Numerical control turning machining parameter recommendation method and device

Abstract

The invention discloses a numerical control turning machining parameter recommendation method and device, and belongs to the technical field of numerical control turning machining. The numerical control turning machining parameter recommendation method comprises the steps that whether a target part material is in a machining parameter knowledge base or not is judged; determining the dynamic weight of the preset processing performance of the material sample in the processing parameter data set by adopting a particle calculation method to obtain a performance index weight; and searching a processing material most similar to the target part material in a processing parameter knowledge base based on the performance index weight, and determining the most similar processing material as a candidate processing material. Searching in a processing parameter knowledge base on the basis of the candidate processing materials and the target processing type to obtain candidate processing parameters, corresponding to the target processing type, of the candidate processing materials, and then obtaining target processing parameters according to a preset large model. The degree of dependence on human experience and the threshold of compiling numerical control machining codes in numerical control machining are reduced, and the quality and efficiency of machining parameter determination are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of CNC turning processing, and more specifically, to a method and device for recommending CNC turning processing parameters. Background Art

[0002] CNC technology and CNC machine tools are the core and foundation of the manufacturing industry's industrial revolution. Writing CNC code is the first step in CNC machining, and its quality and efficiency determine the quality and efficiency of workpiece processing. Determining machining parameters is a crucial step in the CNC code writing process. This determination typically requires experienced process technicians or engineers, drawing on past CNC machining experience and extensive actual machining adjustments. This method is time-consuming and labor-intensive, and cannot be saved and reused. Therefore, accurate and efficient determination of machining parameters in CNC machining directly impacts the quality and efficiency of CNC program writing, and, by extension, the quality and efficiency of CNC machining.

[0003] Chinese invention patent specification CN 115270616 A discloses a method for determining parameters for laser drilling of composite materials based on a particle swarm optimization neural network and a multi-objective algorithm. This method trains a neural network model using historical processing and quality data, and combines it with a multi-objective optimization algorithm to automatically generate optimal parameter solutions tailored to different processing requirements. Chinese invention patent specification CN 107480354 A discloses a method for determining and recommending turning parameters based on reliability indicators. This method combines reliability analysis with maximum material removal rate by integrating an optimization model based on system stability limits and random variable boundary constraint reliability. Based on the set initial vibration conditions and critical stability state information of the turning system, it analyzes the impact of uncertainties on the turning process to determine optimal turning parameters.

[0004] The current main method for recommending machining parameters involves collecting past experimental and machining data, constructing mathematical models targeting different optimization effects, and then combining them with optimization algorithms to recommend machining parameters. However, these methods suffer from the following drawbacks: a) model construction is difficult; b) the scope of parameter recommendations is relatively limited; and c) they cannot be integrated with the process and the operator's previous experience or data.

[0005] Currently, the primary method for recommending machining parameters involves collecting past experimental and machining data, constructing mathematical models targeting different optimization effects, and combining them with optimization algorithms to recommend machining parameters appropriate for the current machining state. However, this approach suffers from common problems such as model construction difficulties, a limited scope of application for parameter recommendations, and an inability to integrate with the process and machining operator's prior experience or data. These issues lead to an over-reliance on human experience when determining machining parameters during CNC program development, impacting both efficiency and quality. Summary of the Invention

[0006] The embodiments of the present invention provide a method and device for recommending CNC turning machining parameters, which are used to solve the technical defect in the prior art that the determination of machining parameters when writing CNC programs is overly dependent on human experience, affecting the efficiency and quality of CNC program writing.

[0007] An embodiment of the present invention provides a method for recommending CNC turning machining parameters, the method comprising:

[0008] Obtaining a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed; wherein the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials; and the processing parameter data set includes target part materials and target processing types;

[0009] Determining whether the target part material is in the processing parameter knowledge base, and if the target part material is not in the processing parameter knowledge base, using a granular computing method to determine a dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance indicator weight;

[0010] searching the processing parameter knowledge base for a processing material most similar to the target part material based on the performance indicator weight, and determining the most similar processing material as a candidate processing material;

[0011] In a case where the target part material is in the processing parameter knowledge base, determining the target part material as a candidate processing material;

[0012] Searching the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type;

[0013] The candidate processing materials and candidate processing parameters are input into a preset macro model to obtain target processing parameters.

[0014] Furthermore, the step of inputting the candidate processing materials and candidate processing parameters into a preset macro model to obtain target processing parameters includes:

[0015] The processing parameter influencing rules are used as constraint conditions to constrain decoding of the output results of the preset large model to obtain target processing parameters; wherein the processing parameter influencing rules are the mapping relationship between the material properties of the processing material and the processing parameters.

[0016] Furthermore, after inputting the candidate processing materials and candidate processing parameters into a preset macro model to obtain target processing parameters, the method further includes:

[0017] Receive user adjustment operations on target processing parameters;

[0018] Record the adjusted processing parameters and the corresponding processing effect evaluation;

[0019] The adjusted processing parameters are updated to the processing parameter knowledge base according to the user confirmation instruction.

[0020] Furthermore, the granular computing method is used to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain the performance index weight, including:

[0021] Converting material property data of the processed material into multi-level machinability grade values according to the material machinability grade table;

[0022] Constructing a fuzzy similarity matrix and a fuzzy compatible quotient space family of material samples in a processing parameter knowledge base based on the multi-level processability grade values;

[0023] Calculating the objective weight of each preset processing performance through a multi-granularity quotient space based on the fuzzy similarity matrix and the fuzzy compatible quotient space family;

[0024] The dynamic weight of each preset processing performance is determined based on the objective weight to obtain a performance indicator weight.

[0025] Furthermore, the processing parameter knowledge base is constructed in the following manner:

[0026] The material property data set stores dual-version data of original values and processability grade values with the processed material brand as the index; the processing parameter data set adopts a four-dimensional storage structure, the dimensions of which include material brand, processing type, equipment model and parameter combination.

[0027] Furthermore, it includes: recording the adjusted processing parameters and the corresponding processing effect evaluation through a buffer window memory mechanism.

[0028] Furthermore, the step of obtaining a processing parameter data set corresponding to the processing parameter recommendation task to be processed includes:

[0029] Get the part processing description input by the user;

[0030] The large model API is called to extract keywords from the part processing description to obtain a processing parameter data set.

[0031] On the other hand, an embodiment of the present invention provides a CNC turning machining parameter recommendation device, the device comprising:

[0032] a processing parameter acquisition module, configured to acquire a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed; wherein the processing parameter data set includes a target part material and a target processing type; and the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials;

[0033] a first processing module, configured to determine whether the target part material is in the processing parameter knowledge base; if the target part material is not in the processing parameter knowledge base, using a granular computing method to determine a dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance indicator weight;

[0034] searching the processing parameter knowledge base for a processing material most similar to the target part material based on the performance indicator weight, and determining the most similar processing material as a candidate processing material;

[0035] The first processing module is further configured to determine the target part material as a candidate processing material when the target part material is in the processing parameter knowledge base;

[0036] a second processing module, configured to search the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type;

[0037] The processing parameter recommendation module is used to input the candidate processing materials and candidate processing parameters into a preset large model to obtain target processing parameters.

[0038] On the other hand, the present invention 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 any one of the above-described methods for recommending CNC turning machining parameters are implemented.

[0039] In one aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described methods for recommending CNC turning machining parameters.

[0040] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0041] This application obtains a processing parameter knowledge base and a processing parameter data set corresponding to the processing parameter recommendation task to be processed; determines whether the target part material is in the processing parameter knowledge base. If the target part material is not in the processing parameter knowledge base, a granular computing method is used to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance index weight; searches the processing parameter knowledge base for the processing material most similar to the target part material based on the performance index weight, and determines the most similar processing material as a candidate processing material. If the target part material is in the processing parameter knowledge base, the target part material is determined as a candidate processing material; searches the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type; inputs the candidate processing material and candidate processing parameters into a preset large model to obtain the target processing parameters. In CNC machining, especially for difficult-to-machine materials and processes, a machining parameter knowledge base is established for process personnel or machining operators based on past professional knowledge, which reduces the degree of dependence of CNC machining code writing on human experience and the threshold for writing CNC machining codes, and significantly improves the quality and efficiency of determining machining parameters in CNC code writing. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 One of the flow charts of an optional method for recommending CNC turning machining parameters provided in an embodiment of the present application;

[0044] FIG2 is a schematic diagram of an optional processing material and its performance index data set provided in an embodiment of the present application;

[0045] Figure 3 A second flow chart of an optional method for recommending CNC turning machining parameters provided in an embodiment of the present application;

[0046] Figure 4 A schematic flow chart of an optional method for calculating weights of processing material performance indicators provided in an embodiment of the present application;

[0047] Figure 5 A schematic structural diagram of an optional electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0049] The terms "first," "second," "third," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0050] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described herein.

[0051] Application Overview

[0052] In the field of CNC turning, the existing machining parameter recommendation methods have the following problems:

[0053] 1. The traditional method relies on experienced process personnel or engineers to determine processing parameters based on past experience and a large number of actual processing adjustments. This method is time-consuming and labor-intensive and cannot save and reuse experience.

[0054] 2. The main method for recommending machining parameters currently is to collect past experimental and machining data, build a mathematical model targeting different optimization effects, and then combine it with an optimization algorithm to recommend machining parameters. However, this method has the following disadvantages: a) Model construction is difficult; b) The scope of application of parameter recommendations is relatively limited; c) It cannot be combined with the process and the past experience or data of the machining operator.

[0055] These problems lead to excessive reliance on human experience in determining machining parameters when writing NC programs, affecting the efficiency and quality of NC program writing.

[0056] In response to the above technical problems, the present application provides a method and device for recommending CNC turning machining parameters. By collecting the experience accumulated by process personnel or machining operators during the CNC machining process and organizing it into a machining parameter data set and a common material property data set, a machining parameter knowledge base is constructed, which includes machining materials and machining parameters of different machining types corresponding to the machining materials. Combined with the large language model RAG (retrieval enhanced generation) technology, data similar to the current machining state can be retrieved from the machining parameter data set and the common material property data set based on the part materials and machining procedures of the parts to be machined, and the data is returned to the large model. Then, the currently required machining parameters are inferred based on certain rules as prompt words.

[0057] This method can intelligently recommend machining parameters based on the material and process of the part being machined, and has a wide range of applications. Furthermore, compared to current approaches that use experimental machining data to build a machining parameter recommendation model and then optimize a specific result for parameter recommendations, this approach eliminates the need for model building and offers a wider range of applications.

[0058] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0059] Exemplary Methods

[0060] Figure 1 The figure illustrates one of the flow charts of the method for recommending CNC turning machining parameters according to an embodiment of the present application.

[0061] like Figure 1 As shown, the method for recommending CNC turning machining parameters according to an embodiment of the present application includes:

[0062] S110 , obtaining a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed.

[0063] The processing parameter data set includes target part materials and target processing types; the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials.

[0064] S120, determine whether the target part material is in the processing parameter knowledge base. If the target part material is not in the processing parameter knowledge base, use the particle computing method to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain the performance index weight.

[0065] The processing material most similar to the target part material is searched in the processing parameter knowledge base based on the performance index weight, and the most similar processing material is determined as the candidate processing material.

[0066] S130: If the target part material is in the processing parameter knowledge base, determine the target part material as a candidate processing material.

[0067] S140 , searching in a processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type.

[0068] And S150, inputting the candidate processing materials and candidate processing parameters into the preset macro model to obtain target processing parameters.

[0069] The first step is data collection and preprocessing. For example, we collect the characteristic data of 100 common processing materials and 1,000 sets of processing parameter data for different processing types. This data is organized into two datasets: a material characteristic dataset and a processing parameter dataset, and then a processing parameter knowledge base is established.

[0070] Secondly, information extraction is performed. From the user input: "A part made of 45 steel needs to be processed and rough turned." Key information is extracted through the preset large model: the target part material to be queried is "45 steel" and the target processing type is "rough turning".

[0071] Then, a similar material search is performed, first checking whether 45 steel is included in the material property dataset. If not, a granular calculation method is used to calculate the material performance index weights to find the material with the most similar processing properties to 45 steel, such as "40Cr steel".

[0072] Parameter generation then proceeds. The machining parameter dataset retrieves the rough turning parameters for 40Cr steel, finding, for example, the following: spindle speed 1000 rpm, feed 0.2 mm / r, and depth of cut 2 mm. These parameters, along with the material property data for 45 and 40Cr steel, are then input into a pre-set macromodel, along with rules such as "for every 10 HBS increase in hardness, reduce spindle speed by 5%." Based on this information and rules, the macromodel generates parameters suitable for rough turning 45 steel, obtaining the target machining parameters, such as spindle speed 950 rpm, feed 0.18 mm / r, and depth of cut 1.8 mm, enabling intelligent parameter recommendations.

[0073] Below, each step will be described in detail.

[0074] In step S110 , a processing parameter knowledge base and a processing parameter data set corresponding to the processing parameter recommendation task to be processed are obtained.

[0075] The processing parameters and material properties are collected and preprocessed in a specified format to form a processing parameter data set and a material property data set, which are then plugged into the preset large model as a knowledge base.

[0076] In an optional embodiment, material properties are first collected, namely performance indicators that reflect material machinability, such as hardness (HBS), tensile strength (MPa), elongation (%), impact toughness (KJ / ㎡), and thermal conductivity (W / m·K). Because different types of materials contain different non-metallic elements and have different heat treatment processes, common CNC machining materials can be classified into four categories: carbon steel, stainless steel, copper-aluminum alloy, and titanium alloy. These four categories can be stored in a text format such as CSV to form a dataset of common machining materials and their performance indicators. The format is shown in Figure 2(a).

[0077] At the same time, based on the common processing materials collected, processing parameters for different processing types are collected. Processing types must cover basic turning processes such as cutting, grooving, undercutting, threading, roughing, finishing, grooving, profiling, drilling, center drilling, boring, reaming, and tapping. Simple milling processes such as trajectory milling and contour milling can also be expanded.

[0078] Then, according to different machining processes, relevant machining parameters such as spindle speed, feed, and cutting depth are collected and stored in text tables such as CSV to form a machining parameter data set, as shown in Figure 2(b). Thus, a machining parameter knowledge base is established according to the above steps.

[0079] In an optional embodiment, a method for constructing a processing parameter knowledge base may include: a material property data set stores dual-version data of original values and processability grade values with the processing material brand as the index; wherein the processing parameter data set adopts a four-dimensional storage structure, and the dimensions include material brand, processing type, equipment model and parameter combination.

[0080] In an optional embodiment, obtaining a processing parameter data set corresponding to a processing parameter recommendation task to be processed includes:

[0081] Get the part processing description input by the user;

[0082] The large model API is called to extract keywords describing the part processing and obtain a processing parameter data set.

[0083] Specifically, after building a processing parameter knowledge base, we design prompts. We then call the big model API to extract keywords from the user-entered part processing description to determine the target part material and processing type. The prompt design should focus on extracting the part material and processing type. Based on the processing type in the processing parameter dataset, we can design appropriate examples to enhance the big model's reasoning capabilities.

[0084] In step S120, it is determined whether the target part material is in the processing parameter knowledge base. If the target part material is not in the processing parameter knowledge base, the particle computing method is used to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain the performance indicator weight.

[0085] In step S130 , if the target part material is in the machining parameter knowledge base, the target part material is determined as a candidate machining material.

[0086] Specifically, based on the performance index weight, a processing material that is most similar to the target part material is searched in the processing parameter knowledge base, and the most similar processing material is determined as a candidate processing material. Figure 3 The second flow chart of an optional method for recommending CNC turning processing parameters provided in the embodiment of the present application; Figure 3 As shown in the figure, using the RAG architecture, the large model extracts key information such as the target processing type and target part material from the user-entered processing description. It then determines whether the target part material exists in the processing parameter knowledge base. If the part material does not exist in the processing parameter knowledge base, the large model is first used to query the material type and calculate the most similar material as a candidate processing material. If it exists, no calculation is required and the current material is directly output as a candidate processing material in this step.

[0087] In an optional embodiment, a granular computing method is used to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain the performance indicator weight, including:

[0088] Converting material property data of the processed material into multi-level machinability grade values according to the material machinability grade table;

[0089] Based on the multi-level machinability grade values, the fuzzy similarity matrix and fuzzy compatible quotient space family of material samples in the machining parameter knowledge base are constructed;

[0090] The objective weight of each preset processing performance is calculated through multi-granularity quotient space based on fuzzy similarity matrix and fuzzy compatible quotient space family;

[0091] The dynamic weight of each preset processing performance is determined based on the objective weight to obtain the performance index weight.

[0092] The performance index weight is a dynamic weight set of each preset processing performance of each material sample.

[0093] Specifically, each preset processing performance of each material sample is first collected, that is, the material property data of each material sample is collected to obtain a material machinability grading table, such as Table 1. The preset processing performance may include hardness (HBS), tensile strength (MPa), elongation (%), impact toughness (KJ / ㎡), and thermal conductivity (W / m·K). Then, according to the material machinability grading table in Table 1, the material property data is converted into a grade value of 0-10.

[0094] Then, the fuzzy compatible quotient space theory can be applied to construct a fuzzy compatible quotient space family for the collected material property data set, and the clustering results of material samples in a series of granular quotient spaces can be used as the classification of decision attributes under the corresponding granular space.

[0095] Then, in each granularity quotient space, the importance value of each performance indicator in the quotient space is obtained by adopting the attribute importance calculation method of rough set theory. Finally, the normalization method is used to solve the objective weight of each performance indicator, and the subjective and objective combined weighting method is adopted to combine the objective information of the data with people's domain expertise to realize the generation of performance indicator weights for judging the degree of processability similarity.

[0096] Table 1 Material machinability classification table

[0097]

[0098] For example, if the target part material is a new alloy, the most similar known material is found. First, the five characteristic data of the alloy are collected, and then the similarity with the known material is calculated according to the above steps. If the alloy has a hardness of 200 HBS, a tensile strength of 800 MPa, an elongation of 22%, an impact toughness of 600 kJ / ㎡, and a thermal conductivity of 50 W / m·K, then according to Table 1, these can be converted into grade values: 4, 4, 3, 3, 4. Then, an algorithm is used to calculate the similarity with the known material and identify candidate processing materials that are similar to the target part material for subsequent processing parameter recommendations.

[0099] Furthermore, in a specific embodiment, the following describes how to use a granular computing method to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set.

[0100] In this embodiment, Figure 4 A flow chart of an optional method for calculating the weight of processing material performance indicators provided in an embodiment of the present application is shown as follows: Figure 4 As shown:

[0101] (1) Referring to Table 1, each performance index in the material property data set is ranked from 0 to 10 to construct a machinability grade table for the material samples;

[0102] (2) The maximum-minimum method is used to calculate the similarity between material samples xi and xj, and the fuzzy similarity matrix R of all material samples is constructed. The calculation formula is as follows:

[0103]

[0104] The calculation method of rij is:

[0105]

[0106] (3) Using the network method, a family of fuzzy compatible quotient spaces {X(λ)|0≤λ≤1} of material samples with a hierarchical structure is obtained from R. The specific implementation method is to arrange rij from large to small, and select rij in turn to construct X(rij). The clustering result of X(rij) is to fuzzily consider the two material samples with values greater than rij to have the same processing performance and take the union. In this way, subsets of the fuzzy compatible quotient space with a decreasing number of clusters are constructed step by step, and the process stops when the number of clusters reaches 1.

[0107] (4) Discretize the machinability grade values of the material samples and generate equivalence classes U / ind(C-{ai})i=1, 2, 3, 4, 5 after deleting each performance index. The specific implementation method is to classify each performance index in the material performance data set into 1, 2, 3, and 4 according to the machinability column in Table 1, easy to cut, relatively easy to cut, relatively difficult to cut, and difficult to cut. Then delete the ai (i=1, 2, 3, 4, 5) column, determine which material samples can be approximated as materials with the same machinability when excluding the ai performance index, and calculate their union.

[0108] (5) Taking the fuzzy compatible quotient space family {X(λ)|0≤λ≤1} as the classification of decision attributes in the corresponding granularity space, the importance of each performance indicator in each granularity quotient space is calculated respectively. The calculation formula of the importance of each performance indicator in each granularity quotient space is as follows:

[0109]

[0110] in:

[0111]

[0112] Where POSc(D) is the positive domain of C with respect to D, and |U| is the element of the entire set.

[0113] (6) According to step 5, the importance of each performance indicator is calculated under different granularity spaces. The importance of each performance indicator is calculated by comprehensive calculation. The calculation formula is as follows:

[0114]

[0115] Where q is the number of elements in the fuzzy compatible quotient space family.

[0116] (7) Normalize and solve the objective weight of each performance indicator. The calculation formula is as follows:

[0117]

[0118] (8) The comprehensive weight of each performance indicator is determined according to the multiplication combination weighting method. The calculation formula is as follows:

[0119]

[0120] in is the objective weight of the performance indicator ak, is the subjective weight of the performance indicator ak.

[0121] According to the above eight steps, a dynamic weight of each preset processing performance of each material sample in the processing parameter data set can be constructed, and the performance index weight is obtained to calculate the candidate processing materials similar to the target part material.

[0122] This application evaluates the machinability of materials more comprehensively by considering multiple material property indicators (hardness, tensile strength, elongation, impact toughness, and thermal conductivity), thereby improving the accuracy of material similarity judgment. By adopting the fuzzy compatible quotient space theory and rough set theory, it can process material property data of different granularity levels, with greater adaptability and enhanced algorithm adaptability. Through the subjective and objective combined weighting method, the objective information of the data and the domain expertise of people are integrated, making the similarity calculation more reasonable and combining objective data with subjective experience.

[0123] In step S140, a search is performed in a processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type. In step S150, the candidate processing material and candidate processing parameters are input into a preset macro model to obtain target processing parameters.

[0124] According to the material to be retrieved (candidate processing material or target part material in the data set) output in the previous step, it is merged with the target processing type extracted by the large model, and the processing parameters in this case are retrieved in the processing parameter data set to complete the retrieval part in the RAG framework, such as Figure 3 As shown, the retrieved processing parameters, similar material properties, and raw material properties are input into the large model as context to infer and generate the processing parameters required in the target processing type process.

[0125] In an optional embodiment, the CNC turning machining parameter recommendation method provided in this embodiment inputs candidate machining materials and candidate machining parameters into a preset macro model to obtain target machining parameters, including:

[0126] The processing parameter influencing rules are used as constraints to constrain and decode the output results of the preset large model to obtain the target processing parameters; wherein the processing parameter influencing rules are the mapping relationship between the material properties of the processing material and the processing parameters.

[0127] Specifically, we first designed processing parameter influence rules that reflect the mapping relationship between the material properties and processing parameters, such as "increased hardness corresponds to a decreased spindle speed," as constraints. These constraints were then fed into the macromodel to complete the enhanced RAG framework. Finally, the output of the pre-set macromodel was subjected to constraint decoding based on the processing parameter influence rules, and the target processing parameters required for the zero-level machining process were inferred.

[0128] Optionally, the processing parameter influencing rule may also be a negative correlation regulation rule between material hardness and spindle speed, a piecewise linear relationship rule between tensile strength and feed rate, an exponential decay rule between thermal conductivity and cutting depth, etc.

[0129] This application replaces the traditional RAG vector search by combining it with the material processing performance similarity search, which is more in line with the processing parameter recommendation logic. At the same time, the impact of the performance indicators of the processing parameters on the results is used as a rule prompt to complete the model professional knowledge enhancement link, reduce the "hallucination" phenomenon of large models, and improve the reliability of the recommendation results.

[0130] In an optional embodiment, the CNC turning machining parameter recommendation method provided in this embodiment inputs candidate machining materials and candidate machining parameters into a preset macro model to obtain target machining parameters, further comprising:

[0131] Receive user adjustment operations on target processing parameters;

[0132] Record the adjusted processing parameters and the corresponding processing effect evaluation;

[0133] The adjusted processing parameters are updated to the processing parameter knowledge base according to the user confirmation instruction.

[0134] In this embodiment, a user interaction interface is also provided to allow fine-tuning of the generated processing parameters through dialogue. By setting up an interface for modifying and adding processing parameters, the user can decide whether to update the current parameters to the knowledge base based on the actual processing results.

[0135] First, an interactive interface is provided to the user, allowing them to fine-tune and generate new machining parameters based on the generated target machining parameters through a dialogue. Then, based on the user's actual machining results, the system receives adjustment instructions to decide whether to update the current parameters to the knowledge base. If the user chooses to update, the new machining parameters are added to the machining parameter dataset.

[0136] For example, suppose the system recommends the following parameters for rough turning of 45 steel: spindle speed 950 rpm, feed 0.18 mm / r, and depth of cut 1.8 mm. During actual machining, the user discovers that slightly increasing the feed rate can improve efficiency without affecting machining quality. Therefore, the user adjusts the feed rate to 0.2 mm / r through the interactive interface. After machining is complete, the user believes that this new set of parameters is effective and chooses to update it to the knowledge base. The system then adds this new set of parameters (spindle speed 950 rpm, feed 0.2 mm / r, and depth of cut 1.8 mm) as a new set of data for rough turning of 45 steel to the machining parameter dataset. This way, the next time the system recommends machining parameters for a similar situation, it can take this set of proven parameters into account, improving the accuracy of the recommendation.

[0137] Optionally, the adjusted processing parameters and the corresponding processing effect evaluation are recorded through a buffer window memory mechanism.

[0138] This application introduces memory capabilities, improves interactivity, and designs a data set update interface to complete the continuous updating of the knowledge base, thereby improving real-time performance.

[0139] This application can recommend processing parameters to process personnel or machining operators based on past professional knowledge in CNC machining, especially in difficult-to-machine materials and difficult-to-machine processes. It can reduce the degree of dependence of CNC machining code writing on human experience and the threshold for writing CNC machining codes, and significantly improve the quality and efficiency of determining processing parameters in CNC code writing.

[0140] According to another aspect of the embodiments of the present application, a device for implementing the above-mentioned CNC turning machining parameter recommendation is also provided. The device may include:

[0141] A processing parameter acquisition module is used to obtain a processing parameter knowledge base and a processing parameter data set corresponding to the processing parameter recommendation task to be processed; wherein the processing parameter data set includes the target part material and the target processing type; the processing parameter knowledge base includes the processing material and the processing parameters of different processing types corresponding to the processing material;

[0142] The first processing module is used to determine whether the target part material is in the processing parameter knowledge base. If the target part material is not in the processing parameter knowledge base, the granular computing method is used to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain the performance index weight;

[0143] Searching for the processing material most similar to the target part material in the processing parameter knowledge base based on the performance index weight, and determining the most similar processing material as the candidate processing material;

[0144] The first processing module is further configured to determine the target part material as a candidate processing material if the target part material is in the processing parameter knowledge base;

[0145] A second processing module is configured to search a processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type;

[0146] The processing parameter recommendation module is used to input candidate processing materials and candidate processing parameters into a preset large model to obtain target processing parameters.

[0147] It should be noted here that the examples and scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can run in a hardware environment, can be implemented by software, and can also be implemented by hardware, where the hardware environment includes a network environment.

[0148] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned CNC turning machining parameter recommendation methods in the embodiments of the present application.

[0149] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0150] S1, obtaining a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed; wherein the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials; and the processing parameter data set includes target part materials and target processing types;

[0151] S2, determining whether the target part material is in the processing parameter knowledge base. If the target part material is not in the processing parameter knowledge base, using a granular computing method to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance indicator weight;

[0152] searching the processing parameter knowledge base for a processing material most similar to the target part material based on the performance indicator weight, and determining the most similar processing material as a candidate processing material;

[0153] S3, if the target part material is in the processing parameter knowledge base, determining the target part material as a candidate processing material;

[0154] S4, searching the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type;

[0155] S5, inputting the candidate processing materials and candidate processing parameters into a preset macro model to obtain target processing parameters.

[0156] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0157] Among them, computer-readable storage media may include, but are not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0158] According to another aspect of the embodiments of the present application, an electronic device for implementing the grasping method of the above-mentioned CNC turning machining parameter recommendation method is also provided. The electronic device can be a server, a terminal, or a combination thereof.

[0159] Figure 5 is a schematic structural diagram of an optional electronic device according to an embodiment of the present application, such as Figure 5 As shown, it includes a processor 502, a communication interface 504, a memory 506 and a communication bus 508, wherein the processor 502, the communication interface 504, and the memory 506 communicate with each other via the communication bus 508, wherein,

[0160] Memory 506, for storing computer programs;

[0161] The processor 502 is configured to execute the computer program stored in the memory 506 to implement the following steps:

[0162] S1, obtaining a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed; wherein the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials; and the processing parameter data set includes target part materials and target processing types;

[0163] S2, determining whether the target part material is in the processing parameter knowledge base. If the target part material is not in the processing parameter knowledge base, using a granular computing method to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance indicator weight;

[0164] searching the processing parameter knowledge base for a processing material most similar to the target part material based on the performance indicator weight, and determining the most similar processing material as a candidate processing material;

[0165] S3, if the target part material is in the processing parameter knowledge base, determining the target part material as a candidate processing material;

[0166] S4, searching the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type;

[0167] S5, inputting the candidate processing materials and candidate processing parameters into a preset macro model to obtain target processing parameters.

[0168] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The communication interface is used for communication between the electronic device and other devices.

[0169] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Alternatively, the memory may also be at least one storage device located away from the aforementioned processor.

[0170] The above-mentioned processor can be a general-purpose processor, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0171] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0172] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0173] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0174] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0175] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0176] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0178] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0179] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0180] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0181] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for recommending CNC turning machining parameters, characterized in that: include: Obtaining a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed; wherein the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials; and the processing parameter data set includes target part materials and target processing types; Determining whether the target part material is in the processing parameter knowledge base, and if the target part material is not in the processing parameter knowledge base, using a granular computing method to determine a dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance indicator weight; searching the processing parameter knowledge base for a processing material most similar to the target part material based on the performance indicator weight, and determining the most similar processing material as a candidate processing material; In a case where the target part material is in the processing parameter knowledge base, determining the target part material as a candidate processing material; Searching the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type; The candidate processing materials and candidate processing parameters are input into a preset macro model to obtain target processing parameters.

2. The method for recommending CNC turning machining parameters according to claim 1, wherein: The step of inputting the candidate processing materials and candidate processing parameters into a preset macro model to obtain target processing parameters includes: The processing parameter influencing rules are used as constraint conditions to constrain decoding of the output results of the preset large model to obtain target processing parameters; wherein the processing parameter influencing rules are the mapping relationship between the material properties of the processing material and the processing parameters.

3. The method for recommending CNC turning machining parameters according to claim 1, wherein: After inputting the candidate processing materials and candidate processing parameters into a preset macro model to obtain target processing parameters, the method further includes: Receive user adjustment operations on target processing parameters; Record the adjusted processing parameters and the corresponding processing effect evaluation; The adjusted processing parameters are updated to the processing parameter knowledge base according to the user confirmation instruction.

4. The method for recommending CNC turning machining parameters according to claim 1, wherein: The method of using a granular computing method to determine the dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain the performance index weight includes: Converting material property data of the processed material into multi-level machinability grade values according to the material machinability grade table; Constructing a fuzzy similarity matrix and a fuzzy compatible quotient space family of material samples in a processing parameter knowledge base based on the multi-level processability grade values; Calculating the objective weight of each preset processing performance through a multi-granularity quotient space based on the fuzzy similarity matrix and the fuzzy compatible quotient space family; The dynamic weight of each preset processing performance is determined based on the objective weight to obtain a performance indicator weight.

5. The method for recommending CNC turning machining parameters according to claim 1, wherein: The processing parameter knowledge base construction method includes: The material property data set stores dual-version data of original values and processability grade values with the processed material brand as the index; the processing parameter data set adopts a four-dimensional storage structure, the dimensions of which include material brand, processing type, equipment model and parameter combination.

6. The method for recommending CNC turning machining parameters according to claim 1, wherein: include: The adjusted processing parameters and the corresponding processing effect evaluation are recorded through the buffer window memory mechanism.

7. The method for recommending CNC turning machining parameters according to claim 1, wherein: The step of obtaining a processing parameter data set corresponding to a processing parameter recommendation task to be processed includes: Get the part processing description input by the user; The large model API is called to extract keywords from the part processing description to obtain a processing parameter data set.

8. A CNC turning parameter recommendation device, characterized in that: The device comprises: a processing parameter acquisition module, configured to acquire a processing parameter knowledge base and a processing parameter data set corresponding to a processing parameter recommendation task to be processed; wherein the processing parameter data set includes a target part material and a target processing type; and the processing parameter knowledge base includes processing materials and processing parameters of different processing types corresponding to the processing materials; a first processing module, configured to determine whether the target part material is in the processing parameter knowledge base; if the target part material is not in the processing parameter knowledge base, using a granular computing method to determine a dynamic weight of each preset processing performance of each material sample in the processing parameter data set to obtain a performance indicator weight; searching the processing parameter knowledge base for a processing material most similar to the target part material based on the performance indicator weight, and determining the most similar processing material as a candidate processing material; The first processing module is further configured to determine the target part material as a candidate processing material when the target part material is in the processing parameter knowledge base; a second processing module, configured to search the processing parameter knowledge base based on the candidate processing material and the target processing type to obtain candidate processing parameters corresponding to the candidate processing material and the target processing type; The processing parameter recommendation module is used to input the candidate processing materials and candidate processing parameters into a preset large model to obtain target processing parameters.

9. An electronic device comprising: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for recommending CNC turning machining parameters as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to execute the method for recommending CNC turning machining parameters according to any one of claims 1 to 7.

Images