Numerical control machine tool fault propagation model construction method based on digital twinning

Abstract

The invention belongs to the field of numerical control machine tools, and particularly discloses a numerical control machine tool fault propagation model construction method based on digital twinning, which comprises the following steps: arranging a peripheral sensor, and collecting related operation information of a numerical control machine tool through the peripheral sensor; constructing a numerical control machine tool state information database for storing numerical control machine tool state information; coupling the constructed multi-system coupling model and the multi-physics field coupling model to establish a multi-system-multi-physics field digital twinborn model, and performing real-time mapping on the multi-system-multi-physics field digital twinborn model by using the state information of the numerical control machine tool in the database; and fault simulation is carried out through the multi-system-multi-physics field digital twin model, a fault propagation path of the numerical control machine tool is determined, and a fault propagation model is established. The numerical control machine tool fault propagation model is constructed, when the numerical control machine tool breaks down, fault traceability analysis is conducted in time through real-time data by means of the model, the fault diagnosis and maintenance efficiency of the numerical control machine tool is effectively improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of CNC machine tools, and specifically relates to a method for constructing a CNC machine tool fault propagation model based on digital twins. Background Art

[0002] CNC machine tools are complex systems that combine mechanical, electrical, thermal, and hydraulic components. The strong coupling of their structures leads to complex fault mechanisms and fault path propagation. At the same time, the number of fault samples in the actual working process is usually extremely rare. Once a machine tool fails, it is difficult to find the cause of the failure in time due to the unclear fault propagation path, which will lead to long maintenance time and high costs, resulting in serious economic losses. Therefore, analyzing the fault propagation path of CNC machine tools can timely and effectively repair and maintain CNC machine tools, reduce maintenance costs, and improve operating efficiency.

[0003] At present, the research on the fault propagation path of CNC machine tools mainly includes qualitative analysis based on expert knowledge and data-driven analysis. Qualitative analysis based on expert knowledge is highly subjective and inefficient, while data-driven analysis ignores the fault mechanism of CNC machine tools, making it difficult to qualitatively analyze fault propagation and unable to meet the development needs of CNC machine tool maintenance at this stage. Summary of the invention

[0004] To solve the above problems, the present invention provides a method for constructing a CNC machine tool fault propagation model based on digital twins. By constructing a CNC machine tool fault propagation model, when a CNC machine tool fails, the model is used to promptly perform fault tracing analysis through real-time data, thereby effectively improving the CNC machine tool fault diagnosis and repair and maintenance efficiency and reducing repair and maintenance costs.

[0005] The technical solution of the present invention is a method for constructing a fault propagation model of a CNC machine tool based on digital twins, comprising the following steps: Arrange peripheral sensors to collect relevant operation information of CNC machine tools through peripheral sensors; Constructing a CNC machine tool status information database for storing CNC machine tool status information, wherein the CNC machine tool status information includes operation information collected by peripheral sensors; Construct a multi-system coupling model and a multi-physics field coupling model respectively, and couple the multi-system coupling model and the multi-physics field coupling model to establish a multi-system-multi-physics field digital twin model, and use the CNC machine tool status information in the database to perform real-time mapping of the multi-system-multi-physics field digital twin model; Fault simulation is performed through the multi-system-multi-physics field digital twin model to determine the fault propagation path of the CNC machine tool and establish a fault propagation model.

[0006] In an optional implementation, after the peripheral sensor is arranged, the following steps are also included: Get the operation information collected by peripheral sensors; Obtain the health status indicators of CNC machine tools in the same period; Analyze the correlation between the operation information collected by peripheral sensors and the health status indicators of CNC machine tools in the same period; The layout of peripheral sensors is optimized based on the correlation analysis results.

[0007] In an optional embodiment, the correlation between the operation information collected by the peripheral sensor and the health status index of the CNC machine tool in the same period is analyzed, specifically including calculating the correlation coefficient by the following formula: ,

[0008] In the formula, is the standard deviation of the operation information samples collected by the peripheral sensors, is the sample standard deviation of the CNC machine tool health status index, It is the sample covariance of the operation information samples collected by the peripheral sensors and the health status index samples of the CNC machine tool.

[0009] In an optional implementation, constructing a CNC machine tool status information database specifically includes: Obtain the CNC machine tool operation information collected by the peripheral sensor, recorded as data set S; Acquire the first target operation information from the numerical control system of the numerical control machine tool, which is recorded as data set N; Obtain the second target operation information from the servo system of the CNC machine tool, which is recorded as data set M; Obtain static information data of the CNC machine tool, recorded as data set I; wherein the static information data includes geometric dimensions, system structure, physical properties, and model; Constructing a database of CNC machine tool status information .

[0010] In an optional implementation, constructing a multi-system coupling model specifically includes: Select physical parameters for each subsystem, including the mechanical system, electrical system, and hydraulic system of the CNC machine tool; Based on the selected physical parameters, digital description models of each subsystem are constructed using the Modelica language; According to the coupling mechanism between the subsystems, the digital description models of the subsystems are connected to form a multi-system coupling model, which is expressed as ,in Represents the nth subsystem.

[0011] In an optional implementation, constructing a multi-physics field coupling model specifically includes: Select the target physical field, which includes vibration and heat generated by the load; A multi-physics coupling model is constructed according to the selected target physical field, which is expressed as ,in represents the mth physical field.

[0012] In an optional implementation, the multi-system coupling model and the multi-physics field coupling model are coupled to establish a multi-system-multi-physics field digital twin model, and the multi-system-multi-physics field digital twin model is mapped in real time using the CNC machine tool status information in the database, specifically including: Adopt FMI standard to encapsulate multi-system coupling model and multi-physics coupling model into FMU model with the same platform interface; Set the corresponding physical parameter interaction interface to realize the interaction between the multi-system coupling model and the multi-physics field coupling model, and obtain the multi-system-multi-physics field digital twin model, which is expressed as ; Encapsulate the multi-system and multi-physics digital twin model and leave a data interface; The database inputs the target CNC machine tool status information into the multi-system-multi-physics field digital twin model through the data interface, updates the multi-system-multi-physics field digital twin model, and realizes real-time mapping of the multi-system-multi-physics field digital twin model.

[0013] In an optional implementation, a multi-system-multi-physics field digital twin model is used to perform fault simulation, determine the fault propagation path of the CNC machine tool, and establish a fault propagation model, specifically including: According to the expert experience and knowledge, a fault propagation directed graph of CNC machine tools is qualitatively established. The qualitative fault propagation directed graph uses nodes and directed edges to represent variables and potential qualitative causal relationships between variables. Nodes represent the parts of CNC machine tools, and the node set is , directed edges represent the fault propagation relationship between CNC machine tool parts, and the directed edge set is , then the qualitative fault propagation directed graph is expressed as ; According to the qualitative fault propagation directed graph , for multi-system-multi-physics digital twin models Perform fault injection to obtain status information of various CNC machine tool components under different types of fault injection; Based on the state information under fault injection, the KNN method is used to quantitatively analyze the fault causal relationship between the components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and establish a fault propagation model.

[0014] In an optional implementation, based on the state information under fault injection, the KNN method is used to quantitatively analyze the causal relationship between the faults of various components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and establish a fault propagation model, which specifically includes: Step 1, assume and Faulty nodes and The i-th sampling point set, the corresponding data vectors are and ,but right The prediction performance of can be expressed by the following distance formula:

[0015] In the formula, represents the prediction performance between nodes, is the K value of the KNN method; Step 2, The self-prediction performance of is expressed by the following formula,

[0016] Step 3, after Q iterations, we get:

[0017] In the formula, It means that after Q iterations, right The prediction performance of , Q is the number of iterations; Step 4, then the node and The causal relationship is expressed as:

[0018] In the formula, express and The causal relationship value of , then it means is the dependent variable, is the result variable, otherwise, is the dependent variable, is the outcome variable; Step 5, calculate the causal relationship between any two nodes through steps 1 to 4, obtain the quantitative analysis of the fault causal relationship between the components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and obtain the fault propagation model.

[0019] The method for constructing a CNC machine tool fault propagation model based on digital twins provided by the present invention has the following beneficial effects compared with the prior art: by arranging peripheral sensors to collect operation data, and constructing a database for storing CNC machine tool status information, a multi-system-multi-physical field digital twin model is constructed at the same time, and data twins are realized based on the status information in the database, which can reflect the changes in physical properties during operation and improve the model fidelity. Fault simulation is performed based on the multi-system-multi-physical field digital twin model to realize quantitative analysis of the fault propagation path. When a CNC machine tool fails, the model is used to promptly perform fault tracing analysis through real-time data, thereby effectively improving the efficiency of CNC machine tool fault diagnosis and repair and maintenance, and reducing repair and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flow chart of a method for constructing a fault propagation model of a CNC machine tool based on digital twins provided in an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of the process principle of a specific embodiment of a method for constructing a fault propagation model of a CNC machine tool based on digital twins provided by the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0025] The key terms appearing in the present invention are explained below.

[0026] FMI: Functional Mock-up Interface, is an international open software standard that provides a unified model interface for hybrid simulation between simulation software.

[0027] FMU: Functional Mock-up Units, or functional model units, is a model standard that is independent of the development environment As a key enabling technology for intelligent manufacturing, digital twin (DT) has been increasingly used in the field of CNC machine tools in recent years. By building a CNC machine and integrating the large amount of data generated by the digital twin model with the real-time monitoring data of the CNC machine tool, interactive feedback, data fusion and analysis of the digital space and the physical space can be achieved. The high-fidelity digital twin model can analyze the full life cycle status of the CNC machine tool and provide a solution for the fault propagation path analysis of the CNC machine tool.

[0028] In view of the current problem that it is difficult to qualitatively analyze fault propagation and cannot meet the current development needs of CNC machine tool repair and maintenance, this embodiment provides a method for constructing a CNC machine tool fault propagation model based on digital twins. By constructing a CNC machine tool fault propagation model, when a CNC machine tool fails, the model is used to promptly perform fault tracing analysis through real-time data, thereby effectively improving the efficiency of CNC machine tool fault diagnosis and repair and maintenance, and reducing repair and maintenance costs.

[0029] Figure 1 is a flow chart of a method for constructing a fault propagation model of a CNC machine tool based on digital twins provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes the following steps.

[0030] S1, arrange peripheral sensors and collect relevant operation information of CNC machine tools through peripheral sensors.

[0031] This embodiment installs external sensors according to the mechanical structure characteristics of the CNC machine tool, analyzes the correlation between the sensor data and the health status of the CNC machine tool, determines whether the measuring point is the optimal measuring point based on the correlation, and formulates a sensor monitoring plan that best reflects the health status of the CNC machine tool without affecting the processing status of the CNC machine tool.

[0032] S2, constructing a CNC machine tool status information database for storing CNC machine tool status information, wherein the CNC machine tool status information includes operation information collected by peripheral sensors.

[0033] This embodiment obtains relevant information of CNC machine tools based on the developed sensor monitoring scheme and CNC system, builds a CNC machine tool status information database, and realizes the storage and call of multi-dimensional historical data and real-time data of CNC machine tools.

[0034] S3, construct a multi-system coupling model and a multi-physics field coupling model respectively, and couple the multi-system coupling model and the multi-physics field coupling model to establish a multi-system-multi-physics field digital twin model, and use the CNC machine tool status information in the database to perform real-time mapping of the multi-system-multi-physics field digital twin model.

[0035] This embodiment constructs a multi-domain model and a multi-physical field model of a CNC machine tool respectively, and performs joint simulation. The two types of models interact with each other through a common interface to construct a multi-domain and multi-physical field digital twin model of a CNC machine tool. The real-time dynamic data of the CNC machine tool status information database is used to realize real-time mapping of the digital twin model and the physical system of the CNC machine tool.

[0036] S4, conduct fault simulation through multi-system-multi-physics field digital twin model, determine the fault propagation path of CNC machine tools, and establish a fault propagation model.

[0037] This embodiment analyzes the traditional failure modes of CNC machine tools, and qualitatively establishes a directed graph of CNC machine tool fault propagation based on expert experience and knowledge; fault simulation is performed through a digital twin model, and the KNN method is introduced based on the directed graph to quantitatively analyze the cause-effect relationship between the faults of various components of the CNC machine tools, clarify the fault propagation path of the CNC machine tools, and establish a fault propagation model.

[0038] In order to further understand the present invention, a specific embodiment is provided below to further describe the present invention in detail. Figure 2 The figure is a schematic diagram of the process principle of this specific embodiment. This specific embodiment first arranges sensor measuring points, analyzes the correlation between mechanical characteristics such as CNC machine tool processing accuracy and measuring point data, optimizes measuring points, and establishes a sensor monitoring solution for CNC machine tools; at the same time, a CNC machine tool status information database is constructed to store dynamic and static information of CNC machine tools; and a multi-domain-multi-physical field coupled digital twin model of CNC machine tools is constructed, and the interactive mapping of the digital twin model and the physical system is realized through the real-time data stored in the database; finally, the fault mode of the CNC machine tools is analyzed, and a directed graph (Directed Acyclic Graph, DAG) is used to qualitatively establish a CNC machine tool fault propagation directed graph based on expert experience and knowledge; the digital twin model is used to perform fault simulation to obtain CNC machine tool fault data, and the K nearest neighbors (KNN) method is introduced to quantitatively analyze and obtain a CNC machine tool fault propagation model.

[0039] SS1, sensor monitoring and measurement point optimization for CNC machine tools.

[0040] For most existing CNC machine tools, it is difficult to directly obtain data directly related to faults such as vibration and noise, so it is necessary to install external sensors for collection. First, analyze the mechanical structure characteristics of the CNC machine tool, and design the sensor wiring and installation position without affecting the normal operation of the CNC machine tool. Secondly, use the correlation analysis method to determine the correlation between the collected information and the machine tool health status indicators (machine tool self-monitoring data), and optimize the sensor layout position based on the correlation, which specifically includes the following steps.

[0041] Step 1: Obtain the operation information collected by the peripheral sensor.

[0042] Step 2: Obtain the health status indicators of the CNC machine tools in the same period.

[0043] Step 3: Analyze the correlation between the operation information collected by the peripheral sensors and the health status indicators of the CNC machine tools in the same period.

[0044] The correlation coefficient is calculated by the following formula ,

[0045] In the formula, is the standard deviation of the operation information samples collected by the peripheral sensors, is the sample standard deviation of the CNC machine tool health status index, It is the sample covariance of the operation information samples collected by the peripheral sensors and the health status index samples of the CNC machine tool.

[0046] Step 4: Optimize the layout of the peripheral sensors according to the correlation analysis results.

[0047] In this embodiment, The closer it is to -1, the negative correlation between the measuring point and the operating status is; the closer it is to 1, the positive correlation between the measuring point and the operating status of the CNC machine tool is; the closer it is to 0, the worse the correlation between the measuring point and the operating status of the CNC machine tool is. The value of is used to adjust and optimize the measuring points and formulate the optimal sensor monitoring plan. For example, when there is a negative correlation, the measuring point position is adjusted so that the measuring point is positively correlated with the operating status of the CNC machine tool.

[0048] SS2, CNC machine tool data acquisition and storage.

[0049] Step 1: Obtain the CNC machine tool operation information collected by the peripheral sensor, which is recorded as data set S.

[0050] Step 2: Acquire the first target operation information from the numerical control system of the numerical control machine tool, which is recorded as data set N.

[0051] Step 3: Acquire the second target operation information from the servo system of the CNC machine tool, which is recorded as data set M.

[0052] In this embodiment, the CNC machine tool can use the CNC system and servo system to collect information such as current and voltage. Therefore, the dynamic data of the CNC machine tool is collected through external sensors, the CNC system, and the servo system. The obtained data sets are represented by S, N, and M respectively, including vibration, rotation speed, displacement, feed speed, noise, current, voltage, etc.

[0053] Step 4, obtaining static information data of the CNC machine tool, recorded as data set I; the static information data includes geometric dimensions, system structure, physical properties, and model.

[0054] It should be noted that static information data is obtained through machine tool design drawings, on-site surveys and other methods.

[0055] Step 5: Build a CNC machine status information database .

[0056] SS3, construction of multi-system and multi-physics digital twin model for CNC machine tools.

[0057] Step 1: Construct a multi-system coupling model.

[0058] Step 1.1, select physical parameters for each subsystem, including the mechanical system, electrical system, and hydraulic system of the CNC machine tool.

[0059] Step 1.2, based on the selected physical parameters, construct digital description models of each subsystem using the Modelica language.

[0060] Step 1.3, according to the coupling mechanism between the subsystems, the digital description models of the subsystems are connected to form a multi-system coupling model, which is expressed as ,in Represents the nth subsystem.

[0061] A CNC machine tool is a complex electromechanical device coupled with multiple subsystems such as a mechanical system, an electrical system, and a hydraulic system. In this embodiment, appropriate physical parameters are selected, and mathematical description models of each subsystem are constructed using the Modelica language. The subsystems are connected according to the coupling mechanism between the subsystems to form a multi-system coupled digital twin model of the CNC machine tool.

[0062] Step 2: Build a multi-physics coupling model.

[0063] Step 2.1, select the target physics field, which includes the vibration generated by the load.

[0064] Step 2.2, construct a multi-physics coupling model based on the selected target physical field, expressed as ,in represents the mth physical field.

[0065] The multi-system coupling model expresses the geometric motion, mechanical control and other dimensions of CNC machine tools. For the physical performance dimension, it is expressed by constructing a multi-physics field coupling model. During the operation of CNC machine tools, they are affected by loads and impacts, which will cause vibrations and heat generation. Therefore, a multi-physics field coupling model of CNC machine tools is constructed.

[0066] Step 3: Couple the multi-system coupling model and the multi-physics field coupling model to establish a multi-system-multi-physics field digital twin model, and use the CNC machine tool status information in the database to perform real-time mapping of the multi-system-multi-physics field digital twin model.

[0067] Step 3.1: Use the FMI standard to encapsulate the multi-system coupling model and the multi-physics field coupling model into an FMU model with the same platform interface.

[0068] Step 3.2, set the corresponding physical parameter interaction interface to realize the interaction between the multi-system coupling model and the multi-physics field coupling model, and obtain the multi-system-multi-physics field digital twin model, which is expressed as .

[0069] Step 3.3, encapsulate the multi-system-multi-physics field digital twin model and reserve a data interface.

[0070] This embodiment adopts the FMI (Functional Mockup Interface) standard to encapsulate the above two models into an FMU (Functional Mock-up Units) model with a unified platform interface, and sets the corresponding physical parameter interaction interface (such as machine tool speed, feed speed, etc.) according to needs to realize the interaction between the two models, and finally obtain a multi-system-multi-physical field coupled digital twin model that can characterize the physical performance and motion relationship of CNC machine tools.

[0071] In step 3.4, the database inputs the target CNC machine tool status information into the multi-system-multi-physics field digital twin model through the data interface, updates the multi-system-multi-physics field digital twin model, and realizes real-time mapping of the multi-system-multi-physics field digital twin model.

[0072] Encapsulate the constructed digital twin model of the CNC machine tool, leave relevant data interfaces, and input dynamic data information such as speed, displacement, feed speed, etc. in the database D into the digital twin model , update the model and realize real-time mapping of the model from multiple dimensions such as geometry, physics, behavior, and rules.

[0073] SS4, Construction of fault propagation model for CNC machine tools.

[0074] Step 1: Based on expert experience and knowledge, a directed graph of fault propagation of CNC machine tools is qualitatively established.

[0075] This step implements qualitative analysis of fault propagation of CNC machine tools. In this embodiment, based on expert experience and knowledge, various fault modes of CNC machine tools and fault correlations between various systems of CNC machine tools are analyzed to model the fault propagation process. The qualitative fault propagation directed graph uses nodes and directed edges to represent variables and potential qualitative causal relationships between variables, respectively. Nodes represent parts of CNC machine tools (such as spindle bearings, shafts, etc.), and the node set is , directed edges represent the fault propagation relationship between CNC machine tool parts, and the directed edge set is , then the qualitative fault propagation directed graph is expressed as .

[0076] Step 2: Based on the qualitative fault propagation directed graph , for multi-system-multi-physics digital twin models Perform fault injection to obtain the status information of each CNC machine tool component under different types of fault injection.

[0077] This step implements fault injection into the digital twin model. Due to the complex mechanical structure and various fault modes of CNC machine tools, it is difficult to obtain effective fault data of CNC machines. , for the constructed Perform fault injection. As the fault is injected, the digital twin model shows the operating status under different fault modes. According to the visualization characteristics of the digital twin model, analyze each system fault, determine the signal characteristics of other system components when a fault is injected into a certain system component, and collect relevant variable sets.

[0078] Step 3: Based on the state information under fault injection, the KNN method is used to quantitatively analyze the fault causal relationship between the various components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and establish a fault propagation model.

[0079] This step realizes the quantitative analysis of fault propagation in CNC machine tools. It is a directed graph drawn using expert experience and knowledge, which has a certain degree of subjectivity. In order to further clarify the causal relationship between the faults of various system components of CNC machine tools, the digital twin data injected by faults and the monitoring data of database D are used to introduce the KNN method to further clarify the causal relationship between various components when the fault occurs and realize the quantitative analysis of the fault propagation path. It specifically includes the following steps.

[0080] Assumptions and Faulty nodes and The i-th sampling point set, the corresponding data vectors are and ,but right The prediction performance of can be expressed by the following distance formula:

[0081] In the formula, represents the prediction performance between nodes, is the K value of the KNN method.

[0082] The self-prediction performance of is expressed by the following formula,

[0083] After Q iterations, we get:

[0084] In the formula, It means that after Q iterations, right The prediction performance of , Q is the number of iterations.

[0085] Then the node and The causal relationship is expressed as:

[0086] In the formula, express and The causal relationship value of , then it means is the dependent variable, is the result variable, otherwise, is the dependent variable, is the outcome variable.

[0087] Through the above steps, the causal relationship between any two nodes is calculated, the fault causal relationship between the various components of the CNC machine tool is quantitatively analyzed, the fault propagation path of the CNC machine tool is determined, and the fault propagation model is obtained.

[0088] Through the above steps, this embodiment obtains an accurate fault propagation directed graph model for CNC machine tools. When a fault occurs in a CNC machine tool, reasoning is performed based on the fault propagation directed graph model to help the staff effectively find the source of the fault, repair and eliminate the fault in time, and reduce maintenance costs.

[0089] The above disclosure is only a preferred embodiment of the present invention, but the present invention is not limited thereto. Any non-creative changes that can be thought of by a person skilled in the art, as well as several improvements and modifications made without departing from the principle of the present invention, should fall within the protection scope of the present invention.

Claims

1. A method for constructing a fault propagation model for CNC machine tools based on digital twins, characterized in that: The following steps are involved: Arrange peripheral sensors to collect relevant operation information of CNC machine tools through peripheral sensors; Constructing a CNC machine tool status information database for storing CNC machine tool status information, wherein the CNC machine tool status information includes operation information collected by peripheral sensors; Construct a multi-system coupling model and a multi-physics field coupling model respectively, and couple the multi-system coupling model and the multi-physics field coupling model to establish a multi-system-multi-physics field digital twin model, and use the CNC machine tool status information in the database to perform real-time mapping of the multi-system-multi-physics field digital twin model; Fault simulation is performed through the multi-system-multi-physics field digital twin model to determine the fault propagation path of the CNC machine tool and establish a fault propagation model.

2. The method for constructing a fault propagation model of a CNC machine tool based on digital twin according to claim 1, characterized in that: After arranging the peripheral sensors, the following steps are also included: Obtain operation information collected by peripheral sensors; Obtain the health status indicators of CNC machine tools in the same period; Analyze the correlation between the operation information collected by peripheral sensors and the health status indicators of CNC machine tools in the same period; The layout of peripheral sensors is optimized based on the correlation analysis results.

3. The method for constructing a fault propagation model of a CNC machine tool based on digital twin according to claim 2, characterized in that: Analyze the correlation between the operating information collected by the peripheral sensors and the health status indicators of the CNC machine tools in the same period, including calculating the correlation coefficient through the following formula , In the formula, is the standard deviation of the operation information samples collected by the peripheral sensors, is the sample standard deviation of the CNC machine tool health status index, It is the sample covariance of the operation information samples collected by the peripheral sensors and the health status index samples of the CNC machine tool.

4. The method for constructing a fault propagation model of a CNC machine tool based on digital twin according to claim 1, characterized in that: Construct a CNC machine tool status information database, including: Obtain the CNC machine tool operation information collected by the peripheral sensor, recorded as data set S; Acquire the first target operation information from the numerical control system of the numerical control machine tool, which is recorded as data set N; Obtain the second target operation information from the servo system of the CNC machine tool, which is recorded as data set M; Obtain static information data of CNC machine tools, recorded as data set I; wherein the static information data includes geometric dimensions, system structure, physical properties, and model; Constructing a database of CNC machine tool status information .

5. The method for constructing a fault propagation model of a CNC machine tool based on digital twin according to claim 1, characterized in that: Construct a multi-system coupling model, including: Select physical parameters for each subsystem, including the mechanical system, electrical system, and hydraulic system of the CNC machine tool; Based on the selected physical parameters, the digital description models of each subsystem are constructed using the Modelica language; According to the coupling mechanism between the subsystems, the digital description models of the subsystems are connected to form a multi-system coupling model, which is expressed as ,in Represents the nth subsystem.

6. The method for constructing a fault propagation model of a CNC machine tool based on digital twin according to claim 5, characterized in that: Construct a multi-physics coupling model, including: Select the target physical field, which includes vibration and heat generated by the load; A multi-physics coupling model is constructed according to the selected target physical field, which is expressed as ,in represents the mth physical field.

7. The method for constructing a fault propagation model for a CNC machine tool based on digital twin according to claim 6, characterized in that: The multi-system coupling model and the multi-physics field coupling model are coupled to establish a multi-system-multi-physics field digital twin model, and the CNC machine tool status information in the database is used to map the multi-system-multi-physics field digital twin model in real time, including: Adopt FMI standard to encapsulate multi-system coupling model and multi-physics coupling model into FMU model with the same platform interface; Set the corresponding physical parameter interaction interface to realize the interaction between the multi-system coupling model and the multi-physics field coupling model, and obtain the multi-system-multi-physics field digital twin model, which is expressed as ; Encapsulate the multi-system and multi-physics digital twin model and leave a data interface; The database inputs the target CNC machine tool status information into the multi-system-multi-physics field digital twin model through the data interface, updates the multi-system-multi-physics field digital twin model, and realizes real-time mapping of the multi-system-multi-physics field digital twin model.

8. The method for constructing a fault propagation model for a CNC machine tool based on digital twins according to claim 7, characterized in that: Through the multi-system-multi-physics field digital twin model, fault simulation is carried out to determine the fault propagation path of the CNC machine tool and establish a fault propagation model, including: According to the expert experience and knowledge, a fault propagation directed graph of CNC machine tools is qualitatively established. The qualitative fault propagation directed graph uses nodes and directed edges to represent variables and potential qualitative causal relationships between variables. Nodes represent the parts of CNC machine tools, and the node set is , directed edges represent the fault propagation relationship between CNC machine tool parts, and the directed edge set is , then the qualitative fault propagation directed graph is expressed as ; According to the qualitative fault propagation directed graph , for multi-system-multi-physics digital twin models Perform fault injection to obtain status information of various CNC machine tool components under different types of fault injection; Based on the state information under fault injection, the KNN method is used to quantitatively analyze the fault causal relationship between the various components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and establish a fault propagation model.

9. The method for constructing a fault propagation model for a CNC machine tool based on digital twin according to claim 8, characterized in that: Based on the state information under fault injection, the KNN method is used to quantitatively analyze the causal relationship between the faults of various components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and establish a fault propagation model, including: Step 1, assume and Faulty nodes and The i-th sampling point set, the corresponding data vectors are and ,but right The prediction performance of can be expressed by the following distance formula: In the formula, represents the prediction performance between nodes, is the K value of the KNN method; Step 2, The self-prediction performance of is expressed by the following formula, Step 3, after Q iterations, we get: In the formula, It means that after Q iterations, right The prediction performance of , Q is the number of iterations; Step 4, then the node and The causal relationship is expressed as: In the formula, express and The causal relationship value of , then it means is the dependent variable, is the result variable, otherwise, is the dependent variable, is the outcome variable; Step 5, calculate the causal relationship between any two nodes through steps 1 to 4, obtain the quantitative analysis of the fault causal relationship between the components of the CNC machine tool, determine the fault propagation path of the CNC machine tool, and obtain the fault propagation model.

Images