CN116595889B - Processing method and system for thin rib uniform distribution structure based on PEEK material - Google Patents
Processing method and system for thin rib uniform distribution structure based on PEEK material Download PDFInfo
- Publication number
- CN116595889B CN116595889B CN202310664133.8A CN202310664133A CN116595889B CN 116595889 B CN116595889 B CN 116595889B CN 202310664133 A CN202310664133 A CN 202310664133A CN 116595889 B CN116595889 B CN 116595889B
- Authority
- CN
- China
- Prior art keywords
- processing
- uniform distribution
- distribution structure
- thin
- processing state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009827 uniform distribution Methods 0.000 title claims abstract description 105
- 239000000463 material Substances 0.000 title claims abstract description 27
- 239000004696 Poly ether ether ketone Substances 0.000 title claims abstract description 22
- JUPQTSLXMOCDHR-UHFFFAOYSA-N benzene-1,4-diol;bis(4-fluorophenyl)methanone Chemical compound OC1=CC=C(O)C=C1.C1=CC(F)=CC=C1C(=O)C1=CC=C(F)C=C1 JUPQTSLXMOCDHR-UHFFFAOYSA-N 0.000 title claims abstract description 22
- 229920002530 polyetherether ketone Polymers 0.000 title claims abstract description 22
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 252
- 238000000034 method Methods 0.000 claims abstract description 83
- 230000007547 defect Effects 0.000 claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims abstract description 37
- 238000005516 engineering process Methods 0.000 claims abstract description 33
- 238000001746 injection moulding Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000013461 design Methods 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims description 66
- 238000012549 training Methods 0.000 claims description 28
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000013441 quality evaluation Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 17
- 210000002435 tendon Anatomy 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000005457 optimization Methods 0.000 description 8
- 238000004140 cleaning Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000005094 computer simulation Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012067 mathematical method Methods 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 239000004697 Polyetherimide Substances 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 229920006351 engineering plastic Polymers 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 229920001601 polyetherimide Polymers 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a processing method and a system of a thin rib uniformly distributed structure based on PEEK materials, wherein the method comprises the following steps: constructing a processing technology design database of the thin rib uniform distribution structure; extracting characteristics of the processing state information to obtain preset processing state information; obtaining processing state information of the thin rib uniform distribution structure through a processing state analysis model of the thin rib uniform distribution structure; selecting and obtaining a processing technological scheme set of the thin rib uniformly distributed structure; obtaining optimal technological parameters based on an evolutionary algorithm; inputting the optimal technological parameters into an injection molding demolding defect prediction model of a thin rib uniform distribution structure, and predicting possible demolding defects in an injection molding processing state; and screening an optimal processing scheme according to the prediction result. According to the invention, the processing efficiency of the thin rib uniformly distributed structure of the PEEK material can be effectively improved; the occurrence of demoulding defects is avoided or reduced by optimizing the processing technological parameters, so that the rejection rate can be reduced, and the production cost is reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a processing method and a processing system of a thin rib uniform distribution structure based on PEEK materials.
Background
PEEK (polyetherimide) is a high-performance engineering plastic material, has the characteristics of excellent high temperature resistance, corrosion resistance, mechanical strength and the like, and is widely applied to the fields of aviation, automobiles, medical treatment and the like. In the actual production process, the PEEK material can be used to make a relatively complex structure, for example, parts including a plurality of rib structures that are led out and uniformly distributed, and the processing process of the thin rib uniform distribution structure based on the PEEK material currently has the following problems:
firstly, due to the complexity of a thin rib uniform distribution structure, a plurality of factors such as injection molding parameters, mold design and the like need to be comprehensively considered in the processing process, so that the processing difficulty and cost are increased; secondly, the demolding defect is one of the common problems in the injection molding process of PEEK materials, and if the problems cannot be found and solved in time, the problems of product quality reduction, cost increase and the like are caused; how to obtain the optimal processing scheme of the thin-type rib uniformly distributed structure, thereby solving the problems and becoming the problem to be solved urgently.
Disclosure of Invention
The invention provides a processing method and a processing system for a thin rib uniformly distributed structure based on PEEK materials, and therefore the problems pointed out in the background art are effectively solved.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a processing method of a thin rib uniformly distributed structure based on PEEK materials comprises the following steps:
constructing a processing technology design database of the thin rib uniform distribution structure;
acquiring processing state information of the thin rib uniformly distributed structure;
extracting characteristics of the processing state information to obtain preset processing state information;
inputting the preset processing state information into a processing state analysis model of the thin-type rib uniform distribution structure to obtain processing state information of the thin-type rib uniform distribution structure;
selecting and obtaining a processing process scheme set of the thin rib uniformly-distributed structure from a processing process scheme library of the thin rib uniformly-distributed structure based on the processing state information of the thin rib uniformly-distributed structure;
calculating process parameters in the processing process scheme set of the thin rib uniform distribution structure based on an evolutionary algorithm to obtain optimal process parameters;
inputting the optimal technological parameters into an injection molding and demolding defect prediction model of a thin rib uniform distribution structure, and predicting possible demolding defects in an injection molding processing state;
and screening an optimal processing scheme according to the prediction result.
Further, the steps of constructing a processing technology design database of the thin-type rib uniform distribution structure comprise:
determining a database construction range;
collecting various data in the processing process of the thin rib uniform distribution structure;
the collected various data are arranged and stored;
determining a database management system, and constructing a processing technology design database of the thin rib uniform distribution structure;
and designing a database query interface for a user to query and acquire related information of the thin rib uniform distribution structure processing technology according to the needs.
Further, extracting features of the processing state information to obtain preset processing state information, where the steps include:
preprocessing the acquired processing state information;
extracting a plurality of features representing processing state information from the preprocessed data;
integrating a plurality of features into a new feature vector, and reducing the dimension of the feature vector;
adjusting the feature vectors after dimension reduction to the same size range;
and integrating the adjusted feature vectors to form new feature vectors serving as preset processing state information.
Further, the step of establishing the processing state analysis model of the thin-type rib uniformly-distributed structure comprises the following steps:
collecting data in the processing process of the thin rib uniform distribution structure;
preprocessing the data, and extracting features capable of representing processing states from the preprocessed data;
screening and sorting the extracted features to obtain a first importance sorting result, and determining representative important features according to the first importance sorting result;
determining a model for semi-supervised learning according to the selected important features and the predicted targets, and selecting a collaborative training algorithm;
and performing model training by using historical data, and testing and verifying the model by adopting new data to obtain the processing state analysis model of the thin-type tendon uniform distribution structure.
Further, the step of establishing the processing state analysis model of the thin-type rib uniformly-distributed structure further comprises the following steps:
collecting historical quality evaluation data after the thin rib uniform distribution structure is processed, and obtaining a second importance ranking result according to the historical quality evaluation data;
and determining representative important features by combining the second importance ranking result on the basis of the first importance ranking result.
Further, obtaining a second importance ranking result according to the historical quality assessment data, including:
preprocessing the historical quality evaluation data, and extracting features capable of representing processing quality from the preprocessed historical evaluation data;
and performing feature screening and sorting on the historical quality evaluation data to obtain a second importance sorting result.
Further, determining a representative important feature based on the first importance ranking result in combination with the second importance ranking result includes:
combining the feature set with the top ranking in the first importance ranking result and the second importance ranking result to form an important feature pre-combination set;
the important features are selected in the pre-aggregate set of important features by setting a threshold or a set number.
Further, the step of establishing the injection molding demolding defect prediction model of the thin rib uniform distribution structure comprises the following steps:
collecting data related to injection molding and demolding defects of the thin rib uniformly-distributed structure;
preprocessing the data, and selecting characteristics related to demolding defect prediction from the preprocessed data;
dividing the data set into a training set and a testing set, and determining a prediction model;
training the prediction model by using a training set, and evaluating the trained prediction model by using a testing set;
and optimizing and adjusting the model according to the evaluation result.
Thin muscle equipartition structure system of processing based on PEEK material, the system includes:
the process design database construction module is used for realizing the construction of a thin rib uniform distribution structure processing process design database;
the processing state information acquisition module is used for acquiring processing state information of the thin rib uniformly distributed structure;
the feature extraction module is used for extracting features of the processing state information to obtain preset processing state information;
the processing state analysis module is used for inputting the preset processing state information into a processing state analysis model of the thin-type rib uniform distribution structure to obtain the processing state information of the thin-type rib uniform distribution structure;
the selection module is used for selecting and obtaining a processing technology scheme set of the thin rib uniform distribution structure from a processing technology scheme library of the thin rib uniform distribution structure based on the processing state information of the thin rib uniform distribution structure;
the calculation module is used for calculating the process parameters in the processing process scheme set of the thin-type rib uniform distribution structure based on an evolutionary algorithm to obtain optimal process parameters;
the injection molding and demolding defect prediction module is used for inputting the optimal technological parameters into an injection molding and demolding defect prediction model of the thin rib uniform distribution structure to predict possible demolding defects in an injection molding processing state;
and the screening module screens the optimal processing scheme according to the prediction result.
Further, the processing state analysis module includes:
the data collection unit is used for collecting data in the processing process of the thin rib uniform distribution structure;
a preprocessing unit for preprocessing the data;
the feature analysis unit is used for extracting features capable of representing the processing state from the preprocessed data, screening and sorting the extracted features to obtain a first importance sorting result, and determining representative important features according to the first importance sorting result;
the model selection unit is used for determining a model for semi-supervised learning according to the selected important features and the predicted targets and selecting a collaborative training algorithm;
and the machine learning training unit is used for performing model training by using historical data, and testing and verifying the model by adopting new data to obtain the thin tendon uniform distribution structure processing state analysis model.
By the technical scheme of the invention, the following technical effects can be realized:
according to the invention, the optimal technological parameters are calculated by utilizing an evolutionary algorithm through collecting and analyzing the processing state information, and possible demolding defects are predicted, so that an optimal processing scheme is screened out, and the processing quality can be effectively improved; the processing technology design database of the thin-type rib uniform structure is constructed, so that the rapid acquisition and processing of the processing state information are realized, and meanwhile, the processing technology scheme set of the thin-type rib uniform structure is selected and obtained in the processing technology scheme library, so that the processing efficiency can be effectively improved; the occurrence of demoulding defects is avoided or reduced by optimizing the processing technological parameters, so that the rejection rate can be reduced, and the production cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a flow chart of a processing method of a thin rib uniform distribution structure based on PEEK materials;
FIG. 2 is a flow chart of a process design database for constructing a thin rib uniform structure;
FIG. 3 is a flowchart of feature extraction of processing state information to obtain preset processing state information;
FIG. 4 is a step of establishing a processing state analysis model of the thin-type rib uniform distribution structure;
FIG. 5 is an optimization step of the process state analysis model establishment of the thin-type rib uniform distribution structure;
FIG. 6 is a flow chart for obtaining a second importance ranking result based on historical quality-assessment data;
FIG. 7 shows the steps of establishing an injection molding demolding defect prediction model of the thin rib uniform distribution structure.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
The processing method of the thin rib uniformly distributed structure based on the PEEK material is as shown in figure 1, and comprises the following steps:
s100: constructing a processing technology design database of the thin rib uniform distribution structure; all process schemes can be conveniently stored and managed, and the usability and reliability of data are improved;
s200: acquiring processing state information of the thin rib uniformly distributed structure; the thin rib uniform distribution structure is a special structure form, and each parameter needs to be accurately controlled in the processing process to meet the design requirement, so that in the processing method of the invention, the processing state information of the thin rib uniform distribution structure needs to be acquired and obtained so as to further perform process analysis and optimization.
The processing state information acquired by the thin rib uniformly distributed structure may include the following contents:
preparation work before processing, such as material selection, cutting, cleaning and the like; all links in the processing process, such as clamping, injection molding, cooling, demolding and the like of a mold; various parameters involved in the processing, such as injection molding temperature, pressure, speed, etc.; faults or anomalies that occur during processing, such as machine failure, material waste, product quality problems, etc. The manner of obtaining the processing state information can be diversified, for example, the processing state information can be collected through real-time monitoring of sensors, meters, cameras and the like; recording by manual inspection; recognition analysis by machine learning algorithms, etc.
S300: extracting characteristics of the processing state information to obtain preset processing state information; during processing of the thin rib uniform structure, the acquired processing state information may contain a great amount of data and details, wherein some information is more important for subsequent process analysis and optimization, and some information is relatively less important. Therefore, in this step, feature extraction needs to be performed on the acquired processing state information in order to obtain preset processing state information capable of reflecting the entire processing procedure.
Specifically, feature extraction refers to extracting some key features or attributes from original data, so as to describe the essential characteristics of the data; in the processing of the thin-type rib uniform distribution structure, feature extraction can be performed through various mathematical methods and algorithms, such as principal component analysis, wavelet transformation, entropy calculation and the like, and the original data can be converted into a more concise and easier-to-process feature vector or feature matrix through the methods, so that subsequent process analysis and optimization can be performed better, and the state and rule of the whole processing process can be understood and mastered better.
S400: inputting preset processing state information into a processing state analysis model of the thin-type rib uniform distribution structure to obtain processing state information of the thin-type rib uniform distribution structure; in the step, the preset processing state information obtained by previous extraction is required to be input into a pre-established processing state analysis model of the thin-type tendon uniform distribution structure, and model solution is carried out by using a computer simulation and mathematic method, so that more detailed and accurate processing state information is obtained; such information may include various parameter values and physical characteristics, such as temperature distribution, stress distribution, deformation state, quality index, and the like.
S500: selecting a processing technological scheme set of the thin rib uniformly distributed structure from a processing technological scheme library of the thin rib uniformly distributed structure based on the processing state information of the thin rib uniformly distributed structure; in the step, the processing technology is analyzed and optimized according to the processing state information of the thin-type rib uniformly distributed structure obtained before, so that a processing technology scheme set which meets the requirements best is selected from a processing technology scheme library; these sets of solutions may include different combinations of processing parameters, different injection mold designs, different processing equipment configurations, etc., in order to meet different processing and production requirements. In general, a plurality of factors, such as processing efficiency, product quality, cost control, environmental protection, etc., need to be considered in selecting a processing technology scheme set, so that the influence of each factor needs to be comprehensively considered, and an optimal processing technology scheme set needs to be selected, so that the processing efficiency and the product quality are ensured, and meanwhile, the cost and the environmental pollution are reduced. In summary, in this step, a library of process recipes is needed to obtain an optimal set of process recipes and to prepare them for subsequent calculations and analysis.
S600: calculating process parameters in a processing process scheme set of the thin rib uniformly distributed structure based on an evolutionary algorithm to obtain optimal process parameters;
the processing process of the thin rib uniform distribution structure involves a plurality of parameters and variables, such as injection molding temperature, pressure, speed and the like, and the parameters have important influences on processing efficiency and product quality. In this step, the set of previously obtained process recipes needs to be calculated and optimized based on an evolutionary algorithm in order to find the optimal combination of process parameters.
Specifically, the evolutionary algorithm is a calculation method based on the biological evolutionary principle, and the optimization target is maximized or minimized by continuously iterating and optimizing and simulating natural selection and genetic mechanism; in this step, an evolutionary algorithm is used to find the optimal combination of processing parameters, such as particle swarm algorithm, genetic algorithm, etc. Before the evolutionary algorithm is applied to calculation, firstly, an optimization target and constraint conditions are required to be determined so as to solve the problem better; for example, factors such as processing efficiency, product quality, cost control and the like can be taken as optimization targets, and corresponding constraint conditions are set, such as that the injection molding temperature cannot be too high, the pressure cannot be too low and the like.
After the previous work is completed, the technological parameters in the processing technological scheme set are calculated and optimized by utilizing an evolutionary algorithm, so that the optimal technological parameter combination is obtained, the processing process is better controlled, the production efficiency is improved, and the automation and the intellectualization of the processing process are realized.
S700: inputting the optimal technological parameters into an injection molding demolding defect prediction model of a thin rib uniform distribution structure, and predicting possible demolding defects in an injection molding processing state; in this step, the optimal process parameters obtained in step S600 are input into a model for predicting the injection molding and demolding defects of the thin rib uniform structure, and the model can be solved by using a computer simulation and mathematical method, so as to predict the possible demolding defect conditions in the injection molding and machining state, wherein the defects include but are not limited to flaws on the surface of the product, defects on the internal structure, and the like.
S800: and screening an optimal processing scheme according to the prediction result. In this step, the optimal processing scheme should be a comprehensive scheme capable of satisfying a plurality of factors such as processing efficiency, product quality, and cost control at the same time. Based on the factors, the processing scheme obtained before can be evaluated and screened, and the processing scheme which meets the requirements best is selected as a final scheme; if there are multiple candidates, then comparisons and trade-offs are required to find the optimal processing scheme.
In summary, the method and the device for processing the steel wire rope by the metal wire rope through the evolutionary algorithm calculate the optimal technological parameters by collecting and analyzing the processing state information, and predict the possible demolding defects, so that the optimal processing scheme is screened out, and the processing quality can be effectively improved; the processing technology design database of the thin-type rib uniform structure is constructed, so that the rapid acquisition and processing of the processing state information are realized, and meanwhile, the processing technology scheme set of the thin-type rib uniform structure is selected and obtained in the processing technology scheme library, so that the processing efficiency can be effectively improved; the occurrence of demoulding defects is avoided or reduced by optimizing the processing technological parameters, so that the rejection rate can be reduced, and the production cost is reduced.
As a preferred embodiment of the foregoing embodiment, the step of constructing a processing technology design database of the thin-type tendon uniform distribution structure, as shown in fig. 2, includes:
s110: determining a database construction range; in the step, determining the range and the content of a processing technology design database of the thin rib uniform distribution structure, wherein the range and the content comprise processing technology parameters, processing equipment information, processing material information and the like;
s120: collecting various data in the processing process of the thin rib uniform distribution structure; various data, such as temperature, pressure, speed and other parameters, in the processing process of the thin-type rib uniform distribution structure are collected through laboratory testing, production site observation and other modes;
s130: the collected various data are arranged and stored; specifically, the method comprises the steps of carrying out unified formatting according to a set standard and storing the unified formatting in a database;
s140: determining a database management system, and constructing a thin rib uniform distribution structure processing technology design database; in the step, a proper database management system, such as MySQL, oracle and the like, is required to be selected, a thin rib uniform structure processing technology design database is built, and data in the database is managed and maintained;
s150: and designing a database query interface for a user to query and acquire related information of the thin-type tendon uniform distribution structure processing technology according to the needs.
The processing technology design database of the thin-type rib uniform distribution structure is established through the steps, and the processing technology design database has the following advantages: through unified management and arrangement of the database, a large number of parameters, equipment information, material information and the like involved in the processing process of the thin rib uniform distribution structure can be collected, stored, searched and inquired rapidly, and the data management efficiency is improved; based on the established database, various parameters and state information in the processing process can be analyzed, so that an optimal processing scheme is searched; meanwhile, the data can be mined, and potential problems can be found and solved.
In the implementation process, feature extraction is performed on the processing state information to obtain preset processing state information, as shown in fig. 3, and specific steps include:
s310: preprocessing the acquired processing state information; the processing in the step comprises filtering, noise reduction, smoothing and the like;
s320: extracting a plurality of features representing processing state information from the preprocessed data; in the embodiment, according to the characteristics of the thin rib uniform distribution structure, parameters such as temperature, pressure, flow, speed, time and the like can be selected as characteristics;
s330: integrating the plurality of features into a new feature vector, and reducing the dimension of the feature vector; the method has the advantages that the characteristics are integrated into the new characteristic vector and the dimension is reduced, so that certain advantages are brought to the aspects of improving algorithm efficiency, removing redundant information, improving generalization capability, reducing storage space and the like on the premise of not losing information;
s340: the feature vectors after dimension reduction are adjusted to the same size range, so that subsequent processing is facilitated;
s350: and integrating the adjusted feature vectors to form new feature vectors serving as preset processing state information.
By the method, different feature extraction methods and feature screening methods can be selected according to the specific conditions of the thin rib uniform distribution structure under specific application scenes so as to obtain the most effective feature representation.
In step S400, the step of establishing the processing state analysis model of the thin-type rib uniform distribution structure, as shown in fig. 4, includes:
s410: collecting data in the processing process of the thin rib uniform distribution structure; in the step, data related to the processing process of the thin rib uniform distribution structure is required to be collected, and specifically, the data can comprise parameter setting, material properties, process parameters and the like in the processing process;
s420: preprocessing the data, and extracting features capable of representing the processing state from the preprocessed data; the method specifically comprises the steps of cleaning, converting and normalizing the original data, ensuring the quality and accuracy of the data, and aiming at cleaning the data, eliminating noise, filling missing values and the like; then, extracting features capable of representing the processing state from the preprocessed data, wherein the features can comprise statistical features, frequency domain features, time sequence features and the like, and selecting a proper feature extraction method according to specific situations;
s430: screening and sorting the extracted features to obtain a first importance sorting result, and determining representative important features according to the first importance sorting result;
s440: determining a model for semi-supervised learning according to the selected important features and the predicted targets, and selecting a collaborative training algorithm;
the co-training algorithm can effectively utilize unlabeled data in semi-supervised learning, and simultaneously improves performance through mutual cooperation of a plurality of classifiers; the data types in the invention comprise continuous data and discrete data, and a collaborative training algorithm based on a decision tree or a collaborative training algorithm based on a neural network and the like can be considered to be used; in addition, the algorithm performance can be further improved by adjusting algorithm parameters, increasing the sample size and the like.
S450: and (3) performing model training by using historical data, and testing and verifying the model by adopting new data to obtain the thin tendon uniform distribution structure processing state analysis model.
By the method, reliable data base, noise and redundancy of data are reduced, important features are identified, proper models and algorithms are selected, model performance is verified, and the advantages are conducive to establishing an efficient and accurate thin tendon uniform distribution structure processing state analysis model and improving processing quality control and prediction capability.
In order to obtain a better technical effect, the step of establishing the processing state analysis model of the thin-type tendon uniform distribution structure, as shown in fig. 5, further comprises:
a010: collecting historical quality evaluation data after the thin-type rib uniform distribution structure is processed, and obtaining a second importance sorting result according to the historical quality evaluation data;
a020: and collecting second importance ranking results on the basis of the first importance ranking results to determine representative importance characteristics.
In the implementation process, this step may be combined to the above step S440, so that the important features of the two aspects of processing state and quality evaluation are comprehensively considered, so as to more comprehensively and accurately establish the processing state analysis model of the thin-type tendon uniform distribution structure. In the present optimization scheme, the quality evaluation data may include an index related to quality evaluation such as dimensional accuracy, strength index, surface quality, and the like.
Wherein, obtain the second importance ranking result according to the historical quality evaluation data, as shown in fig. 6, include:
a011: preprocessing the historical quality evaluation data, and extracting features capable of representing processing quality from the preprocessed historical evaluation data; the method comprises the steps of data cleaning, missing value processing, feature extraction and the like, and features capable of representing processing quality are extracted from historical quality evaluation data according to requirements of problems.
A012: and performing feature screening and sorting on the historical quality evaluation data to obtain a second importance sorting result.
Wherein determining representative important features based on the first importance ranking result in combination with the second importance ranking result comprises:
a021: combining the feature set with the top ranking in the first importance ranking result and the second importance ranking result to form an important feature pre-combination set;
a022: the important features are selected in the important feature pre-set by setting a threshold or a set number.
In the preferred embodiment, the threshold may be set to a threshold value of the importance ranking value, and the feature having only an importance exceeding the threshold value is selected. For example, setting the threshold to 0.5, only features with importance ranking values greater than 0.5 will be selected as important features; another way to set the threshold is to select a certain number of important features, in particular a fixed number of features may be set as important features according to the requirements of the problem and the resource limitations, e.g. only the top 5 or top 10 features may be set as important features.
As a preferable mode of the above embodiment, the step of establishing the injection molding demolding defect prediction model of the thin-type rib uniform distribution structure, as shown in fig. 7, includes:
s710: collecting data related to injection molding and demolding defects of the thin rib uniformly-distributed structure;
s720: preprocessing the data, and selecting features related to demolding defect prediction from the preprocessed data to form a data set;
s730: dividing the data set into a training set and a testing set, and determining a prediction model;
s740: training the prediction model by using a training set, and evaluating the trained prediction model by using a testing set;
s750: and optimizing and adjusting the model according to the evaluation result.
In summary, the method has the advantages that through systematic data processing, model training and evaluation processes, a reliable and accurate injection molding demolding defect prediction model with a thin rib uniform distribution structure can be constructed, and scientific basis is provided for predicting and preventing demolding defects.
Embodiment two:
thin muscle equipartition structure system of processing based on PEEK material, the system includes:
the process design database construction module is used for realizing the construction of a thin rib uniform distribution structure processing process design database;
the processing state information acquisition module is used for acquiring processing state information of the thin rib uniformly distributed structure;
the feature extraction module is used for extracting features of the processing state information to obtain preset processing state information;
the processing state analysis module is used for inputting preset processing state information into a processing state analysis model of the thin-type rib uniform distribution structure to obtain the processing state information of the thin-type rib uniform distribution structure;
the selection module is used for selecting and obtaining a processing process scheme set of the thin rib uniform distribution structure from a processing process scheme library of the thin rib uniform distribution structure based on processing state information of the thin rib uniform distribution structure;
the calculation module is used for calculating the process parameters in the processing process scheme set of the thin-type rib uniform distribution structure based on the evolutionary algorithm to obtain the optimal process parameters;
the injection molding and demolding defect prediction module inputs the optimal technological parameters into an injection molding and demolding defect prediction model of the thin rib uniform distribution structure to predict possible demolding defects in an injection molding processing state;
and the screening module screens the optimal processing scheme according to the prediction result.
Wherein, the processing state analysis module includes:
the data collection unit is used for collecting data in the processing process of the thin rib uniform distribution structure;
a preprocessing unit for preprocessing data;
the feature analysis unit is used for extracting features capable of representing the processing state from the preprocessed data, screening and sorting the extracted features to obtain a first importance sorting result, and determining representative important features according to the first importance sorting result;
the model selection unit is used for determining a model for semi-supervised learning according to the selected important features and the predicted targets and selecting a collaborative training algorithm;
and the machine learning training unit is used for performing model training by using historical data, and testing and verifying the model by adopting new data to obtain the thin-type tendon uniform distribution structure processing state analysis model.
The system form in this embodiment achieves the same technical effects as those of the above embodiment, and will not be described here again.
The foregoing has outlined and described the basic principles, features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. The processing method of the thin rib uniformly distributed structure based on the PEEK material is characterized by comprising the following steps of:
constructing a processing technology design database of the thin rib uniform distribution structure;
acquiring processing state information of the thin rib uniformly distributed structure;
extracting features of the processing state information to obtain preset processing state information, wherein the steps comprise:
preprocessing the acquired processing state information;
extracting a plurality of features representing processing state information from the preprocessed data;
integrating a plurality of features into a new feature vector, and reducing the dimension of the feature vector;
adjusting the feature vectors after dimension reduction to the same size range;
integrating the adjusted feature vectors to form new feature vectors serving as preset processing state information;
inputting the preset processing state information into a processing state analysis model of the thin-type rib uniform distribution structure to obtain the processing state information of the thin-type rib uniform distribution structure, wherein the establishing step of the processing state analysis model of the thin-type rib uniform distribution structure comprises the following steps:
collecting data in the processing process of the thin rib uniform distribution structure;
preprocessing the data, and extracting features capable of representing processing states from the preprocessed data;
screening and sorting the extracted features to obtain a first importance sorting result, and determining representative important features according to the first importance sorting result;
determining a model for semi-supervised learning according to the selected important features and the predicted targets, and selecting a collaborative training algorithm;
performing model training by using historical data, and testing and verifying the model by adopting new data to obtain a processing state analysis model of the thin-type tendon uniform distribution structure;
further comprises:
collecting historical quality evaluation data after the thin rib uniform distribution structure is processed, and obtaining a second importance ranking result according to the historical quality evaluation data;
determining representative important features by combining the second importance ranking result on the basis of the first importance ranking result;
obtaining a second importance ranking result according to the historical quality assessment data, including:
preprocessing the historical quality evaluation data, and extracting features capable of representing processing quality from the preprocessed historical evaluation data;
feature screening and sorting are carried out on the historical quality evaluation data, and a second importance sorting result is obtained;
selecting and obtaining a processing process scheme set of the thin rib uniformly-distributed structure from a processing process scheme library of the thin rib uniformly-distributed structure based on the processing state information of the thin rib uniformly-distributed structure;
calculating process parameters in the processing process scheme set of the thin rib uniform distribution structure based on an evolutionary algorithm to obtain optimal process parameters;
inputting the optimal technological parameters into an injection molding and demolding defect prediction model of a thin rib uniform distribution structure, and predicting possible demolding defects in an injection molding processing state;
and screening an optimal processing scheme according to the prediction result.
2. The method for processing the thin-type rib uniform distribution structure based on the PEEK material according to claim 1, wherein the step of constructing a processing technology design database of the thin-type rib uniform distribution structure comprises the following steps:
determining a database construction range;
collecting various data in the processing process of the thin rib uniform distribution structure;
the collected various data are arranged and stored;
determining a database management system, and constructing a processing technology design database of the thin rib uniform distribution structure;
and designing a database query interface for a user to query and acquire related information of the thin rib uniform distribution structure processing technology according to the needs.
3. The method for processing a thin-type rib uniform distribution structure based on a PEEK material according to claim 1, wherein determining representative important features based on the first importance ranking result in combination with the second importance ranking result includes:
combining the feature set with the top ranking in the first importance ranking result and the second importance ranking result to form an important feature pre-combination set;
the important features are selected in the pre-aggregate set of important features by setting a threshold or a set number.
4. The method for processing the thin rib uniform distribution structure based on the PEEK material according to claim 1, wherein the step of establishing an injection molding demolding defect prediction model of the thin rib uniform distribution structure comprises the following steps:
collecting data related to injection molding and demolding defects of the thin rib uniformly-distributed structure;
preprocessing the data, and selecting characteristics related to demolding defect prediction from the preprocessed data;
dividing the data set into a training set and a testing set, and determining a prediction model;
training the prediction model by using a training set, and evaluating the trained prediction model by using a testing set;
and optimizing and adjusting the model according to the evaluation result.
5. The processing system of the thin rib uniform distribution structure based on the PEEK material adopts the processing method of the thin rib uniform distribution structure based on the PEEK material as set forth in claim 1, and is characterized in that the system comprises:
the process design database construction module is used for realizing the construction of a thin rib uniform distribution structure processing process design database;
the processing state information acquisition module is used for acquiring processing state information of the thin rib uniformly distributed structure;
the feature extraction module is used for extracting features of the processing state information to obtain preset processing state information;
the processing state analysis module is used for inputting the preset processing state information into a processing state analysis model of the thin-type rib uniform distribution structure to obtain the processing state information of the thin-type rib uniform distribution structure;
the selection module is used for selecting and obtaining a processing technology scheme set of the thin rib uniform distribution structure from a processing technology scheme library of the thin rib uniform distribution structure based on the processing state information of the thin rib uniform distribution structure;
the calculation module is used for calculating the process parameters in the processing process scheme set of the thin-type rib uniform distribution structure based on an evolutionary algorithm to obtain optimal process parameters;
the injection molding and demolding defect prediction module is used for inputting the optimal technological parameters into an injection molding and demolding defect prediction model of the thin rib uniform distribution structure to predict possible demolding defects in an injection molding processing state;
and the screening module screens the optimal processing scheme according to the prediction result.
6. The PEEK material based thin tendon uniform distribution structure processing system of claim 5, wherein the processing state analysis module includes:
the data collection unit is used for collecting data in the processing process of the thin rib uniform distribution structure;
a preprocessing unit for preprocessing the data;
the feature analysis unit is used for extracting features capable of representing the processing state from the preprocessed data, screening and sorting the extracted features to obtain a first importance sorting result, and determining representative important features according to the first importance sorting result;
the model selection unit is used for determining a model for semi-supervised learning according to the selected important features and the predicted targets and selecting a collaborative training algorithm;
and the machine learning training unit is used for performing model training by using historical data, and testing and verifying the model by adopting new data to obtain the thin tendon uniform distribution structure processing state analysis model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310664133.8A CN116595889B (en) | 2023-06-06 | 2023-06-06 | Processing method and system for thin rib uniform distribution structure based on PEEK material |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310664133.8A CN116595889B (en) | 2023-06-06 | 2023-06-06 | Processing method and system for thin rib uniform distribution structure based on PEEK material |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116595889A CN116595889A (en) | 2023-08-15 |
CN116595889B true CN116595889B (en) | 2023-10-27 |
Family
ID=87599079
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310664133.8A Active CN116595889B (en) | 2023-06-06 | 2023-06-06 | Processing method and system for thin rib uniform distribution structure based on PEEK material |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116595889B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783898A (en) * | 2018-12-27 | 2019-05-21 | 广东工业大学 | A kind of intelligent optimization method of injection molding manufacturing technique parameter |
CN110640982A (en) * | 2019-08-26 | 2020-01-03 | 江苏师范大学 | Multi-target optimization method for injection molding process parameters of thin-wall injection molding part |
CN115099147A (en) * | 2022-06-29 | 2022-09-23 | 中国电子科技集团公司第十研究所 | Process analysis and intelligent decision method based on SMT production line |
CN115270558A (en) * | 2022-07-19 | 2022-11-01 | 中山大学 | Optimization method of injection molding process of biological fiber material |
CN116151133A (en) * | 2023-04-20 | 2023-05-23 | 南京邮电大学 | Module packaging injection molding process parameter prediction method based on machine learning |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW202022633A (en) * | 2018-12-10 | 2020-06-16 | 財團法人資訊工業策進會 | Optimization method and module thereof based on feature extraction and machine learning |
-
2023
- 2023-06-06 CN CN202310664133.8A patent/CN116595889B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783898A (en) * | 2018-12-27 | 2019-05-21 | 广东工业大学 | A kind of intelligent optimization method of injection molding manufacturing technique parameter |
CN110640982A (en) * | 2019-08-26 | 2020-01-03 | 江苏师范大学 | Multi-target optimization method for injection molding process parameters of thin-wall injection molding part |
CN115099147A (en) * | 2022-06-29 | 2022-09-23 | 中国电子科技集团公司第十研究所 | Process analysis and intelligent decision method based on SMT production line |
CN115270558A (en) * | 2022-07-19 | 2022-11-01 | 中山大学 | Optimization method of injection molding process of biological fiber material |
CN116151133A (en) * | 2023-04-20 | 2023-05-23 | 南京邮电大学 | Module packaging injection molding process parameter prediction method based on machine learning |
Also Published As
Publication number | Publication date |
---|---|
CN116595889A (en) | 2023-08-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Caiazzo et al. | Towards Zero Defect Manufacturing paradigm: A review of the state-of-the-art methods and open challenges | |
Zhang et al. | A systematic review on data of additive manufacturing for machine learning applications: the data quality, type, preprocessing, and management | |
CN110757510B (en) | Method and system for predicting remaining life of robot | |
Wang et al. | A sequence-to-sequence model with attention and monotonicity loss for tool wear monitoring and prediction | |
CN114015825B (en) | Method for monitoring abnormal state of blast furnace heat load based on attention mechanism | |
CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
CN116944700B (en) | Detection and control method and system for laser cutting | |
CN113741362A (en) | Method, system, medium, and computing device for optimizing operation of liquefied natural gas receiving station | |
CN115062674B (en) | Tool arrangement and tool changing method and device based on deep learning and storage medium | |
CN115718880A (en) | Prediction method for degradation stage of complex equipment | |
CN114548494B (en) | Visual cost data prediction intelligent analysis system | |
CN117784710A (en) | Remote state monitoring system and method for numerical control machine tool | |
CN109960146A (en) | The method for improving soft measuring instrument model prediction accuracy | |
Li et al. | A remaining useful life prediction method considering the dimension optimization and the iterative speed | |
CN116595889B (en) | Processing method and system for thin rib uniform distribution structure based on PEEK material | |
CN113726558A (en) | Network equipment flow prediction system based on random forest algorithm | |
CN110320802B (en) | Complex system signal time sequence identification method based on data visualization | |
CN116821828A (en) | Multi-dimensional time sequence prediction method based on industrial data | |
Meng et al. | Performance prediction of a modular product variant with RS-SVM | |
Hu et al. | Task-driven data fusion for additive manufacturing: Framework, approaches, and case studies | |
CN116774058B (en) | Battery life prediction method, device, equipment and storage medium | |
CN118092362B (en) | Method, device and equipment for analyzing abnormal reasons in sintering process | |
Ji | Reliability Evaluation and Prediction of Mechanical System Based on Machine Learning Technology | |
CN114048600A (en) | Digital twin-driven multi-model fusion industrial system anomaly detection method | |
Yin et al. | Remaining useful life prediction based on parallel multi-scale feature fusion network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |