fault signal classification layer, classify fault signals based on extreme learning machines, and determine the fault type and cause; Construct the maintenance method output layer, and determine the maintenance measures based on the least squares calculation method according to the feature information output by the fault signal classification layer.
6. The fast reflector fault diagnosis method based on digital twin according to claim 5, characterized in that: The long short-term memory units of multiple residual network structures include four structures: forget gate, input gate, memory gate and output gate.
7. The fast reflector fault diagnosis method based on digital twin according to claim 3, characterized in that: Iteratively optimize the fault diagnosis model, including: Taking the fault diagnosis evaluation function as the standard, the fault diagnosis model is iteratively optimized.
8. The fast reflector fault diagnosis method based on digital twin according to claim 7, characterized in that: Based on the fault diagnosis evaluation function, the fault diagnosis model is iteratively optimized, including: When the error value calculated by the fault diagnosis evaluation function is within a preset range, the iteration is stopped to obtain an optimized fault diagnosis model.
9. The fast reflector fault diagnosis method based on digital twin according to claim 1, characterized in that: Get the information data of the fast reflector entity, including: Obtain the reflector surface parameters, drive element parameters, angle sensor parameters, overall structure parameters and control parameters.
10. A fast reflector fault diagnosis system based on digital twin, characterized in that: include: A construction unit, used for acquiring information data of a rapid reflector entity, and constructing a rapid reflector digital twin based on the information data of the rapid reflector entity; A monitoring unit, used to monitor the operating status of the rapid reflector entity in real time and collect real-time data and send it to the rapid reflector digital twin; An analysis and judgment unit is used to analyze real-time data in the digital twin of the fast reflector using a deep learning-based fault diagnosis model, and to identify potential or existing faults in the operation of the entity and determine the cause of the fault; The result unit is used to provide fault repair measures according to the cause of the fault.