Winding process optimization method and system for hose
By analyzing and deciding the performance and material characteristics of the hose, building a chain of winding process and optimizing the winding process, the problem of low winding accuracy and adaptability in the existing technology is solved, and the production quality of hose is improved.
Patent Information
- Application Number
- CN202411577719.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-07
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-11-07
AI Technical Summary
The existing hose wrapping process does not take into account the hose's own characteristics, resulting in low winding accuracy and adaptability, which affects production quality.
By collecting the performance characteristics parameters and material characteristics parameters of the hose, perform performance enhancement analysis of winding process and multi-character decision analysis of winding layer, build a winding process optimization chain, identify associated equipment, find optimization solutions, and improve the accuracy of winding process and Fitness.
It improves the accuracy and adaptability of the hose wrapping process and improves the production quality of the hose.
Smart Images

Figure CN119066897A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a winding process optimization method and system for a hose. Background Art
[0002] Hoses are important components in modern industry. They are corrosion-resistant, heat-resistant, light-weight and flexible. They are widely used in aviation, chemical, electric power, wood, medicine, food and transportation industries. The winding process of hoses is an important part of the hose manufacturing process. By designing the winding rules according to the stress conditions of the product, the strength of the fiber is brought into play, the mechanical properties of the hose are improved, and the hose can show better stability and durability when subjected to external forces such as pressure and stretching.
[0003] However, the current winding process does not take the characteristics of the hose itself into consideration, which reduces the accuracy and adaptability of the hose winding process, thereby affecting the production quality of the hose. Summary of the invention
[0004] The present application provides a winding process optimization method and system for a hose, which is used to solve the technical problem in the prior art that the winding process has low accuracy and adaptability, affecting production quality, due to failure to consider the hose's own characteristics.
[0005] According to a first aspect of the present application, a method for optimizing a winding process for a hose is provided, the method comprising: collecting performance characteristic parameters of a first hose to be wound to obtain first hose performance characteristic data; performing winding process performance enhancement analysis on the first hose to be wound based on the first hose performance characteristic data to determine first winding enhancement performance characteristic data; loading material characteristic parameters and structural characteristic parameters of the first hose to be wound to obtain first hose body characteristic data; performing winding layer multi-feature decision analysis on the first hose to be wound based on the first hose body characteristic data and the first winding enhancement performance characteristic data to determine a first hose winding layer decision plan; identifying associated equipment according to hose winding process information to obtain a hose winding process associated equipment set, and constructing a hose winding process optimization chain based on the hose winding process associated equipment set, wherein the hose winding process optimization chain includes multiple hose winding process optimization nodes; based on a winding process search constraint, performing winding process search and optimization on the first hose to be wound according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain to obtain a first hose winding process optimization plan.
[0006] According to a second aspect of the present application, a winding process optimization system for a hose is provided, the system comprising: a performance characteristic parameter acquisition module, the performance characteristic parameter acquisition module is used to collect performance characteristic parameters of a first hose to be wound and obtain first hose performance characteristic data; a performance enhancement analysis module, the performance enhancement analysis module is used to perform winding process performance enhancement analysis on the first hose to be wound based on the first hose performance characteristic data and determine first winding enhancement performance characteristic data; a hose body characteristic data acquisition module, the hose body characteristic data acquisition module is used to load material characteristic parameters and structural characteristic parameters of the first hose to be wound and obtain first hose body characteristic data; a winding layer multi-feature decision analysis module, the winding layer multi-feature decision analysis module is used to perform winding process performance enhancement analysis on the first hose to be wound based on the first hose body characteristic data and the first winding enhancement performance characteristic data. A hose winding process optimization chain construction module is used to identify associated equipment according to the hose winding process information, obtain a hose winding process associated equipment set, and construct a hose winding process optimization chain based on the hose winding process associated equipment set, wherein the hose winding process optimization chain includes multiple hose winding process optimization nodes; a winding process search and optimization module is used to search and optimize the winding process of the first hose to be wound based on the winding process search constraints, according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain, to obtain the first hose winding process optimization plan.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application provides a winding process optimization method for a hose, which relates to the field of data processing technology. Through the winding process performance enhancement analysis, the first winding enhancement performance characteristic data is determined, and a winding layer multi-feature decision analysis is performed to determine the first hose winding layer decision plan. The related equipment is identified according to the hose winding process information, and a hose winding process optimization chain is constructed. The winding process is searched and optimized for the first hose to be wound, and the first hose winding process optimization plan is obtained. The technical problem in the prior art that the accuracy and adaptability of the winding process are low due to the failure to consider the characteristics of the hose itself, which affects the production quality, is solved, and the technical effect of improving the accuracy and adaptability of the hose winding process and thus improving the production quality of the hose is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0009] Figure 1 A schematic flow chart of a winding process optimization method for a hose provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for determining first winding enhancement performance characteristic data in a winding process optimization method for a hose provided in an embodiment of the present application; Figure 3 A schematic diagram of a process flow of obtaining a first hose winding process optimization solution in a hose winding process optimization method provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a winding process optimization system for a hose provided in an embodiment of the present application.
[0010] Explanation of the reference numerals: performance characteristic parameter acquisition module 11, performance enhancement analysis module 12, hose body characteristic data acquisition module 13, winding layer multi-feature decision analysis module 14, hose winding process optimization chain construction module 15, winding process search and optimization module 16. DETAILED DESCRIPTION
[0011] The present application provides a winding process optimization method for a hose, which is used to solve the technical problem in the prior art that the winding process has low accuracy and adaptability, affecting production quality, due to failure to consider the hose's own characteristics.
[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.
[0014] Embodiment 1 like Figure 1 As shown, the present application provides a winding process optimization method for a hose, the method comprising: P10: Collecting performance characteristic parameters of the first hose to be wound, and obtaining performance characteristic data of the first hose; It should be understood that any sample of the hose to be wrapped is randomly selected as the first hose to be wrapped, and the performance characteristic parameters of the first hose to be wrapped, such as the material, strength, wear resistance, pressure resistance, etc. of the hose, are collected through product instructions, experimental test results or actual usage feedback, as the first hose performance characteristic data and as the basic data for performance analysis of the first hose to be wrapped.
[0015] P20: performing winding process performance enhancement analysis on the first hose to be wound based on the first hose performance characteristic data to determine first winding enhancement performance characteristic data; Further, such as Figure 2 As shown, step P30 of the embodiment of the present application also includes: P21: Loading the production performance requirement parameters of the first hose to be wound, and obtaining the first hose performance requirement characteristic data; P22: performing a performance deviation comparison between the first hose performance requirement characteristic data and the first hose performance characteristic data to obtain a plurality of performance deviation characteristic data; P23: Perform winding process enhancement prediction based on the plurality of performance deviation characteristic data to obtain a plurality of performance winding enhancement prediction coefficients; P24: Based on the performance winding enhancement prediction constraint, the plurality of performance deviation characteristic data are screened according to the plurality of performance winding enhancement prediction coefficients to obtain the first winding enhancement performance characteristic data satisfying the performance winding enhancement prediction constraint.
[0016] Optionally, the first hose performance characteristic data is used to perform winding process performance enhancement analysis on the first hose to be wound. Specifically, before the analysis, the production performance requirement parameters of the first hose to be wound are collected and loaded, including the pressure, temperature, degree of wear, etc. that the hose needs to withstand in the working environment, to obtain the first hose performance requirement characteristic data, and further, the first hose performance requirement characteristic data is compared and calculated with various performance data of the first hose performance characteristic data to obtain multiple performance deviation characteristic data, which can reflect the gap between the current hose performance and the expected performance, and provide a basis for subsequent performance enhancement prediction.
[0017] Furthermore, based on the multiple performance deviation characteristic data, sample winding process enhancement records are collected as training data, supervised training is performed in combination with machine learning principles, and winding process enhancement prediction is performed through the trained model to obtain multiple performance winding enhancement prediction coefficients, which can reflect the potential improvement effect of different winding processes on hose performance. According to the performance winding enhancement prediction constraints, the multiple performance winding enhancement prediction coefficients are screened, and the performance deviation characteristic data corresponding to the performance winding enhancement prediction coefficients that meet the performance winding enhancement prediction constraints are extracted, that is, the winding process solution that can meet the performance improvement requirements and meet the actual process conditions is extracted as the first winding enhancement performance characteristic data.
[0018] Furthermore, step P23 of the embodiment of the present application also includes: P23-1: traverse the plurality of performance deviation characteristic data and extract the first performance deviation characteristic data; P23-2: Performing feature identification according to the first performance deviation feature data to determine a first performance deviation feature index; P23-3: Perform winding process performance enhancement record collection based on the first performance deviation characteristic indicator to obtain a first sample performance deviation characteristic data set and a first sample performance winding process enhancement coefficient set; P23-4: Training a fully connected neural network based on the first sample performance deviation feature data set and the first sample performance winding process enhancement coefficient set to obtain a performance winding enhancement prediction deviation; P23-5: When the performance winding enhancement prediction deviation is less than the performance winding enhancement prediction deviation threshold for consecutive preset times, generating a first performance winding process enhancement prediction model; P23-6: Input the first performance deviation characteristic data into the first performance winding process enhancement prediction model to generate a first performance winding enhancement prediction coefficient, and add the first performance winding enhancement prediction coefficient to the multiple performance winding enhancement prediction coefficients.
[0019] Specifically, the plurality of performance deviation feature data are traversed, and any one of the performance deviation feature data is randomly extracted as the first performance deviation feature data, and the first performance deviation feature data is feature identified, and key performance deviation feature indicators are extracted as the first performance deviation feature indicators. Furthermore, for the first performance deviation feature indicator, winding process performance enhancement record collection is performed, including collecting performance deviation feature data of different winding processes and their corresponding performance improvement effects, and obtaining a first sample performance deviation feature data set and a first sample performance winding process enhancement coefficient set.
[0020] The first sample performance deviation feature data set and the first sample performance winding process enhancement coefficient set are used as training data, and the first sample performance winding process enhancement coefficient set is used as supervision data to train the fully connected neural network, and the deviation between the output data of the neural network and the supervision data is calculated to obtain the performance winding enhancement prediction deviation, which represents the gap between the prediction result and the actual result. Iterative training is continuously performed until the obtained performance winding enhancement prediction deviation is continuously less than the performance winding enhancement prediction deviation threshold within a preset number of times, then the training is stopped to obtain the first performance winding process enhancement prediction model, and the performance winding enhancement prediction deviation threshold can be set by professionals based on industry experience.
[0021] Furthermore, the first performance deviation characteristic data is input into the first performance winding process enhancement prediction model to predict the process enhancement degree, generate a first performance winding enhancement prediction coefficient, and add the first performance winding enhancement prediction coefficient to the multiple performance winding enhancement prediction coefficients.
[0022] P30: Loading material characteristic parameters and structural characteristic parameters of the first hose to be wound, and obtaining characteristic data of the first hose body; Exemplarily, the material characteristic parameters and structural characteristic parameters of the first hose to be wound are obtained. The material characteristic parameters mainly include the material, composition, physical properties, chemical properties, etc. of the hose, which can reflect the strength, wear resistance, heat resistance and other key performances of the hose. The structural characteristic parameters include structural information such as the shape, size, number of layers, and weaving method of the hose. For example, the inner diameter, outer diameter, wall thickness, weaving angle and other parameters of the hose will affect its performance. The material characteristic parameters and structural characteristic parameters are used together as the first hose body characteristic data.
[0023] P40: performing a winding layer multi-feature decision analysis on the first hose to be wound based on the first hose body feature data and the first winding enhancement performance feature data, and determining a first hose winding layer decision plan; Furthermore, step P40 of the embodiment of the present application also includes: P41: Based on big data, multiple winding layer multi-feature decision record groups are loaded, wherein each winding layer multi-feature decision record group includes sample hose body feature data, sample winding enhancement performance feature data and sample hose winding layer decision scheme; P42: Performing data cleaning on the plurality of winding layer multi-feature decision record groups based on a multi-dimensional preset data cleaning constraint to obtain a winding layer multi-feature decision record set; P43: Based on the knowledge graph, data fusion is performed on the entanglement layer multi-feature decision record set to construct an entanglement layer multi-feature decision model; P44: Input the first hose body characteristic data and the first winding enhancement performance characteristic data into the winding layer multi-characteristic decision model to generate the first hose winding layer decision plan.
[0024] Optionally, the first hose body characteristic data and the first winding enhancement performance characteristic data are used to perform winding layer multi-feature decision analysis on the first hose to be wound to determine the best first hose winding layer decision plan. Specifically, based on big data, multiple winding layer multi-feature decision record groups are collected, and each winding layer multi-feature decision record group includes sample hose body characteristic data, sample winding enhancement performance characteristic data and sample hose winding layer decision plan.
[0025] Furthermore, multi-dimensional preset data cleaning constraints are set, which may include data range, format, consistency, etc., and the plurality of winding layer multi-feature decision record groups are cleaned based on the multi-dimensional preset data cleaning constraints to remove noise, outliers and duplicates in the data, and obtain a winding layer multi-feature decision record set. Furthermore, the winding layer multi-feature decision record set is data fused based on a knowledge graph, and the knowledge graph can integrate data from different sources and different formats, and mine the associations and rules between data. Through the fusion of the knowledge graph, the feature data of multiple dimensions are associated to form a winding layer multi-feature decision model, and the first hose body feature data and the first winding enhancement performance feature data are input into the winding layer multi-feature decision model to perform feature decision and obtain the first hose winding layer decision plan.
[0026] P50: Identify associated equipment according to the hose winding process information, obtain a hose winding process associated equipment set, and construct a hose winding process optimization chain based on the hose winding process associated equipment set, wherein the hose winding process optimization chain includes multiple hose winding process optimization nodes; It should be understood that the hose winding process information is obtained, including the process links, equipment layout, etc. of the winding process, and then the related equipment is identified according to the hose winding process information, the equipment information of each process link is obtained, and the hose winding process related equipment set is obtained. Then, based on the hose winding process related equipment set and combined with the connection relationship between the equipment, a hose winding process optimization chain is constructed, and the hose winding process optimization chain includes multiple hose winding process optimization nodes.
[0027] P60: Based on the winding process search constraints, the winding process of the first hose to be wound is searched and optimized according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain to obtain the first hose winding process optimization plan.
[0028] Specifically, based on the winding process search constraints, including the value range of process parameters, production efficiency requirements, cost constraints, etc., the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain perform winding process search and optimization for the first hose to be wound, and obtain the first hose winding process optimization plan by traversing different process parameter combinations and node control plans.
[0029] Further, such as Figure 3 As shown, step P60 of the embodiment of the present application also includes: P61: Based on the first hose winding layer decision plan, the node control feature analysis of the hose winding process optimization chain is performed to construct a multi-dimensional node control feature space; P62: traverse the multi-dimensional node control feature space to randomly select values, and obtain a first hose winding node control scheme; P63: performing control quality prediction and evaluation on the first hose winding node control scheme based on the first winding enhancement performance characteristic data, the first hose body characteristic data and the first hose winding layer decision scheme to obtain a first control quality prediction and evaluation coefficient; P64: taking the first hose winding node control scheme as the current optimal node control scheme, and taking the first control quality prediction evaluation coefficient as the current optimal control quality prediction evaluation coefficient; P65: Based on the current optimal control quality prediction evaluation coefficient, the current optimal node control scheme is searched and optimized according to the multi-dimensional node control feature space to generate an optimal hose winding node control scheme that meets the winding process search constraints; P66: Integrate data based on the first hose winding layer decision plan and the optimal hose winding node control plan to generate the first hose winding process optimization plan.
[0030] In a possible embodiment of the present application, the node control feature analysis of the hose winding process optimization chain is performed in the first hose winding layer decision plan to obtain the control features of each node in the optimization chain, and the corresponding control scheme is extracted according to the control features of each node to construct a multi-dimensional node control feature space.
[0031] Furthermore, the multidimensional node control feature space is traversed, and a first hose winding node control scheme is randomly selected to obtain. Based on the first winding enhancement performance characteristic data, the first hose body characteristic data and the first hose winding layer decision scheme, a control quality prediction and evaluation of the first hose winding node control scheme is performed through a winding simulation test to obtain a first control quality prediction evaluation coefficient, that is, a quantitative coefficient of the winding control effect of the first hose winding node control scheme.
[0032] Furthermore, the first hose winding node control scheme is taken as the current optimal node control scheme, that is, the temporary optimal scheme, and the first control quality prediction evaluation coefficient is taken as the current optimal control quality prediction evaluation coefficient, that is, the temporary optimal coefficient. Furthermore, the second hose winding node control scheme is randomly extracted in the multi-dimensional node control feature space, and the control quality prediction evaluation is performed according to the second hose winding node control scheme to obtain the second control quality prediction evaluation coefficient, and the second control quality prediction evaluation coefficient is compared with the current optimal control quality prediction evaluation coefficient, and the one with the larger value is taken as the optimal control quality prediction evaluation coefficient, and the corresponding hose winding node control scheme is taken as the optimal node control scheme. In this way, iterative optimization is continuously performed until the number of iterations meets the winding process search constraint, that is, the search optimization number threshold, and the hose winding node control scheme obtained for the last time is taken as the optimal hose winding node control scheme.
[0033] Furthermore, the first hose winding layer decision scheme and the optimal hose winding node control scheme are data integrated to generate a complete first hose winding process optimization scheme. The first hose winding process optimization scheme integrates the optimization results of multiple dimensions and can maximize the efficiency and quality of the hose winding process.
[0034] Furthermore, step P61 of the embodiment of the present application also includes: P61-1: traverse the hose winding process optimization chain and extract the first hose winding process optimization node; P61-2: Based on the first hose winding process optimization node, node control record backtracking is performed to obtain multiple groups of first node control records, wherein each group of first node control records includes a historical hose winding layer decision plan and a historical first node control plan; P61-3: performing correlation analysis on the first hose winding layer decision scheme and each historical hose winding layer decision scheme in the plurality of groups of first node control records to obtain a plurality of winding layer decision correlation coefficients; P61-4: Based on the winding layer decision association constraint, each historical first node control scheme in the plurality of groups of first node control records is screened according to the plurality of winding layer decision association coefficients, and a first node association control scheme source that satisfies the winding layer decision association constraint is constructed; P61-5: Construct a multi-dimensional control domain based on the first node association control scheme source, generate a first node control feature space, and add the first node control feature space to the multi-dimensional node control feature space.
[0035] Specifically, according to the optimization target, each optimization node of the hose winding process optimization chain is traversed, the first hose winding process optimization node is extracted, and then the node control record is backtracked based on the first hose winding process optimization node, and the control records related to the node are queried to obtain multiple groups of first node control records, wherein each group of first node control records includes a historical hose winding layer decision plan and a historical first node control plan.
[0036] Further, the first hose winding layer decision scheme is subjected to correlation analysis with each historical hose winding layer decision scheme in the plurality of groups of first node control records, the similarity and difference between the current decision scheme and the historical scheme are quantified, and a plurality of winding layer decision correlation coefficients are obtained. Further, according to the preset winding layer decision correlation constraint, each historical first node control scheme in the plurality of groups of first node control records corresponding to the plurality of winding layer decision correlation coefficients is screened, and the historical control scheme with a high correlation with the current decision scheme and meeting the constraint condition is extracted as the first node associated control scheme source that meets the winding layer decision correlation constraint.
[0037] Furthermore, a multi-dimensional control domain is constructed based on the first node associated control scheme source as basic data to generate a first node control feature space, and control feature spaces of other process optimization nodes are constructed in the same way to form the multi-dimensional node control feature space.
[0038] Furthermore, step P63 of the embodiment of the present application also includes: P63-1: Modeling based on the first hose body characteristic data to obtain a first hose model; P63-2: Fitting and winding the first hose model based on the first hose winding node control scheme to obtain first fitting hose enhancement performance data and first fitting hose winding layer data; P63-3: Based on the first winding enhancement performance characteristic data, a performance enhancement evaluation is performed on the first fitting hose enhancement performance data to obtain a first control performance enhancement evaluation coefficient; P63-4: Based on the first hose winding layer decision scheme, perform winding layer quality evaluation on the first fitting hose winding layer data to obtain a first control winding layer quality evaluation coefficient; P63-5: Weighting the first control performance enhancement evaluation coefficient and the first control winding layer quality evaluation coefficient based on the control quality prediction evaluation weight rule to generate the first control quality prediction evaluation coefficient.
[0039] It should be understood that the first hose body characteristic data is used in combination with three-dimensional simulation software for modeling to obtain the first hose model. Furthermore, the first hose model is fitted and wound with reference to the first hose winding node control scheme, that is, a winding simulation is performed, and after the winding is completed, the first fitting hose enhancement performance data is obtained through a simulated performance test, and the first fitting hose winding layer data is collected, including the winding layer thickness, uniformity, density, integrity, etc., which can be used as basic data for subsequent winding layer quality evaluation.
[0040] Furthermore, a performance enhancement evaluation is performed on the first fitting hose enhancement performance data based on the first winding enhancement performance characteristic data, by comparing the expected enhancement performance characteristics with the enhanced performance data obtained by simulation, calculating the performance enhancement difference, and setting the enhancement coefficient according to the difference, to obtain a first control performance enhancement evaluation coefficient.
[0041] Furthermore, based on the first hose winding layer decision scheme, the first fitting hose winding layer data is evaluated for winding layer quality. By comparing the expected winding layer quality in the decision scheme and the simulated winding layer data, the difference between each winding layer data is calculated, such as the expected winding layer thickness and the simulated winding layer thickness. The differences are weighted according to the differences between each winding layer data, and a corresponding quality evaluation coefficient is set as the first control winding layer quality evaluation coefficient.
[0042] Furthermore, according to production requirements, a control quality prediction evaluation weight rule is preset, that is, weights are assigned to the two optimization directions of performance enhancement and winding layer quality, and the first control performance enhancement evaluation coefficient and the first control winding layer quality evaluation coefficient are weighted averaged according to the assigned weights to obtain the first control quality prediction evaluation coefficient, which can reflect the control quality of the first hose winding node control scheme.
[0043] In summary, the embodiments of the present application have at least the following technical effects: The present application determines the first winding enhancement performance characteristic data through winding process performance enhancement analysis, performs winding layer multi-feature decision analysis, determines the first hose winding layer decision plan, identifies related equipment based on the hose winding process information, constructs a hose winding process optimization chain, performs winding process search and optimization on the first hose to be wound, and obtains the first hose winding process optimization plan.
[0044] The technical effect of improving the accuracy and adaptability of the hose winding process and thus improving the production quality of the hose is achieved.
[0045] Embodiment 2 Based on the same inventive concept as the winding process optimization method for a hose in the aforementioned embodiment, Figure 4 As shown, the present application provides a winding process optimization system for a hose, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: A performance characteristic parameter acquisition module 11, wherein the performance characteristic parameter acquisition module 11 is used to collect performance characteristic parameters of the first hose to be wound and obtain performance characteristic data of the first hose; A performance enhancement analysis module 12, the performance enhancement analysis module 12 is used to perform winding process performance enhancement analysis on the first hose to be wound based on the first hose performance characteristic data, and determine first winding enhancement performance characteristic data; A hose body characteristic data acquisition module 13, the hose body characteristic data acquisition module 13 is used to load the material characteristic parameters and structural characteristic parameters of the first hose to be wound, and obtain the first hose body characteristic data; A winding layer multi-feature decision analysis module 14, the winding layer multi-feature decision analysis module 14 is used to perform a winding layer multi-feature decision analysis on the first hose to be wound based on the first hose body feature data and the first winding enhancement performance feature data, and determine a first hose winding layer decision plan; A hose winding process optimization chain construction module 15, the hose winding process optimization chain construction module 15 is used to identify associated equipment according to the hose winding process information, obtain a hose winding process associated equipment set, and construct a hose winding process optimization chain based on the hose winding process associated equipment set, wherein the hose winding process optimization chain includes a plurality of hose winding process optimization nodes; The winding process search and optimization module 16 is used to search and optimize the winding process of the first hose to be wound based on the winding process search constraints, according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain, to obtain the first hose winding process optimization plan.
[0046] Furthermore, the performance enhancement analysis module 12 is further configured to perform the following steps: Loading the production performance requirement parameters of the first hose to be wound to obtain the first hose performance requirement characteristic data; Performing a performance deviation comparison between the first hose performance requirement characteristic data and the first hose performance characteristic data to obtain a plurality of performance deviation characteristic data; Perform winding process enhancement prediction based on the plurality of performance deviation characteristic data to obtain a plurality of performance winding enhancement prediction coefficients; Based on the performance winding enhancement prediction constraint, the plurality of performance deviation characteristic data are screened according to the plurality of performance winding enhancement prediction coefficients to obtain the first winding enhancement performance characteristic data satisfying the performance winding enhancement prediction constraint.
[0047] Furthermore, the performance enhancement analysis module 12 is further configured to perform the following steps: Traversing the plurality of performance deviation characteristic data, and extracting first performance deviation characteristic data; Performing feature recognition according to the first performance deviation feature data to determine a first performance deviation feature indicator; Based on the first performance deviation characteristic index, winding process performance enhancement record collection is performed to obtain a first sample performance deviation characteristic data set and a first sample performance winding process enhancement coefficient set; Training a fully connected neural network based on the first sample performance deviation feature data set and the first sample performance winding process enhancement coefficient set to obtain a performance winding enhancement prediction deviation; When the performance winding enhancement prediction deviation is less than the performance winding enhancement prediction deviation threshold for a consecutive preset number of times, generating a first performance winding process enhancement prediction model; The first performance deviation characteristic data is input into the first performance winding process enhancement prediction model to generate a first performance winding enhancement prediction coefficient, and the first performance winding enhancement prediction coefficient is added to the plurality of performance winding enhancement prediction coefficients.
[0048] Furthermore, the winding layer multi-feature decision analysis module 14 is also used to perform the following steps: Based on the big data, multiple winding layer multi-feature decision record groups are loaded, wherein each winding layer multi-feature decision record group includes sample hose body feature data, sample winding enhancement performance feature data and sample hose winding layer decision scheme; Performing data cleaning on the plurality of winding layer multi-feature decision record groups based on a multi-dimensional preset data cleaning constraint to obtain a winding layer multi-feature decision record set; Based on the knowledge graph, data fusion is performed on the entanglement layer multi-feature decision record set to construct an entanglement layer multi-feature decision model; The first hose body characteristic data and the first winding enhancement performance characteristic data are input into the winding layer multi-characteristic decision model to generate the first hose winding layer decision plan.
[0049] Furthermore, the winding process search and optimization module 16 is also used to perform the following steps: Based on the first hose winding layer decision plan, node control feature analysis is performed on the hose winding process optimization chain to construct a multi-dimensional node control feature space; Traversing the multi-dimensional node control feature space to randomly select values, and obtaining a first hose winding node control scheme; Based on the first winding enhancement performance characteristic data, the first hose body characteristic data and the first hose winding layer decision plan, a control quality prediction evaluation is performed on the first hose winding node control plan to obtain a first control quality prediction evaluation coefficient; Taking the first hose winding node control scheme as the current optimal node control scheme, and taking the first control quality prediction evaluation coefficient as the current optimal control quality prediction evaluation coefficient; Based on the current optimal control quality prediction evaluation coefficient, the current optimal node control scheme is searched and optimized according to the multi-dimensional node control feature space to generate an optimal hose winding node control scheme that meets the winding process search constraints; Data integration is performed according to the first hose winding layer decision plan and the optimal hose winding node control plan to generate the first hose winding process optimization plan.
[0050] Furthermore, the winding process search and optimization module 16 is also used to perform the following steps: Traversing the hose winding process optimization chain to extract the first hose winding process optimization node; Based on the first hose winding process optimization node, node control record backtracking is performed to obtain multiple groups of first node control records, wherein each group of first node control records includes a historical hose winding layer decision plan and a historical first node control plan; Performing correlation analysis on the first hose winding layer decision scheme and each historical hose winding layer decision scheme in the plurality of groups of first node control records to obtain a plurality of winding layer decision correlation coefficients; Based on the winding layer decision association constraint, each historical first node control scheme in the plurality of groups of first node control records is screened according to the plurality of winding layer decision association coefficients, and a first node association control scheme source satisfying the winding layer decision association constraint is constructed; A multi-dimensional control domain is constructed based on the first node association control solution source to generate a first node control feature space, and the first node control feature space is added to the multi-dimensional node control feature space.
[0051] Furthermore, the winding process search and optimization module 16 is also used to perform the following steps: Modeling is performed based on the first hose body characteristic data to obtain a first hose model; Perform fitting winding on the first hose model based on the first hose winding node control scheme to obtain first fitting hose enhancement performance data and first fitting hose winding layer data; Performing a performance enhancement evaluation on the first fitting hose enhancement performance data based on the first winding enhancement performance characteristic data to obtain a first control performance enhancement evaluation coefficient; Based on the first hose winding layer decision scheme, the first fitting hose winding layer data is evaluated for winding layer quality to obtain a first control winding layer quality evaluation coefficient; The first control performance enhancement evaluation coefficient and the first control winding layer quality evaluation coefficient are weighted based on a control quality prediction evaluation weight rule to generate the first control quality prediction evaluation coefficient.
[0052] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0053] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
[0054] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.
Claims
1. A method for optimizing the winding process of a hose, characterized in that: The method comprises: Collecting performance characteristic parameters of the first hose to be wound to obtain performance characteristic data of the first hose; Perform winding process performance enhancement analysis on the first hose to be wound based on the first hose performance characteristic data to determine first winding enhancement performance characteristic data; Loading material characteristic parameters and structural characteristic parameters of the first hose to be wound to obtain first hose body characteristic data; Based on the first hose body characteristic data and the first winding enhancement performance characteristic data, a winding layer multi-characteristic decision analysis is performed on the first hose to be wound to determine a first hose winding layer decision plan; Identify associated equipment according to the hose winding process information to obtain a hose winding process associated equipment set, and construct a hose winding process optimization chain based on the hose winding process associated equipment set, wherein the hose winding process optimization chain includes multiple hose winding process optimization nodes; Based on the winding process search constraints, the winding process of the first hose to be wound is searched and optimized according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain to obtain the first hose winding process optimization plan.
2. The method according to claim 1, characterized in that Based on the first hose performance characteristic data, the first hose to be wound is subjected to a winding process performance enhancement analysis to determine first winding enhancement performance characteristic data, including: Loading the production performance requirement parameters of the first hose to be wound to obtain the first hose performance requirement characteristic data; Performing a performance deviation comparison between the first hose performance requirement characteristic data and the first hose performance characteristic data to obtain a plurality of performance deviation characteristic data; Perform winding process enhancement prediction based on the plurality of performance deviation characteristic data to obtain a plurality of performance winding enhancement prediction coefficients; Based on the performance winding enhancement prediction constraint, the plurality of performance deviation characteristic data are screened according to the plurality of performance winding enhancement prediction coefficients to obtain the first winding enhancement performance characteristic data satisfying the performance winding enhancement prediction constraint.
3. The method according to claim 2, characterized in that Based on the plurality of performance deviation characteristic data, winding process enhancement prediction is performed to obtain a plurality of performance winding enhancement prediction coefficients, including: Traversing the plurality of performance deviation characteristic data, and extracting first performance deviation characteristic data; Performing feature recognition according to the first performance deviation feature data to determine a first performance deviation feature indicator; Based on the first performance deviation characteristic index, winding process performance enhancement record collection is performed to obtain a first sample performance deviation characteristic data set and a first sample performance winding process enhancement coefficient set; Training a fully connected neural network based on the first sample performance deviation feature data set and the first sample performance winding process enhancement coefficient set to obtain a performance winding enhancement prediction deviation; When the performance winding enhancement prediction deviation is less than the performance winding enhancement prediction deviation threshold for a consecutive preset number of times, generating a first performance winding process enhancement prediction model; The first performance deviation characteristic data is input into the first performance winding process enhancement prediction model to generate a first performance winding enhancement prediction coefficient, and the first performance winding enhancement prediction coefficient is added to the plurality of performance winding enhancement prediction coefficients.
4. The method according to claim 1, characterized in that Based on the first hose body characteristic data and the first winding enhancement performance characteristic data, a winding layer multi-characteristic decision analysis is performed on the first hose to be wound to determine a first hose winding layer decision plan, including: Based on the big data, multiple winding layer multi-feature decision record groups are loaded, wherein each winding layer multi-feature decision record group includes sample hose body feature data, sample winding enhancement performance feature data and sample hose winding layer decision scheme; Performing data cleaning on the plurality of winding layer multi-feature decision record groups based on a multi-dimensional preset data cleaning constraint to obtain a winding layer multi-feature decision record set; Based on the knowledge graph, data fusion is performed on the entanglement layer multi-feature decision record set to construct an entanglement layer multi-feature decision model; The first hose body characteristic data and the first winding enhancement performance characteristic data are input into the winding layer multi-characteristic decision model to generate the first hose winding layer decision plan.
5. The method according to claim 1, characterized in that Based on the winding process search constraint, the winding process of the first hose to be wound is searched and optimized according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain to obtain the first hose winding process optimization plan, including: Based on the first hose winding layer decision plan, node control feature analysis is performed on the hose winding process optimization chain to construct a multi-dimensional node control feature space; Traversing the multi-dimensional node control feature space to randomly select values, and obtaining a first hose winding node control scheme; Based on the first winding enhancement performance characteristic data, the first hose body characteristic data and the first hose winding layer decision plan, a control quality prediction evaluation is performed on the first hose winding node control plan to obtain a first control quality prediction evaluation coefficient; Taking the first hose winding node control scheme as the current optimal node control scheme, and taking the first control quality prediction evaluation coefficient as the current optimal control quality prediction evaluation coefficient; Based on the current optimal control quality prediction evaluation coefficient, the current optimal node control scheme is searched and optimized according to the multi-dimensional node control feature space to generate an optimal hose winding node control scheme that meets the winding process search constraints; Data integration is performed according to the first hose winding layer decision plan and the optimal hose winding node control plan to generate the first hose winding process optimization plan.
6. The method according to claim 5, characterized in that Based on the first hose winding layer decision scheme, the node control feature of the hose winding process optimization chain is analyzed to construct a multi-dimensional node control feature space, including: Traversing the hose winding process optimization chain to extract the first hose winding process optimization node; Based on the first hose winding process optimization node, node control record backtracking is performed to obtain multiple groups of first node control records, wherein each group of first node control records includes a historical hose winding layer decision plan and a historical first node control plan; Performing correlation analysis on the first hose winding layer decision scheme and each historical hose winding layer decision scheme in the plurality of groups of first node control records to obtain a plurality of winding layer decision correlation coefficients; Based on the winding layer decision association constraint, each historical first node control scheme in the plurality of groups of first node control records is screened according to the plurality of winding layer decision association coefficients, and a first node association control scheme source satisfying the winding layer decision association constraint is constructed; A multi-dimensional control domain is constructed based on the first node association control solution source to generate a first node control feature space, and the first node control feature space is added to the multi-dimensional node control feature space.
7. The method according to claim 5, characterized in that Based on the first winding enhancement performance characteristic data, the first hose body characteristic data and the first hose winding layer decision plan, a control quality prediction evaluation is performed on the first hose winding node control plan to obtain a first control quality prediction evaluation coefficient, including: Modeling is performed based on the first hose body characteristic data to obtain a first hose model; Perform fitting winding on the first hose model based on the first hose winding node control scheme to obtain first fitting hose enhancement performance data and first fitting hose winding layer data; Performing a performance enhancement evaluation on the first fitting hose enhancement performance data based on the first winding enhancement performance characteristic data to obtain a first control performance enhancement evaluation coefficient; Based on the first hose winding layer decision scheme, the first fitting hose winding layer data is evaluated for winding layer quality to obtain a first control winding layer quality evaluation coefficient; The first control performance enhancement evaluation coefficient and the first control winding layer quality evaluation coefficient are weighted based on a control quality prediction evaluation weight rule to generate the first control quality prediction evaluation coefficient.
8. A winding process optimization system for a hose, characterized in that: The system comprises: A performance characteristic parameter acquisition module, the performance characteristic parameter acquisition module is used to collect performance characteristic parameters of the first hose to be wound, and obtain performance characteristic data of the first hose; A performance enhancement analysis module, the performance enhancement analysis module is used to perform winding process performance enhancement analysis on the first hose to be wound based on the first hose performance characteristic data, and determine first winding enhancement performance characteristic data; A hose body characteristic data acquisition module, the hose body characteristic data acquisition module is used to load the material characteristic parameters and structural characteristic parameters of the first hose to be wound, and obtain the first hose body characteristic data; A winding layer multi-feature decision analysis module, the winding layer multi-feature decision analysis module is used to perform a winding layer multi-feature decision analysis on the first hose to be wound based on the first hose body feature data and the first winding enhancement performance feature data, and determine a first hose winding layer decision plan; A hose winding process optimization chain construction module, the hose winding process optimization chain construction module is used to identify associated equipment according to hose winding process information, obtain a hose winding process associated equipment set, and construct a hose winding process optimization chain based on the hose winding process associated equipment set, wherein the hose winding process optimization chain includes a plurality of hose winding process optimization nodes; A winding process search and optimization module, wherein the winding process search and optimization module is used to search and optimize the winding process of the first hose to be wound based on the winding process search constraints, according to the first winding enhancement performance characteristic data, the first hose body characteristic data, the first hose winding layer decision plan and the hose winding process optimization chain, to obtain the first hose winding process optimization plan.
Citation Information
Patent Citations
Optimal design method for high-pressure rubber hose structure on the basis of finite element
CN108804837A
Treatment system for optimizing wear resistance of outer film of hose
CN118657957A
Cited By
Method, system and equipment for optimizing quality of insulating layer in high-density winding of multi-core cable
CN120124314A
Method, system and equipment for optimizing insulation layer quality in high-density winding of multi-core cables
CN120124314B
