Intelligent optimization method for precision part machining process based on multi-modal data fusion

Abstract

The application discloses a precision part processing process intelligent optimization method based on multi-modal data fusion, and belongs to the technical field of part processing supervision; and aims to solve the technical problem of poor diversity and reliability of active processing and analysis of quality inspection data of different processing links of precision parts in the prior art; through processing and analysis and combination of supervision index data of different abnormal manufacturing structures of different processing links of precision parts, supervision index operation sequences and index supervision values corresponding to all supervision indexes of different abnormal manufacturing structures are obtained, active diversification of supervision and analysis of existing abnormalities of the supervision indexes of different abnormal manufacturing structures is carried out, and diversified optimization management is implemented on different abnormal manufacturing structures according to the analysis results; active mining and analysis of the optimization management scheme data of different abnormal manufacturing structures on the optimization implementation influence of the processing links are carried out, and active optimization management of other non-abnormal manufacturing structures of the processing links is adaptively carried out.

Description

Technical Field

[0001] This invention relates to the field of parts processing monitoring technology, specifically to an intelligent optimization method for precision parts processing technology based on multimodal data fusion. Background Technology

[0002] Precision parts machining refers to the manufacturing process of parts to meet the requirements of high precision and high quality. It usually involves complex operations and technologies to ensure that the dimensional accuracy, shape accuracy and surface finish of the final product meet the design requirements.

[0003] Existing optimization schemes for precision parts processing technology cannot conduct multi-dimensional monitoring and negative impact assessment of the quality inspection results of different aspects of the finished parts during implementation. They also cannot adaptively optimize and manage the processing links and processes of precision parts based on the negative impact assessment results of different dimensions. This results in technical problems such as the diversity and poor reliability of proactive processing and analysis of quality inspection data of different processing links of precision parts. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent optimization method for the machining process of precision parts by multimodal data fusion, which can solve the technical problems of poor diversity and reliability of active processing and analysis of quality inspection data in different machining stages of precision parts in existing solutions.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] Intelligent optimization methods for precision component manufacturing processes based on multimodal data fusion include:

[0007] Actively monitor and process the quality inspection results of different processing stages of precision parts, and conduct data analysis on the impact of abnormal manufacturing on all abnormal manufacturing structures obtained from the monitoring of different processing stages. Based on the analysis results, dynamically mark different abnormal manufacturing structures in different processing stages and implement targeted optimization management solutions.

[0008] By utilizing optimization management scheme data for different abnormal manufacturing structures, we can proactively mine and analyze the impact of optimization implementation on the corresponding processing links, and adaptively and proactively optimize and manage other non-abnormal manufacturing structures in the processing links based on the analysis results.

[0009] Preferably, all quality inspection results corresponding to different processing stages of each batch of precision parts are obtained, and all abnormal causes and abnormal manufacturing structures are determined based on all abnormal quality inspection results corresponding to different processing stages;

[0010] When analyzing the impact of abnormal manufacturing on all abnormal manufacturing structures obtained from the supervision of different processing stages, the regulatory indicator values ​​corresponding to all preset regulatory indicators when the abnormal manufacturing structure processes precision parts are obtained, and the regulatory indicator values ​​corresponding to different regulatory indicators are matched and analyzed with the preset monitoring indicator range. Based on the analysis results, the reliability identifiers of the indicators associated with the regulatory indicators are dynamically set.

[0011] The reliability indicator for dynamically set metrics contains a value of 0 or 1.

[0012] Preferably, the reliable identifiers of all preset regulatory indicators obtained from the abnormal manufacturing structure are sorted and combined to obtain a regulatory indicator operation sequence. All elements in the regulatory indicator operation sequence are summed and set as the regulatory value ZJi corresponding to the abnormal manufacturing structure; i represents different abnormal manufacturing structures, i=1, 2, 3, ..., n; n is a positive integer.

[0013] Data analysis of the indicator monitoring values ​​determines the normal execution status corresponding to the abnormal manufacturing structure.

[0014] If the indicator monitoring value is 0, the abnormal execution status corresponding to the abnormal manufacturing structure is determined to be normal, and it is marked as the first manufacturing structure.

[0015] Preferably, when performing data analysis on the abnormal manufacturing impact corresponding to the first manufacturing structure, the total number of abnormal parts ni´ that cause abnormalities in the processing of the first manufacturing structure is obtained, where i´ represents different first manufacturing structures, i´=1, 2, 3, ..., m; m is a positive integer; and the abnormality occurrence monitoring formula is used. Calculate and obtain the anomaly occurrence value YFi´ corresponding to the first manufacturing structure; where Ni´ is the total number of precision parts processed in the batch corresponding to the first manufacturing structure; αi´ is the anomaly occurrence requirement value corresponding to the first manufacturing structure;

[0016] If YFi´<1, then the abnormality in the production and processing corresponding to the first manufacturing structure is determined to have a normal impact, and the label of the first manufacturing structure is updated to a normal manufacturing impact structure;

[0017] Conversely, if the abnormality in the production and processing corresponding to the first manufacturing structure is determined to have an impact on the abnormality, the mark of the first manufacturing structure will be updated to a special manufacturing impact structure.

[0018] The first optimized management scheme is to pre-set regulatory indicators for all special manufacturing impact structures.

[0019] Preferably, if the indicator monitoring value is not 0, the abnormal execution state corresponding to the abnormal manufacturing structure is determined to be abnormal, and it is marked as the second manufacturing structure. The abnormal occurrence value corresponding to the second manufacturing structure is calculated and analyzed through the abnormal occurrence monitoring formula.

[0020] Preferably, if the abnormal occurrence value corresponding to the second manufacturing structure is less than 1, it is determined that the abnormal occurrence of the production and processing corresponding to the second manufacturing structure has a normal impact, and a second optimized management scheme with preset monitoring indicators is implemented.

[0021] Conversely, if the abnormality in the production and processing corresponding to the second manufacturing structure is determined to have an abnormal impact, a first optimization management plan and a second optimization management plan with preset monitoring indicators will be implemented.

[0022] Preferably, the total number of optimizations in the processing stage is M1 (where only the first optimization management scheme is implemented), M2 (where only the second optimization management scheme is implemented), and M3 (where both the first and second optimization management schemes are implemented). The total number of optimizations in the processing stage is then calculated sequentially using the formula... Calculate the corresponding optimization implementation impact value YYk; where k is 1, 2, and 3, representing only implementing the first optimization management scheme, only implementing the second optimization management scheme, and simultaneously implementing both the first and second optimization management schemes, respectively; M0 is the total number of all manufacturing structures under supervision in the processing stage; βk is β1, β2, and β3, which are the optimization implementation impact thresholds corresponding to implementing different optimization management schemes.

[0023] Preferably, when conducting proactive optimization necessity analysis and management of other non-abnormal manufacturing structures in the processing stage:

[0024] If YYk≤0, it indicates that the optimization management scheme does not need to actively optimize other non-abnormal manufacturing structures in the processing stage;

[0025] Conversely, it indicates that the optimization management plan needs to proactively optimize other non-abnormal manufacturing structures in the processing stage, and proactively optimizes other non-abnormal manufacturing structures in the processing stage using the optimization management plan.

[0026] Compared to existing solutions, the beneficial effects achieved by this invention are:

[0027] This invention processes, analyzes, and combines regulatory indicator data for different abnormal manufacturing structures at different processing stages of precision parts. It obtains the operational sequence and regulatory values ​​of all regulatory indicators corresponding to different abnormal manufacturing structures. This not only enables the digital representation of the regulatory status of all regulatory indicators corresponding to different abnormal manufacturing, but also provides reliable data support for subsequent analysis of abnormal execution status corresponding to abnormal manufacturing structures.

[0028] This invention proactively and diversely monitors and analyzes the anomalies in existing regulatory indicators for different abnormal manufacturing structures, and implements diversified optimization management for different abnormal manufacturing structures based on the analysis results, thereby improving the diversity of proactive processing and analysis of quality inspection data for different processing stages of precision parts.

[0029] This invention utilizes optimization management scheme data of different abnormal manufacturing structures to proactively mine and analyze the impact of optimization implementation on the corresponding processing links, and adaptively optimizes and manages other non-abnormal manufacturing structures in the processing links based on the analysis results. This realizes proactive data analysis and management of proactive optimization of other non-abnormal manufacturing structures in different processing links, further improving the diversity of proactive processing and analysis of quality inspection data in different processing links of precision parts. Attached Figure Description

[0030] The invention will now be further described with reference to the accompanying drawings.

[0031] Figure 1 This is a flowchart illustrating the operation of the intelligent optimization method for precision component manufacturing process based on multimodal data fusion, as described in this invention.

[0032] Figure 2 This is a flowchart of the active optimization analysis of the second manufacturing structure in this invention.

[0033] Figure 3 This is a flowchart illustrating the necessity analysis for proactively optimizing other non-abnormal manufacturing structures in the processing stage in this invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] like Figure 1 As shown, this invention is an intelligent optimization method for precision parts machining processes based on multimodal data fusion, comprising:

[0036] Actively monitor and process the quality inspection results of different processing stages of precision parts, and conduct data analysis on the impact of abnormal manufacturing on all abnormal manufacturing structures obtained from the monitoring of different processing stages. Based on the analysis results, dynamically mark different abnormal manufacturing structures in different processing stages and implement targeted optimization management solutions; including:

[0037] Obtain all quality inspection results for each batch of precision parts at different processing stages, and determine all abnormal causes and abnormal manufacturing structures based on all abnormal quality inspection results for different processing stages;

[0038] It should be noted that different processing stages are classified according to the actual processing requirements of precision parts, or they can be classified according to the processing equipment.

[0039] In addition, each processing stage is equipped with several manufacturing structure supervisions, and each manufacturing structure has several preset supervision indicators; specifically, the manufacturing structure can be the spindle in the machine tool, and the preset supervision indicators are spindle radial runout and spindle axial displacement.

[0040] It should be explained that the spindle in a machine tool is affected by both radial runout and axial movement.

[0041] Spindle radial runout: Spindle bearing wear or assembly errors can cause the tool rotation center to shift; for example, when the spindle radial runout exceeds 2μm, the coaxiality error of the machined hole can reach more than 5μm.

[0042] Spindle axial movement: Spindle axial displacement during machining (such as thermal expansion) can cause depth dimension deviations; in precision machining, a 0.5μm axial movement can amplify the deep hole machining error to 3μm;

[0043] The specific number of manufacturing structures set up in different processing stages and the number of regulatory indicators preset in different manufacturing structures are not limited and can be determined according to the existing requirements for precision parts processing and production.

[0044] In addition, determining all causes of abnormalities and abnormal manufacturing structures based on abnormal quality inspection results can be achieved either through existing automated fault monitoring technology, through manual monitoring, or through a combination of automated fault monitoring and manual monitoring. The specific determination method is not limited here.

[0045] When analyzing the impact of abnormal manufacturing on all abnormal manufacturing structures obtained from the supervision of different processing stages, the regulatory indicator values ​​corresponding to all preset regulatory indicators when the abnormal manufacturing structure processes precision parts are obtained, and the regulatory indicator values ​​corresponding to different regulatory indicators are matched and analyzed with the preset monitoring indicator range.

[0046] Among them, all the preset regulatory indicators for different manufacturing structures are preset with a corresponding monitoring indicator range. The monitoring indicator range corresponding to the regulatory indicator can be determined based on the design requirements data of precision parts processing or based on the historical processing and optimization adjustment data of precision parts. The specific value of the monitoring indicator range is not limited.

[0047] If the values ​​of the regulatory indicators corresponding to the regulatory indicators all fall within the pre-defined monitoring indicator range, then the reliability identifier of the indicator associated with the regulatory indicator will be set to 0.

[0048] If an active processing control is generated when the value of the regulatory indicator corresponding to the regulatory indicator is outside the preset monitoring indicator range, the reliability identifier of the indicator associated with the regulatory indicator will be set to 0. This can be understood as the regulatory indicator of the manufacturing structure being abnormal, but the existing fault automation monitoring technology actively intervenes to handle it, such as controlling the manufacturing structure to stop operating.

[0049] If the value of the regulatory indicator corresponding to the regulatory indicator is outside the preset monitoring indicator range, and no active processing control is generated when the value of the regulatory indicator is outside the preset monitoring indicator range, then the reliability identifier of the indicator associated with the regulatory indicator is set to 1. This can be understood as the regulatory indicator of the manufacturing structure being abnormal, but the existing fault automation monitoring technology has not actively intervened to handle it, such as not actively suspending the operation of the manufacturing structure.

[0050] The reliable identifiers of all preset regulatory indicators of the abnormal manufacturing structure are sorted and combined to obtain the regulatory indicator operation sequence. All elements in the regulatory indicator operation sequence are summed and set as the regulatory value ZJi of the corresponding abnormal manufacturing structure; i represents different abnormal manufacturing structures, i=1, 2, 3, ..., n; n is a positive integer, representing the total number of abnormal manufacturing structures.

[0051] In this embodiment of the invention, by processing, analyzing and combining regulatory indicator data for different abnormal manufacturing structures in different processing stages of precision parts, the operating sequence and regulatory value of all regulatory indicators corresponding to different abnormal manufacturing structures are obtained. This not only enables the digital representation of the regulatory status of all regulatory indicators corresponding to different abnormal manufacturing, but also provides reliable data support for the subsequent analysis of abnormal execution status corresponding to abnormal manufacturing structures.

[0052] Data analysis of the indicator monitoring values ​​determines the normal execution status corresponding to the abnormal manufacturing structure.

[0053] If the indicator monitoring value is 0, the abnormal execution status corresponding to the abnormal manufacturing structure is determined to be normal, and it is marked as the first manufacturing structure.

[0054] When performing data analysis on the impact of abnormal manufacturing corresponding to the first manufacturing structure, the total number of abnormal parts ni´ that caused the abnormality in the processing of the first manufacturing structure is obtained, where i´ represents different first manufacturing structures, i´=1, 2, 3, ..., m; m is a positive integer representing the total number of first manufacturing structures; and the abnormality occurrence monitoring formula is used. Calculate and obtain the anomaly occurrence value YFi´ corresponding to the first manufacturing structure; where Ni´ is the total number of precision parts processed in the batch corresponding to the first manufacturing structure; αi´ is the anomaly occurrence requirement value corresponding to the first manufacturing structure, which can be determined based on the existing processing industry design requirement data of the first manufacturing structure, or the preliminary test data before the first manufacturing structure is put into production.

[0055] It should be explained that the anomaly occurrence value is used to process and calculate all the regulatory indicator data of the first manufacturing structure to digitally represent the impact of anomalies in the corresponding production and processing of the first manufacturing structure; the larger the anomaly occurrence value, the greater the impact of the corresponding first manufacturing structure on the anomalies in the production and processing.

[0056] If YFi´<1, then the abnormality in the production and processing corresponding to the first manufacturing structure is determined to have a normal impact, and the label of the first manufacturing structure is updated to a normal manufacturing impact structure;

[0057] Conversely, if the abnormality in the production and processing corresponding to the first manufacturing structure is determined to have an impact on the abnormality, the mark of the first manufacturing structure will be updated to a special manufacturing impact structure.

[0058] The first optimized management plan is to pre-set regulatory indicators for all special manufacturing impact structures;

[0059] The first optimization management plan specifically involves supplementing and adding to all existing regulatory indicators of the first manufacturing structure to address the incomplete coverage of existing regulatory indicators.

[0060] In this embodiment of the invention, when the abnormal execution state corresponding to the abnormal manufacturing structure is normal, data analysis is performed on the abnormal manufacturing impact corresponding to the first manufacturing structure, and the preset regulatory indicators of different first manufacturing structures are dynamically optimized and managed based on the analysis results, thereby improving the proactive regulatory optimization effect of preset regulatory indicators of different manufacturing structures in different processing stages.

[0061] like Figure 2 As shown, if the indicator monitoring value is not 0, the abnormal execution status corresponding to the abnormal manufacturing structure is determined to be abnormal, and it is marked as the second manufacturing structure. The abnormal occurrence value corresponding to the second manufacturing structure is calculated and analyzed through the abnormal occurrence monitoring formula.

[0062] If the abnormal occurrence value corresponding to the second manufacturing structure is less than 1, it is determined that the abnormal occurrence of the production and processing corresponding to the second manufacturing structure has a normal impact, and a second optimized management plan with preset regulatory indicators is implemented.

[0063] Conversely, if the abnormality in the production and processing corresponding to the second manufacturing structure is determined to have an abnormal impact, a first optimization management plan and a second optimization management plan with preset monitoring indicators will be implemented.

[0064] The second optimization management plan specifically involves adding, deleting, and modifying the regulatory rules and content of all existing regulatory indicators in the second manufacturing structure to improve the reliability of existing regulatory indicator supervision.

[0065] It is understandable that when the abnormal execution state corresponding to the abnormal manufacturing structure is abnormal, there are two problems: one is that the existing preset supervision indicators of the second manufacturing structure are abnormal in operation, and the other is that the existing preset supervision indicators of the second manufacturing structure are abnormal in operation, and the coverage of the existing preset supervision indicators of the second manufacturing structure is incomplete and can no longer meet the quality supervision requirements of the second manufacturing structure.

[0066] It is worth noting that, unlike existing technical solutions that only focus on the processing, analysis and alerting of regulatory data for conventional regulatory indicators, this invention proactively conducts diversified monitoring and analysis of anomalies in existing regulatory indicators for different abnormal manufacturing structures, and implements diversified optimization management for different abnormal manufacturing structures based on the analysis results, thereby improving the diversity of proactive processing and analysis of quality inspection data for different processing stages of precision parts.

[0067] By utilizing optimization management scheme data for different abnormal manufacturing structures, proactive analysis is conducted to uncover the impact of optimization implementation on the relevant processing stages. Based on the analysis results, proactive optimization management is then adaptively applied to other non-abnormal manufacturing structures within the processing stages; including:

[0068] In the statistical processing stage, the total number of optimizations implemented under the first optimization management plan (M1), the total number of optimizations implemented under the second optimization management plan (M2), and the total number of optimizations implemented under both the first and second optimization management plans (M3) are calculated. The total number of optimizations in the first, second, and third optimization stages are then sequentially calculated using the formula... Calculate the corresponding optimization implementation impact value YYk; where k is 1, 2, and 3, representing implementing only the first optimization management plan, implementing only the second optimization management plan, and implementing both the first and second optimization management plans, respectively; M0 is the total number of all manufacturing structures under supervision for the processing stage; βk is β1, β2, and β3, which are the optimization implementation impact thresholds corresponding to implementing different optimization management plans, which can be determined based on the existing processing industry design requirements data for different processing stages, or the preliminary test data before the processing stage is put into production;

[0069] It should be explained that the optimization implementation impact value is used to process and calculate the data of different optimization management schemes implemented in the processing stage, so as to digitally represent the impact of different optimization management schemes on other non-abnormal manufacturing structures in the processing stage; the larger the optimization implementation impact value, the greater the impact of the corresponding optimization management scheme on other non-abnormal manufacturing structures in the processing stage.

[0070] like Figure 3 As shown, when conducting proactive optimization necessity analysis and management of other non-abnormal manufacturing structures in the processing stage:

[0071] If YYk≤0, it indicates that the optimization management scheme does not need to actively optimize other non-abnormal manufacturing structures in the processing stage;

[0072] Conversely, it indicates that the optimization management plan needs to proactively optimize other non-abnormal manufacturing structures in the processing stage, and proactively optimizes other non-abnormal manufacturing structures in the processing stage using the optimization management plan.

[0073] It is understandable that the greater the impact value of optimization implementation, the more effective it is to proactively optimize other non-abnormal manufacturing structures in the processing stage using the corresponding optimization management plan. This can effectively reduce the impact of other non-abnormal manufacturing structures on processing quality, improve the proactive processing impact prevention effect of different non-abnormal manufacturing structures, and enhance the targeted implementation effect of different optimization management plans.

[0074] In this embodiment of the invention, the optimization management scheme data of different abnormal manufacturing structures are used to actively mine and analyze the impact of optimization implementation on the corresponding processing links. Based on the analysis results, other non-abnormal manufacturing structures in the processing links are proactively optimized and managed. This realizes the data analysis and management of proactive optimization of other non-abnormal manufacturing structures in different processing links, and further improves the diversity of proactive processing and analysis of quality inspection data of different processing links of precision parts.

[0075] In the several embodiments provided by this invention, it should be understood that the disclosed system can be implemented in other ways. For example, the embodiments of the invention described above are merely illustrative; for example, the division of modules is only a logical functional division, and there may be other division methods in actual implementation.

[0076] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or in the form of hardware plus software functional modules.

[0078] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for intelligent optimization of precision component machining processes based on multimodal data fusion, characterized in that, include: Actively monitor and process the quality inspection results of different processing stages of precision parts, and conduct data analysis on the impact of abnormal manufacturing on all abnormal manufacturing structures obtained from the monitoring of different processing stages. Based on the analysis results, dynamically mark different abnormal manufacturing structures in different processing stages and implement targeted optimization management solutions. Obtain all quality inspection results for each batch of precision parts at different processing stages, and determine all abnormal causes and abnormal manufacturing structures based on all abnormal quality inspection results for different processing stages; When analyzing the impact of abnormal manufacturing on all abnormal manufacturing structures obtained from the supervision of different processing stages, the regulatory indicator values ​​corresponding to all preset regulatory indicators when the abnormal manufacturing structure processes precision parts are obtained, and the regulatory indicator values ​​corresponding to different regulatory indicators are matched and analyzed with the preset monitoring indicator range. If the values ​​of the regulatory indicators corresponding to the regulatory indicators all fall within the preset monitoring indicator range, then the reliability identifier of the indicator associated with the regulatory indicator will be set to 0. If the value of a regulatory indicator is outside the preset monitoring indicator range, and the automatic fault monitoring technology actively intervenes to handle the situation, the reliability identifier of the indicator associated with the regulatory indicator will be set to 0. If the value of the regulatory indicator corresponding to the regulatory indicator is outside the preset monitoring indicator range, and the fault automation monitoring technology does not actively intervene to handle the situation when the value of the regulatory indicator is outside the preset monitoring indicator range, then the reliability flag of the indicator associated with the regulatory indicator will be set to 1. The reliable identifiers of all preset regulatory indicators obtained from the abnormal manufacturing structure are sorted and combined to obtain the regulatory indicator operation sequence. All elements in the regulatory indicator operation sequence are summed and set as the regulatory value ZJi corresponding to the abnormal manufacturing structure; i represents different abnormal manufacturing structures, i=1,2,3,...,n; n is a positive integer. Data analysis of the indicator monitoring values ​​is conducted to determine whether the abnormal execution status corresponding to the abnormal manufacturing structure is normal. If the indicator monitoring value is 0, the abnormal execution status corresponding to the abnormal manufacturing structure is determined to be normal, and it is marked as the first manufacturing structure. When performing data analysis on the abnormal manufacturing impact corresponding to the first manufacturing structure, obtain the total number of abnormal parts ni´ that are generated by the processing of the first manufacturing structure, where i´ represents different first manufacturing structures, i´=1, 2, 3, ..., m; m is a positive integer; And through the abnormal occurrence monitoring formula Calculate and obtain the anomaly occurrence value YFi´ corresponding to the first manufacturing structure; where Ni´ is the total number of precision parts processed in the batch corresponding to the first manufacturing structure; αi´ is the anomaly occurrence requirement value corresponding to the first manufacturing structure; If YFi´<1, then the abnormality in the production and processing corresponding to the first manufacturing structure is determined to have a normal impact, and the label of the first manufacturing structure is updated to a normal manufacturing impact structure; Conversely, if the abnormality in the production and processing corresponding to the first manufacturing structure is determined to have an impact on the abnormality, the mark of the first manufacturing structure will be updated to a special manufacturing impact structure. The first optimized management plan is to pre-set regulatory indicators for all special manufacturing impact structures; wherein, the first optimized management plan is to supplement and add to all existing regulatory indicators for the first manufacturing structure; If the indicator monitoring value is not 0, the abnormal execution state corresponding to the abnormal manufacturing structure is determined to be abnormal, and it is marked as the second manufacturing structure. The abnormal occurrence value YFi´´ corresponding to the second manufacturing structure is calculated and analyzed by the abnormal occurrence monitoring formula; i´´ represents different second manufacturing structures, i´´=1,2,3,……,nm;nm is a positive integer; If YFi´´<1, then the abnormality in the production and processing of the second manufacturing structure is determined to have a normal impact, and a second optimized management plan with preset regulatory indicators is implemented; wherein, the second optimized management plan is to add, delete, or modify the regulatory rules and regulatory content of all existing regulatory indicators of the second manufacturing structure. Conversely, if the abnormality in the production and processing corresponding to the second manufacturing structure is determined to have an abnormal impact, a first optimization management plan and a second optimization management plan with preset monitoring indicators will be implemented. By utilizing optimization management scheme data for different abnormal manufacturing structures, we can proactively mine and analyze the impact of optimization implementation on the corresponding processing links, and adaptively and proactively optimize and manage other non-abnormal manufacturing structures in the processing links based on the analysis results.

2. The intelligent optimization method for precision component machining process based on multimodal data fusion according to claim 1, characterized in that, In the statistical processing stage, the total number of optimizations implemented under the first optimization management plan (M1), the total number of optimizations implemented under the second optimization management plan (M2), and the total number of optimizations implemented under both the first and second optimization management plans (M3) are calculated. The total number of optimizations in the first, second, and third optimization stages are then sequentially calculated using the formula... Calculate the corresponding optimization implementation impact value YYk; where k is 1, 2, and 3, representing only implementing the first optimization management scheme, only implementing the second optimization management scheme, and simultaneously implementing both the first and second optimization management schemes, respectively; M0 is the total number of all manufacturing structures under supervision in the processing stage; βk is β1, β2, and β3, which are the optimization implementation impact thresholds corresponding to implementing different optimization management schemes.

3. The intelligent optimization method for precision component machining process based on multimodal data fusion according to claim 2, characterized in that, When actively optimizing other non-abnormal manufacturing structures in the processing stage, if YYk≤0, it indicates that the optimization management scheme does not need to actively optimize other non-abnormal manufacturing structures in the processing stage. Conversely, it indicates that the optimization management plan needs to proactively optimize other non-abnormal manufacturing structures in the processing stage, and proactively optimizes other non-abnormal manufacturing structures in the processing stage using the optimization management plan.

Images