Intelligent configuration method, device and system for fixture standard parts in flexible production scenario

Abstract

This invention discloses an intelligent configuration method, device, and system for standard fixture parts in flexible manufacturing scenarios. The method includes: modularly decomposing standard fixture parts from a standard fixture parts library, extracting features from each module to obtain a standardized feature parameter set for each standard fixture part; for each workpiece, extracting a workpiece feature parameter set, and performing neural network selection reasoning between the workpiece feature parameter set and the standardized feature parameter set to obtain a candidate set of standard fixture parts matching the workpiece; determining the parameter constraints for the workpiece, and adaptively and dynamically adjusting the adjustable standard fixture parameters of each standard fixture part in the candidate set based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece. This invention solves the technical problem of low efficiency in selecting standard fixture parts in flexible manufacturing scenarios.

Description

Technical Field

[0001] This invention relates to the field of intelligent automotive design, and more specifically, to an intelligent configuration method, apparatus, and system for standard fixture parts in flexible production scenarios. Background Technology

[0002] As the manufacturing industry moves towards "customization, multiple batches, and short cycles," flexible production models have become an important means to meet the demands of multi-variety, small-batch production. As a key device for workpiece positioning and clamping, the structural adaptability and changeover efficiency of fixtures directly affect the flexibility level of the production line.

[0003] In existing technologies, fixture standard parts libraries typically employ modular design and categorized storage, achieving basic reuse and standardized management of fixture components. However, in flexible manufacturing scenarios, the application of existing fixture standard parts libraries still faces the following challenges:

[0004] First, the selection efficiency is low. The selection process in the existing standard parts library usually relies on manual searching and matching by engineers, requiring verification of parameters such as workpiece dimensions, processing technology, and positioning requirements one by one. This is not only time-consuming but also prone to inaccurate selection due to differences in experience, thus affecting processing accuracy and clamping stability. Second, parameter adaptability is insufficient. The structural dimensions, clamping force, positioning stroke, and other parameters of standard parts are mostly fixed levels, making it difficult to dynamically adjust for different workpiece materials (such as aluminum alloys and high-strength steel) or special structures (such as thin-walled parts), which can easily cause problems such as workpiece deformation or unstable positioning. Third, system integration is poor. The existing standard parts library is disconnected from the Manufacturing Execution System (MES) and Computer-Aided Design / Simulation System (CAD / CAE). The standard parts selection results cannot be automatically synchronized with production equipment or simulation platforms, requiring manual secondary input, resulting in long changeover and debugging times and low equipment utilization. In addition, scalability is also insufficient. When adding new standard part types, the classification and attribute information in the library needs to be updated manually. The lack of an automatic identification and classification mechanism makes it difficult to adapt to the rapid iteration needs of new parts and structures under flexible production.

[0005] For example, in traditional automated machining lines, the selection of standard parts and parameter debugging alone often takes 30 to 40 minutes during fixture changeover, accounting for more than half of the total changeover time, which significantly affects production cycle and capacity improvement.

[0006] There is currently no effective solution to the above problems. Summary of the Invention

[0007] This invention provides an intelligent configuration method, device, and system for standard fixture parts in flexible production scenarios, so as to at least solve the technical problem of low selection efficiency of standard fixture parts in flexible production scenarios.

[0008] According to one aspect of the present invention, an intelligent configuration method for standard fixture parts in a flexible production scenario is provided, comprising: modularly decomposing standard fixture parts in a standard fixture parts library, and extracting features from each standard fixture parts module obtained by the decomposition to obtain a standardized feature parameter set of the standard fixture parts; for each workpiece, extracting a workpiece feature parameter set, and performing neural network selection reasoning on the workpiece feature parameter set and the standardized feature parameter set to obtain a candidate set of standard fixture parts matching the workpiece; determining the parameter constraints of the workpiece, and adaptively and dynamically adjusting the adjustable standard fixture parts parameters of each standard fixture parts in the candidate set of standard fixture parts based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece.

[0009] According to another aspect of the present invention, an intelligent configuration device for standard fixture parts in a flexible production scenario is also provided, comprising: a feature extraction module configured to modularly decompose standard fixture parts in a standard fixture parts library, and extract features from each standard fixture parts module obtained by the decomposition to obtain a standardized feature parameter set of the standard fixture parts; an inference module configured to extract a workpiece feature parameter set for each workpiece, and perform neural network selection inference on the workpiece feature parameter set and the standardized feature parameter set to obtain a candidate set of standard fixture parts matching the workpiece; and a parameter adjustment module configured to determine the parameter constraints of the workpiece, and adaptively and dynamically adjust the adjustable standard fixture parts parameters of each standard fixture part in the candidate set of standard fixture parts based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece.

[0010] According to another aspect of the present invention, an intelligent configuration system for standard fixture parts in a flexible production scenario is also provided, comprising: a workpiece to be processed; and an intelligent configuration device as described above, for intelligently configuring a candidate set of standard fixture parts and the corresponding optimal parameter configuration for the workpiece to be processed.

[0011] In this embodiment of the invention, the standard fixture parts in the standard fixture parts library are modularly decomposed, and features are extracted from each modular standard fixture part to obtain a standardized feature parameter set for the standard fixture parts. For each workpiece, a workpiece feature parameter set is extracted, and neural network selection reasoning is performed between the workpiece feature parameter set and the standardized feature parameter set to obtain a candidate set of standard fixture parts matching the workpiece. The parameter constraints of the workpiece are determined, and the adjustable standard fixture parameters of each standard fixture part in the candidate set are adaptively and dynamically adjusted based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece. This solution addresses the technical problem of low efficiency in selecting standard fixture parts in flexible production scenarios. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0013] Figure 1 This is a flowchart of an optional intelligent configuration method for standard fixture parts in a flexible production scenario according to an embodiment of the present invention;

[0014] Figure 2 This is a flowchart of another optional intelligent configuration method for standard fixture parts in a flexible production scenario according to an embodiment of the present invention;

[0015] Figure 3 This is a flowchart of an optional standard parts selection method according to an embodiment of the present invention;

[0016] Figure 4 This is a flowchart of an optional adaptive adjustment parameter according to an embodiment of the present invention;

[0017] Figure 5 This is a flowchart illustrating the cross-platform collaborative operation of an intelligent configuration system for standard fixture parts in a flexible production scenario according to an embodiment of the present invention.

[0018] Figure 6 This is a flowchart illustrating the rapid switching of an intelligent configuration system for standard fixture parts in a flexible production scenario according to an embodiment of the present invention.

[0019] Figure 7 This is a schematic diagram of the intelligent configuration of standard fixture parts in an optional flexible production scenario according to an embodiment of the present invention;

[0020] Figure 8 A schematic diagram of the structure of a computer device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] According to an embodiment of the present invention, a method embodiment of an intelligent configuration method for standard fixture parts in a flexible production scenario is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] To address the shortcomings of existing standard fixture parts libraries in flexible production scenarios, such as low selection efficiency, poor parameter adaptability, and insufficient collaboration, this application provides an intelligent configuration of standard fixture parts for flexible production scenarios that integrates intelligent selection and parameter self-adaptation. This enables rapid and accurate selection of standard fixture parts, dynamic parameter matching, and cross-system data collaboration, thereby shortening fixture design and changeover time and improving the flexibility of the production line.

[0025] Figure 1 This is an intelligent configuration method for standard fixture parts in a flexible production scenario according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0026] Step S102: Modularly decompose the standard fixture parts in the standard fixture parts library, and extract features from each standard part module to obtain a standardized feature parameter set of the standard fixture parts;

[0027] For example, according to the structural and functional relationship of the fixture standard parts, the fixture standard parts are modularly decomposed at the functional unit level; the features of each standard part module obtained by the decomposition are extracted to obtain the standardized feature parameter set, wherein the standardized feature parameter set includes at least one of the following: workpiece size parameters, material properties, processing requirements, positioning reference and installation direction.

[0028] Step S104: For each workpiece, extract the workpiece feature parameter set, and perform neural network selection reasoning on the workpiece feature parameter set and the standardized feature parameter set to obtain a standard part candidate set that matches the workpiece.

[0029] For example, for each workpiece, the workpiece feature parameter set is extracted, and the workpiece feature parameter set is preprocessed to obtain the preprocessed workpiece feature parameter set; a random forest model is used to perform feature importance analysis on the preprocessed workpiece feature parameter set, and the random forest feature importance of each feature parameter in the preprocessed workpiece feature parameter set is calculated; based on the preprocessed workpiece feature parameter set, the random forest feature importance, and the standardized feature parameter set, a neural network selection reasoning is performed to obtain a set of standard parts candidate sets matching the workpiece.

[0030] In some embodiments, the following method can be used for neural network selection reasoning: The random forest feature importance is used to weight each feature parameter in the preprocessed workpiece feature parameter set; based on the standardized feature parameter set and the weighted workpiece feature parameter set, selection reasoning is performed on each standard part module to obtain the initial fit probability corresponding to each standard part module; the feature similarity between the weighted workpiece feature parameter set and the standardized feature parameter set is calculated through semantic matching to obtain the similarity result corresponding to each standard part module; based on the random forest feature importance, the initial fit probability, and the similarity result, fit degree fusion calculation is performed on each standard part module to obtain the final fit degree of each standard part module; based on the final fit degree, standard part modules that meet the preset fit threshold condition are selected to determine the standard part candidate set.

[0031] Step S106: Determine the parameter constraints of the workpiece, and based on the parameter constraints, adaptively and dynamically adjust the adjustable standard part parameters of each fixture standard part in the standard part candidate set to obtain the optimal parameter configuration corresponding to the workpiece.

[0032] First, the parameter constraints are constructed using the workpiece's material yield strength, dimensional fit, and dimensional tolerance as constraint factors. Next, for each fixture standard part in the candidate standard part set, the constraint relationship of the adjustable standard part parameters is determined based on the parameter constraints. Under the constraints, the initial parameters of the adjustable standard part are dynamically calculated to obtain the initial parameter configuration corresponding to each fixture standard part. Finally, within the feasible range of the initial parameter configuration, the adjustable standard part parameters of each fixture standard part in the candidate standard part set are adaptively and dynamically adjusted to generate the optimal parameter configuration. For example, based on the initial parameter configuration, the clamping state during processing, the post-assembly station status, and the cycle time are simulated and analyzed. Based on the simulation analysis results, it is determined whether the initial parameter configuration meets the parameter constraints. If the simulation analysis results do not meet the parameter constraints, based on the preset optimization objective and the parameter constraints, within the feasible range of the initial parameter configuration, the adjustable standard part parameters are iteratively optimized and corrected to obtain a corrected parameter configuration that meets the parameter constraints, which is then used as the optimal parameter configuration.

[0033] This application also provides another intelligent configuration method for standard fixture parts in flexible manufacturing scenarios, such as... Figure 2 As shown, the method includes the following steps:

[0034] Step S202, Feature modeling.

[0035] Construct a standardized feature model library. Modularly decompose the standard fixture parts, clarifying the core functional modules (positioning module, clamping module, support module, connection module, etc.), and define the standardized attributes of each module: including interface dimensions (such as T-slot spacing, locating pin specifications), material parameters (such as high-strength aluminum alloy, Cr12MoV alloy steel), accuracy level (such as locating surface flatness ≤0.01mm / m), and compatible workpiece types (shafts, boxes, plates, etc.). Simultaneously, establish a workpiece feature model, extracting key features such as workpiece dimensions, material properties, processing requirements, and positioning datum, forming a standardized feature parameter set as shown in Table 1, achieving feature correspondence between standard parts and workpieces.

[0036] Table 1

[0037]

[0038]

[0039]

[0040] In other embodiments, ontological semantic modeling or feature vector clustering can be used instead of structured table mapping.

[0041] Step S204, intelligent selection.

[0042] A smart selection model is constructed based on machine learning algorithms (such as random forests and neural networks), taking the workpiece feature parameter set as input, and then using methods such as... Figure 3 The following process is shown to implement standard parts selection:

[0043] Step S2041, data preprocessing.

[0044] The workpiece feature parameters are normalized to remove outlier data. For example, min-max normalization is used to eliminate the influence of features with different dimensions. The specific formula is as follows:

[0045]

[0046] in, These are the normalized eigenvalues. These are the original eigenvalues. This is the minimum value of this feature dimension. This is the maximum value of this feature dimension.

[0047] Step S2042: Calculate the importance of random forest features.

[0048] The Gini coefficient is used to measure the weight of each workpiece feature on the selection result.

[0049]

[0050] Gini(D) represents the purity of the feature dataset D, and K represents the number of feature classes. Let be the proportion of the k-th feature in the dataset. The formula for calculating the feature importance weight is:

[0051]

[0052] in, For the j-th feature before and after splitting The coefficient change, where m is the total number of workpiece features, and the weight value is used for weighting the results of the subsequent fusion model;

[0053] Step S2043, BP neural network selection reasoning.

[0054] A basic selection model is constructed using a 3-layer BP neural network. The number of nodes in the input layer is m (number of workpiece feature dimensions), the number of nodes in the hidden layer is 2m+1 (empirical optimal value), and the number of nodes in the output layer is n (number of standard part module types).

[0055] Hidden layer output layer:

[0056] in Output for the l-th hidden layer node. The connection weights from the input layer to the hidden layer. Here, f is the hidden layer bias, and f is the Sigmoid activation function:

[0057]

[0058] in, This represents the net input to the hidden layer neurons. The output layer output formula is:

[0059]

[0060] in, Let be the initial adaptation probability of the k-th standard component module. The connection weights from the hidden layer to the output layer. As a bias for the output layer, the softmax function transforms the output into a probability distribution.

[0061] Step S2044, feature matching.

[0062] The feature model library is called to calculate the similarity between the workpiece features and the standard parts module through semantic matching;

[0063] Step S2045, Selection Recommendation.

[0064] By combining historical selection data and processing quality feedback data, the optimal standard parts combination scheme is output, and evaluation indicators such as the scheme's adaptation efficiency and accuracy assurance capability are marked. Then, by combining the feature importance weights of the random forest and the initial adaptation probability of the neural network, a feature similarity correction factor is introduced to calculate the final adaptation degree.

[0065]

[0066] in, For the final fit of the k-th standard component module, This represents the similarity (calculated using cosine similarity) between the j-th feature of the workpiece and the corresponding feature of the k-th module of the standard part. Select... Candidate solutions are formed from standard parts modules with a value of ≥ 0.85. Based on historical selection success rates and processing quality feedback data, the optimal standard parts combination solution is output.

[0067] In some other embodiments, SVM + genetic algorithm or rule engine + case reasoning can be used instead of random forest + BP neural network.

[0068] Step S2046, manual verification.

[0069] This embodiment provides an engineer review channel, which supports manual adjustment and optimization of recommended solutions, and feeds the adjustment results back to the selection model to achieve iterative optimization of the model.

[0070] Specifically, an engineer review channel is provided to allow for manual adjustments to the recommended solutions. The adjustments are then fed back into the selection model as new samples, and the model parameters are updated using gradient descent.

[0071]

[0072] in, These are the model parameters (weights, biases). The learning rate is set between 0.01 and 0.05. The gradient of the loss function is used to continuously improve the accuracy of model selection.

[0073] Step S206: Adaptively adjust parameters.

[0074] For the selected standard parts, a parameter self-adaptive model is constructed to achieve dynamic adjustment of key parameters. Specifically, such as... Figure 4 As shown, it includes the following steps:

[0075] Step S2062: Multi-dimensional constraint modeling to determine parameter constraints.

[0076] Using the workpiece material yield strength, dimensional fit, and dimensional tolerance as constraint factors, parametric constraints are established for parameters such as clamping force, positioning stroke, and support stiffness, as shown in the following constraint equations:

[0077] 1) Material strength constraint: The clamping force must not exceed the maximum allowable clamping force corresponding to the yield strength of the workpiece material to avoid plastic deformation of the workpiece. The specific constraint equation is as follows:

[0078]

[0079] in, The maximum allowable clamping force is given by σs, where σs is the yield strength of the workpiece material (MPa) and A is the area of ​​the clamping surface (mm²). For safety factors (take 1.5-2.5 based on material properties, 1.5-2.0 for aluminum alloys, and 2.0-2.5 for high-strength steel);

[0080] 2) Machining accuracy constraints: The positioning error must be controlled within 1 / 3 of the machining dimensional tolerance to ensure machining accuracy. The specific constraint equation is as follows:

[0081]

[0082] Where △x is the positioning error (mm) and T is the dimensional tolerance of the critical dimension of the workpiece (mm);

[0083] 3) Stiffness balance constraint: The support stiffness must satisfy the requirement that the workpiece deformation during processing is less than the allowable deformation. The specific constraint equation is as follows:

[0084]

[0085] Where δ is the workpiece deformation (mm), Fc is the dimensional fit (N), and K is the support stiffness (N / mm). max Allowable deformation (0.005-0.02mm depending on machining accuracy requirements).

[0086] 4) Equipment compatibility constraints: Standard parts parameters must be within the rated working range of the production equipment. For example, the working air pressure of pneumatic clamps must be within the range of the equipment's air source pressure (0.4-0.8MPa), and the working oil pressure of hydraulic clamps must be within the rated pressure of the equipment's hydraulic system (5-20MPa).

[0087] Step S2064: Dynamically calculate initial parameters.

[0088] Based on the constraint equation system and combined with empirical formulas from finite element simulation, the initial optimal values ​​of key parameters of standard parts are calculated.

[0089] First, considering both material strength constraints and cutting force balance requirements, the initial clamping force is calculated using the following formula:

[0090]

[0091] in, L1 is the initial value of the clamping force, L2 is the distance (mm) from the point of application of the cutting force to the positioning datum, and L2 is the distance (mm) from the point of application of the clamping force to the positioning datum. The maximum value of the two is taken to ensure stable clamping without damaging the workpiece.

[0092] Next, the initial value of the positioning stroke is calculated. Specifically, it is calculated based on the fit clearance and adjustment allowance between the workpiece positioning datum and the standard part. The specific formula is as follows:

[0093]

[0094] in, To locate the initial value of the travel, d is the diameter of the workpiece positioning hole (mm), and d is the diameter of the positioning pin (mm). To adjust the allowance (take 0.5-2mm depending on the batch size, the larger the batch size).

[0095] Next, the initial support height is calculated. Specifically, the initial support height is calculated by combining the workpiece machining surface height and the equipment table height, using the following formula:

[0096]

[0097] Where Hw is the target height of the workpiece machining surface (mm), and Ht is the height of the equipment worktable (mm). Allowance for height adjustment (2-5mm).

[0098] Step S2066, simulation verification and parameter correction.

[0099] Initial parameters are input into the CAD / CAE simulation platform to establish a coupled simulation model of the workpiece, fixture, and equipment. This model simulates clamping and cutting conditions during the machining process and analyzes the stress distribution, deformation, and positioning error of the workpiece. If the simulation results do not meet the constraints (e.g., deformation exceeds the allowable value), a particle swarm optimization algorithm is used for iterative parameter correction.

[0100] Objective function: (Minimum workpiece deformation)

[0101] Constraints:

[0102] Iteration formula:

[0103]

[0104]

[0105] in, Let be the velocity of the i-th particle in generation t+1. The inertia weight is set to 0.5-0.8. Let be the velocity of the i-th particle in generation t, c1 and c2 be learning factors (both set to 2.0), and r1 and r2 be random numbers between 0 and 1. Let be the individual optimal solution for the i-th particle. This is the globally optimal solution. This represents the position (i.e., parameter value) of the i-th particle in the (t+1)-th generation. Let be the position of the i-th particle in generation t. Iterate until the simulation results satisfy the constraints, and output the corrected optimal parameter values.

[0106] In another embodiment, a genetic algorithm plus fuzzy control or model predictive control can be used instead of particle swarm optimization + PID.

[0107] Step S2068: Real-time feedback and correction of the closed loop.

[0108] In actual production, a sensor array (pressure sensor, laser rangefinder, strain sensor) collects data in real time, including clamping force (clamping status), positioning accuracy (post-assembly station status), and workpiece deformation (cycle time). This data is then compared with the threshold values ​​corresponding to the optimal parameter values. If the deviation exceeds the allowable range (e.g., clamping force deviation ±5%, positioning error deviation ±0.01mm), a real-time correction mechanism is triggered, using a PID control algorithm to dynamically adjust the parameters.

[0109]

[0110] Where u(t) is the regulating output (such as air pressure or oil pressure regulation), Kp is the proportional coefficient (taken as 5-10), Ki is the integral coefficient (taken as 0.1-0.5), and Kd is the derivative coefficient (taken as 0.5-2.0). For the integral deviation variable, This represents the deviation between the actual and target values. Closed-loop adjustment ensures that parameters remain optimal throughout the machining process, guaranteeing stable machining quality.

[0111] Step S2069: Store the parameter configuration package.

[0112] The adjusted optimal parameters are bound to the standard parts combination scheme to form a unique parameter configuration package, which includes information such as standard parts model, key parameter values, constraint thresholds, compatible workpiece characteristics, and simulation verification results. This package is stored in the standard parts library and indexed for easy and quick retrieval later.

[0113] This application also provides an intelligent configuration system for standard fixture parts in flexible production scenarios. This system integrates the data flow between the standard parts library, the MES system, the CAD / CAE simulation platform, and the production equipment. Its specific operation process is as follows: Figure 5 As shown, it includes:

[0114] Step S502, data synchronization.

[0115] The standard parts selection scheme and parameter configuration package are automatically synchronized to the CAD / CAE platform to enable rapid assembly and simulation verification of fixtures.

[0116] Step S504, equipment linkage.

[0117] The parameter configuration package is sent to the production equipment (CNC machine tools, robots, conveyor lines) via industrial Ethernet (Profinet / EtherCAT) to realize one-click access and automatic calibration of equipment parameters.

[0118] This system records the requisition, use, maintenance, and disposal data of standard parts through the MES system, establishing a unique identification code to achieve full lifecycle management. In another embodiment, IIoT+MQTT or OPC UA can be used to replace Industrial Ethernet+TCP / IP.

[0119] This system also enables rapid switching between multiple manufacturer libraries. Specifically, it allows for dynamic iterative optimization of the standard parts library, building a rapid switching system for standard parts libraries from multiple OEMs, and improving the adaptability of production lines to multiple orders.

[0120] This system establishes a dynamic update mechanism for standard parts within the library to ensure optimal resource allocation. It also constructs a rapid switching module for standard parts libraries from multiple OEMs, enabling quick adaptation to different OEM technical specifications. The specific rapid switching process is as follows: Figure 6 As shown, it includes:

[0121] Step S602: Dynamically update the standard parts library.

[0122] 1) Automatic classification of newly added standard parts

[0123] When adding a new standard part, its functional attributes (module type, core parameters, and applicable scenarios) and applicable features are automatically extracted through a feature recognition algorithm (based on SIFT feature extraction). The similarity is matched with the feature model in the standard part library, and the classification and storage are automatically completed, and the feature index is updated. If it is a brand new functional module, a new module classification and feature attribute table is automatically created, and standardized attribute codes are generated to ensure that the new standard part is quickly integrated into the library without the need for manual classification.

[0124] 2) Optimization of in-library resources

[0125] Monthly statistics are compiled on data such as the reuse rate, failure frequency, maintenance cost, and processing quality pass rate of standard parts. A multi-dimensional evaluation index system is established, using the formula:

[0126]

[0127] in Let i be the evaluation score for the i-th standard part. For reuse rate, To achieve the processing quality pass rate, Fault frequency, The unit time maintenance cost is represented by α, β, γ, and δ, which are weighting coefficients (set according to production priority, α=0.3, β=0.3, γ=0.2, δ=0.2). The elimination evaluation score is below the threshold ( To reduce the cost of tooling manufacturing, we can eliminate inefficient and high-loss standard parts, optimize resource allocation within the warehouse, and lower tooling manufacturing costs.

[0128] Step S604: Quick switching between multiple warehouses.

[0129] A full-process rapid switching module consisting of "factory standard modeling - switching triggering - data compatibility - fast loading - linkage adaptation" was constructed to enable rapid calling and adaptation of standard parts libraries from different OEMs, as shown in Table 2.

[0130] Table 2

[0131]

[0132]

[0133] In another embodiment, containerization + preloading or configuration file + interpolation can be used instead of virtualization + LRU caching.

[0134] Compared to existing technologies, the core advantage of this flexible production fixture standard parts library optimization solution lies in its construction of a fully intelligent and collaborative standard parts management and adaptation system: It solves the problems of incomplete feature coverage and matching deviations in existing technologies through standardized feature full-dimensional mapping, laying a data foundation for accurate selection; it integrates a machine learning selection engine to overcome reliance on experience, significantly improving selection accuracy and efficiency; a multi-constraint dynamic parameter adaptation closed loop upgrades parameters from static preset to dynamic optimization, effectively avoiding workpiece deformation and positioning deviations; cross-system collaborative management breaks down data barriers, enabling equipment linkage and automatic parameter synchronization, shortening changeover and debugging time; and dynamic updates and rapid switching mechanisms between multiple factory libraries improve library adaptability and the production line's multi-order response capability, ultimately significantly improving the stability, efficiency, and quality control level of flexible production.

[0135] This application also provides an intelligent configuration device for standard fixture parts in flexible production scenarios, such as... Figure 7 As shown, it includes: a feature extraction module 72, configured to modularly decompose the standard fixture parts in the standard fixture parts library, and extract features from each standard fixture parts module to obtain a standardized feature parameter set of the standard fixture parts; an inference module 74, configured to extract a workpiece feature parameter set for each workpiece, and perform neural network selection inference between the workpiece feature parameter set and the standardized feature parameter set to obtain a candidate set of standard fixture parts matching the workpiece; and a parameter adjustment module 76, configured to determine the parameter constraints of the workpiece, and adaptively and dynamically adjust the adjustable standard fixture parts parameters of each standard fixture part in the candidate set of standard fixture parts based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece.

[0136] It should be noted that the intelligent configuration device for standard fixture parts in flexible production scenarios provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent configuration device for standard fixture parts in flexible production scenarios provided in the above embodiments and the intelligent configuration method for standard fixture parts in flexible production scenarios belong to the same concept. The specific implementation process is detailed in the method embodiments and will not be repeated here.

[0137] Figure 8 A schematic diagram of a computer device suitable for implementing embodiments of the present disclosure is shown. It should be noted that... Figure 8 The computer device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0138] like Figure 8 As shown, the computer device includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage section 1008 into a random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0139] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0140] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for intelligent configuration of standard fixture parts in flexible manufacturing scenarios, characterized in that, include: The standard fixture parts in the standard fixture parts library are modularly decomposed, and features are extracted from each standard part module to obtain a standardized feature parameter set of the standard fixture parts. For each workpiece, a set of workpiece feature parameters is extracted, and the set of workpiece feature parameters is combined with the standardized set of feature parameters to perform neural network selection reasoning to obtain a set of standard parts candidate matching the workpiece. The parameter constraints of the workpiece are determined, and the adjustable standard parameters of each fixture standard part in the candidate set of standard parts are adaptively and dynamically adjusted based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece.

2. The method according to claim 1, characterized in that, The standard fixture parts in the standard fixture parts library are modularized, and features are extracted from each modularized standard part to obtain a standardized feature parameter set for the standard fixture parts, including: Based on the structural and functional relationship of the fixture standard parts, the fixture standard parts are modularly decomposed at the functional unit level; The features of each standard part module obtained by the split are extracted to obtain the standardized feature parameter set, wherein the standardized feature parameter set includes at least one of the following: workpiece size parameters, material properties, processing requirements, positioning reference and installation direction.

3. The method according to claim 1, characterized in that, For each workpiece, a set of workpiece feature parameters is extracted, and the workpiece feature parameter set is compared with the standardized feature parameter set using a neural network selection inference to obtain a candidate set of standard parts matching the workpiece, including: For each workpiece, the workpiece feature parameter set is extracted, and the workpiece feature parameter set is preprocessed to obtain the preprocessed workpiece feature parameter set. The random forest model is used to perform feature importance analysis on the preprocessed workpiece feature parameter set, and the random forest feature importance of each feature parameter in the preprocessed workpiece feature parameter set is calculated. Based on the preprocessed set of workpiece feature parameters, the importance of random forest features, and the standardized set of feature parameters, a neural network selection reasoning is performed to obtain a set of standard parts candidate matching the workpiece.

4. The method according to claim 3, characterized in that, Based on the preprocessed workpiece feature parameter set, the random forest feature importance, and the standardized feature parameter set, a neural network selection inference is performed to obtain a candidate set of standard parts matching the workpiece, including: The random forest feature importance is used to weight each feature parameter in the preprocessed workpiece feature parameter set. Based on the standardized feature parameter set and the weighted workpiece feature parameter set, selection reasoning is performed on each standard part module to obtain the initial adaptation probability corresponding to each standard part module. The similarity between the weighted set of workpiece feature parameters and the standardized set of feature parameters is calculated by semantic matching to obtain the similarity results for each standard part module. Based on the importance of the random forest features, the initial fit probability, and the similarity results, the fit degree of each standard component module is fused and calculated to obtain the final fit degree of each standard component module. Based on the final fit, standard parts modules that meet the preset fit threshold conditions are selected to determine the standard parts candidate set.

5. The method according to claim 1, characterized in that, The parameter constraints of the workpiece are determined, and the adjustable standard parameters of each fixture standard part in the candidate set of standard parts are adaptively and dynamically adjusted based on the parameter constraints to obtain the optimal parameter configuration corresponding to the workpiece, including: The parameter constraint conditions are constructed using the material yield strength, dimensional fit, and dimensional tolerance of the workpiece as constraint factors. For each fixture standard part in the candidate set of standard parts, based on the parameter constraints, the constraint relationship of the adjustable standard part parameters is determined, and under the constraint of the constraint relationship, the initial parameters of the adjustable standard part parameters are dynamically calculated to obtain the initial parameter configuration corresponding to each fixture standard part; Within the feasible range of the initial parameter configuration, the adjustable standard part parameters of each fixture standard part in the candidate set of standard parts are adaptively and dynamically adjusted to generate the optimal parameter configuration.

6. The method according to claim 5, characterized in that, Within the feasible range of the initial parameter configuration, the adjustable standard part parameters of each fixture standard part in the candidate set of standard parts are adaptively and dynamically adjusted to generate the optimal parameter configuration, including: Based on the initial parameter configuration, the clamping state, post-assembly station status, and cycle time during the processing are simulated and analyzed. Based on the simulation analysis results, it is determined whether the initial parameter configuration meets the parameter constraint conditions. When the simulation analysis results do not meet the parameter constraints, based on the preset optimization objective and the parameter constraints, within the feasible range of the initial parameter configuration, the adjustable standard part parameters are iteratively optimized and corrected to obtain a corrected parameter configuration that meets the parameter constraints, which is then used as the optimal parameter configuration.

7. An intelligent configuration device for standard fixture parts in a flexible production scenario, characterized in that, include: The feature extraction module is configured to modularly decompose the fixture standard parts in the fixture standard parts library, and extract features from each standard part module obtained by the decomposition to obtain a standardized feature parameter set of the fixture standard parts; The reasoning module is configured to extract a set of feature parameters for each workpiece, and perform neural network selection reasoning on the set of feature parameters and the standardized set of feature parameters to obtain a set of candidate standard parts that match the workpiece. The parameter adjustment module is configured to determine the parameter constraints of the workpiece, and based on the parameter constraints, adaptively and dynamically adjust the adjustable standard part parameters of each fixture standard part in the standard part candidate set to obtain the optimal parameter configuration corresponding to the workpiece.

8. An intelligent configuration system for standard fixture parts in flexible production scenarios, characterized in that, include: Workpiece to be processed; The intelligent configuration device as described in claim 7 is used to intelligently configure a set of standard parts candidates and the corresponding optimal parameter configuration for the workpiece to be processed.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 6.

10. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the method according to any one of claims 1 to 6.

Images