Production intelligent control method and system for hook stress distribution optimization
By obtaining hook task information, simulation analysis and building a simplified stress mapping model, the problems of high cost and low efficiency of optimization of hook stress distribution are solved, and the optimization cost reduction, efficiency improvement and flexibility enhancement are achieved.
Patent Information
- Application Number
- CN202510259002.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-06
- Publication Date
- 2025-06-24
AI Technical Summary
In the prior art, the optimization of the link stress distribution is costly and low in efficiency, making it difficult to quickly respond to complex and diversified needs.
By obtaining hook task information, traversing the matching hook plan library, performing simulation analysis, identifying stress concentration areas, building a simplified stress mapping model based on machine learning, combining optimization algorithms for iterative optimization to obtain the optimal plan.
It has achieved reduced optimization costs, improved efficiency and enhanced flexibility, and can quickly respond to complex and diversified needs.
Smart Images
Figure CN120197475A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of machining technology, and particularly to a production intelligent control method and system for optimizing the stress distribution of hooks. Background Art
[0002] Hooks are widely used in industrial production, construction, transportation and other fields. During use, they bear complex stress distributions, and stress concentration problems are often one of the main reasons for hook failure. By optimizing the stress distribution in the hook design and production process, it helps to improve the service life and reliability of the hook.
[0003] Existing methods for optimizing the stress distribution of hooks include analysis and improvement using finite element simulation methods, optimizing the hook structure design through a large number of experimental tests, or production optimization based on a single parameter (such as material properties), which have technical problems such as high optimization costs, low optimization efficiency, and difficulty in quickly responding to complex and diverse requirements. Summary of the Invention
[0004] The present invention provides a production intelligent control method and system for optimizing the stress distribution of hooks to solve the technical problems of high optimization costs, low optimization efficiency, and difficulty in quickly responding to complex and diverse requirements in the prior art, and to achieve the technical effects of reducing optimization costs, improving efficiency, and enhancing flexibility.
[0005] In a first aspect, the present invention provides a production intelligent control method for optimizing the stress distribution of hooks, wherein the method includes:
[0006] Obtain hook task information, and based on the hook task information, traverse and match in the hook plan library to obtain N adapted hook plans, and output them as an alternative hook plan set, where N is a positive integer greater than or equal to 2.
[0007] Extract the target application environment according to the hook task information, define the target requirement constraints according to the target application environment, and perform simulation analysis on the alternative hook plan set.
[0008] Analyze the simulation analysis results to identify stress concentration areas, and define plan optimization parameters according to the identification results.
[0009] Combine the historical hook production records and historical simulation analysis records to construct a simplified stress mapping model, where the construction of the simplified stress mapping model is a piecewise model based on machine learning.
[0010] Based on the optimization parameters and the simplified stress mapping model, combine an optimization algorithm to iteratively optimize the alternative hook plan set to obtain an optimal plan as the target production plan.
[0011] Second aspect, the present invention also provides a production intelligent control system for optimizing the stress distribution of hooks. Wherein, the system includes:
[0012] A task information acquisition module, configured to acquire hook task information, and based on the hook task information, traverse and match in a hook plan library to obtain N adapted hook plans, and output them as an alternative hook plan set, where N is a positive integer greater than or equal to 2.
[0013] A requirement constraint definition module, configured to extract a target application environment according to the hook task information, define target requirement constraints according to the target application environment, and perform simulation analysis on the alternative hook plan set.
[0014] A region identification module, configured to analyze the simulation analysis results to identify stress concentration regions, and define plan optimization parameters according to the identification results.
[0015] A simplified mapping module, configured to combine historical hook production records and historical simulation analysis records to construct a simplified stress mapping model, where the construction of the simplified stress mapping model is a piecewise model based on machine learning.
[0016] An iterative optimization module, configured to iteratively optimize the alternative hook plan set based on the optimization parameters and the simplified stress mapping model, in combination with an optimization algorithm, to obtain an optimal plan as the target production plan.
[0017] The present invention discloses a production intelligent control method and system for optimizing the stress distribution of hooks, including: acquiring hook task information, and based on this information, traversing and matching in a hook plan library to screen out N adapted hook plans to form an alternative hook plan set, where N is a positive integer not less than 2; extracting a target application environment according to the hook task information, and defining target requirement constraints based on the target application environment to perform simulation analysis on the alternative hook plan set; analyzing the simulation analysis results, identifying stress concentration regions, and defining plan optimization parameters according to the identification results; combining historical hook production records and historical simulation analysis records to construct a piecewise simplified stress mapping model based on machine learning; using the optimization parameters and the simplified stress mapping model, in combination with an optimization algorithm, to iteratively optimize the alternative hook plan set, and finally obtaining an optimal plan as the target production plan. The production intelligent control method and system for optimizing the stress distribution of hooks disclosed by the present invention solve the technical problems of high optimization cost, low optimization efficiency, and difficulty in quickly responding to complex and diverse requirements, and achieve the technical effects of reducing optimization cost, improving efficiency, and enhancing flexibility. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a schematic flowchart of the production intelligent control method for optimizing the stress distribution of hooks according to the present invention;
[0019] Figure 2 It is a schematic structural diagram of the production intelligent control system for optimizing the stress distribution of hooks in the present invention.
[0020] Explanation of reference numerals in the drawings: Task information acquisition module 11, requirement constraint definition module 12, area recognition module 13, simplified mapping module 14, iterative optimization module 15. Detailed implementation manners
[0021] In the embodiments of the present invention, the overall idea adopted for the technical solution provided to solve the technical problems of high optimization cost, low optimization efficiency, and difficulty in quickly responding to complex and diverse requirements existing in the prior art is as follows:
[0022] First, obtain the hook task information, and traverse and match in the hook plan library based on this information to obtain N adapted hook plans, and output them as an alternative hook plan set, where N is a positive integer greater than or equal to 2. Next, extract the target application environment according to the hook task information, define the target requirement constraints, and perform a simulation analysis on the alternative hook plan set. According to the simulation analysis results, analyze the stress concentration areas, and identify the plan optimization parameters based on these areas. Combine the historical hook production records and historical simulation analysis records to construct a simplified stress mapping model, which is a piecewise model based on machine learning. Finally, based on the optimization parameters and the simplified stress mapping model, combine the optimization algorithm to perform iterative optimization on the alternative hook plan set, so as to obtain the optimal plan as the target production plan.
[0023] The above technical solution will be described in detail below in combination with the drawings in the specification and specific implementation manners to better understand the above technical solution. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments only for explaining the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention. In addition, it should be noted that, for the sake of description, only the parts related to the present invention are shown in the drawings rather than all of them.
[0024] Embodiment 1
[0025] Figure 1 It is a schematic flow diagram of the production intelligent control method for optimizing the stress distribution of hooks in the present invention, where the method includes:
[0026] S100: Obtain the hook task information, and traverse and match in the hook plan library based on the hook task information to obtain N adapted hook plans, and output them as an alternative hook plan set, where N is a positive integer greater than or equal to 2.
[0027] Specifically, first, based on the hook task information, multiple hook plans with a high degree of adaptability are retrieved and obtained from the hook plan library, and the output is the alternative hook plan set. Among them, the hook plan library is a database for storing various predefined hook plans, and each hook plan represents a hook production process and its corresponding parameter combination (such as bending parameters, bending radius, post-processing parameters, applicable size specification parameters, material parameters, etc.) to support task management and matching requirements.
[0028] Specifically, by traversing all the hook plans in the hook plan library, comparing the task requirements with the parameters of the hook plans, calculating the matching degree, and sorting according to the matching degree, N best-matching hook plans are selected as the alternative hook plan set.
[0029] By traversing the hook plan library, alternative plans highly relevant to the task can be screened out in a short time. By outputting at least two alternative plans, the flexibility and selectivity of subsequent optimization can be ensured.
[0030] In some embodiments, the hook task information is obtained, and based on the hook task information, traversal matching is performed in the hook plan library to obtain N adapted hook plans, and the output is the alternative hook plan set, including:
[0031] The hook task information is obtained, and the hook parameters of the hook task are analyzed to generate a hook parameter set; with the hook parameter set as the retrieval constraint, similar hook plans are retrieved and matched in the hook plan library, and the retrieval results are sorted, and the top N plans with the highest matching degree are selected as the alternative hook plan set.
[0032] Specifically, first, the specific information about the hook task is collected, including the shape and size requirements of the hook, the load-bearing requirements, the use environment, the material characteristics, etc.; then, the key hook parameters are extracted from the hook task information, that is, the parameters that have a major impact on the hook performance and the hook production process, such as the geometric shape, size specification, material strength, etc. of the hook, to generate a hook parameter set for guiding the retrieval of hook plans.
[0033] Specifically, using the hook parameter set as the retrieval constraint condition, retrieval is performed in the hook plan library, including checking whether the parameter range is covered, whether the process type is consistent, whether the material attributes match, etc., to ensure that the retrieval process can focus on the hook plans that match the task requirements.
[0034] Specifically, based on the overlapping degree between the parameter range in the hooking plan and the task parameter range, the matching degree between the hooking task target and the production target in the plan, and the adaptation degree between the task conditions and the plan execution conditions, calculate the matching degree of the retrieval results, and sort the retrieval results in descending order of the matching degree; then, according to the sorting results, select the top N plans with the highest similarity as the alternative hooking plan set, where N is a positive integer greater than or equal to 2.
[0035] The above method steps accurately retrieve the plan library through the hooking parameter set, support personalized adjustment of the alternative plan results, and meet the requirements of different task scenarios; the obtained hooking plans with high matching degree provide an optimization basis for improving the efficiency and quality of the hooking production process in the future.
[0036] S200: Extract the target application environment according to the hooking task information, define the target requirement constraints according to the target application environment, and perform a simulation analysis on the alternative hooking plan set.
[0037] Specifically, the target application environment includes: the usage scenario, that is, the specific application field of the hook, such as construction, automotive, home furnishing, etc.; the environmental conditions, that is, the environmental factors that the hook may face during use, such as temperature, humidity, corrosiveness, etc.; the load requirement, which refers to the maximum load or strength requirement that the hook bears during use. By obtaining the target application environment in the hooking task information, the corresponding target requirement constraints in the simulation analysis can be configured, so as to realize the accurate simulation of the target application environment.
[0038] In some embodiments, extracting the target application environment according to the hooking task information, defining the target requirement constraints according to the target application environment, and performing a simulation analysis on the alternative hooking plan set includes:
[0039] Identify the target application environment in the hooking task information, and set the target requirement constraints according to the target application environment, where the target requirement constraints include force constraints and environmental constraints; combine the target requirement constraints to perform simulation initialization, and analyze the stress distribution of the simulated hook in the target application environment, and the output is the simulation analysis result.
[0040] Specifically, first extract the target application environment corresponding to the target hook from the hooking task information. The target application environment includes the usage scenario, environmental factors, load requirements (such as maximum static load, dynamic impact load, continuous fatigue stress) of the target hook, etc., which are used to provide a parameter setting basis for subsequent simulation analysis; then, according to the obtained target application environment, configure the simulation initialization settings, including material property parameters (such as elastic modulus, yield strength), geometric model parameters (the structure and size of the hook), force conditions (loading method, magnitude, direction), environmental conditions (temperature, humidity, corrosion rate, etc.).
[0041] Furthermore, according to the constraint conditions of the hooking process in the alternative hooking plan (such as the number of bends, bending radius, post-treatment temperature, etc.), a finite element model of the target hook is established in the simulation software, and the target requirement constraints (simulation initialization settings) are applied to simulate the stress distribution of the target hook in the target application environment, and the simulation analysis results are obtained; wherein, the simulation analysis results include the stress magnitude, stress type and stress direction of each part of the target hook.
[0042] Exemplarily, the simulation analysis results are characterized as the stress distribution diagram of the hook structure, the maximum stress and its position, the fatigue life estimation of the stressed area, etc.
[0043] The above method steps ensure that the simulation analysis conforms to the actual use conditions by combining the requirement constraints of the target application environment for simulation, and further identify the possible stress concentration problems of the hook under different alternative hooking plans in the target environment, providing a scientific basis for the selection and optimization of the hooking plan.
[0044] S300: Analyze the simulation analysis results to identify the stress concentration area, and define the plan optimization parameters according to the identification results.
[0045] Specifically, analyzing the simulation analysis results, including the stress distribution diagram, stress concentration points, maximum stress values, etc., to identify the stress concentration areas in the simulation model, and these areas correspond to the weak points in the hook under the design and process; then, judge the stress type of the stress concentration area, and analyze the stress distribution in the concentration area, and formulate a structure optimization strategy. For example, for bending stress concentration, it is necessary to increase the bending radius or adjust the number of bends; for thermal stress concentration, it may be necessary to adjust the heat treatment process; at the same time, according to the concentration degree and stress magnitude of the stress concentration area, set the corresponding adjustment step for the parameter dimension in the optimization strategy to balance the efficiency and accuracy of the optimization.
[0046] Through the definition of the optimization parameters and the selection of the adjustment step in the above process, it helps to precisely control the optimization process and ensure the performance and safety of the hook in various application environments.
[0047] In some embodiments, analyzing the simulation analysis results to identify the stress concentration area, and defining the plan optimization parameters according to the identification results includes:
[0048] Perform quantitative analysis on the simulation analysis results to determine the stress concentration area; based on the stress concentration area, extract the stress value and stress direction, and compare them with the preset stress limit baseline to determine the stress overrun vector; according to the stress overrun vector, define the stress optimization direction and stress optimization step, and output the stress optimization direction and stress optimization step as the plan optimization parameters.
[0049] Specifically, first, obtain the stress distribution data of the hook structure from the simulation analysis results, including the node stress values and directions; then, by comparing the local stress values with the mean of the overall stress distribution, screen the areas where the stress values exceed a certain multiple (such as 2 times) of the global average stress as stress concentration areas, such as the hook bending points, sharp corners, etc.; next, extract the stress values (magnitudes) and stress directions of the nodes in the stress concentration area one by one to form a stress vector set; then, combine the force constraints of the target application environment and the performance constraints of the material, preset a stress limit baseline, calculate the vector difference between the stress vector set and the preset stress limit baseline to form a stress overrun vector set, which characterizes the direction and magnitude of the deviation of the stress concentration area from the expected stress level.
[0050] Furthermore, based on the direction of the stress overrun vector, determine the main direction in which the stress needs to be reduced in the optimization area. Exemplarily, if the stress concentration area is mainly caused by tensile stress, the optimization direction points to design adjustments or material improvements to reduce tensile stress; according to the magnitude of the overrun value, set the optimization step size. Exemplarily, for slight overrun (such as the overrun value < 10%), select a smaller optimization step size or set a smaller total step size for the parameters adjusted in each optimization.
[0051] The above method steps clarify the key areas that need to be optimized through stress overrun vector analysis, and then analyze and determine the stress optimization direction and step size, providing a clear optimization direction and optimization constraints for the hook plan, which helps to improve the efficiency of stress distribution adjustment and optimization.
[0052] S400: Combine the historical hook production records and historical simulation analysis records to construct a simplified stress mapping model, where the construction of the simplified stress mapping model is a piecewise model based on machine learning.
[0053] Specifically, the simplified stress mapping model is used to construct an end-to-end mapping path between the hook plan and the stress distribution situation, realizing the end-to-end prediction of the hook plan to the stress distribution. Among them, the simplified stress mapping model includes multiple segments, and the segmented simplified stress mapping model of each segment is an independent machine learning model for predicting the stress distribution under specific conditions.
[0054] Optionally, the segmentation basis of the piecewise model includes: geometric segmentation, which is divided into different geometric feature intervals according to the geometric characteristics of the hook (such as curvature, thickness, length); material segmentation, which is divided into different material characteristic intervals according to material parameters (such as strength, ductility); load segmentation, which is classified based on the load types in historical simulations (such as static load, dynamic load).
[0055] Through simplified segmented modeling, it helps to reduce the computational complexity of stress distribution prediction, quickly generate stress distribution prediction results, and thus improve the optimization efficiency.
[0056] In some embodiments, a simplified stress mapping model is constructed by combining historical hook production records and historical simulation analysis records. The construction of the simplified stress mapping model is a machine learning-based piecewise model, including:
[0057] Based on the historical hook production records, a set of historical shape coefficients is calculated and obtained, and clustering analysis is performed based on the set of historical shape coefficients to determine a set of hook shape intervals; based on the set of hook shape intervals, historical simulation records are interactively sampled to generate an interval sample set, where the interval sample set includes interval sample subsets corresponding to the hook shape intervals; using the interval sample subsets as training sample data, an interval simplified stress mapping model is constructed and trained; the simplified stress mapping model is generated by integrating the interval simplified stress mapping models of multiple hook shape intervals.
[0058] Exemplarily, a quantitative analysis based on shape features is performed on the historical hook production records to obtain a corresponding set of historical shape coefficients, and then clustering analysis based on shape differences is realized to determine different shape categories, where the historical shape coefficients can be weighted values or arithmetic values of multiple shape feature indicators.
[0059] Specifically, clustering algorithms such as K-means or DBSCAN are used to perform clustering analysis on the set of historical shape coefficients, and several hook shape intervals are divided according to multiple clusters in the clustering results, and each hook shape interval corresponds to a similar type of hook.
[0060] Specifically, according to the set of hook shape intervals, hook shapes and corresponding stress distribution data are extracted from the historical simulation records, that is, the simulation records with hook shape parameters in a certain interval are classified into the corresponding interval sample subsets, and multiple interval sample subsets are output as the interval sample set.
[0061] Furthermore, for each interval sample subset, hook shape parameters (such as curvature radius, thickness) are extracted as inputs, and stress distribution characteristics (such as maximum stress, stress concentration area) are extracted as outputs; then, an interval simplified stress mapping model is independently constructed for each subset to reflect the specific stress response characteristics of a similar type of hook.
[0062] Through the above method steps, complex continuous and wide-range hooks are divided into multiple similar intervals, and an end-to-end simplified mapping model is constructed, which helps to improve the prediction accuracy and realize the rapid prediction from the hook plan to the stress distribution.
[0063] In some implementation manners, based on the historical hook production records, a set of historical shape coefficients is calculated and obtained, and clustering analysis is performed based on the set of historical shape coefficients to determine a set of hook shape intervals, including:
[0064] Collect and organize historical hook production records, extract shape feature data from the historical hook production records, and obtain a shape feature set; use statistical analysis methods to extract key shape features from the shape feature set, and perform weighted calculations on the key shape features to obtain the historical shape coefficient set; apply a clustering algorithm to perform clustering analysis on the historical shape coefficient set, and determine the hook shape interval set according to the clustering results.
[0065] Specifically, first, extract the geometric parameters of the hook from the historical hook production records, including the radius of curvature, thickness, cross-sectional shape, aspect ratio, etc., to obtain a shape feature set; then, analyze the relationship between the shape features and the stress distribution through the correlation coefficient, and screen out the key shape features, such as the radius of curvature and material thickness; next, define a shape coefficient calculation formula for synthesizing multiple geometric parameters into a single metric. Exemplarily, the shape coefficient is defined as the ratio of the radius of curvature to the material thickness (diameter); furthermore, calculate the shape coefficients corresponding to the historical hook production records according to the defined shape coefficient calculation formula to obtain the historical shape coefficient set; finally, select an appropriate clustering algorithm to divide the shape coefficient set into several clustering categories, and each category corresponds to a hook shape interval.
[0066] Through the above method, shape features can be extracted from the historical hook production records, and through weighted calculation and clustering analysis, a hook shape interval set can be generated, providing a scientific basis for the construction of the subsequent hook stress mapping model.
[0067] In some implementation manners, using the interval sample subset as the training sample data, construct and train an interval simplified stress mapping model, including:
[0068] Randomly select in the interval sample set to determine the first interval sample subset; use the sample simulation input data in the first interval sample subset as the training input, and the corresponding sample simulation stress data as the training output to construct and train the first interval simplified stress mapping model; based on the hook shape interval set, traverse the historical hook production records to extract the production records corresponding to the first hook shape interval and configure them as the first verification set, where the first hook shape interval is the interval where the first interval simplified stress mapping model is located; verify and enhance the training of the first interval simplified stress mapping model through the first verification set; traverse the interval sample set and construct the interval simplified stress mapping model corresponding to each interval sample subset respectively.
[0069] Specifically, the interval simplified stress mapping model includes a model based on linear regression or machine learning, which is respectively applicable to the segments with a linear relationship and the segments with a strong non-linear relationship between stress and characteristics.
[0070] Specifically, first, a subset is randomly selected from the given interval sample set for model training. This first interval sample subset contains the simulation input data and corresponding stress data of multiple samples. Then, using the sample simulation input data in the first interval sample subset as the training input and the corresponding sample simulation stress data as the training output, the first interval simplified stress mapping model is trained.
[0071] Specifically, based on the hook shape interval set, the historical hook production records are traversed, the production records corresponding to the first hook shape interval are extracted, and the extracted production records are configured as the first validation set. This first validation set is a true sample based on the historical hook production records and is used for model validation and enhanced training.
[0072] Furthermore, the first interval simplified stress mapping model is validated through the first validation set to evaluate the prediction accuracy of the model. If the model accuracy does not meet the expected goal, the model is enhanced trained according to the validation result and the first validation set, including adjusting model parameters, increasing training data, etc., so as to improve the performance of the first interval simplified stress mapping model.
[0073] Specifically, the entire interval sample set is traversed, and the above process is repeated for each interval sample subset. The interval simplified stress mapping models corresponding to each interval sample subset are respectively constructed, and each constructed model is trained and validated to ensure the accuracy and reliability of the model.
[0074] Through the above process, a simplified stress mapping model can be constructed for each hook shape interval. These models can quickly predict the stress distribution of the hook under specific shape and material conditions, thus helping to improve the efficiency of hook design and analysis, reduce the need for physical testing, and accelerate the product development cycle.
[0075] S500: Based on the optimization parameters and the simplified stress mapping model, the alternative hook plan set is iteratively optimized by combining an optimization algorithm to obtain the optimal plan as the target production plan.
[0076] Specifically, the simplified stress mapping model is defined as the cost function in the optimization, and the initial optimization direction and initial optimization step size of different parameters in the optimization are defined according to the optimization parameters. Among them, preferably, the cost function is the difference between the target demand constraint (such as the maximum stress not exceeding the allowable value) and the maximum stress in the stress distribution result.
[0077] Specifically, analyze the alternative hook plan set, extract the plan parameters as optimization variables, and generate an initial solution set according to the initial optimization direction and optimization step. Then, iteratively update the initial solution set. In each iteration, calculate the cost value of the current solution, and update the plan parameters according to the optimization algorithm to gradually approach the optimal solution. When the cost function value is less than the preset threshold (target demand constraint) or the number of iterations reaches the upper limit, stop the iteration, and output the solution with the minimum cost function value as the corresponding hook plan, which is used as the target production plan.
[0078] By defining a simplified stress mapping model as the cost function and combining the optimization algorithm to iteratively optimize the alternative hook plan set, the optimal plan that meets the target demand constraint can be quickly obtained, realizing the intelligent optimization of the hook production process.
[0079] In summary, the production intelligent control method for hook stress distribution optimization provided by the present invention has the following technical effects:
[0080] By obtaining hook task information and traversing and matching in the hook plan library based on this information, N adaptable hook plans are screened out to form an alternative hook plan set, where N is a positive integer not less than 2. Extract the target application environment according to the hook task information, and define the target demand constraint based on this target application environment to conduct a simulation analysis on the alternative hook plan set. Analyze the simulation analysis results, identify the stress concentration area, and define the plan optimization parameters based on the identification results. Combine the historical hook production records and historical simulation analysis records to construct a piecewise simplified stress mapping model based on machine learning. Use the optimization parameters and the simplified stress mapping model, and combine the optimization algorithm to iteratively optimize the alternative hook plan set, and finally obtain the optimal plan as the target production plan, so as to achieve the technical effects of reducing optimization costs, improving efficiency, and enhancing flexibility.
[0081] Embodiment 2
[0082] Figure 2 It is a schematic structural diagram of the production intelligent control system for hook stress distribution optimization of the present invention. For example, Figure 1 The flow schematic diagram of the production intelligent control method for hook stress distribution optimization in the present invention can be implemented through a structure as shown in Figure 2 shown.
[0083] Based on the same concept as the production intelligent control method for hook stress distribution optimization in the above embodiment, the production intelligent control system for hook stress distribution optimization provided by the present invention further includes:
[0084] The task information acquisition module 11 is configured to acquire the hook task information, traverse and match in the hook plan library based on the hook task information, acquire N adapted hook plans, and output them as an alternative hook plan set, where N is a positive integer greater than or equal to 2.
[0085] The requirement constraint definition module 12 is configured to extract the target application environment according to the hook task information, define the target requirement constraint according to the target application environment, and perform a simulation analysis on the alternative hook plan set.
[0086] The area recognition module 13 is configured to analyze the simulation analysis result to identify the stress concentration area, and define the plan optimization parameter according to the recognition result.
[0087] The simplified mapping module 14 is configured to combine the historical hook production record and the historical simulation analysis record to construct a simplified stress mapping model, where the construction of the simplified stress mapping model is a piecewise model based on machine learning.
[0088] The iterative optimization module 15 is configured to perform iterative optimization on the alternative hook plan set based on the optimization parameter and the simplified stress mapping model, in combination with an optimization algorithm, to acquire the optimal plan as the target production plan.
[0089] In some embodiments, the task information acquisition module 11 includes:
[0090] The hook task information acquisition and analysis unit is configured to acquire the hook task information, analyze the hook parameters of the hook task, and generate a hook parameter set.
[0091] The hook plan retrieval and sorting unit is configured to use the hook parameter set as a retrieval constraint, retrieve and match similar hook plans in the hook plan library, sort the retrieval results, and select the top N plans with the highest matching degree as the alternative hook plan set.
[0092] In some embodiments, the requirement constraint definition module 12 includes:
[0093] The target application environment recognition unit is configured to recognize the target application environment in the hook task information, and set the target requirement constraint according to the target application environment, where the target requirement constraint includes a force constraint and an environment constraint.
[0094] The simulation initialization unit is configured to perform simulation initialization in combination with the target requirement constraint, and analyze the stress distribution of the simulated hook in the target application environment, and output it as the simulation analysis result.
[0095] In some embodiments, the area recognition module 13 includes:
[0096] The simulation result quantitative analysis unit is used to quantitatively analyze the simulation analysis results and determine the stress concentration area.
[0097] The stress overrun vector determination unit is used to extract the stress value and stress direction based on the stress concentration area, and compare them with a preset stress limit baseline to determine the stress overrun vector.
[0098] The pre-plan optimization parameter definition unit is used to define the stress optimization direction and stress optimization step based on the stress overrun vector, and output the stress optimization direction and stress optimization step as the pre-plan optimization parameters.
[0099] In some embodiments, the simplified mapping module 14 includes:
[0100] The historical shape coefficient set calculation unit is used to calculate and obtain the historical shape coefficient set based on the historical hook production records, and perform cluster analysis based on the historical shape coefficient set to determine the hook shape interval set.
[0101] The interval sample extraction unit is used to extract samples by interacting with historical simulation records based on the hook shape interval set to generate an interval sample set, where the interval sample set includes interval sample subsets corresponding to the hook shape intervals.
[0102] The interval simplified stress mapping model construction unit is used to construct and train an interval simplified stress mapping model with the interval sample subsets as training sample data.
[0103] The simplified stress mapping model integration unit is used to integrate the interval simplified stress mapping models of multiple hook shape intervals to generate the simplified stress mapping model.
[0104] In some implementation manners, the historical shape coefficient set calculation unit in the simplified mapping module 14 includes:
[0105] The historical hook production record sorting unit is used to collect and sort the historical hook production records, and extract shape feature data from the historical hook production records to obtain a shape feature set.
[0106] The key shape feature extraction unit is used to extract key shape features from the shape feature set using statistical analysis methods and perform weighted calculation on the key shape features to obtain the historical shape coefficient set.
[0107] The cluster analysis determination unit is used to perform cluster analysis on the historical shape coefficient set using a clustering algorithm, and determine the hook shape interval set according to the clustering result.
[0108] In some implementation manners, the interval simplified stress mapping model construction unit in the simplified mapping module 14 includes:
[0109] An interval sample random selection unit for randomly selecting in the interval sample set to determine a first interval sample subset.
[0110] A first interval simplified stress mapping model construction and training unit for constructing and training a first interval simplified stress mapping model with the sample simulation input data in the first interval sample subset as the training input and the corresponding sample simulation stress data as the training output.
[0111] A first verification set configuration unit for traversing the historical hook production records based on the hook shape interval set to extract the production records corresponding to the first hook shape interval and configuring them as the first verification set, where the first hook shape interval is the interval where the first interval simplified stress mapping model is located.
[0112] A model verification and enhanced training unit for verifying and enhancing the training of the first interval simplified stress mapping model through the first verification set.
[0113] An interval simplified stress mapping model construction traversal unit for traversing the interval sample set and respectively constructing the interval simplified stress mapping models corresponding to each interval sample subset.
[0114] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the foregoing Embodiment 1 are equally applicable to the production intelligent control system for hook stress distribution optimization described in Embodiment 2. For the sake of brevity of the specification, no further elaboration will be made here.
[0115] It should be understood that the disclosed embodiments of the present invention and the above descriptions enable those skilled in the art to implement the present invention using the present invention. At the same time, the present invention is not limited to the above-mentioned part of the embodiments. It should be understood that those of ordinary skill in the art can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention and should all be included in the protection scope of the present invention.
Claims
1. A production intelligent control method for optimizing hook stress distribution, characterized in that: The method comprises: Obtain hook task information, and perform traversal matching in a hook plan library based on the hook task information to obtain N suitable hook plans, and output them as a candidate hook plan set, where N is a positive integer greater than or equal to 2; Extracting a target application environment according to the hook task information, defining a target demand constraint according to the target application environment, and performing simulation analysis on the candidate hook plan set; Analyze the simulation results to identify stress concentration areas, and define the optimization parameters of the plan based on the identification results; Combining historical hook production records and historical simulation analysis records, a simplified stress mapping model is constructed, wherein the simplified stress mapping model is a segmented model based on machine learning; Based on the optimization parameters and the simplified stress mapping model, the alternative hook plan set is iteratively optimized in combination with an optimization algorithm to obtain the optimal plan as the target production plan.
2. The production intelligent control method for optimizing hook stress distribution according to claim 1, characterized in that: Obtain hook task information, and perform traversal matching in the hook plan library based on the hook task information to obtain N suitable hook plans, and output them as a set of candidate hook plans, including: Acquire the hook task information, analyze the hook parameters of the hook task, and generate a hook parameter set; Using the hook parameter set as a search constraint, search for similar hook plans in the hook plan library, sort the search results, and select the top N plans with the highest matching degree as the candidate hook plan set.
3. The production intelligent control method for optimizing hook stress distribution according to claim 2, characterized in that: Extracting a target application environment according to the hook task information, defining a target demand constraint according to the target application environment, and performing simulation analysis on the candidate hook plan set, including: Identify the target application environment in the hook task information, and set the target demand constraint according to the target application environment, wherein the target demand constraint includes a force constraint and an environment constraint; The simulation is initialized in combination with the target demand constraints, and the stress distribution of the simulated hook in the target application environment is analyzed, and the output is the simulation analysis result.
4. The production intelligent control method for optimizing hook stress distribution according to claim 3, characterized in that: Analyze the simulation results to identify stress concentration areas and define the optimization parameters of the plan based on the identification results, including: Performing quantitative analysis on the simulation analysis results to determine stress concentration areas; Based on the stress concentration area, extract the stress value and stress direction, and compare them with the preset stress limit baseline to determine the stress excess vector; According to the stress excess vector, a stress optimization direction and a stress optimization step length are defined, and the stress optimization direction and the stress optimization step length are output as optimization parameters of the plan.
5. The production intelligent control method for optimizing hook stress distribution according to claim 4, combining historical hook production records with historical simulation analysis records to construct a simplified stress mapping model, wherein: The simplified stress mapping model is constructed as a segmented model based on machine learning, including: Based on the historical hook production records, a historical shape coefficient set is calculated and obtained, and a cluster analysis is performed based on the historical shape coefficient set to determine a hook shape interval set; Based on the hook shape interval set, the interactive historical simulation record performs sample extraction to generate an interval sample set, wherein the interval sample set includes an interval sample subset corresponding to the hook shape interval; Using the interval sample subset as training sample data, an interval simplified stress mapping model is constructed and trained; The simplified stress mapping model is generated by integrating the interval simplified stress mapping models of a plurality of hook shape intervals.
6. The production intelligent control method for optimizing hook stress distribution according to claim 5, characterized in that: Based on the historical hook production records, a historical shape coefficient set is calculated and obtained, and cluster analysis is performed based on the historical shape coefficient set to determine a hook shape interval set, including: Collecting and arranging historical hook production records, and extracting shape feature data from the historical hook production records to obtain a shape feature set; Extracting key shape features from the shape feature set using a statistical analysis method, and performing weighted calculation on the key shape features to obtain the historical shape coefficient set; A clustering algorithm is applied to perform cluster analysis on the historical shape coefficient set, and the hook shape interval set is determined according to the clustering result.
7. The production intelligent control method for optimizing hook stress distribution according to claim 6, characterized in that: Using the interval sample subset as training sample data, an interval simplified stress mapping model is constructed and trained, including: Randomly select from the interval sample set to determine a first interval sample subset; Using the sample simulation input data in the first interval sample subset as training input and the corresponding sample simulation stress data as training output, constructing and training a first interval simplified stress mapping model; Based on the hook shape interval set, traverse the historical hook production records to extract the production records corresponding to the first hook shape interval, and configure them as a first verification set, wherein the first hook shape interval is the interval where the simplified stress mapping model of the first interval is located; Performing verification and enhanced training of the first interval simplified stress mapping model through the first verification set; The interval sample set is traversed, and the interval simplified stress mapping model corresponding to each interval sample subset is constructed respectively.
8. A production intelligent control system for optimizing hook stress distribution, characterized in that: The system is used to execute the production intelligent control method for optimizing hook stress distribution according to any one of claims 1 to 7, and the system comprises: A task information acquisition module is used to acquire hook task information, and perform traversal matching in a hook plan library based on the hook task information to acquire N suitable hook plans, and output them as a candidate hook plan set, where N is a positive integer greater than or equal to 2; A demand constraint definition module, used for extracting a target application environment according to the hook task information, defining a target demand constraint according to the target application environment, and performing simulation analysis on the candidate hook plan set; The region identification module is used to analyze the simulation analysis results to identify the stress concentration area and define the optimization parameters of the plan based on the identification results; A simplified mapping module, used to combine historical hook production records and historical simulation analysis records to construct a simplified stress mapping model, wherein the simplified stress mapping model is a segmented model based on machine learning; An iterative optimization module is used to iteratively optimize the set of alternative hook plans based on the optimization parameters and the simplified stress mapping model in combination with an optimization algorithm to obtain an optimal plan as a target production plan.