Process scheme generation method, system and equipment based on knowledge base and medium

Abstract

The invention provides a process scheme generation method, system and equipment based on a knowledge base and a medium, and belongs to the technical field of production intellectualization. The method comprises the following steps: firstly, constructing a process knowledge model comprising a processing task, a resource and a scheme model, generating a corresponding task table and a scheme table, and storing the task table and the scheme table in a process knowledge database; then, the processing task file is analyzed in detail, and basic information, blank information, workpiece shape information and feature attribute information of the processing task are extracted; the information is utilized to gradually retrieve and screen out the process scheme meeting the requirements in the process knowledge base, and the temporary file is continuously updated according to the new information in the process. Finally, in combination with a local processing resource file, feasibility verification is performed on the screened schemes, the schemes which cannot be implemented are excluded, and it is ensured that the output process scheme is efficient and feasible. According to the method, the universality of the knowledge base and the accuracy of real-time resource verification are combined, and the intelligent level of process scheme generation is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent production, and more specifically relates to a process plan generation method, system, equipment and medium based on a knowledge base. Background Art

[0002] In modern manufacturing systems, process planning is the bridge between design and production, and its importance is self-evident. Especially in the context of the prevalence of mass customization production, process planning plays a core role in accurately transforming design specifications into actual production operations. However, traditional process planning methods are unable to cope with this complex and ever-changing challenge, and there are many defects that need to be solved.

[0003] Firstly, the traditional process planning is cumbersome and requires a lot of time and manpower for manual calculation and evaluation, which results in low overall planning efficiency and inability to respond to market changes in a timely manner and meet the needs of diversified products.

[0004] Secondly, traditional process planning methods are highly dependent on manual experience and fixed processes, resulting in a lack of flexibility and customizability in process plans, making it difficult to quickly adjust and optimize them to meet the needs of different products.

[0005] Furthermore, there is a problem of poor information exchange in traditional process planning methods. In the process of process planning, each link needs to work closely together and share data and information. However, traditional process planning methods often lead to the formation of information islands between each link, and data and information cannot be effectively shared, which not only increases the uncertainty and error in the planning process, but also reduces the overall production efficiency.

[0006] In addition, traditional process planning methods rely heavily on the experience of staff, resulting in instability and unpredictability of planning results.

[0007] As an important part of modern manufacturing systems, intelligent process planning aims to overcome the shortcomings of traditional process planning and improve planning efficiency and accuracy. However, intelligent process planning is a complex task involving multiple subtasks, such as machine selection, determining process routes, setting process parameters, and tool selection. Among these subtasks, determining process routes is one of the difficulties in realizing intelligent manufacturing. Traditional process route determination methods often rely on manual experience and trial and error, which is not only inefficient but also difficult to guarantee the optimal solution.

[0008] Therefore, there is an urgent need for an efficient, accurate and intelligent process route determination method to meet the diverse product needs under the mass customization production model. Summary of the invention

[0009] In response to the above problems, the purpose of the present invention is to provide a process plan generation method, system, equipment and medium based on a knowledge base. By constructing a process knowledge model and storing it in a database, and utilizing technical means such as multi-level information screening, feature similarity calculation and process parameter generator, it is possible to intelligently match and generate process plans that meet the requirements of processing tasks, while ensuring the feasibility and high-quality output of the plan under local resource conditions.

[0010] In order to achieve the above object, the present invention is implemented through the following technical solutions: In a first aspect, an embodiment of the present application provides a method for generating a process plan based on a knowledge base, comprising: Obtain an existing process plan, build a process knowledge model based on the existing process plan, generate a task table and a plan table, and store them in a process knowledge database; the process knowledge model includes: a processing task model, a processing resource model, and a process plan model; Obtain the processing task file, parse the processing task file, and extract the basic information of the processing task, blank information, workpiece shape information and feature attribute information; Retrieve the corresponding process plan from the process knowledge database according to the basic information of the processing task, and store the retrieved process plan in a temporary file; According to the blank information, the corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan; According to the workpiece shape information, the corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan; According to the characteristic attribute information, the corresponding process scheme is screened out in the temporary file, and the temporary file is updated based on the screened process scheme; Read the local processing resource file, check and exclude the process plans that cannot be supported by local resources based on the process plans recorded in the temporary file, and output the process plans that can be supported by local resources.

[0011] In an optional embodiment, the obtaining of an existing process plan, building a process knowledge model according to the existing process plan, generating a task table and a plan table, and storing them in a process knowledge database includes: A processing task model is constructed according to the existing process plan. The processing task model uses a nested key-value pair structure to store basic information of the processing task, blank information, workpiece shape, and feature attribute information; the key-value pair structure is: task:{basic_information, workblank, shape_code, feature}; Among them, task represents the processing task, basic_information, workblank, shape_code, and feature respectively record the basic information of the processing task, blank information, workpiece shape code, and feature attribute information; the feature attribute information includes feature serial number, feature code, processing element, outer circle length, outer circle diameter, and associated features; A process scheme model is constructed according to an existing process scheme. The process scheme model uses a nested key-value pair structure to record individual processes, process attributes and process step information. The process attributes include process content, process equipment, process equipment, and process type. The process step information includes process parameters, processing features, and tools used in the process step. The processing features are used to link the process step with the information of feature attributes in the processing task, including feature serial number, feature code, workpiece shape code, and feature coordinates. Construct a processing resource model based on the existing process plan to describe the processing capabilities of the machine tools and cutting tools used in the process plan; According to the process plan corresponding to each processing task model, processing resource model, and process plan model, a unique process plan identification code process_id is set respectively; A task table is constructed according to the processing task model, a plan table is constructed according to the processing resource model and the processing resource model, and the information stored in the task table and the plan table are linked using the process plan identification code process_id and stored in the process knowledge database.

[0012] In an optional implementation, the method of selecting a corresponding process solution from a temporary file according to the workpiece shape information, and updating the temporary file based on the selected process solution, further includes: If the corresponding process plan cannot be screened out in the temporary file based on the workpiece shape information, the following process plan update process is executed: S501: Based on the processing task file, the feature information of the processing task is disassembled using the feature code feature_code and the feature serial number serial in the feature individual as keywords, and converted into a description file feature_list for multiple single features; S502: Select a feature of the feature_list file, calculate and select process plans with feature similarity that meets the requirements in the process knowledge database according to the weighted similarity calculation formula, and extract the process plan model in the plan table according to the process_id corresponding to the screening result; generate a processing chain file according to the process step information and process attributes of the process plan model; S503: Extract the processing task model in the task table according to the process_id corresponding to the screening result, obtain the associated features by extracting the feature attribute information, distinguish the main class features and sub-class features in the processing chain file according to the associated features; record the main class features directly in the processing chain file; match the sub-class features to the processing chain according to the process attributes, and record them in the processing chain file.

[0013] S504: Determine whether all features in the feature_list file have been matched to the corresponding processing chain and recorded in the processing chain file; if so, update the temporary file based on the processing chain file; if not, execute step S502.

[0014] In an optional embodiment, the process schemes whose feature similarity meets the requirements are selected in the process knowledge database according to the weighted similarity calculation, including: When the feature similarity is less than 1, read the task feature information in the feature_list file, and package it together with the local resource information and pass it to the process parameter generator to generate new process parameters; The new process parameters are used as the processing chain parameters of the feature to generate the corresponding processing chain file.

[0015] In an optional embodiment, the process parameter generator adopts a process parameter generation model based on a generative adversarial network; the process parameters output by the process parameter generation model include: feature coding, machining allowance reserved for finishing, tool, dimensional accuracy, cutting speed, back cutting amount, feed speed and roughness.

[0016] In an optional implementation, the reading of the local processing resource file, based on the process scheme recorded in the temporary file, checking and excluding the process scheme that the local resources cannot support processing, and outputting the process scheme that the local resources can support processing, includes the following steps: S701: Obtain a local processing resource file, extract internal information and convert it into a key-value pair format; S702: Check the processing capability of the local processing resources according to the machine tool keywords, select the process solutions matching the capability from the temporary file, and update the temporary file based on the process solutions matching the capability; S703: Check the local tool resources according to the tool keywords, select process solutions with the same tool resources or the same processing effects from the temporary file, and update the temporary file based on the selected process solutions.

[0017] In an optional implementation, the weighted similarity calculation formula includes:

[0018] in, is the similarity of a single feature; are weight coefficients respectively; , , , They represent the local similarity of surface quality, form and position error, dimensional information and dimensional tolerance respectively; are the feature types in local tasks and database process cases respectively; is the discriminant formula, as follows: ; The similarity formulas for surface quality, form and position error, dimensional information, and dimensional tolerance are as follows:

[0019]

[0020]

[0021]

[0022] Among them, t represents the data information of the processing task, and p represents the data information of the case. R represents the roughness; datum represents the positioning reference; type represents the type of geometric tolerance; d represents the size of the feature; IT represents the tolerance grade; is the Euclidean distance.

[0023] In a second aspect, the embodiment of the present application further provides a process plan generation system based on a knowledge base, comprising: A process knowledge database construction module is used to obtain an existing process plan, construct a process knowledge model based on the existing process plan, generate a task table and a plan table, and store them in a process knowledge database; the process knowledge model includes: a processing task model, a processing resource model, and a process plan model; The task acquisition module is used to acquire the processing task file, parse the processing task file, and extract the basic information of the processing task, blank information, workpiece shape information and feature attribute information; A retrieval module is used to retrieve the corresponding process plan from the process knowledge database according to the basic information of the processing task, and store the retrieved process plan in a temporary file; The first screening module is used to screen out the corresponding process scheme in the temporary file according to the blank information, and update the temporary file based on the screened process scheme; The second screening module is used to screen out the corresponding process scheme in the temporary file according to the workpiece shape information, and update the temporary file based on the screened process scheme; The third screening module is used to screen out the corresponding process scheme in the temporary file according to the characteristic attribute information, and update the temporary file based on the screened process scheme; The inspection module is used to read the local processing resource file, check and exclude the process plans that cannot be supported by local resources based on the process plans recorded in the temporary file, and output the process plans that can be supported by local resources.

[0024] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for generating a process plan based on a knowledge base as described in any one of the above items are implemented.

[0025] In a fourth aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the process plan generation method based on the knowledge base as described in any of the above items are implemented.

[0026] It can be seen from the above technical solutions that the present invention has the following advantages: In the process scheme generation method based on the knowledge base provided in the present application, by constructing a process knowledge database including a processing task model, a processing resource model and a process scheme model, efficient management and utilization of the existing process schemes are achieved. In the process of scheme generation, the method first obtains the processing task file, and uses multi-level information screening technology, including the analysis and extraction of basic information of the processing task, blank information, workpiece shape information and feature attribute information, to gradually retrieve and screen out the process scheme that meets the requirements in the process knowledge database. In view of the situation where direct matching is not possible, the method innovatively adopts feature similarity calculation technology, accurately evaluates the similarity between features through a weighted similarity formula, and generates a processing chain file based on this, so as to flexibly respond to complex processing tasks. In addition, the method also integrates a process parameter generator, and uses an advanced generative adversarial network model to generate new process parameters according to the processing task features and local resource information, further enhancing the adaptability and feasibility of the scheme. Before the final scheme is output, the method will also perform a feasibility check on the screened process schemes according to the local processing resource files to ensure that all schemes can be smoothly implemented under local resource conditions.

[0027] Based on the processing connection between complex features and simple features in the processing process, this application proposes a process route reorganization method based on feature association and constructs a corresponding system, which makes up for the shortcomings of poor flexibility and generalization ability of traditional process route reorganization methods.

[0028] When the database cannot match data similar to the processing task, the present application can use the generative adversarial network to generate new process parameters, and combine the hybrid reasoning mechanism to obtain a process plan that meets the requirements of the processing task, thereby improving the generalization ability of process planning.

[0029] This application utilizes the database to realize the aggregation and sharing of processing technology knowledge, and on this basis designs a weighted similarity calculation method based on Euclidean distance, which realizes the data recommendation of the processing technology knowledge base under the change of processing requirements, and effectively improves the flexibility of intelligent process plan planning.

[0030] This application supports multi-level screening based on detailed information of the processing task file, including basic information of the processing task, blank information, workpiece shape information and feature attribute information. This multi-level screening mechanism ensures that the generated process plan can accurately match the actual processing requirements and improves the flexibility and adaptability of the plan.

[0031] This application reads the local processing resource file and checks the feasibility of the process plan. This method ensures that the generated process plan can be smoothly implemented under local resource conditions. This resource optimization mechanism avoids the problem of plan failure caused by insufficient or mismatched resources, and improves the feasibility and practicality of the plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0033] Figure 1 A schematic diagram of the process flow of the knowledge base-based process plan generation method provided in this application.

[0034] Figure 2 Updated flow chart of the process scheme provided for this application.

[0035] Figure 3 A schematic flow chart of a method for checking the feasibility of the process scheme provided in this application.

[0036] Figure 4 A schematic diagram of the structure of the process plan generation system based on the knowledge base provided in this application.

[0037] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION

[0038] In the specific steps of the process scheme generation method based on the knowledge base, which will be described in detail below, various embodiments of the present disclosure will be described more comprehensively. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0039] Hereinafter, the terms "include" or "may include" used in various embodiments of the present disclosure indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "include", "have", and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or a combination of the foregoing, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components, or a combination of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or a combination of the foregoing.

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 The figure is a flow chart of a method for generating a process plan based on a knowledge base in a specific embodiment, the method comprising: S1: Obtain an existing process plan, construct a process knowledge model based on the existing process plan, generate a task table and a plan table, and store them in a process knowledge database; the process knowledge model includes: a processing task model, a processing resource model, and a process plan model.

[0042] In a specific implementation, the process knowledge database is constructed from the following aspects: 1. Build a processing task model based on the existing process plan. The processing task structure is represented as a nested key-value pair structure and stored in a json file. The structure is: task:{basic_information, workblank, shape_code, feature}, where task represents the processing task, and the brackets represent the basic information of the processing task, blank, workpiece shape code, and feature attribute information in order. The workpiece shape code (shape_code) is a string composed of the feature code of the workpiece in order. The basic information of the processing task (basic_information) includes the processing scale, product type, etc. The blank information (workblank) includes the blank material, shape, size, and heat treatment. The storage structure of the feature attribute information is: feature:{shape_code, coordinate,feature_1,feature_2,,,}, where the information in the brackets is in order: the mirror image of the shape code, the machine tool coordinate system, and the feature information. Feature information represents different features, and the ontology models of different types of features are also different. The feature information structure is: feature:{outer_diameter_cylinder:{outer_diameter_cylinder_1,,,}, groove:{groove_1,groove_2},,,,,}, where outer_diameter_cylinder represents the outer circle feature type, and outer_diameter_cylinder_1 represents the specific feature individual. The structure of the feature individual is outer_diameter_cylinder_1:{serial, feature_code, machining_element, length, diameter, link_feture}, and the brackets represent the feature serial number, feature code, machining element, outer circle length, outer circle diameter, and associated feature respectively. Among them, the feature serial number (serial) is used to determine different individuals in the same type of feature, and the feature code (feature_code) is a four-digit string describing the feature type and shape. The machining element (machining _element) includes information such as roughness, shape tolerance, and position tolerance.

[0043] Furthermore, the associated feature (link_feture) means: complex features (subclasses) are obtained by processing on the basis of simple features (main class). For example, in turning, the thread feature is a complex feature, and the corresponding simple feature is an outer cylindrical feature. Taking turning as an example, the corresponding relationship is shown in the following table. After the feature type is determined, the associated feature type can be determined according to the following table 1.

[0044] Table 1: Comparison table of related feature types

[0045] 2. Build a process plan model based on the existing process plan. The structure of the process plan model is: plan: {process_1:{property,step},process_2{{property, step},,,}. Process_1 represents the process individual, property represents the process attribute, and the structure is: property: {process_content, process_equipment, accessibility, operation_type}, in brackets, the order is process content, process equipment, process equipment, and process type.

[0046] Among them, process equipment refers to the machine tool equipment used; process equipment refers to the process equipment used in this process, such as three-jaw chuck and center; process type refers to the processing operation type of this process, such as rough turning, fine turning, etc. The corresponding process content is composed of operation type and processing object, such as rough turning of diameter XX outer circle, turning XX thread, etc.

[0047] Step represents a work step, and its structure is: step:{step_1{technal_ parameter, feature, cutting tool},,,}, where step_1 represents a specific work step, and the brackets contain the process parameters, machining features, and the tool used in the work step. The process parameters include feed rate, feed direction, cutting depth, cutting speed, spindle speed, and number of passes; the machining features are information used to link the work step with the feature attributes in the machining task, including feature serial number, feature code, workpiece shape code, and feature coordinates.

[0048] 3. Construct a processing resource model based on the existing process plan. The processing resource model describes the processing capabilities of the machine tools and cutting tools used in the process case. For machine tools, it is manifested in the processing capabilities such as the maximum spindle speed, auxiliary components, accuracy, maximum feed rate, etc. For cutting tools, it is manifested in information such as the type, size, angle, material, etc. of the tool.

[0049] 4. According to the process plan corresponding to each processing task model, processing resource model, and process plan model, a unique process plan identification code process_id is set respectively.

[0050] 5. Based on MySQL database, use navicat platform to build process knowledge database. First, design the get_sql module to generate the cursor pointer of the database, which is used to query, call and store the case data in the database. The get_sql module is implemented with the help of the pymsql tool library of python programming. Secondly, according to the application requirements, two table structures are designed to store process knowledge information, namely: create a task table (task) to use the processing task model to store the processing task related information, and create a plan table (plan) to use the processing resource model and the processing resource model to store the processing resources and process plan information. In addition, the information in different tables is linked by process_id, and the feature attribute information and the processing resource information used can be called through the corresponding keywords for the processing operation.

[0051] Among them, the task table (task) stores the processing task model, and the plan table (plan) stores the processing resource model and the processing resource model. To facilitate module calling, the task table is divided into multiple column families according to the matching links and inference rules: basic_information, work_blank, shape_code, feature, process_id. They correspond to the basic information of the processing task, blank information, workpiece shape coding, and feature information of the processing task model respectively. The plan table is proce_plan, resource, process_id. They correspond to the process plan model and the processing resource model respectively. The storage structure in the two tables uses nested key-value pairs, for example: To call the diameter information of the outer circle, you need to locate the keys in sequence: feature>outer_diameter_cylinder>outer_diameter_cylinder_X>diameter. The same row of data in the database is the same case. proscess_id is a string randomly generated by the computer and unique to each case. It is an important call key in the reasoning process.

[0052] S2: Obtain the processing task file, parse the processing task file, and extract the basic information of the processing task, blank information, workpiece shape information and feature attribute information.

[0053] S3: Retrieve the corresponding process plan from the process knowledge database according to the basic information of the processing task, and store the retrieved process plan in a temporary file.

[0054] As an example, the value of the corresponding basic information of the processing task is called according to the key "basic_information", and the database is traversed to check whether there are cases with the same content. The process_id of the case that meets the condition is recorded in the temporary file id_list.

[0055] S4: According to the blank information, the corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan.

[0056] As an example, the value of the corresponding blank information is called according to the key "workblank", the cases with the same blank information used in the temporary file id_list are filtered, and the id_list file is updated. The blank information includes: blank shape type, material, size, and processing technology.

[0057] S5: According to the workpiece shape information, a corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan.

[0058] As an example, filter the process cases with the same workpiece shape as the processing task, and update the id_list file. In other words, check whether the shape codes of the workpieces in the processing task model are the same. The shape code is a string obtained by combining the feature codes in the order of the positions of the workpieces. The feature code refers to the description information of the feature type and shape of the workpiece, which consists of a 4-digit string, in which the first digit is a letter, indicating the feature type; the last three digits are numbers, indicating the feature ancillary information, feature direction and other information describing the feature shape.

[0059] S6: According to the characteristic attribute information, a corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan.

[0060] As an example, check the attribute information of each feature and update the id_list file according to the process cases with the same processing requirements. That is, call the specific feature individual information corresponding to the feature.

[0061] S7: Read the local processing resource file, check and exclude the process plans that cannot be supported by local resources based on the process plans recorded in the temporary file, and output the process plans that can be supported by local resources.

[0062] The purpose of this step is to read the local processing resource file, check and exclude the process cases that the local resources cannot support processing, and output the process plan that finally meets all conditions.

[0063] In an embodiment of the present invention, based on step S5, a possible embodiment is given below to illustrate its specific implementation in a non-limiting manner.

[0064] refer to Figure 2 As shown in the figure, if the corresponding process plan cannot be screened out in the temporary file according to the workpiece shape information, the following process plan update process is executed: S501: Based on the processing task file, feature information of the processing task is disassembled using the feature code feature_code and the feature serial number serial in the feature individual as keywords, and converted into a description file feature_list for multiple single features.

[0065] As an example, based on the machining task file, the feature information of the machining task is disassembled according to the feature code (feature_code) and feature serial number (serial) in the feature individual as keywords, and converted into a description file (feature_list) for multiple single features. The format of feature_list is: [feature_1, feature_2,,,], where feature_1 represents the feature individual, and the structure is similar to that in 2.1 above, such as: if the feature is a certain outer circle, its structure is outer_diameter_cylinder_ 1: {serial, feature_code, machining_element, length,diameter, link_feture}, and the brackets represent the feature serial number, feature code, machining element, outer circle length, outer circle diameter, and associated features respectively.

[0066] S502: Select a feature of the feature_list file, calculate and select process plans whose feature similarity meets the requirements in the process knowledge database according to the weighted similarity calculation formula, and extract the process plan model in the plan table according to the process_id corresponding to the screening result; generate a processing chain file according to the process step information and process attributes of the process plan model.

[0067] As an example, select a feature of the feature_list file, and select the feature cases that meet the requirements in the database based on the weighted similarity calculation. And extract the process steps for processing the feature in the process_plan in the plan table according to the process_id, and confirm the process steps based on the processing features (feature) in the individual process step (step_x). After screening all the process steps, integrate the process steps according to the process attributes (property) of the superior information of the process steps, that is, store all the process steps with the same process attributes under the same process, and sort them according to the suffix numbers of the original individual process steps, and then form these processes into a processing chain file. Among them, the screening requirement is the case feature with the largest similarity value, and retain the case IDs with the 2nd to 5th similarity for backup.

[0068] If the similarity of the selected features is less than 1, the following operations can be performed: First, read the task feature information in the feature_list file, and package it together with the local resource information and pass it to the process parameter generator to obtain new process parameters. Among them, the process parameter generator refers to a process parameter generation system based on the generative adversarial network (GAN). After the model training is completed, the input generator is sampled from the normal distribution, and the generator outputs the process parameter results. The output process parameters include eight parameters: feature coding, machining allowance reserved for finishing, tool, dimensional accuracy, cutting speed, back cutting amount, feed speed, and roughness.

[0069] Then, the obtained process parameters are used to replace the processing chain parameters of the case features to obtain new processing chain information. The replaced case features have the largest similarity value.

[0070] S503: Extract the processing task model in the task table according to the process_id corresponding to the screening result, obtain the associated features by extracting the feature attribute information, distinguish the main class features and sub-class features in the processing chain file according to the associated features; record the main class features directly in the processing chain file; match the sub-class features to the processing chain according to the process attributes, and record them in the processing chain file.

[0071] As an example, according to the comparison table of associated feature types, the associated feature category can be determined by the feature type. Then the processing chain is marked according to the feature associated category. For simple features (main category), the processing chain file is directly recorded; for complex features (subcategory), the processing chain is divided into two parts: the processing of the main category feature and the forming processing of the subcategory feature according to different processes, in which the key of the processing operation of the main category feature is changed to the corresponding main category feature name. That is, step>feature>link_feature is changed to the name of the corresponding main category feature.

[0072] S504: Determine whether all features in the feature_list file have been matched to the corresponding processing chain and recorded in the processing chain file; if so, update the temporary file based on the processing chain file; if not, execute step S502.

[0073] Through this step, the feature_list file is traversed to check whether all features have been matched to the corresponding processing chain.

[0074] It should be noted that in the process plan update flow, the weighted similarity calculation formula used includes:

[0075] in, is the similarity of a single feature; are weight coefficients respectively; , , , They represent the local similarity of surface quality, form and position error, dimensional information and dimensional tolerance respectively; are the feature types in local tasks and database process cases respectively; is the discriminant formula, as follows: ; The similarity formulas for surface quality, form and position error, dimensional information, and dimensional tolerance are as follows:

[0076]

[0077]

[0078]

[0079] Among them, t represents the data information of the processing task, and p represents the data information of the case. R represents the roughness; datum represents the positioning reference; type represents the type of geometric tolerance; d represents the size of the feature; IT represents the tolerance grade; is the Euclidean distance.

[0080] In one embodiment of the present invention, after step S504 is completed and the processing chains of all task features are obtained, the following operations may be performed: Step 1: Determine the overall process route. Obtain the process type (operation_type) content under the process attribute (property) in all processing chain files. Since simple features only have external cylindrical, cone, and end face features, their process sequence is basically determined: end face turning-rough turning-semi-finishing turning-finishing turning. For example, the process type of the thread feature is rough turning-semi-finishing turning-finishing turning-thread turning in the process sequence; the process type of the backing groove is rough turning-semi-finishing turning-finishing turning-groove turning, so the process sequence of the overall simple feature is rough turning-semi-finishing turning-finishing turning, and the groove turning and thread turning processes are retained for analysis.

[0081] Step 2: Based on the sequence of simple feature processes, the processing operations of simple features are integrated according to the process type information under the process property to obtain a preliminary processing solution file. The preliminary processing solution file is the processing of all simple features of the workpiece. The processing operation integration includes two parts: the sorting of processes and the reorganization of steps within the process. The sorting of processes first arranges the processes of simple features according to the overall process route, and then merges the process content according to the process equipment (process_ equipment) information and processing technology rules under the process property; the reorganization of steps is first classified according to information such as cutting tools (cutting_tool), process equipment (accessibility), feed direction (feed_direction), and then sorted according to feature positions (feature_point) and process parameters (technal_ parameter). The sorting rules follow the process rules of primary first, secondary second, datum first, and others.

[0082] Step 3: Based on the solution file, add the process of complex features. According to the process rules, the process type (operation_type) of complex features can be arranged to obtain the corresponding process sequence of complex features.

[0083] Step 4: Supplement the solution file based on the process sequence of complex features. The supplement rules are the same as step 2.

[0084] Step 5: Finally, check and optimize the solution according to the process planning constraints, which include: clamping constraints, positioning constraints, reference constraints, tool change times, clamping times, etc.

[0085] In an embodiment of the present invention, based on step S7, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0086] refer to Figure 3 As shown, this embodiment discloses a method for checking the feasibility of a process scheme, which specifically includes the following steps: S701: Obtain the local processing resource file, extract the internal information and convert it into a key-value pair format.

[0087] S702: Check the processing capability of the local processing resources according to the machine tool keywords, select the process solutions with matching capability from the temporary file, and update the temporary file based on the process solutions with matching capability.

[0088] As an example, check whether the processing capability of the local machine tool resources can meet the processing of the case according to the machine tool keyword, and update the id_list file according to the structure. Loop through the check until all cases are traversed to obtain the updated id_list file.

[0089] S703: Check the local tool resources according to the tool keywords, select process solutions with the same tool resources or the same processing effects from the temporary file, and update the temporary file based on the selected process solutions.

[0090] As an example, check whether the local tool resource is the same as the case tool or can achieve the same processing effect according to the tool keyword, and update the id_list file. Loop through the check until all case tools are traversed to obtain the updated id_list file.

[0091] like Figure 4 As shown, the following is an embodiment of the process plan generation system based on the knowledge base provided in the embodiment of the present disclosure. The system and the process plan generation method based on the knowledge base in the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the process plan generation system based on the knowledge base, please refer to the embodiment of the process plan generation method based on the knowledge base.

[0092] A process plan generation system based on a knowledge base includes: a process knowledge database construction module 1, a task acquisition module 2, a retrieval module 3, a first screening module 4, a second screening module 5, a third screening module 6 and an inspection module 7.

[0093] The process knowledge database construction module 1 is used to obtain the existing process plan, construct a process knowledge model based on the existing process plan, generate a task table and a plan table, and store them in the process knowledge database; the process knowledge model includes: a processing task model, a processing resource model, and a process plan model.

[0094] The task acquisition module 2 is used to acquire the processing task file, parse the processing task file, and extract the basic information of the processing task, blank information, workpiece shape information and feature attribute information.

[0095] The retrieval module 3 is used to retrieve the corresponding process plan from the process knowledge database according to the basic information of the processing task, and store the retrieved process plan in a temporary file.

[0096] The first screening module 4 is used to screen out corresponding process solutions in the temporary file according to the blank information, and update the temporary file based on the screened process solutions.

[0097] The second screening module 5 is used to screen out the corresponding process plan in the temporary file according to the workpiece shape information, and update the temporary file based on the screened process plan.

[0098] The third screening module 6 is used to screen out corresponding process solutions in the temporary file according to the characteristic attribute information, and update the temporary file based on the screened process solutions.

[0099] The inspection module 7 is used to read the local processing resource file, check and exclude the process plans that cannot be supported by the local resources based on the process plans recorded in the temporary file, and output the process plans that can be supported by the local resources.

[0100] The knowledge base-based process plan generation system provided in this embodiment constructs a process knowledge model and stores it in a database. It uses technical means such as multi-level information screening, feature similarity calculation and process parameter generator to intelligently match and generate process plans that meet the requirements of processing tasks, while ensuring the feasibility and high-quality output of the plan under local resource conditions.

[0101] Figure 5 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0102] The process scheme generation method based on knowledge base provided in the embodiment of the present application can be applied to electronic devices. It will be appreciated by those skilled in the art that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or less components than shown, or combine certain components, or different component arrangements. In an embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the embodiments of the present application described herein and / or required.

[0103] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, buttons, a camera, a display, and a SIM card interface, etc.

[0104] The processor may include one or more processing units, for example, the processor may include a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated into one or more processors.

[0105] The processor can be the nerve center and command center of the electronic device. The controller can generate an operation control signal according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0106] A memory may also be provided in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. The memory may store instructions or data that the processor has just used or is cyclically used. If the processor needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor, and thus improves system efficiency.

[0107] The external memory interface can be used to connect an external memory card, such as a MicroSD card, to expand the storage capacity of the electronic device. The external memory card communicates with the processor through the external memory interface to implement data storage functions. For example, files such as music and videos can be saved in the external memory card.

[0108] The internal memory can be used to store computer executable program codes, which include instructions. The processor executes various functional applications and data processing of the electronic device by running the instructions stored in the internal memory. The internal memory may include a program storage area and a data storage area. The internal memory may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0109] The wireless communication function of an electronic device can be realized through an antenna, a wireless communication module, a modem processor, and a baseband processor.

[0110] The wireless communication module can provide wireless communication solutions for electronic devices, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0111] Electronic devices can implement audio functions, etc. through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0112] Electronic devices can achieve shooting functions through ISP, camera, video codec, GPU, display and application processor.

[0113] Electronic devices can achieve display functions through GPU, display screen and application processor.

[0114] The GPU is a microprocessor for image processing that connects the display screen and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor may include one or more GPUs that execute program instructions to generate or change display information.

[0115] The display screen is used to display images, videos, etc. The display screen includes a display panel.

[0116] The above-mentioned electronic device implements the knowledge base-based process plan generation method of the present application by constructing a process knowledge database, using multi-level information screening technology to parse processing task files, combining feature similarity calculation (using weighted similarity formula) with process parameter generator (based on generative adversarial network model) to intelligently match and optimize process plans, and at the same time perform feasibility verification based on local processing resource files, thereby realizing efficient, accurate and intelligent generation of process plans that adapt to local resource conditions, and achieving the beneficial effect of providing strong support for the intelligent upgrade of the manufacturing industry.

[0117] The storage medium provided in the present application stores a program product that can implement a process plan generation method based on a knowledge base.

[0118] The process plan generation method based on the knowledge base includes: obtaining the existing process plan, building a process knowledge model according to the existing process plan, generating a task table and a plan table, and storing them in a process knowledge database; obtaining a processing task file, parsing the processing task file, and extracting the basic information of the processing task, blank information, workpiece shape information and feature attribute information; retrieving the corresponding process plan from the process knowledge database according to the basic information of the processing task, and storing the retrieved process plan in a temporary file; screening out the corresponding process plan in the temporary file according to the blank information, and updating the temporary file based on the screened process plan; screening out the corresponding process plan in the temporary file according to the workpiece shape information, and updating the temporary file based on the screened process plan; screening out the corresponding process plan in the temporary file according to the feature attribute information, and updating the temporary file based on the screened process plan; reading the local processing resource file, based on the process plan recorded in the temporary file, checking and excluding the process plan that the local resources cannot support for processing, and outputting the process plan that the local resources can support for processing.

[0119] In some possible embodiments, the knowledge base-based process plan generation method of the present disclosure can be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure.

[0120] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0121] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a process plan based on a knowledge base, characterized in that: include: Obtain the existing process plan, build a process knowledge model based on the existing process plan, generate a task table and a plan table, and store them in the process knowledge database; The process knowledge model includes: a processing task model, a processing resource model, and a process solution model; Obtain the processing task file, parse the processing task file, and extract the basic information of the processing task, blank information, workpiece shape information and feature attribute information; Retrieve the corresponding process plan from the process knowledge database according to the basic information of the processing task, and store the retrieved process plan in a temporary file; According to the blank information, the corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan; According to the workpiece shape information, the corresponding process plan is screened out in the temporary file, and the temporary file is updated based on the screened process plan; According to the characteristic attribute information, the corresponding process scheme is screened out in the temporary file, and the temporary file is updated based on the screened process scheme; Read the local processing resource file, check and exclude the process plans that cannot be supported by local resources based on the process plans recorded in the temporary file, and output the process plans that can be supported by local resources.

2. The process scheme generation method based on the knowledge base according to claim 1 is characterized in that: The method of obtaining an existing process plan, constructing a process knowledge model according to the existing process plan, generating a task table and a plan table, and storing them in a process knowledge database includes: A processing task model is constructed according to the existing process plan. The processing task model uses a nested key-value pair structure to store basic information of the processing task, blank information, workpiece shape, and feature attribute information; the key-value pair structure is: task:{basic_information, workblank, shape_code, feature}; Among them, task represents the processing task, basic_information, workblank, shape_code, and feature respectively record the basic information of the processing task, blank information, workpiece shape code, and feature attribute information; the feature attribute information includes feature serial number, feature code, processing element, outer circle length, outer circle diameter, and associated features; A process scheme model is constructed according to an existing process scheme. The process scheme model uses a nested key-value pair structure to record individual processes, process attributes and process step information. The process attributes include process content, process equipment, process equipment, and process type. The process step information includes process parameters, processing features, and tools used in the process step. The processing features are used to link the process step with the information of feature attributes in the processing task, including feature serial number, feature code, workpiece shape code, and feature coordinates. Construct a processing resource model based on the existing process plan to describe the processing capabilities of the machine tools and cutting tools used in the process plan; According to the process plan corresponding to each processing task model, processing resource model, and process plan model, a unique process plan identification code process_id is set respectively; A task table is constructed according to the processing task model, a plan table is constructed according to the processing resource model and the processing resource model, and the information stored in the task table and the plan table are linked using the process plan identification code process_id and stored in the process knowledge database.

3. The method for generating a process plan based on a knowledge base according to claim 2, characterized in that: The method further comprises: filtering out a corresponding process solution in a temporary file according to the workpiece shape information, and updating the temporary file based on the filtered process solution. If the corresponding process plan cannot be screened out in the temporary file based on the workpiece shape information, the following process plan update process is executed: S501: Based on the processing task file, the feature information of the processing task is disassembled using the feature code feature_code and the feature serial number serial in the feature individual as keywords, and converted into a description file feature_list for multiple single features; S502: Select a feature of the feature_list file, calculate and select process plans with feature similarity that meets the requirements in the process knowledge database according to the weighted similarity calculation formula, and extract the process plan model in the plan table according to the process_id corresponding to the screening result; generate a processing chain file according to the process step information and process attributes of the process plan model; S503: extract the processing task model in the task table according to the process_id corresponding to the screening result, obtain the associated features by extracting the feature attribute information, distinguish the main class features and subclass features in the processing chain file according to the associated features; directly record the main class features in the processing chain file; match the subclass features to the processing chain according to the process attributes, and record them in the processing chain file; S504: Determine whether all features in the feature_list file have been matched to the corresponding processing chain and recorded in the processing chain file; if so, update the temporary file based on the processing chain file; if not, execute step S502.

4. The process scheme generation method based on the knowledge base according to claim 3 is characterized in that: The process schemes whose feature similarity meets the requirements are selected in the process knowledge database according to the weighted similarity calculation, including: When the feature similarity is less than 1, read the task feature information in the feature_list file, and package it together with the local resource information and pass it to the process parameter generator to generate new process parameters; The new process parameters are used as the processing chain parameters of the feature to generate the corresponding processing chain file.

5. The method for generating a process plan based on a knowledge base according to claim 4, characterized in that: The process parameter generator adopts a process parameter generation model based on a generative adversarial network; The process parameters output by the process parameter generation model include: feature coding, machining allowance reserved for finishing, tool, dimensional accuracy, cutting speed, back cutting amount, feed speed and roughness.

6. The method for generating a process plan based on a knowledge base according to claim 5, characterized in that: The process of reading the local processing resource file, checking and excluding the process schemes that cannot be processed by the local resources based on the process schemes recorded in the temporary file, and outputting the process schemes that can be processed by the local resources includes the following steps: S701: Obtain a local processing resource file, extract internal information and convert it into a key-value pair format; S702: Check the processing capability of the local processing resources according to the machine tool keywords, select the process solutions matching the capability from the temporary file, and update the temporary file based on the process solutions matching the capability; S703: Check the local tool resources according to the tool keywords, select process solutions with the same tool resources or the same processing effects from the temporary file, and update the temporary file based on the selected process solutions.

7. The method for generating a process plan based on a knowledge base according to claim 3, characterized in that: The weighted similarity calculation formula includes: in, is the similarity of a single feature; are weight coefficients respectively; , , , They represent the local similarity of surface quality, form and position error, dimensional information and dimensional tolerance respectively; are the feature types in local tasks and database process cases respectively; is the discriminant formula, as follows: ； The similarity formulas for surface quality, form and position error, dimensional information, and dimensional tolerance are as follows: Among them, t represents the data information of the processing task, p represents the data information of the case, R represents the roughness, datum represents the positioning reference, type represents the type of geometric tolerance, d represents the size of the feature, and IT represents the tolerance grade. is the Euclidean distance.

8. A process plan generation system based on a knowledge base, characterized in that: The system adopts the process plan generation method based on the knowledge base as described in any one of claims 1 to 7; The system comprises: A process knowledge database construction module is used to obtain an existing process plan, construct a process knowledge model based on the existing process plan, generate a task table and a plan table, and store them in a process knowledge database; the process knowledge model includes: a processing task model, a processing resource model, and a process plan model; The task acquisition module is used to acquire the processing task file, parse the processing task file, and extract the basic information of the processing task, blank information, workpiece shape information and feature attribute information; A retrieval module is used to retrieve the corresponding process plan from the process knowledge database according to the basic information of the processing task, and store the retrieved process plan in a temporary file; The first screening module is used to screen out the corresponding process scheme in the temporary file according to the blank information, and update the temporary file based on the screened process scheme; The second screening module is used to screen out the corresponding process scheme in the temporary file according to the workpiece shape information, and update the temporary file based on the screened process scheme; The third screening module is used to screen out the corresponding process scheme in the temporary file according to the characteristic attribute information, and update the temporary file based on the screened process scheme; The inspection module is used to read the local processing resource file, check and exclude the process plans that cannot be supported by local resources based on the process plans recorded in the temporary file, and output the process plans that can be supported by local resources.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the process plan generation method based on the knowledge base as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the process plan generation method based on the knowledge base as claimed in any one of claims 1 to 7 are implemented.

Images