A precision part machining monitoring system and method based on digital twinning

Abstract

The application provides a precision part machining monitoring system and method based on digital twinning, relates to the technical field of machining monitoring, collects machining tool data, constructs an initial digital twin body according to the machining tool data, determines tool pre-wear data through the initial digital twin body, compares the tool wear data and the tool pre-wear data, generates a damage resistance correction index, dynamically corrects the initial digital twin body based on the damage resistance correction index, and obtains a corrected digital twin body; the tool pre-damage index is obtained according to the corrected digital twin body and machining instructions, the confidence loss amount of the tool is determined according to the tool pre-damage index, the machining control strategy is determined through the confidence loss amount and each loss threshold value, and the target precision part is processed through the machining control strategy. The application can construct a self-optimized digital twin body, realizes accurate prediction and monitoring of tool wear, guarantees machining precision, and significantly improves production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of processing monitoring, more particularly, the present application relates to a precision part processing monitoring system and method based on digital twinning. BACKGROUND

[0002] In the prior art, the monitoring of the precision part processing process mainly relies on a plurality of sensors installed on the machine tool to collect processing data in real time, and the life prediction is carried out by establishing an empirical model or a mechanism model of tool wear. Some advanced systems have tried to build a digital twin of the processing process, and realize the visual monitoring of the processing state by combining real-time data with simulation models. These systems usually use a fixed parameter prediction model to realize the early warning function of processing abnormalities by setting a simple threshold alarm mechanism.

[0003] In the prior art, the precision part processing process is faced with the problem of insufficient accuracy of tool wear prediction: the traditional empirical model is difficult to adapt to the dynamically changing processing conditions, resulting in the gradual accumulation of the deviation between the predicted value and the measured data; the simulation model with fixed parameters cannot be self-calibrated according to the actual wear data, so that the prediction accuracy continues to decline with the processing process; there is a lack of a closed-loop mechanism for converting the prediction results into accurate control strategies, so that the equipment can only respond passively after the abnormality occurs, and cannot realize the self-adaptive processing based on the prospective adjustment of process parameters. Therefore, how to build a self-optimized digital twin to realize accurate prediction and monitoring of tool wear, while ensuring processing accuracy and significantly improving production efficiency, has become a problem faced by the industry. SUMMARY

[0004] The present application provides a precision part processing monitoring system and method based on digital twinning, which can build a self-optimized digital twin to realize accurate prediction and monitoring of tool wear, while ensuring processing accuracy and significantly improving production efficiency.

[0005] In a first aspect, the present application provides a precision part processing monitoring method based on digital twinning, which comprises the following steps:

[0006] Collecting processing tool data in the processing of the target precision part, constructing an initial digital twin according to the processing tool data, and determining tool pre-wear data in the processing of the target precision part through the initial digital twin;

[0007] Obtaining tool wear data in the processing of the target precision part, comparing the tool wear data and the tool pre-wear data, generating an anti-damage correction index in the processing of the target precision part, dynamically correcting the initial digital twin based on the anti-damage correction index, and obtaining a corrected digital twin;

[0008] initializing a machining instruction, performing real-time prediction on a machining process of the target precision part according to the modified digital twin and the machining instruction, obtaining a tool pre-damage index in the machining process of the target precision part, determining a confidence loss amount of a tool in the machining process of the target precision part according to the tool pre-damage index, and determining a machining control strategy of the target precision part through the confidence loss amount and each loss threshold value;

[0009] controlling the machining of the target precision part through the machining control strategy, and thereby completing the machining monitoring of the target precision part.

[0010] In the embodiment, the machining tool data in the machining process of the target precision part is obtained by scanning tool point cloud data in the machining process of the target precision part through an industrial camera, and the tool point cloud data is taken as the machining tool data in the machining process of the target precision part.

[0011] In the embodiment, constructing the initial digital twin according to the machining tool data specifically includes:

[0012] constructing a tool model through the machining tool data in the machining process of the target precision part;

[0013] obtaining part data of the target precision part;

[0014] constructing a part model according to the part data;

[0015] embedding the tool model and the part model into a simulation platform to obtain the initial digital twin.

[0016] In the embodiment, the comparison between the tool wear data and the tool pre-wear data generates an anti-damage correction index in the machining process of the target precision part, which specifically includes:

[0017] interpolating the tool wear data to obtain a tool wear curve;

[0018] determining each tool instantaneous offset in the machining process of the target precision part according to the tool wear curve and the tool pre-wear data;

[0019] determining an offset trend and a tool error degree through each tool instantaneous offset;

[0020] determining the anti-damage correction index according to the offset trend and the tool error degree.

[0021] In the embodiment, the initial digital twin is dynamically modified based on the anti-damage correction index to obtain a modified digital twin, which specifically includes:

[0022] determine a sensitive parameter through the initial digital twin;

[0023] perform parameter correction according to the sensitive parameter and the anti-damage correction index, to obtain a corrected sensitive parameter;

[0024] determine a corrected digital twin according to the corrected sensitive parameter.

[0025] In the embodiment, the confidence loss amount of the tool in the machining process of the target precision part according to the tool pre-damage index specifically includes:

[0026] determine a tool health index through the tool pre-damage index;

[0027] initialize a tool reference health index;

[0028] perform health offset measurement according to the tool health index and the tool reference health index, to obtain the confidence loss amount of the tool in the machining process of the target precision part.

[0029] In the embodiment, the machining control strategy of the target precision part is determined through the confidence loss amount and each loss threshold specifically includes:

[0030] generate a machining risk state of the target precision part through the confidence loss amount and each loss threshold;

[0031] determine the machining control strategy of the target precision part according to the machining risk state.

[0032] In a second aspect, the application provides a precision part machining monitoring system based on digital twin, which is used to execute a precision part machining monitoring method based on digital twin, and the precision part machining monitoring system includes:

[0033] a data acquisition module, configured to acquire machining tool data in a machining process of a target precision part, construct an initial digital twin according to the machining tool data, and determine tool pre-wear data in the machining process of the target precision part through the initial digital twin;

[0034] a digital correction module, configured to acquire tool wear data in the machining process of the target precision part, compare the tool wear data and the tool pre-wear data, generate an anti-damage correction index in the machining process of the target precision part, and dynamically correct the initial digital twin based on the anti-damage correction index, to obtain a corrected digital twin;

[0035] a processing strategy module, configured to initialize a processing instruction, perform real-time prediction on the target precision part processing process according to the modified digital twin and the processing instruction, obtain a tool pre-damage index in the target precision part processing process, determine a confidence loss amount of the tool in the target precision part processing process according to the tool pre-damage index, and determine a processing control strategy of the target precision part by the confidence loss amount and each loss threshold value;

[0036] a processing control module, configured to perform processing control on the target precision part through the processing control strategy, and thus complete processing monitoring of the target precision part.

[0037] In a third aspect, the present application provides a computer device, which comprises a memory and a processor, the memory is configured to store a computer program, and the processor is configured to call and run the computer program from the memory, so that the computer device executes the precision part processing monitoring method based on digital twin.

[0038] In a fourth aspect, the present application provides a computer readable storage medium, which stores instructions or codes, when the instructions or codes are run on a computer, the computer executes the precision part processing monitoring method based on digital twin.

[0039] The technical scheme provided by the embodiments of the present application has the following beneficial effects:

[0040] The processing tool data in the target precision part processing process is collected, the initial digital twin is constructed according to the processing tool data, and the tool pre-wear data in the target precision part processing process is determined through the initial digital twin; the tool wear data in the target precision part processing process is obtained, the tool wear data and the tool pre-wear data are compared, the anti-damage correction index in the target precision part processing process is generated, the initial digital twin is dynamically modified based on the anti-damage correction index, and the modified digital twin is obtained; the processing instruction is initialized, the target precision part processing process is predicted in real time according to the modified digital twin and the processing instruction, the tool pre-damage index in the target precision part processing process is obtained, the confidence loss amount of the tool in the target precision part processing process is determined according to the tool pre-damage index, the processing control strategy of the target precision part is determined by the confidence loss amount and each loss threshold value; the processing control strategy is used to control the processing of the target precision part, and thus the processing monitoring of the target precision part is completed.

[0041] Therefore, in this application, firstly, the machining control strategy for the target precision parts is determined based on the machining risk status. A high-fidelity initial digital twin is constructed by collecting actual machining tool data, achieving precise digital mapping of the machining process. This digital twin is used for advanced simulation to generate accurate tool pre-wear data, providing a crucial data foundation for predictive maintenance and intelligent decision-making. Secondly, by comparing the actual tool wear data with the pre-wear data predicted by the digital twin in real time, a damage resistance correction index is generated. Based on this index, the initial digital twin is dynamically corrected, establishing a closed-loop feedback mechanism. This allows the digital twin to continuously and adaptively optimize its prediction model, constantly improving prediction accuracy and providing reliable assurance for subsequent precise control and decision-making. Then, by inputting actual machining commands into the dynamically corrected digital twin… The digital twin enables high-precision real-time prediction of the machining process, generates a statistically significant tool wear index, calculates the confidence loss based on the tool wear index, and establishes an intelligent decision-making mechanism based on quantitative risk assessment. Through multi-threshold comparison, it automatically generates hierarchical control strategies, transforming machining process control from experience-driven to data-driven, significantly improving the adaptive capability and intelligence level of the machining system. Finally, by executing the machining control strategy based on digital twin prediction, it achieves proactive intervention and closed-loop control of the precision parts machining process. By adjusting process parameters and preventive measures in real time, it constructs a complete monitoring closed loop while ensuring machining quality, ultimately realizing a paradigm shift in the machining process from passive monitoring to proactive optimization.

[0042] In summary, the technical solution adopted in this application can construct a self-optimizing digital twin, realizing accurate prediction and monitoring of tool wear, and significantly improving production efficiency while ensuring machining accuracy. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is an exemplary flowchart of a precision parts machining monitoring method based on digital twins provided in this application;

[0045] Figure 2 This is an exemplary flowchart of the process for generating a damage resistance correction index during the machining of a target precision component, as provided in this application.

[0046] Figure 3This is an exemplary flowchart for determining the confidence wear of a tool during the machining of a target precision component, as provided in this application.

[0047] Figure 4 This is a module structure diagram of a precision parts processing monitoring system based on digital twins provided in this application;

[0048] Figure 5 This is a schematic diagram of the structure of a computer device for implementing a precision parts processing monitoring method based on digital twins, as provided in this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] This application provides a precision component machining monitoring system and method based on digital twins. The core of the system involves: collecting tool data during the machining process of a target precision component; constructing an initial digital twin based on the tool data; determining tool pre-wear data during the machining process using the initial digital twin; acquiring tool wear data during the machining process; comparing the tool wear data with the tool pre-wear data to generate a damage resistance correction index; dynamically correcting the initial digital twin based on the damage resistance correction index to obtain a corrected digital twin; initializing machining instructions; predicting the machining process of the target precision component in real time based on the corrected digital twin and the machining instructions to obtain the tool pre-wear index; determining the confidence loss of the tool during the machining process based on the tool pre-wear index; determining the machining control strategy for the target precision component using the confidence loss and various loss thresholds; and controlling the machining of the target precision component using the machining control strategy to complete the machining monitoring of the target precision component. The above approach can construct a self-optimizing digital twin, enabling accurate prediction and monitoring of tool wear, and significantly improving production efficiency while ensuring machining accuracy.

[0051] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of a precision parts machining monitoring method based on digital twins according to this embodiment of the present application. The machining monitoring method includes the following steps:

[0052] In step S1, the machining tool data during the machining process of the target precision part is collected, an initial digital twin is constructed based on the machining tool data, and the tool pre-wear data during the machining process of the target precision part is determined through the initial digital twin.

[0053] In this embodiment, the tool data during the machining process of the target precision component is collected by scanning the tool point cloud data during the machining process of the target precision component with an industrial camera, and then using the tool point cloud data as the tool data during the machining process of the target precision component. In specific implementation, the tool point cloud data can be generated by scanning the tool during the machining process of the target precision component with an industrial camera, and then used as the tool data during the machining process of the target precision component.

[0054] In this embodiment, constructing an initial digital twin based on the machining tool data can be achieved through the following steps:

[0055] A tool model is constructed using the machining tool data during the machining process of the target precision parts;

[0056] Obtain component data for the target precision parts;

[0057] Construct a component model based on the component data;

[0058] The tool model and the component model are embedded into the simulation platform to obtain an initial digital twin.

[0059] In specific implementation, firstly, a tool model can be constructed using the machining tool data during the machining process of the target precision component; that is, a tool model can be constructed using CAD software based on the machining tool data during the machining process of the target precision component. Secondly, component data of the target precision component can be obtained; that is, component data of the target precision component can be obtained from the machining system. Then, a component model can be constructed based on the component data; that is, a component model can be constructed using CAD software based on the component data of the target precision component. Finally, the tool model and the component model can be embedded into a simulation platform to obtain an initial digital twin; that is, the tool model and the component model can be imported into a finite element simulation platform, and tool machining instructions can be obtained from the machining system to define the kinematic model of the virtual tool, thereby obtaining the initial digital twin.

[0060] In this embodiment, the tool pre-wear data during the machining process of the target precision parts is determined by the initial digital twin. In specific implementation, the tool machining instructions can be simulated through the initial digital twin to output the instantaneous pre-wear rate of the tool. The cumulative pre-wear amount of the tool is then calculated over the entire simulation time domain. The instantaneous pre-wear rate of the tool and the time points are combined to generate a tool pre-wear curve. The tool pre-wear curve and the cumulative pre-wear amount are then used as the tool pre-wear data during the machining process of the target precision parts.

[0061] It should be noted that the machining control strategy for the target precision parts is determined based on the aforementioned machining risk status. By collecting actual machining tool data to construct a high-fidelity initial digital twin, a precise digital mapping of the machining process is achieved. Using this digital twin for advanced simulation, accurate tool pre-wear data is generated, providing a crucial data foundation for predictive maintenance and intelligent decision-making.

[0062] In step S2, tool wear data during the machining process of the target precision parts is acquired. The tool wear data and the tool pre-wear data are compared to generate a damage resistance correction index during the machining process of the target precision parts. The initial digital twin is dynamically corrected based on the damage resistance correction index to obtain a corrected digital twin.

[0063] In practice, tool wear data during the machining of the target precision parts can be obtained. That is, during the actual machining process, the tool surface image is acquired in real time by an industrial camera embedded in the machine tool, and the tool wear rate is calculated in real time according to a pre-trained deep learning network, thereby obtaining the tool wear data during the machining of the target precision parts.

[0064] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flowchart of generating the damage resistance correction index during the machining process of the target precision parts in this embodiment of the application. In this embodiment, the damage resistance correction index during the machining process of the target precision parts is generated by comparing the tool wear data and the tool pre-wear data, which can be achieved by the following steps:

[0065] In step S21, the tool wear data is interpolated to obtain the tool wear curve;

[0066] In step S22, the instantaneous offset of each tool during the machining process of the target precision part is determined based on the tool wear curve and the tool pre-wear data;

[0067] In step S23, the offset trend and tool error degree are determined by the instantaneous offset of each tool;

[0068] In step S24, the damage resistance correction index is determined based on the offset trend and the tool error degree.

[0069] In specific implementation, firstly, the tool wear data can be interpolated to obtain the tool wear curve. That is, the tool wear data can be interpolated using monotonic cubic splines to obtain a tool wear curve synchronized with the time axis of the tool pre-wear curve in the tool pre-wear data. Secondly, the instantaneous tool offsets during the machining process of the target precision parts can be determined based on the tool wear curves and the tool pre-wear data. That is, for multiple time points, the instantaneous tool wear rate and instantaneous tool pre-wear rate of the tool wear curve and tool pre-wear curve at the same time point can be extracted. The instantaneous tool wear rate is subtracted from the instantaneous tool pre-wear rate, and the result is used as the instantaneous tool offset during the machining process of the target precision parts. Thus, the instantaneous tool offsets during the machining process of the target precision parts are obtained. It should be noted that the instantaneous tool offset refers to the deviation between the actual tool wear and the estimated wear at the same moment. Then, the offset trend and tool error can be determined through the instantaneous tool offsets. That is, the offset trend can be obtained by the following formula:

[0070] in, Indicates the trend of deviation; The total number of data points representing the instantaneous offset; This represents the timestamp of the i-th instantaneous offset; Let represent the i-th instantaneous offset, where the offset trend is used to quantify the trend of instantaneous offset changing with time. The tool error can be obtained by the following formula:

[0071]

[0072] in, Indicates the tool error rate; The total number of data points representing the instantaneous offset; Let represent the i-th instantaneous offset. It should be noted that the tool error degree quantifies the deviation between the current actual wear state of the tool and the model's predicted state. Finally, the damage resistance correction index can be determined based on the offset trend and the tool error degree. That is, the maximum permissible offset trend and the maximum permissible tool error degree can be obtained from historical machining data. The offset trend is then divided by the maximum permissible offset trend to obtain the dimensionless offset trend, and the tool error degree is divided by the maximum permissible tool error degree to obtain the dimensionless tool error degree. The dimensionless offset trend and the dimensionless tool error degree are summed, and the sum is halved. The resulting value is used as the damage resistance correction index. It should be noted that the damage resistance correction index refers to the urgency coefficient for tool correction.

[0073] In this embodiment, the initial digital twin is dynamically corrected based on the damage resistance correction index to obtain a corrected digital twin, which can be achieved through the following steps:

[0074] Sensitive parameters are determined using the initial digital twin;

[0075] Based on the sensitive parameters and the damage resistance correction index, the parameters are corrected to obtain the corrected sensitive parameters;

[0076] The modified digital twin is determined based on the modified sensitivity parameters.

[0077] In practical implementation, firstly, sensitive parameters can be determined using the initial digital twin. Specifically, different machining parameter settings can be applied to the initial digital twin, outputting the tool wear rate under each machining parameter. Thus, sensitive parameters are obtained based on the different machining parameter settings and the tool wear rate under each machining parameter. In other words, the sensitivity of each machining parameter to tool wear is calculated using the tool wear rate under each machining parameter, and the machining parameter with the highest sensitivity is taken as the sensitive parameter. Then, parameter correction can be performed based on the sensitive parameter and the damage resistance correction index to obtain the corrected sensitive parameter. Specifically, correction compensation can be determined based on the sensitive parameter and the damage resistance correction index, multiplying the sensitive parameter by 0.05 and then multiplying the result by the damage resistance correction index. A positive exponent is used as the correction compensation. The value 0.05 can be set based on historical experience. The correction direction is determined according to the offset trend. When the offset trend is greater than 0, the sensitivity parameter is increased, and the correction compensation is added to 1. The result is then multiplied by the sensitivity parameter, and this result is used as the correction sensitivity parameter. When the offset trend is less than 0, the sensitivity parameter is decreased, and the correction compensation is subtracted from 1. The result is then multiplied by the sensitivity parameter, and this result is used as the correction sensitivity parameter. It should be noted that the correction sensitivity parameter refers to the parameter after correction. Finally, the corrected digital twin can be determined based on the corrected sensitivity parameter; that is, the corrected sensitivity parameter can be mapped back to the initial digital twin to obtain the corrected digital twin.

[0078] It should be noted that by comparing the actual tool wear data with the pre-wear data predicted by the digital twin in real time, a damage resistance correction index is generated. Based on the damage resistance correction index, the initial digital twin is dynamically corrected, establishing a closed-loop feedback mechanism. This enables the digital twin to continuously and adaptively optimize its prediction model, thereby continuously improving prediction accuracy and providing a reliable guarantee for subsequent precise control and decision-making.

[0079] In step S3, the machining instructions are initialized, and the machining process of the target precision parts is predicted in real time based on the modified digital twin and the machining instructions to obtain the tool pre-wear index during the machining process of the target precision parts. The confidence loss of the tool during the machining process of the target precision parts is determined based on the tool pre-wear index. The machining control strategy of the target precision parts is determined by the confidence loss and various loss thresholds.

[0080] In practice, the initialization of machining instructions can extract the machining instructions for the target precision parts from the machining system.

[0081] In this embodiment, the machining process of the target precision component is predicted in real time based on the modified digital twin and the machining command to obtain the tool pre-wear index during the machining process of the target precision component. In specific implementation, the machining command is input into the modified digital twin, the current position of the tool during the machining process of the target precision component is set as the initial position of the modified digital twin, simulation calculation is performed to obtain the cumulative wear value of the tool, and the cumulative wear value of the tool is used as the tool pre-wear index during the machining process of the target precision component.

[0082] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flowchart for determining the confidence loss of the tool during the machining of a target precision component in an embodiment of this application. In this embodiment, determining the confidence loss of the tool during the machining of a target precision component based on the tool pre-loss index can be achieved using the following steps:

[0083] In step S31, the tool health index is determined by the tool pre-damage index;

[0084] In step S32, the tool baseline health index is initialized;

[0085] In step S33, a health offset measurement is performed based on the tool health index and the tool reference health index to obtain the confidence loss of the tool during the machining of the target precision parts.

[0086] In specific implementation, firstly, the tool health index can be determined through the tool pre-damage index. That is, the tool scrapping threshold can be obtained through historical experience. It should be noted that the scrapping threshold refers to the cumulative wear value when the tool needs to be replaced. The tool pre-damage index is divided by the scrapping threshold, and then 1 is subtracted to obtain the result, which is used as the tool health index. Secondly, the tool baseline health index can be initialized. That is, the standard cumulative wear value of the tool after the same machining operation can be obtained from the historical process database. The standard cumulative wear value is divided by the scrapping threshold, and then 1 is subtracted to obtain the result, which is used as the tool baseline health index. Finally, based on the tool health index and the tool baseline health index, a health offset measurement is performed to obtain the confidence loss of the tool during the machining of the target precision parts. That is, the tool baseline health index is subtracted from the tool health index, and the result is used as the absolute health offset. The absolute health offset is divided by the tool baseline health index, and the result is used as the confidence loss. It should be noted that the confidence loss refers to the numerical value of the relative deviation between the current predicted health state of the tool and the ideal baseline health state.

[0087] In this embodiment, the processing control strategy for determining the target precision component by using the confidence loss amount and various loss thresholds can be implemented using the following steps:

[0088] The processing risk status of the target precision component is generated by the confidence loss amount and various loss thresholds;

[0089] Based on the aforementioned processing risk status, a processing control strategy for the target precision parts is determined.

[0090] In practical implementation, firstly, the processing risk status of the target precision component can be generated using the confidence loss amount and the loss threshold. That is, various loss thresholds can be preset, and the confidence loss amount is mapped to the processing risk status of the target precision component through these thresholds. For example, if the loss thresholds are 0.2 and 0.5, when the confidence loss amount is less than 0.2, the processing risk status is: normal; when the confidence loss amount is greater than 0.2 and less than 0.5, the processing risk status is: needs optimization; when the confidence loss amount is greater than 0.5, the processing risk status is: urgent. Then, the target precision component can be determined based on the processing risk status. The machining control strategy for the component can be generated based on the machining risk status. For example: if the machining risk status is "normal", the machining control strategy is "keep working"; if the machining risk status is "optimization required", the machining control strategy is "the tool has acceptable wear, a modified digital twin can be called for rapid simulation to optimize the tool feed rate and calculate the tool feed rate that minimizes the confidence wear"; if the machining risk status is "emergency", the machining control strategy is "stop machining, check the tool status, and replace the tool", thus obtaining the machining control strategy for the target precision component.

[0091] It should be noted that by inputting the actual machining instructions into the dynamically corrected digital twin, high-precision real-time prediction of the machining process is achieved, generating a statistically significant tool pre-wear index, and calculating the confidence loss based on the tool pre-wear index. An intelligent decision-making mechanism based on quantitative risk assessment is established, and a hierarchical control strategy is automatically generated through multi-threshold comparison, transforming the machining process control from experience-driven to data-driven, significantly improving the adaptive capability and intelligence level of the machining system.

[0092] In step S4, the machining control strategy is used to control the machining of the target precision parts, thereby completing the machining monitoring of the target precision parts.

[0093] In this embodiment, the machining control strategy is used to control the machining of the target precision parts, thereby completing the machining monitoring of the target precision parts. In specific implementation, the machining control strategy can be converted into machining instructions that can be executed by the machine tool. For example: the machining control strategy is: keep working, and the machining instruction is: no instruction; the machining control strategy is: the tool has acceptable wear, a modified digital twin can be called for rapid simulation to optimize the tool feed rate and calculate the tool feed rate that minimizes the confidence wear, and the machining instruction is: set the current tool feed rate to the tool feed rate that minimizes the confidence wear calculated by the modified digital twin; the machining control strategy is: stop machining, check the tool status, and replace the tool, and the machining instruction is: set the tool feed rate to 0, thereby completing the machining monitoring of the target precision parts.

[0094] It should be noted that by implementing a machining control strategy based on digital twin prediction, proactive intervention and closed-loop control of the precision parts machining process were achieved. By adjusting process parameters and preventive measures in real time, a complete monitoring closed loop was constructed while ensuring machining quality, ultimately realizing a paradigm shift in the machining process from passive monitoring to proactive optimization.

[0095] Therefore, in this application, firstly, the machining control strategy for the target precision parts is determined based on the machining risk status. A high-fidelity initial digital twin is constructed by collecting actual machining tool data, achieving precise digital mapping of the machining process. This digital twin is used for advanced simulation to generate accurate tool pre-wear data, providing a crucial data foundation for predictive maintenance and intelligent decision-making. Secondly, by comparing the actual tool wear data with the pre-wear data predicted by the digital twin in real time, a damage resistance correction index is generated. Based on this index, the initial digital twin is dynamically corrected, establishing a closed-loop feedback mechanism. This allows the digital twin to continuously and adaptively optimize its prediction model, constantly improving prediction accuracy and providing reliable assurance for subsequent precise control and decision-making. Then, by inputting actual machining commands into the dynamically corrected digital twin… The digital twin enables high-precision real-time prediction of the machining process, generates a statistically significant tool wear index, calculates the confidence loss based on the tool wear index, and establishes an intelligent decision-making mechanism based on quantitative risk assessment. Through multi-threshold comparison, it automatically generates hierarchical control strategies, transforming machining process control from experience-driven to data-driven, significantly improving the adaptive capability and intelligence level of the machining system. Finally, by executing the machining control strategy based on digital twin prediction, it achieves proactive intervention and closed-loop control of the precision parts machining process. By adjusting process parameters and preventive measures in real time, it constructs a complete monitoring closed loop while ensuring machining quality, ultimately realizing a paradigm shift in the machining process from passive monitoring to proactive optimization.

[0096] In summary, the technical solution adopted in this application can construct a self-optimizing digital twin, realizing accurate prediction and monitoring of tool wear, and significantly improving production efficiency while ensuring machining accuracy.

[0097] Example 2: This application provides a reference for a precision parts machining monitoring system based on digital twins. Figure 4 As shown in the figure, this is a modular structure diagram of a precision parts machining monitoring system based on digital twins according to this embodiment of the present application. The precision parts machining monitoring system based on digital twins includes:

[0098] The data acquisition module 100 is used to acquire machining tool data during the machining process of the target precision parts, construct an initial digital twin based on the machining tool data, and determine the tool pre-wear data during the machining process of the target precision parts through the initial digital twin.

[0099] The digital correction module 200 is used to acquire tool wear data during the machining process of the target precision parts, compare the tool wear data with the tool pre-wear data, generate a damage resistance correction index during the machining process of the target precision parts, and dynamically correct the initial digital twin based on the damage resistance correction index to obtain a corrected digital twin.

[0100] The machining strategy module 300 is used to initialize machining instructions, predict the machining process of the target precision parts in real time based on the modified digital twin and the machining instructions, obtain the tool pre-wear index in the machining process of the target precision parts, determine the confidence wear amount of the tool in the machining process of the target precision parts based on the tool pre-wear index, and determine the machining control strategy of the target precision parts through the confidence wear amount and various wear thresholds.

[0101] The machining control module 400 is used to control the machining of the target precision parts through the machining control strategy, thereby completing the machining monitoring of the target precision parts.

[0102] The foregoing detailed an example of a precision parts machining monitoring system and method based on digital twins provided in this application. It is understood that the corresponding apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0103] In embodiment three, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described method for monitoring the machining of precision parts based on digital twins.

[0104] In this embodiment, reference Figure 5The dashed lines in the figure indicate that the unit or module is optional. This figure is a schematic diagram of the structure of a computer device for a precision parts processing monitoring system based on digital twins, according to an embodiment of this application. The aforementioned precision parts processing monitoring method based on digital twins in the above embodiment can... Figure 5 The computer device shown is used to implement this, and the computer device includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device may be a terminal device, a server or a chip.

[0105] Processor 501 can be a general-purpose processor or a special-purpose processor. For example, processor 501 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 505 to realize signal input (reception) and output (transmission).

[0106] For example, the computer device may be a chip, and the communication unit 505 may be the input and / or output circuit of the chip, or the communication unit 505 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0107] For example, the computer device may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0108] The computer device may include one or more memories 502 storing a program 504. The program 504 can be executed by a processor 501 to generate instructions 503, causing the processor 501 to perform the methods described in the above method embodiments according to the instructions 503. Optionally, the memory 502 may also store data (such as a target audit model). Optionally, the processor 501 may also read data stored in the memory 502, which may be stored at the same storage address as the program 504, or the data may be stored at a different storage address than the program 504.

[0109] The processor 501 and memory 502 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0110] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in processor 501. Processor 501 can be a central processing unit, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other programmable logic device, such as discrete gate, transistor logic device, or discrete hardware component.

[0111] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] In embodiment four, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described method for monitoring the machining of precision parts based on digital twins.

[0113] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0114] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A method for monitoring the machining of precision parts based on digital twins, characterized in that, The processing monitoring method includes: Data on the machining tools during the machining process of the target precision parts is collected. An initial digital twin is constructed based on the machining tool data. The tool pre-wear data during the machining process of the target precision parts is determined through the initial digital twin. Obtain tool wear data during the machining process of the target precision component, and compare the tool wear data with the tool pre-wear data to generate a damage resistance correction index during the machining process of the target precision component. Specifically, generating the damage resistance correction index during the machining process of the target precision component by comparing the tool wear data with the tool pre-wear data includes: The tool wear data is interpolated to obtain the tool wear curve; The instantaneous offset of each tool during the machining process of the target precision parts is determined based on the tool wear curve and the tool pre-wear data. The offset trend and tool error degree are determined by the instantaneous offset of each tool; The damage resistance correction index is determined based on the offset trend and tool error degree. The damage resistance correction index refers to the urgency coefficient for correcting the tool. The initial digital twin is dynamically corrected based on the damage resistance correction index to obtain the corrected digital twin. Initialize machining instructions, perform real-time prediction of the machining process of the target precision part based on the corrected digital twin and the machining instructions, obtain the tool pre-wear index during the machining process of the target precision part, and determine the confidence loss of the tool during the machining process of the target precision part based on the tool pre-wear index. Specifically, determining the confidence loss of the tool during the machining process of the target precision part based on the tool pre-wear index includes: The tool health index is determined by the tool pre-damage index; Initialize the tool baseline health index; Based on the tool health index and the tool reference health index, a health deviation measurement is performed to obtain the confidence loss of the tool during the machining of the target precision parts. The confidence loss refers to the value of the relative deviation between the current predicted health state of the tool and the ideal reference health state. The machining control strategy of the target precision parts is determined by the confidence loss and various loss thresholds. The processing control strategy described above is used to control the processing of the target precision parts, thereby enabling the monitoring of the processing of the target precision parts.

2. The precision component machining monitoring method based on digital twin as described in claim 1, characterized in that, The tool data during the machining process of the target precision parts is collected by scanning the tool point cloud data during the machining process of the target precision parts with an industrial camera, and then using the tool point cloud data as the tool data during the machining process of the target precision parts.

3. The precision component machining monitoring method based on digital twin as described in claim 1, characterized in that, Constructing an initial digital twin based on the machining tool data specifically includes: A tool model is constructed using the machining tool data during the machining process of the target precision parts; Obtain component data for the target precision parts; Construct a component model based on the component data; The tool model and the component model are embedded into the simulation platform to obtain an initial digital twin.

4. The precision component machining monitoring method based on digital twin as described in claim 1, characterized in that, The initial digital twin is dynamically corrected based on the damage resistance correction index to obtain a corrected digital twin, specifically including: Sensitive parameters are determined using the initial digital twin; Based on the sensitive parameters and the damage resistance correction index, the parameters are corrected to obtain the corrected sensitive parameters; The modified digital twin is determined based on the modified sensitivity parameters.

5. The precision component machining monitoring method based on digital twin as described in claim 1, characterized in that, The specific steps for determining the machining control strategy for the target precision parts by using the confidence loss and various loss thresholds include: The processing risk status of the target precision component is generated by the confidence loss amount and various loss thresholds; Based on the aforementioned processing risk status, a processing control strategy for the target precision parts is determined.

6. A precision parts machining monitoring system based on digital twins, used to execute a precision parts machining monitoring method based on digital twins as described in any one of claims 1 to 5, characterized in that, The precision component machining monitoring system includes: The data acquisition module is used to collect machining tool data during the machining process of the target precision parts, construct an initial digital twin based on the machining tool data, and determine the tool pre-wear data during the machining process of the target precision parts through the initial digital twin; A digital correction module is used to acquire tool wear data during the machining process of the target precision part, and to generate a damage resistance correction index during the machining process of the target precision part by comparing the tool wear data and the tool pre-wear data. Specifically, generating the damage resistance correction index during the machining process of the target precision part by comparing the tool wear data and the tool pre-wear data includes: The tool wear data is interpolated to obtain the tool wear curve; The instantaneous offset of each tool during the machining process of the target precision parts is determined based on the tool wear curve and the tool pre-wear data. The offset trend and tool error degree are determined by the instantaneous offset of each tool; The damage resistance correction index is determined based on the offset trend and tool error degree. The damage resistance correction index refers to the urgency coefficient for correcting the tool. The initial digital twin is dynamically corrected based on the damage resistance correction index to obtain the corrected digital twin. The machining strategy module is used to initialize machining instructions, predict the machining process of the target precision part in real time based on the modified digital twin and the machining instructions, obtain the tool pre-wear index during the machining process of the target precision part, and determine the confidence loss of the tool during the machining process of the target precision part based on the tool pre-wear index. Specifically, determining the confidence loss of the tool during the machining process of the target precision part based on the tool pre-wear index includes: The tool health index is determined by the tool pre-damage index; Initialize the tool baseline health index; Based on the tool health index and the tool reference health index, a health deviation measurement is performed to obtain the confidence loss of the tool during the machining of the target precision parts. The confidence loss refers to the value of the relative deviation between the current predicted health state of the tool and the ideal reference health state. The machining control strategy of the target precision parts is determined by the confidence loss and various loss thresholds. The machining control module is used to control the machining of the target precision parts through the machining control strategy, thereby completing the machining monitoring of the target precision parts.

7. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device performs a precision parts processing monitoring method based on digital twins as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement the precision parts processing monitoring method based on digital twins as described in any one of claims 1 to 5.

Images