Robot drilling and riveting process parameter recommendation method and device

Abstract

The invention provides a robot drilling and riveting process parameter recommendation method and device, and the method comprises the steps: calculating the weighted cosine similarity of a target machining quality parameter and a historical machining scheme, and screening out an alternative machining scheme set based on the weighted cosine similarity; judging whether the alternative processing scheme meets a triggering condition of a rule in a preset rule base or not to obtain a judgment result; determining an overall quality score of the alternative processing scheme set according to the judgment result and the weighted cosine similarity corresponding to each alternative processing scheme; determining individual quality scores of the alternative processing schemes; determining the confidence coefficient of the alternative processing scheme according to the individual quality score and the overall quality score; selecting a recommended processing scheme according to the confidence coefficient of the alternative processing scheme; when the recommended processing scheme meets the target rule, processing parameters in the recommended processing scheme are corrected based on correction operation indicated by the target rule, otherwise, original processing parameters are reserved, and a corrected processing scheme is obtained; and recommending the corrected processing scheme to the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot drilling and riveting, and in particular to a robot drilling and riveting process parameter recommendation method and device. BACKGROUND

[0002] Robot drilling and riveting processes are widely used in modern manufacturing, and their processing quality directly affects the performance and reliability of the final product. Reasonably selecting and adjusting drilling and riveting process parameters is crucial for ensuring processing quality and improving production efficiency. With the development of digitalization and intelligentization of manufacturing processes, process parameter recommendation based on historical processing data has gradually become an important means to improve process level.

[0003] Existing process parameter recommendation methods usually rely on similarity measures between historical data and target quality parameters to assist in determining appropriate process parameters by matching historical processing schemes. However, in actual production environments, processing quality parameters are multi-dimensional and complex, and the relative importance of different parameters varies greatly, making it difficult for a single similarity measure to accurately make recommendations. SUMMARY

[0004] Therefore, the present application provides a robot drilling and riveting process parameter recommendation method and device for reliably and accurately recommending dual-robot drilling and riveting process parameters.

[0005] Specifically, the present application is implemented through the following technical solutions:

[0006] The first aspect of the present application provides a robot drilling and riveting process parameter recommendation method, which comprises:

[0007] In response to a user input target processing quality parameter, based on the weight determined in advance for each target processing quality parameter, the weighted cosine similarity between the target processing quality parameter and the historical processing scheme in the pre-established dual-robot drilling and riveting process knowledge graph is calculated, and a set of candidate processing schemes is selected;

[0008] For each candidate processing scheme, it is determined whether the historical processing quality parameters in the candidate processing scheme meet the triggering conditions of the rules in the preset rule library, and a judgment result is obtained;

[0009] According to the judgment result and the weighted cosine similarity of each candidate processing scheme in the candidate processing scheme set, an overall quality score of the candidate processing scheme set is determined;

[0010] For each candidate processing scheme, based on the matching of the candidate processing scheme and the rules in the preset rule library in the judgment result, an individual quality score of the candidate processing scheme is determined, and according to the individual quality score and the overall quality score, a confidence of the candidate processing scheme is determined;

[0011] recommend a recommended machining scheme from the set of alternative machining schemes according to the weighted cosine similarity and the confidence of each alternative machining scheme;

[0012] when the historical machining quality parameters in the recommended machining scheme satisfy the trigger condition of a target rule in the preset rule library, perform a correction operation on the machining parameters in the recommended machining scheme based on the correction operation indicated by the target rule, otherwise, keep the original machining parameters, to obtain a corrected machining scheme;

[0013] recommend the corrected machining scheme to the user.

[0014] The second aspect of the present application provides a robot drilling and riveting process parameter recommendation device, the device comprises a screening module, a judgment module, a determination module, a correction module and a recommendation module; wherein,

[0015] The screening module is configured to calculate the weighted cosine similarity between the target machining quality parameter and historical machining schemes in a pre-established dual-robot drilling and riveting process knowledge graph based on the weight of each target machining quality parameter determined in advance in response to the target machining quality parameter input by the user, and screen out a set of alternative machining schemes.

[0016] The judgment module is configured to determine whether the historical machining quality parameters in each alternative machining scheme satisfy the trigger condition of a rule in a preset rule library, to obtain a judgment result.

[0017] The determination module is configured to determine the overall quality score of the set of alternative machining schemes according to the judgment result and the weighted cosine similarity of each alternative machining scheme in the set of alternative machining schemes.

[0018] The determination module is further configured to determine the individual quality score of each alternative machining scheme based on the matching of the alternative machining scheme and the rule in the preset rule library in the judgment result, and determine the confidence of the alternative machining scheme according to the individual quality score and the overall quality score.

[0019] The determination module is further configured to recommend a recommended machining scheme from the set of alternative machining schemes according to the weighted cosine similarity and the confidence of each alternative machining scheme.

[0020] The correction module is configured to perform a correction operation on the machining parameters in the recommended machining scheme based on the correction operation indicated by the target rule when the historical machining quality parameters in the recommended machining scheme satisfy the trigger condition of a target rule in the preset rule library, otherwise, keep the original machining parameters, to obtain a corrected machining scheme.

[0021] The recommendation module is configured to recommend the modified machining scheme to the user.

[0022] The robot drilling process parameter recommendation method and device provided by the application, first aspect: when screening the set of alternative machining schemes, the weight of each target machining quality parameter is determined, and the weighted cosine similarity between the target machining quality parameter and the historical machining scheme is calculated by using the weights, so that the historical machining scheme similar to the target machining requirement can be more accurately found, and the set of alternative machining schemes is screened out; second aspect: by matching the historical machining quality parameter in each alternative machining scheme with the rules in the preset rule library, it is ensured that the alternative machining scheme not only is similar to the target requirement, but also strictly follows the key rules of process safety, quality and efficiency, effectively filters out the schemes that do not meet the process requirements, and improves the overall quality level of the recommended scheme; third aspect: the confidence of each alternative machining scheme is calculated by combining the overall quality score and the individual quality score, so as to provide a comprehensive and quantifiable evaluation index, which not only enhances the interpretability of the recommended result, but also provides a more intuitive and reliable basis; fourth aspect: when the recommended machining scheme meets the specific rule triggering condition, the technology can automatically correct the parameters, so as to ensure that the machining scheme can flexibly cope with the dynamic changes in actual production, and greatly improves the adaptability and robustness of the machining process. In this way, through precise matching, rule constraint, comprehensive evaluation, dynamic adjustment and recommendation in turn, the accuracy, flexibility and practicality of the double-robot drilling process parameter recommendation are significantly improved, and the reliable guarantee of the robot drilling operation is realized. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The flowchart of the robot drilling process parameter recommendation method provided by the application is provided.

[0024] Figure 2 The construction schematic diagram of the double-robot drilling process knowledge graph provided by the exemplary embodiment of the application is provided.

[0025] Figure 3 The schematic diagram of the mode layer of the double-robot drilling process knowledge graph provided by the exemplary embodiment of the application is provided.

[0026] Figure 4 The hardware structure diagram of the robot drilling process parameter recommendation device provided by the application is provided.

[0027] Figure 5 The structural schematic diagram of the robot drilling process parameter recommendation device provided by the application is provided. DETAILED DESCRIPTION

[0028] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description of the exemplary embodiments is only to illustrate the present application and is not intended to represent all the embodiments consistent with the present application.

[0029] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0030] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0031] The following specific embodiments are given to illustrate the technical solutions of the present application in detail.

[0032] Figure 1 The flowchart of the robot drilling and riveting process parameter recommendation method embodiment one of the present application is provided. Please refer to Figure 1 The method provided in the embodiment can include:

[0033] S101, in response to the target machining quality parameter input by the user, based on the weight determined in advance for each target machining quality parameter, calculating the weighted cosine similarity of the target machining quality parameter and the historical machining scheme in the pre-established double robot drilling and riveting process knowledge graph, and selecting a set of candidate machining schemes based on the calculated weighted cosine similarity.

[0034] Specifically, the specific data types contained in the target machining quality parameter input by the user are pre-set according to actual needs, which are not limited in the embodiment. For example, in an embodiment, the target machining quality parameter required during drilling and riveting operation can be determined according to the model of the robot. For example, in an embodiment, the target machining quality parameter is specifically shown in Table 1:

[0035] Table 1 Target machining quality parameter

[0036] Further, in combination with the example shown in Table 1, for example, in an embodiment, the target machining quality parameters input by the user are: pier head height 2.0±0.05mm, pier head diameter 7.0±0.1mm, riveting interference 0.05±0.02mm, nail head flatness ≤0.03mm, hole diameter 5.0±0.02mm, burr height ≤0.04mm.

[0037] It should be noted that each target machining quality corresponds to a weight, and the weight reflects the importance of different machining quality parameters in the recommendation process.

[0038] Optionally, in a possible implementation, the determination process of the weight of each target machining quality parameter determined in advance is as follows:

[0039] (1) The relative importance of any two target machining quality parameters in machining quality is judged, and a judgment matrix is formed based on the judgment result.

[0040] Specifically, each machining quality parameter in the target machining quality parameters is compared with another machining quality parameter, and the comparison result is placed in the corresponding position of the matrix to form the judgment matrix.

[0041] The element in the judgment matrix can represent the relative importance of the ith target machining quality parameter with respect to the jth target machining quality parameter, and the value of the element is given based on the 1-9 scale method.

[0042] Specifically, the judgment matrix can be as follows:

[0043] ;

[0044] Wherein, A is the judgment matrix; the element can represent the relative importance of the ith target machining quality parameter with respect to the jth target machining quality parameter.

[0045] Specifically, the value of the element in the judgment matrix can be given based on the 1-9 scale method, and then the importance of each target machining quality parameter is determined based on expert experience, and the relatively important parameter is adjusted to a larger value.

[0046] In a specific implementation, in an embodiment, the judgment matrix corresponding to all target machining quality parameters formed based on the relative importance is as follows:

[0047] ;

[0048] Wherein, A1 is the judgment matrix corresponding to all target machining quality parameters.

[0049] ​(2) using a normalization method to solve the eigenvectors and the maximum eigenvalue of the judgment matrix.

[0050] Specifically, the eigenvalue decomposition is performed on the judgment matrix using the normalization method to solve the eigenvectors and the corresponding eigenvalues of the matrix. At this time, the eigenvector corresponding to the maximum eigenvalue is the required weight vector.

[0051] In a specific implementation, the eigenvectors can be calculated based on the following formula:

[0052] ;

[0053] wherein, is the eigenvector corresponding to the i-th row, n is the number of rows of the judgment matrix, and n takes a value from 1 to 6.

[0054] Further, the maximum eigenvalue can be calculated based on the following formula:

[0055] ;

[0056] wherein, is the maximum eigenvalue, is the eigenvector corresponding to the i-th row, is the eigenvector corresponding to the j-th row.

[0057] (3) taking the eigenvector as the initial weight vector of all target machining quality parameters.

[0058] In a specific implementation, for example, in an embodiment, the eigenvector obtained after normalization is taken as the initial weight vector.

[0059] (4) calculating the consistency index of the judgment matrix of the initial weight vector according to the maximum eigenvalue.

[0060] In a specific implementation, the consistency index of the judgment matrix can be calculated based on the following formula:

[0061] ;

[0062] wherein, CI is the consistency index of the judgment matrix, is the maximum eigenvalue.

[0063] (5) calculating the consistency ratio of the judgment matrix according to the consistency index and the random consistency index, and determining the initial weight vector as the weight vector corresponding to all target machining quality parameters when the consistency ratio is less than a preset threshold, otherwise, re-performing the judgment on the relative importance of any two target machining quality parameters in the machining quality, and forming a judgment matrix based on the judgment result until the consistency ratio is less than the preset threshold.

[0064] Specifically, the formula for calculating the consistency ratio is as follows: .

[0065] Specifically, the specific value of the preset threshold is set according to actual needs, and this embodiment does not limit it. For example, in one embodiment, the preset threshold can be 0.1.

[0066] In specific implementation, for example, in one embodiment, the number of rows n of the determination matrix is ​​6, then... Substituting the value into the above formula, we get CI = 0.029. When n is 6, the random consistency index RI = 1.24. When CR < 0.1, the judgment matrix is ​​considered to have satisfactory consistency, and the calculated consistency ratio CI = 0.023 indicates that the judgment matrix has satisfactory consistency. For example, in another embodiment, if CR > 0.1, the consistency of the judgment matrix is ​​considered poor. Therefore, the relative importance of each target processing quality parameter is reassessed, and a new consistency ratio is calculated.

[0067] Understandably, accurately determining the weight of each target machining quality parameter through the analytic hierarchy process (AHP) significantly improves the accuracy of process parameter recommendations. First, pairwise comparisons are performed on the target machining quality parameters to construct a judgment matrix. Then, the relative importance of each parameter is quantified based on expert evaluation results. Subsequently, the eigenvectors and maximum eigenvalues ​​of the judgment matrix are solved using a normalization method to obtain the initial weight vector. By calculating the consistency index and consistency ratio, the consistency of the judgment matrix is ​​ensured to meet a preset threshold, thus obtaining reliable target machining quality parameter weights. This weight determination method not only enhances the scientific rigor of parameter recommendations but also effectively improves the accuracy and practicality of the intelligent recommendation system for dual-robot drilling and riveting process parameters.

[0068] In this step, instead of directly calculating the cosine similarity, the weighted cosine similarity between the target processing quality parameters and the historical processing schemes in the pre-established dual-robot drilling and riveting process knowledge graph is calculated, and a set of alternative processing schemes is selected based on the calculated weighted cosine similarity.

[0069] It should be noted that the dual-robot drilling and riveting process knowledge graph is a domain knowledge graph used to store and organize knowledge related to the dual-robot drilling and riveting process. The dual-robot drilling and riveting process knowledge graph combines information such as process knowledge, material properties, and processing parameters, and is represented and stored in the form of a graph structure.

[0070] The double-robot drilling and riveting process knowledge graph is constructed based on historical drilling and riveting process data related to the robot drilling and riveting process, adopts an ontology structure with tools, processes, workpieces, and processing results as core elements, and realizes the association and organization between multiple elements through a processing scheme entity. Optionally, in one possible implementation, Figure 2 The implementation principle of constructing a double-robot drilling and riveting process knowledge graph is provided for an exemplary embodiment of the present application. Please refer to Figure 2 In constructing the double-robot drilling and riveting process knowledge graph, a top-down and bottom-up combined construction method is adopted in this paper. First, through the analysis of historical process data, and under the guidance of experts, the mode layer of the double-robot drilling and riveting process knowledge graph is analyzed to establish a good concept hierarchy. Then, the construction of the data layer is completed through knowledge extraction of entities, relationships, and attributes. Finally, the mode layer and the data layer are associated and mapped and imported into the Neo4j graph database to obtain the double-robot drilling and riveting process knowledge graph.

[0071] (1) Mode layer design.

[0072] The knowledge graph system structure mainly includes a mode layer and a data layer. The mode layer is above the data layer and includes the concept hierarchy of processing steps, processing parameters, processing quality, and other knowledge classes in the production process, as well as the constraint relationship between levels. The data layer is a unit of fact triples that saves specific data information. Each entity in the triples contains specific attributes and corresponding numerical values.

[0073] Table 2 Knowledge graph structure

[0074] Structure Content Example Instance Schema layer Data source knowledge structure Concept, relationship Entity-relationship-entity, entity-attribute-value Data layer Specific knowledge information Fact triple Workpiece-having work step-welding

[0075] (2) Ontology construction.

[0076] A complete double-robot drilling and riveting process includes multiple procedures such as drilling, dimpling, riveting, and lubrication. Each procedure includes several steps, and in the step content, the processing information of one or more features is described. Therefore, considering the completeness and logicality of the double-robot process knowledge representation, the process knowledge involved in the double-robot drilling and riveting process is divided into the following 5 levels.

[0077] (1) Tool layer: The tool layer mainly includes drill bits, robots performing drilling and riveting processes, and robot combinations composed of two robots. The reason for such setting is that in aviation panel drilling and riveting, the quality of the workpiece varies greatly. If the robot load is less than the workpiece quality, the processing requirements cannot be met.

[0078] (2) Process layer: The process layer mainly includes specific processing parameters, which are mainly divided into drilling process parameters and riveting process parameters. The drilling process parameters include drilling parameters such as hole making speed, hole making feed, counterbore speed, counterbore feed, and hole making depth. The riveting process parameters include top iron pressure, riveting pressure, hammer riveting time, clamping force, and pressing force.

[0079] (3) Workpiece layer: The workpiece layer mainly includes the shape, size, and material of the workpiece to be processed. The material is a sub-entity of the workpiece, including the material name, strength, and thermal conductivity.

[0080] (4) Feature layer: The feature layer mainly includes the processing results corresponding to the processing technology, including hole diameter, head height, head diameter, head flatness, and rivet interference.

[0081] (5) Case layer (processing scheme layer): The case layer mainly serves as a bridge between the entity layers, including the use of robots, tools, workpieces, drilling processes, riveting processes, and drilling and riveting quality. The four levels of information and the relationships between them in the double-robot drilling and riveting process are analyzed from the four levels. The process knowledge can be summarized comprehensively to improve the completeness, relevance, and reasoning speed of the process. Each processing scheme is used to represent the use of robots, tools, workpieces, drilling processes, riveting processes, and drilling and riveting quality, that is, which combination of robots is used, which drill tool is used, which process parameters are called, which workpiece is processed, and the corresponding processing quality parameters.

[0082] (3) Data layer storage.

[0083] After the ontology model is constructed, the data layer is stored: the schema layer and the data layer can be associated and mapped, and imported into the Neo4j graph database, and then a double-robot drilling and riveting process knowledge graph is established in the database, which includes entities, relationships, and attributes.

[0084] In specific implementation, the data can be processed and arranged into a table after decryption, stored in xml format, and the xml data can be automatically read by the panda library in python, stored in the neo4j database, and the ontology relationship is constructed. The constructed part of the triple table is shown in Table 1, and Table 3 shows the triple table of the schema layer according to an example embodiment of the present application.

[0085] Table 3

[0086] It should be noted that in this embodiment, the constructed double-robot drilling and riveting process knowledge graph includes 292 entities and 711 relationships.

[0087] Specifically, in this step, the target machining quality parameters and the pre-established dual-robot drilling and riveting process knowledge graph can be input into the similarity calculation model to obtain the machining scheme with high weighted cosine similarity to the target machining quality parameters in the dual-robot drilling and riveting process knowledge graph.

[0088] In specific implementation, the step of calculating the weighted cosine similarity between the target processing quality parameter and historical processing schemes in a pre-established dual-robot drilling and riveting process knowledge graph, based on pre-determined weights for each target processing quality parameter, includes:

[0089] (1) Normalize the target processing quality parameter and the historical processing quality parameter in the historical processing scheme respectively to obtain the normalized value of the target processing quality parameter and the normalized value of the historical processing quality parameter.

[0090] Specifically, a min-max normalization method can be used to scale the value of each target processing quality parameter to the [0,1] range to eliminate the differences in dimensions and numerical ranges between different target processing quality parameters, making them comparable.

[0091] Furthermore, the same normalization method as the target processing quality parameter can be used to scale the values ​​of the historical processing quality parameters to the [0,1] range, thereby eliminating the differences in dimensions and numerical ranges and making the historical processing quality parameters comparable to the target processing quality parameters.

[0092] (2) Based on the normalized values ​​of the target machining quality parameters and the normalized values ​​of the historical machining quality parameters, calculate the weighted cosine similarity between the target machining quality parameters and the historical machining schemes in the pre-established dual-robot drilling and riveting process knowledge graph according to the following formula:

[0093] ;

[0094] Among them, the The weighted cosine similarity is denoted as n, where n is the number of dimensions of the target processing quality parameter. Let xi be the weights pre-determined for the i-th dimension target processing quality parameter, yi be the normalized value of the i-th dimension target processing parameter, and yi be the normalized value of the i-th dimension historical processing quality parameter.

[0095] It is understandable that the closer the weighted cosine similarity value is to 1, the more similar the target processing quality parameters are to the processing quality parameters of the historical processing scheme; the closer it is to -1, the less similar they are; and the closer it is to 0, the less related they are.

[0096] It can be understood that by calculating the weighted pre-similarity, the accurate matching of the target machining quality parameter and the historical machining scheme in the dual-robot drilling and riveting process knowledge graph is realized, the differences in dimensions and numerical ranges between parameters are eliminated through normalization processing, so that different parameters are comparable, the weighted cosine similarity calculation fully considers the importance of each dimension parameter, and by introducing the pre-determined weight, the similarity between the target machining quality parameter and the historical machining scheme is more accurately reflected, the accuracy of the process parameter recommendation is effectively improved, and a more scientific and reliable parameter selection basis is provided for the dual-robot drilling and riveting process.

[0097] Further, after calculating the weighted cosine similarity value, the topK machining scheme set can be selected according to the order from high to low of the weighted cosine similarity to determine the set of candidate machining schemes.

[0098] Further, the specific value of K is set according to actual needs, and in this embodiment, no limitation is made thereto. For example, in an embodiment, K is 20.

[0099] S102, for each candidate machining scheme, it is judged whether the historical machining quality parameter in the candidate machining scheme meets the triggering condition of the rule in the preset rule library, and a judgment result is obtained.

[0100] Specifically, the preset rule library includes a plurality of rules, each rule is used to indicate that when the preset machining parameter meets the preset triggering condition, the specified machining parameter is modified according to the specified modification operation (i.e. the recommended measure corresponding to the rule); the plurality of rules include basic rules, safety rules, quality rules and efficiency rules.

[0101] Specifically, the rule library constructed in advance can include the category to which the rule belongs, the number of each rule, the triggering condition of the rule and the recommended measure corresponding to the rule:

[0102] For example, in a possible implementation, Table 4 is a partial table of the preset rule library shown in an exemplary embodiment of the application:

[0103] Table 4

[0104] For each candidate machining scheme , the triggering condition in the preset rule library is matched, and after the matched triggering condition is determined, the recommended measure corresponding to the triggering rule is recorded.

[0105] S103, according to the judgment result, the weighted cosine similarity corresponding to each candidate machining scheme in the candidate machining scheme set, the overall quality score of the candidate machining scheme set is determined.

[0106] Specifically, the determination result can determine whether the processing scheme triggers a rule in the table and which rule is triggered. If a rule is triggered, it can be determined that the processing scheme has defects, so its score can be appropriately reduced. In combination with the weighted cosine similarity, the score of the similar processing scheme can be increased to obtain the overall quality score.

[0107] Optionally, in a possible implementation, the specific implementation process of the step can include:

[0108] (1) determining a data size score of the set of alternative processing schemes according to the determination result.

[0109] Specifically, the data size score is determined according to the total number of the set of alternative processing schemes, the number of valid processing schemes in the set of alternative processing schemes (a processing scheme that does not match any rule in the preset rule library is regarded as a valid processing scheme), and whether there is an invalid processing scheme in the set of alternative processing schemes (a processing scheme that matches any basic rule in the preset rule library is regarded as an invalid processing scheme, in addition, a processing scheme that satisfies a triggered rule is regarded as matching). The data size score is used to evaluate the "validity" and "conflict degree with the rule library" of a group of alternative processing schemes.

[0110] In a specific implementation, the data size score can be determined according to the following formula:

[0111] ;

[0112] wherein the data size score is denoted as S data, the number of valid alternative processing schemes in the set of alternative processing schemes that do not match the rules in the preset rule library is denoted as N valid, and the number of alternative processing schemes included in the set of alternative processing schemes is denoted as N total. is an indicator function, which takes a value of 0 when an alternative processing scheme matches a basic rule in the preset rule set, and takes a value of 1 otherwise.

[0113] Referring to the foregoing description, to evaluate the validity and innovation of the set of alternative processing schemes, the data size score is set to reflect the degree of the scheme set outside the coverage of the rule library. When any alternative processing scheme in the set of alternative processing schemes matches a basic rule, the data size score of the set of alternative processing schemes is 0. When each alternative processing scheme in the set of alternative processing schemes does not match a basic rule, the value of S data is 1, and at this time, the data rule score in the set of alternative processing schemes is equal to ​​​, through the above method, as long as there is a scheme matching the basic rule, the whole set of schemes is identified as invalid (scored 0), under the premise that all schemes do not match the basic rule, the score is given according to the proportion of valid schemes, reflecting the data size quality, through the above scoring method, the repetitive design can be effectively screened out, and the scientificity and rationality of the processing scheme evaluation are improved.

[0114] (2) Calculate the average value of the weighted cosine similarity corresponding to each alternative processing scheme in the set of alternative processing schemes, and determine the average value as the data quality score of the set of alternative processing schemes.

[0115] Specifically, by calculating the average value of the weighted cosine similarity of the alternative processing scheme, the overall similarity between the alternative processing scheme set and the target processing quality parameter can be reflected, that is, the quality level of the data can be determined by the similarity degree.

[0116] In specific implementation, the data quality score can be determined according to the following formula:

[0117] ;

[0118] Wherein, is the data quality score, is the weighted cosine similarity of the i th alternative processing scheme, and N is the number of alternative processing schemes.

[0119] (3) Calculate the standard deviation of the weighted cosine similarity corresponding to each alternative processing scheme in the set of alternative processing schemes, and determine the data distribution score of the set of alternative processing schemes based on the standard deviation and the matching of the alternative processing scheme with the safety rules in the preset rule set.

[0120] Specifically, the data distribution score reflects the concentration degree and safety of the alternative processing scheme set in the similarity distribution.

[0121] Further, the standard deviation of the weighted cosine similarity corresponding to each alternative processing scheme can measure the dispersion degree of the case set in the similarity distribution.

[0122] In specific implementation, the data distribution score can be determined according to the following formula:

[0123] ;

[0124] Wherein, D is the data distribution score, and σ is the standard deviation of the weighted cosine similarity corresponding to each alternative processing scheme, is a conflict intensity coefficient, the initial value is 1, and the value is 1.5 when a safety conflict is triggered (at least one alternative machining scheme matches at least one safety rule in the preset rule set, and it is considered that a safety conflict is triggered), so as to improve the sensitivity of the discrete degree penalty.

[0125] It should be noted that by setting the threshold value 0.3, the negative impact of high discrete degree on the overall quality score is suppressed while the advantage of low discrete degree is retained, and the robustness of the model to data noise is strengthened.

[0126] In this embodiment, first, once it is detected that a safety rule is triggered (that is, there is a scheme matching the preset safety rule), automatically increase δconflict to 1.5, reduce , and reduce the data distribution score, which means that in a safety-sensitive scenario, the system more strictly restricts design discreteness and encourages a more concentrated and safety-consistent design direction. By using the formula to calculate the data distribution score, not only can the consistency and safety matching of the scheme set be quantitatively measured, but also the conflict risk in the design process can be dynamically adapted, and the intelligent analysis and control ability of the system in a complex rule environment can be effectively improved.

[0127] (4) According to the data size score, the data quality score, and the data distribution score, determine the overall quality score of the alternative machining scheme set.

[0128] Specifically, the data size score, the data quality score, and the data distribution score can be directly summed to obtain the overall quality score of the alternative machining scheme set; or different weights can be set for the data size score, the data quality score, and the data distribution score, and the weighted result is determined as the overall quality score of the alternative machining scheme set.

[0129] In specific implementation, the overall quality score of the alternative machining scheme set can be determined according to the following formula:

[0130] Ptotal=

[0131] Wherein, Ptotal is the overall quality score.

[0132] S104, for each alternative machining scheme, based on the matching of the alternative machining scheme and the rules in the preset rule library in the judgment result, determine the individual quality score of the alternative machining scheme, and according to the individual quality score and the overall quality score, determine the confidence of the alternative machining scheme.

[0133] Specifically, when the alternative machining scheme matches the rules, the individual quality score of the alternative machining scheme can be calculated to ensure that the alternative machining scheme with more matched rules obtains a lower score, and the alternative machining scheme with less matched rules or no matched rules can obtain a higher score.

[0134] In one possible implementation, the individual quality score of the alternative processing scheme is determined according to the following formula:

[0135] ;

[0136] Among them, the The individual quality score is given, where m is the number of rules contained in the preset rule base. The penalty coefficient is a pre-set value for the i-th rule in the preset rule base. Let be the trigger coefficient of the i-th rule in the preset rule base. If the alternative processing scheme matches the i-th rule, then... Select 1 if the value is 1, otherwise select 0.

[0137] It should be noted that the penalty coefficient pre-set for the i-th rule in the preset rule base is set according to actual needs, and is not limited in this embodiment. For example, in one possible implementation,

[0138] Furthermore, in one possible implementation, determining the confidence level of the alternative processing scheme based on the individual quality score and the overall quality score includes:

[0139] (1) Based on the matching of the alternative processing scheme with the rules in the preset rule base in the judgment result, determine the first weight of the overall quality score and the second weight of the individual quality score.

[0140] In a specific implementation, in one possible approach, the first weight is determined according to the following formula, and the second weight is determined based on the first weight:

[0141] ;

[0142] Among them, the The first weight is m, where m is the number of rules contained in the preset rule base. The penalty coefficient is a pre-set value for the i-th rule in the preset rule base. Let be the trigger coefficient corresponding to the i-th rule in the preset rule base. If the alternative processing scheme matches the i-th rule, then... Select 1 if the value is 1, otherwise select 0.

[0143] Furthermore, the second weight is equal to the difference between 1 and the first weight.

[0144] (2) The individual quality score and the overall quality score are weighted based on the first weight and the second weight, and the weighted result is determined as the confidence level of the alternative processing scheme.

[0145] In a specific implementation, the second weight can be , that is, to ensure that the first weight and the second weight do not affect the rationality of the result after weighting.

[0146] In a specific implementation, the confidence of the alternative processing scheme can be determined according to the following formula:

[0147]

[0148] Wherein, C is the confidence, is the data size score, is the data quality score, and D is the data distribution score, is the first weight, is the second weight, is the individual quality score.

[0149] As described above, it can be understood that and The specific value of is pre-set according to actual needs, which is not limited in the embodiment. For example, in an embodiment, the penalty coefficient can be:

[0150]

[0151] The trigger coefficient can be:

[0152]

[0153] It can be understood that through this calculation method of combining data size score, data quality score and data distribution score, a bidirectional interaction mechanism of knowledge-data is realized, rules are used as filtering conditions for forward constraint and as weighting factors for backward correction, closed-loop feedback of confidence calculation is realized, accurate overall quality score is calculated, and through the combination of constraint truncation and dynamic weight, the balance of safety, quality and efficiency of recommended parameters is realized.

[0154] As described above, it can be understood that ​​​The influence degree of distinguishable safety / quality / efficiency rules can be adapted to different scene requirements, and the personalization and flexibility of the evaluation are improved. As long as a small number of rules are triggered, the first weight of the overall quality score will quickly decrease, which means that the influence of the overall score is rapidly reduced, and the sensitivity and response speed to the rule triggering event are improved. Further, the overall quality score plays a leading role in the confidence, and the overall quality score emphasizes the attributes of the scheme set, such as innovation, sufficient quantity, similarity concentration, and controllable noise. The rule conflict influences the individual quality score, and when the scheme violates multiple rules, ωr tends to 0, and the confidence of the alternative machining scheme depends more on the individual quality score, which strengthens the filtering ability of the rule constraint in the unsafe and unreasonable scheme.

[0155] S105, selecting a recommended machining scheme from the recommended machining scheme set according to the weighted cosine similarity and the confidence of each alternative machining scheme.

[0156] Specifically, the weighted cosine similarity and the confidence are comprehensively considered. The weighted cosine similarity reflects the matching degree of the alternative scheme and the target machining quality parameter, and the confidence reflects the reliability and stability of the alternative scheme.

[0157] In specific implementation, weighted summation, sorting selection and other methods can be used to combine the similarity and the confidence for decision-making. For example, in an embodiment, different weights can be assigned to the similarity and the confidence, the comprehensive score of each alternative scheme is calculated, and then the scheme with the highest comprehensive score is selected as the recommended machining scheme.

[0158] S106, when the historical machining quality parameter in the recommended machining scheme meets the triggering condition of the target rule in the preset rule library, the machining parameter in the recommended machining scheme is modified based on the modification operation indicated by the target rule, otherwise the original machining parameter is retained, and a modified machining scheme is obtained.

[0159] As can be understood from the foregoing description, the preset rule library includes multiple types of rules, and each type of rule has different priority; and the historical machining quality parameter in the recommended machining scheme meets the triggering condition of the target rule in the preset rule library, and the machining parameter in the recommended machining scheme is modified based on the modification operation indicated by the target rule, including:

[0160] (1) If the historical machining quality parameter in the recommended machining scheme meets the triggering condition of at least one rule under the same type of rule, the machining parameter in the recommended machining scheme is modified based on the modification operation indicated by the multiple rules in sequence.

[0161] Specifically, when all triggered rules belong to the same type, the modification is performed in sequence according to the modification operation corresponding to all satisfied triggering conditions.

[0162] In a specific implementation, for example, in an embodiment, the IC-01 and RH-01, which are both safety rules, trigger the safety rule a, and the first modification operation is to replace the high-rigidity tool and modify the step drilling process according to the modification operation indicated by IC-01, and then reduce the riveting force by 5% according to the modification operation indicated by RH-01.

[0163] (2) If the historical machining quality parameters in the recommended machining scheme satisfy the triggering conditions of multiple rules, and the multiple rules belong to different rule categories, the target rule category with the highest priority is identified according to the rule categories to which the multiple rules belong, and the machining parameters in the recommended machining scheme are sequentially modified based on the modification operations corresponding to the target rules in the target rule category.

[0164] Specifically, the target rule category with the highest priority is identified according to the categories to which the rules belong, and the modification operation indicated by the target rule category is performed.

[0165] In a specific implementation, for example, in an embodiment, the rule priority queue is: basic rule > safety rule > quality rule > efficiency rule, and when IC-01 (safety rule) and IC-02 (quality rule) are triggered at the same time, the replacement of the high-rigidity tool and the modification of the step drilling process are directly performed according to IC-01.

[0166] It should be noted that when the modification operations corresponding to multiple target rules triggered conflict, the modification operation of the conflicting part corresponding to the rule with low priority can be cancelled, and only the modification operation of the conflicting part corresponding to the rule with high priority is performed.

[0167] It can be understood that when the historical machining quality parameters in the recommended machining scheme satisfy the triggering conditions of the target rules in the preset rule library, the system can modify the machining parameters in the recommended machining scheme according to the modification operations indicated by the target rules. If the triggering conditions of at least one rule in the same rule category are satisfied, the modification is sequentially performed according to the modification operations indicated by the rules in the category. If the triggering conditions of multiple rules in different rule categories are satisfied, the target rule category with the highest priority is identified according to the priorities of the rules, and the modification is performed based on the modification operations corresponding to the target rules in the category. This modification mechanism based on the rule library ensures that the recommended machining scheme can meet the requirements of safety, quality, and efficiency, and improves the accuracy and reliability of the drilling and riveting process parameters.

[0168] In this embodiment, the preset rule library is introduced into the whole process of machining parameter recommendation. The rules not only participate in the calculation of confidence as filtering conditions in the early stage, but also participate in the modification of machining parameters in the later stage. This mechanism avoids the misjudgment risk caused by simply relying on data similarity and improves the controllability and engineering applicability of the recommended results.

[0169] In addition, this embodiment introduces a dual evaluation model of individual quality score and overall quality score to depict the quality characteristics of a single scheme and the overall scheme set respectively, and dynamically gives different weight coefficients to the scores through rule matching, and then calculates the scheme confidence. This closed-loop feedback structure enables the system to automatically identify and suppress high-similarity schemes that match key rules, thereby improving the robustness and accuracy of the recommendation system.

[0170] In addition, the rule library is subdivided into multiple categories, and the importance of the rules is distinguished through a priority determination mechanism. When multiple rules are triggered by the recommended parameters, the system can prioritize the modification strategies in the high-priority rule set and perform cascading processing on the parameter modification operations indicated by multiple rules, thereby improving the accuracy and relevance of parameter modification and ensuring high consistency between the final recommended results and user goals.

[0171] S107, recommending the modified machining scheme to the user.

[0172] In specific implementation, the modified machining scheme after modification is recommended to the user, so that the user can perform double-robot drilling and riveting operation according to the recommended scheme.

[0173] The robot drilling and riveting process parameter recommendation method has the following beneficial effects:

[0174] (1) Improve the relevance and accuracy of the recommended scheme

[0175] By introducing the weighted cosine similarity calculation between the target machining quality parameters and the historical machining schemes in the knowledge graph, the relevance between the current task and the past experience can be accurately measured, so as to optimize the historical scheme that best matches the current machining target and improve the practicality and effectiveness of the recommended parameters.

[0176] (2) Fusion of rule knowledge to enhance decision rationality

[0177] Combined with the preset rule library, the quality parameters of the candidate machining scheme are judged for compliance, which not only ensures the applicability of the machining parameters within the process rules, but also filters out potential non-compliant or low-quality schemes through the rule triggering mechanism, thereby enhancing the reliability of the recommended scheme.

[0178] (3) Multi-dimensional scoring mechanism to improve screening accuracy

[0179] By introducing individual quality score and overall quality score to the alternative processing scheme, and combining with the confidence calculation, the multi-dimensional quality of the processing scheme is quantitatively expressed, and the accuracy and reliability of the final recommended result are improved.

[0180] (4) Support intelligent correction and optimization of processing parameters

[0181] On the basis of the recommended processing scheme, if the historical processing quality parameters meet the triggering conditions of the target rules, the parameter correction and optimization can be carried out according to the rule opinions, so as to improve the processing quality and efficiency, and enhance the self-adaptation and intelligent ability of the system.

[0182] (5) Improve the process intelligent decision-making ability of the dual-robot drilling and riveting system

[0183] This method relies on the knowledge graph structure and rule reasoning mechanism, structures the experience knowledge, and intelligently recommends the parameters, effectively improving the process parameter self-adaptive decision-making ability of the dual-robot drilling and riveting system in complex manufacturing scenarios.

[0184] (6) Enhance user interaction experience and decision support ability

[0185] This method responds to the target processing quality demand set by the user, provides transparent, interpretable, and quality guaranteed processing parameter scheme through whole-process intelligent analysis and recommendation, and improves the decision support ability and interaction experience of the system for engineers.

[0186] The robot drilling process parameter recommendation method and device provided by the embodiment, first aspect: in screening the candidate processing scheme set, the weight of each target processing quality parameter is determined, and the weighted cosine similarity between the target processing quality parameter and the historical processing scheme is calculated by using the weight, so that the historical processing scheme similar to the target processing requirement can be more accurately found, and the candidate processing scheme set is screened out; second aspect: by matching the historical processing quality parameter in each candidate processing scheme with the rules in the preset rule library, it is ensured that the candidate processing scheme is not only similar to the target requirement, but also strictly follows the key rules such as process safety, quality and efficiency, effectively filters out the schemes that do not meet the process requirements, and improves the overall quality level of the recommended scheme; third aspect: the confidence of each candidate processing scheme is calculated by combining the overall quality score and the individual quality score, so as to provide a comprehensive and quantifiable evaluation index, which not only enhances the interpretability of the recommended result, but also provides more intuitive and reliable basis; fourth aspect: when the recommended processing scheme meets the specific rule triggering condition, the technology can automatically correct the parameters, so as to ensure that the processing scheme can flexibly cope with the dynamic changes in actual production, and greatly improves the adaptability and robustness of the processing process. In this way, through precise matching, rule constraint, comprehensive evaluation, dynamic adjustment and recommendation in turn, the accuracy, flexibility and practicality of the double-robot drilling process parameter recommendation are significantly improved, and the reliable guarantee of the robot drilling operation is realized.

[0187] Corresponding to the foregoing embodiment of the robot drilling process parameter recommendation method, the application also provides a corresponding verification experiment.

[0188] Specifically, the double-robot drilling process parameter recommendation device is built through the Flask framework of Python, aiming to realize the structured management and intelligent parameter decision of process knowledge in complex manufacturing scenarios. The device takes the knowledge graph and rule reasoning fusion method as the core, integrates the process parameter recommendation module through the lightweight Web service architecture, and forms a decision-making system of "data input-knowledge reasoning-parameter push".

[0189] Furthermore, to verify the knowledge graph node retrieval capabilities of the recommendation device, the following functional test was conducted: After the user triggers the node search function on the front-end interface and specifies the entity type as "processing result," they select the specific instance "drilling and riveting quality 21." The device's back-end executes a predefined Cypher retrieval statement through the graph database query engine: MATCH(n:Action{id:'drilling and riveting execution 21'})RETURNn. This statement locates the target node using the entity tag "Action" and the unique identifier "drilling and riveting execution 21," achieving accurate retrieval of specific drilling and riveting execution process entities. The query results are serialized and returned to the front-end, where a visualization component based on D3.js dynamically renders the target node and its relationships in a graph structure, including the robot combination, tools used, drilling process, riveting process, and drilling and riveting quality associated with the execution process.

[0190] Furthermore, taking the drilling and riveting process requirements of a certain enterprise with dual robots as an example, the following process quality requirements are proposed, and Table 5 shows the process quality requirements to be processed:

[0191] Table 5

[0192] Input the above process quality into the recommended device. The Top-5 similar cases recommended by the device are shown in Table 6. Table 6 shows similar cases of robot drilling and riveting processing parameters:

[0193] Table 6

[0194] Using the original cosine similarity algorithm as the baseline method, and comparing it with the improved weighted cosine similarity case recommendation algorithm, the recommended process parameters of both are shown in Table 7. Table 7 shows the recommended processing parameters:

[0195] Table 7

[0196] The overall confidence level of the above recommended parameters is 0.93, which meets the processing parameter requirements.

[0197] To verify the effectiveness of rule-based reasoning, new process quality requirements are introduced as shown in Table 8. Table 8 presents another set of process quality requirements to be processed.

[0198] Table 8

[0199] Among the parameters above, the recommended process parameters before and after the correction of safety rule RH-01 and efficiency rule MA-01 are shown in Table 9. Table 9 shows the recommended processing parameters for rule constraints:

[0200] Table 9

[0201] In the baseline method, no similar cases are found, the comprehensive confidence of the recommended parameters without rule modification is 0.81, and the comprehensive confidence after rule modification is 0.84, which is better than that before modification, proving the effectiveness of the rule constraint.

[0202] Corresponding to the foregoing embodiment of the robot drilling process parameter recommendation method, the present application also provides an embodiment of a robot drilling process parameter recommendation device.

[0203] The embodiment of the robot drilling process parameter recommendation device of the present application can be applied to a robot drilling process parameter recommendation equipment. The device embodiment can be realized by software, or realized by hardware or a combination of software and hardware. Taking software realization as an example, as a logical device, it is formed by reading the corresponding computer program instructions in the non-volatile memory into the memory for running by the processor of the robot drilling process parameter recommendation equipment where the device is located. From the hardware level, as shown in Figure 4 As shown in the figure, it is a hardware structure diagram of the robot drilling process parameter recommendation equipment where the robot drilling process parameter recommendation device of the present application is located. In addition to the processor, the memory, the network interface, and the non-volatile memory shown in the figure, the robot drilling process parameter recommendation equipment where the device in the embodiment is located usually includes other hardware according to the actual functions of the robot drilling process parameter recommendation device, which will not be described here. Figure 4

[0204] As shown in the figure, it is a hardware structure diagram of the robot drilling process parameter recommendation equipment where the robot drilling process parameter recommendation device of the present application is located. In addition to the processor, the memory, the network interface, and the non-volatile memory shown in the figure, the robot drilling process parameter recommendation equipment where the device in the embodiment is located usually includes other hardware according to the actual functions of the robot drilling process parameter recommendation device, which will not be described here. Figure 5 As shown in the figure, it is a hardware structure diagram of the robot drilling process parameter recommendation equipment where the robot drilling process parameter recommendation device of the present application is located. In addition to the processor, the memory, the network interface, and the non-volatile memory shown in the figure, the robot drilling process parameter recommendation equipment where the device in the embodiment is located usually includes other hardware according to the actual functions of the robot drilling process parameter recommendation device, which will not be described here. Figure 5 The device provided in the embodiment includes a screening module 510, a judgment module 520, a determination module 530, a modification module 540, and a recommendation module 550; wherein,

[0205] The screening module 510 is configured to calculate the weighted cosine similarity between the target machining quality parameter input by the user and the historical machining scheme in the pre-established double-robot drilling process knowledge graph based on the weight determined in advance for each target machining quality parameter, and screen out a set of candidate machining schemes.

[0206] The judgment module 520 is configured to judge whether the historical machining quality parameter in each candidate machining scheme meets the trigger condition of the rule in the pre-set rule library, and obtain a judgment result.

[0207] The determining module 530 is configured to determine an overall quality score of the set of alternative machining schemes according to the judgment result and the weighted cosine similarity corresponding to each alternative machining scheme in the set of alternative machining schemes.

[0208] The determining module 530 is further configured to determine, for each alternative machining scheme, an individual quality score of the alternative machining scheme based on a matching condition of the alternative machining scheme and a rule in the preset rule library in the judgment result, and determine a confidence of the alternative machining scheme according to the individual quality score and the overall quality score.

[0209] The determining module 530 is further configured to select a recommended machining scheme from the set of alternative machining scheme recommendation according to the weighted cosine similarity and the confidence of each alternative machining scheme.

[0210] The correcting module 540 is configured to perform a correction operation on a machining parameter in the recommended machining scheme based on a correction operation indicated by a target rule in the preset rule library when a historical machining quality parameter in the recommended machining scheme satisfies a trigger condition of the target rule, or otherwise retain an original machining parameter to obtain a corrected machining scheme.

[0211] The recommending module 550 is configured to recommend the corrected machining scheme to the user.

[0212] The apparatus of the embodiment can be used to execute the steps of the method embodiment, and the specific implementation principle and implementation process are similar, which will not be described here. Figure 1 The steps of the method embodiment are shown in the method embodiment, and the specific implementation principle and implementation process are similar, which will not be described here.

[0213] Please continue to refer to Figure 4 The application further provides a robot drilling process parameter recommendation device, which comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the processor implements the steps of any one of the methods provided in the first aspect of the application when executing the program.

[0214] The application further provides a computer readable storage medium having a computer program stored thereon, and the program is executed by the processor to implement the steps of any one of the methods provided in the application.

[0215] The implementation process of the functions and roles of each unit in the above apparatus is specifically described in the implementation process of the corresponding steps in the above method, which will not be described here.

[0216] For the apparatus embodiment, since it basically corresponds to the method embodiment, the relevant part can be seen from the part of the method embodiment. The apparatus embodiment described above is only illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the application according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0217] The above only describes the preferred embodiments of the present application and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for recommending process parameters for robot drilling and riveting, characterized in that, The method includes: In response to the target processing quality parameters input by the user, the weighted cosine similarity between the target processing quality parameters and the historical processing schemes in the pre-established dual-robot drilling and riveting process knowledge graph is calculated based on the weights pre-determined for each target processing quality parameter. Based on the calculated weighted cosine similarity, a set of alternative processing schemes is selected. For each alternative processing scheme, determine whether the historical processing quality parameters of the alternative processing scheme meet the triggering conditions of the rules in the preset rule base, and obtain the judgment result; Based on the judgment result and the weighted cosine similarity corresponding to each alternative processing scheme in the alternative processing scheme set, the overall quality score of the alternative processing scheme set is determined; For each alternative processing scheme, based on the matching results between the alternative processing scheme and the rules in the preset rule base, the individual quality score of the alternative processing scheme is determined, and the confidence level of the alternative processing scheme is determined based on the individual quality score and the overall quality score. Based on the weighted cosine similarity and confidence of each alternative processing scheme, a recommended processing scheme is selected from the recommended set of alternative processing schemes; When the historical processing quality parameters in the recommended processing scheme meet the triggering conditions of the target rule in the preset rule base, the processing parameters in the recommended processing scheme are corrected based on the correction operation indicated by the target rule; otherwise, the original processing parameters are retained to obtain the corrected processing scheme. The revised processing solution is recommended to the user.

2. The method according to claim 1, characterized in that, The step of determining the overall quality score of the candidate processing scheme set based on the judgment result and the weighted cosine similarity corresponding to each candidate processing scheme in the candidate processing scheme set includes: Based on the judgment result, the data size score of the alternative processing scheme set is determined; Calculate the average weighted cosine similarity of each alternative processing scheme in the alternative processing scheme set, and determine the average value as the data quality score of the alternative processing scheme set; Calculate the standard deviation of the weighted cosine similarity corresponding to each alternative processing scheme in the alternative processing scheme set, and determine the data distribution score of the alternative processing scheme set based on the standard deviation and the matching of the alternative processing scheme with the security class rules in the preset rule set; The overall quality score of the alternative processing scheme set is determined based on the data size score, the data quality score, and the data distribution score.

3. The method according to claim 1, characterized in that, The step of determining the individual quality score of the alternative processing scheme based on the matching results between the alternative processing scheme and the rules in the preset rule base includes: The individual quality score for the alternative processing option is determined using the following formula: ； Among them, the The individual quality score is given, where m is the number of rules contained in the preset rule base. The penalty coefficient is a pre-set value for the i-th rule in the preset rule base. Let be the trigger coefficient corresponding to the i-th rule in the preset rule base. If the alternative processing scheme matches the i-th rule, then... Select 1 if the value is 1, otherwise select 0.

4. The method according to claim 3, characterized in that, Based on the individual quality score and the overall quality score, the confidence level of the alternative processing plan is determined, including: Based on the matching results of the alternative processing scheme with the rules in the preset rule base, the first weight of the overall quality score and the second weight of the individual quality score are determined. The individual quality score and the overall quality score are weighted based on the first weight and the second weight, and the weighted result is determined as the confidence level of the alternative processing scheme.

5. The method according to claim 4, characterized in that, The determination of the first weight of the overall quality score and the second weight of the individual quality score based on the matching of the alternative processing scheme with the rules in the preset rule base in the judgment result includes: The first weight is determined according to the following formula, and the second weight is determined based on the first weight: ； Among them, the The first weight is m, where m is the number of rules contained in the preset rule base. The penalty coefficient is a pre-set value for the i-th rule in the preset rule base. The trigger coefficient is the i-th rule in the preset rule base.

6. The method according to claim 2, characterized in that, The step of determining the data size score of the alternative processing scheme set based on the judgment result includes: Determine the data size score using the following formula: ； Among them, the Scoring is given to the data size, the The number of valid alternative processing schemes in the alternative processing scheme set that do not match the rules in the preset rule base. The number of alternative processing schemes included in the alternative processing scheme set; This is an indicator function. When the alternative processing scheme in the set of alternative processing schemes matches the basic rule in the set of preset rules, its value is 0; otherwise, its value is 1.

7. The method according to claim 1, characterized in that, The step of calculating the weighted cosine similarity between the target machining quality parameter and historical machining schemes in a pre-established dual-robot drilling and riveting process knowledge graph, based on pre-determined weights for each target machining quality parameter, includes: The target processing quality parameters and the historical processing quality parameters in the historical processing schemes are normalized respectively to obtain the normalized values ​​of the target processing quality parameters and the historical processing quality parameters. Based on the normalized values ​​of the target machining quality parameters and the historical machining quality parameters, the weighted cosine similarity between the target machining quality parameters and the historical machining schemes in the pre-established dual-robot drilling and riveting process knowledge graph is calculated using the following formula: ； Among them, the The weighted cosine similarity is denoted as n, where n is the number of dimensions of the target processing quality parameter. Let xi be the weights pre-determined for the i-th dimension target processing quality parameter, yi be the normalized value of the i-th dimension target processing parameter, and yi be the normalized value of the i-th dimension historical processing quality parameter.

8. The method according to claim 1, characterized in that, The preset rule base includes multiple rule categories, each with a different priority; the historical processing quality parameters in the recommended processing scheme meet the triggering conditions of the target rule in the preset rule base, and the processing parameters in the recommended processing scheme are corrected based on the correction operation indicated by the target rule, including: If the historical processing quality parameters in the recommended processing scheme meet the triggering condition of at least one rule under the same type of rule, then the processing parameters in the recommended processing scheme are corrected sequentially based on the correction operations indicated by the multiple rules. If the historical processing quality parameters in the recommended processing scheme meet the triggering conditions of multiple rules, and the multiple rules belong to different rule categories, the target rule category with the highest priority is identified according to the rule category to which the multiple rules belong, and the processing parameters in the recommended processing scheme are corrected in sequence based on the correction operation corresponding to the target rule under the target rule category among the multiple rules.

9. The method according to claim 1, characterized in that, The method for determining the weights pre-determined for each target processing quality parameter includes: The relative importance of any two target processing quality parameters in the processing quality is evaluated, and a judgment matrix is ​​formed based on the evaluation results; The eigenvectors and the largest eigenvalue of the judgment matrix are obtained using a normalization method. The feature vector is used as the initial weight vector for all target processing quality parameters; Based on the largest eigenvalue, calculate the consistency index of the judgment matrix using the initial weight vector; The consistency ratio of the judgment matrix is ​​calculated based on the consistency index and random consistency index of the judgment matrix. When the consistency ratio is less than a preset threshold, the initial weight vector is determined as the weight vector corresponding to all target processing quality parameters. Otherwise, the relative importance of any two target processing quality parameters in the processing quality is evaluated again, and a judgment matrix is ​​formed based on the evaluation results until the consistency ratio is less than the preset threshold.

10. A device for recommending process parameters for robot drilling and riveting, characterized in that, The device includes a screening module, a judgment module, a determination module, a correction module, and a recommendation module; wherein, The filtering module is used to respond to the target processing quality parameters input by the user, calculate the weighted cosine similarity between the target processing quality parameters and the historical processing schemes in the pre-established dual-robot drilling and riveting process knowledge graph based on the weights determined in advance for each target processing quality parameter, and filter out a set of alternative processing schemes. The judgment module is used to determine, for each alternative processing scheme, whether the historical processing quality parameters of the alternative processing scheme meet the triggering conditions of the rules in the preset rule base, and obtain the judgment result; The determining module is used to determine the overall quality score of the set of alternative processing schemes based on the judgment result and the weighted cosine similarity corresponding to each alternative processing scheme in the set of alternative processing schemes. The determining module is further configured to, for each alternative processing scheme, determine the individual quality score of the alternative processing scheme based on the matching situation between the alternative processing scheme and the rules in the preset rule base in the judgment result, and determine the confidence level of the alternative processing scheme based on the individual quality score and the overall quality score; The determining module is further configured to select a recommended processing scheme from the recommended set of alternative processing schemes based on the weighted cosine similarity and confidence of each alternative processing scheme; The correction module is used to correct the processing parameters in the recommended processing scheme based on the correction operation indicated by the target rule when the historical processing quality parameters in the recommended processing scheme meet the triggering conditions of the target rule in the preset rule base; otherwise, the original processing parameters are retained to obtain the corrected processing scheme. The recommendation module is used to recommend the modified processing scheme to the user.

Images