Method and system for optimizing the manufacturing process of communication module housing

By analyzing the appearance defects and flaw detection images of the communication module shell, combining mechanical test data, and optimizing the manufacturing process, the simulation inaccuracy problem caused by simplifying assumptions in the existing process is solved, and the overall optimization efficiency of the communication module shell preparation process is improved. .

CN118657346BActive Publication Date: 2024-11-12SHENZHEN BAOTIAN PRECISION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411129926.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-12
Estimated Expiration
2044-08-16

AI Technical Summary

Technical Problem

The existing optimization methods for shell preparation process of communication modules usually need to simplify assumptions when building models, ignoring key geometric features, material characteristics and production uncertainties, resulting in inaccurate simulation results and the optimization results are local optimal rather than global maximum. Excellent, reducing process efficiency.

Method used

By obtaining the appearance image of the finished shell product, analyzing the appearance defect indicators, combining the flaw detection image and mechanical test data, the defect degree and strength compliance rate of the finished product are calculated, and the manufacturing process is optimized to improve process efficiency.

Benefits of technology

The defect types and defect levels of the finished shell products were clarified, and the process coordination problem was found, and the overall optimization efficiency of the communication module shell preparation process was improved by optimizing the manufacturing process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118657346B_ABST
    Figure CN118657346B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of preparation process optimization, and provides a method and system for realizing the optimization of the preparation process of a communication module shell, including: collecting a shell appearance image corresponding to a finished shell product, determining an appearance defect index corresponding to the finished shell product, analyzing the correlation effect of the appearance defect index on the shell application function, and screening out a target defect index from the appearance defect index; performing flaw detection on a first sampled finished product to obtain a sample flaw detection image, calculating the finished product defect degree corresponding to the finished shell product, performing a mechanical test on a second sampled finished product, collecting mechanical property data during the mechanical test, calculating the finished product strength value corresponding to the second sampled finished product, and calculating the strength compliance rate corresponding to the finished shell product; calculating the process coordination between the shell manufacturing processes; and optimizing the shell manufacturing process to obtain an optimized manufacturing process. The present invention aims to improve the optimization efficiency of the preparation process of the communication module shell.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of preparation process optimization, and in particular to a method and system for optimizing the preparation process of a communication module housing. Background Art

[0002] With the rapid development of communication technology, communication modules are increasingly used in various electronic devices. As a key component to protect internal components and ensure stable signal transmission, the quality and performance of the communication module housing are crucial. However, the current preparation process of the communication module housing has shortcomings.

[0003] The existing communication module shell preparation process optimization adopts the finite element analysis method, which simulates the preparation process and obtains the optimization plan. However, this method usually needs to make a series of simplified assumptions in the process of building the model to reduce the calculation complexity and shorten the calculation time. For example, some tiny but critical geometric features, anisotropic properties of materials, complex boundary conditions and uncertainty factors in actual production may be ignored. These simplifications may cause the model to be unable to accurately capture all the details of the real physical phenomena, thereby affecting the accuracy of the simulation results. Some will adopt the single factor optimization method, which only considers a single factor and obtains the result of local optimization rather than global optimization, thereby reducing the optimization efficiency of the communication module shell preparation process. Summary of the invention

[0004] The present invention provides a method and system for optimizing the manufacturing process of a communication module housing, the main purpose of which is to improve the optimization efficiency of the manufacturing process of the communication module housing.

[0005] To achieve the above object, the present invention provides a method for optimizing the manufacturing process of a communication module housing, comprising:

[0006] Obtaining a finished shell of a communication module shell, collecting a shell appearance image corresponding to the finished shell, determining an appearance defect index corresponding to the finished shell based on the shell appearance image, analyzing the correlation effect of the appearance defect index on the application function of the shell, and screening out a target defect index from the appearance defect index according to the correlation effect;

[0007] Sampling the shell finished product to obtain a first sampled finished product and a second sampled finished product, performing flaw detection on the first sampled finished product to obtain a sample flaw detection image, calculating the finished product defect degree corresponding to the shell finished product based on the sample flaw detection image, performing mechanical testing on the second sampled finished product, and collecting mechanical property data during the mechanical testing process, calculating the finished product strength value corresponding to the second sampled finished product based on the mechanical property data, and calculating the strength compliance rate corresponding to the shell finished product based on the finished product strength value;

[0008] Querying the shell manufacturing process of the communication module shell, scheduling the process manufacturing data and process usage resources corresponding to the shell manufacturing process, and calculating the process coordination degree between the shell manufacturing processes in combination with the process manufacturing data and the process usage resources;

[0009] According to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree, the shell manufacturing process is optimized to obtain an optimized manufacturing process.

[0010] Optionally, determining the appearance defect index corresponding to the finished shell product based on the shell appearance image includes:

[0011] Performing noise reduction processing on the shell appearance image to obtain a target appearance image;

[0012] Performing foreground extraction on the target appearance image to obtain a foreground appearance image;

[0013] marking abnormal image regions in the foreground appearance image;

[0014] Extracting features from the abnormal image region to obtain features of the abnormal region;

[0015] Based on the characteristics of the abnormal area, an appearance defect index corresponding to the shell finished product is determined.

[0016] Optionally, the analyzing the correlation effect of the appearance defect index on the application function of the shell includes:

[0017] Querying the functional factors corresponding to the shell application functions, and collecting factor description information corresponding to the functional factors;

[0018] Extracting key factor information from the factor description information, and calculating the similarity strength between the appearance defect index and the key factor information;

[0019] When the similarity strength is greater than a preset threshold, the correlation effect of the appearance defect index on the application function of the shell is determined.

[0020] Optionally, the calculating the similarity strength between the appearance defect index and the key factor information includes:

[0021] Respectively identifying the text characters in the appearance defect index and the key factor information to obtain defect index characters and factor information characters;

[0022] Performing vectorization processing on the defect indicator character and the factor information character respectively to obtain an indicator character vector and an information character vector;

[0023] Calculating a vector similarity coefficient between the indicator character vector and the information character vector;

[0024] The vector similarity coefficients are summed to obtain the similarity strength between the appearance defect index and the key factor information.

[0025] Optionally, the calculating the finished product defect degree corresponding to the finished shell product according to the sample flaw detection image includes:

[0026] Performing grayscale processing on the sample flaw detection image to obtain a grayscale flaw detection image, and constructing a grayscale histogram corresponding to the grayscale flaw detection image;

[0027] According to the grayscale histogram, setting a grayscale stretching threshold of the grayscale flaw detection image;

[0028] Calculating the stretched gray value corresponding to each pixel in the grayscale flaw detection image according to the grayscale stretching threshold;

[0029] According to the stretched grayscale value, the grayscale flaw detection image is optimized to obtain a target flaw detection image;

[0030] Identify the defect display area in the target flaw detection image, and extract defect quantification parameters corresponding to the defect display area;

[0031] Calculating the defect area corresponding to the defect display area according to the defect quantification parameter;

[0032] The finished product defect degree corresponding to the finished shell product is calculated in combination with the defect area.

[0033] Optionally, calculating the stretched grayscale value corresponding to each pixel in the grayscale flaw detection image according to the grayscale stretching threshold includes:

[0034] Detecting the pixel grayscale value corresponding to each pixel in the grayscale flaw detection image;

[0035] Identifying grayscale extremes among the pixel grayscale values;

[0036] Combining the grayscale extreme value, the grayscale stretching threshold and the pixel grayscale value, the stretching grayscale value corresponding to each pixel in the grayscale flaw detection image is calculated by the following formula:

[0037]

[0038] Among them, A represents the stretched gray value corresponding to each pixel in the grayscale flaw detection image, It represents the gray value of the pixel corresponding to the ath pixel in the grayscale flaw detection image, a represents the pixel sequence number of the grayscale flaw detection image, and Respectively represent the starting value and ending value of the grayscale stretching threshold, and They represent the maximum and minimum values ​​in the grayscale extreme values ​​respectively.

[0039] Optionally, calculating the finished product strength value corresponding to the second sampled finished product according to the mechanical property data includes:

[0040] Identify the mechanical property identifier corresponding to the mechanical property data;

[0041] According to the mechanical property identifier, clustering processing is performed on the mechanical property data to obtain clustered mechanical data;

[0042] Performing data optimization processing on the cluster mechanical data to obtain target cluster mechanical data;

[0043] Analyzing the mechanical indexes corresponding to the target cluster mechanical data;

[0044] Calculating the index strength value corresponding to the mechanical index according to the target clustered mechanical data;

[0045] The finished product strength value corresponding to the second sampled finished product is calculated by combining the index strength value and the mechanical index.

[0046] Optionally, performing data optimization processing on the clustered mechanical data to obtain target clustered mechanical data includes:

[0047] Measuring the amount of mechanical data in each category of the clustered mechanical data, and identifying the mechanical metric value in each category of the clustered mechanical data;

[0048] Combining the amount of mechanical data and the mechanical metric value, the data quality score corresponding to the data in each category in the clustered mechanical data is calculated by the following formula:

[0049]

[0050] Among them, F represents the data quality score corresponding to the data in each category in the clustered mechanical data, q represents the amount of mechanical data in each category in the clustered mechanical data, and b represents the data sequence number in each category in the clustered mechanical data. represents the mechanical metric value corresponding to the bth data in the Hth category of the clustered mechanical data, H represents the category sequence number corresponding to the clustered mechanical data,

[0051] According to the data quality score, the cluster mechanical data is subjected to data optimization processing to obtain target cluster mechanical data.

[0052] Optionally, the calculating the process coordination degree between the shell manufacturing processes by combining the process manufacturing data and the process usage resources includes:

[0053] Identify the preceding and following steps of each step in the shell manufacturing process;

[0054] Determine a coordinated process in the shell manufacturing process by combining the preceding process and the following process;

[0055] Extracting the process processing cycle corresponding to the collaborative process from the process manufacturing data;

[0056] In combination with the process processing cycle, the cycle coordination degree corresponding to the coordinated process is calculated;

[0057] Extracting process resources corresponding to the collaborative process from the process usage resources;

[0058] In combination with the process resources, calculating the resource coordination degree corresponding to the coordinated process;

[0059] The process coordination degree between the shell manufacturing processes is calculated by combining the cycle coordination degree and the resource coordination degree.

[0060] A system for optimizing the manufacturing process of a communication module housing, characterized in that the system comprises:

[0061] A defect index screening module is used to obtain a finished shell of a communication module shell, collect a shell appearance image corresponding to the finished shell, determine an appearance defect index corresponding to the finished shell based on the shell appearance image, analyze the correlation effect of the appearance defect index on the application function of the shell, and screen out a target defect index from the appearance defect index according to the correlation effect;

[0062] a strength compliance rate calculation module, used to perform sampling processing on the shell finished product to obtain a first sampled finished product and a second sampled finished product, perform flaw detection on the first sampled finished product to obtain a sample flaw detection image, calculate the finished product defect degree corresponding to the shell finished product based on the sample flaw detection image, perform mechanical testing on the second sampled finished product, and collect mechanical property data during the mechanical testing process, calculate the finished product strength value corresponding to the second sampled finished product based on the mechanical property data, and calculate the strength compliance rate corresponding to the shell finished product based on the finished product strength value;

[0063] A process coordination degree calculation module is used to query the shell manufacturing process of the communication module shell, schedule the process manufacturing data and process usage resources corresponding to the shell manufacturing process, and calculate the process coordination degree between the shell manufacturing processes in combination with the process manufacturing data and the process usage resources;

[0064] The process optimization module is used to optimize the shell manufacturing process according to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree to obtain an optimized manufacturing process.

[0065] The present invention determines the appearance defect index corresponding to the finished shell product based on the shell appearance image, and can obtain the appearance defect type existing in the finished shell product, so as to facilitate the subsequent analysis of the defect type that affects the finished shell product. The present invention calculates the finished product defect degree corresponding to the finished shell product based on the sample flaw detection image, and can clarify the defect degree of the finished shell product, which is helpful to determine whether the finished shell product meets the quality standard. The present invention calculates the process coordination degree between the shell manufacturing processes by combining the process manufacturing data and the process use resources. The process coordination degree can be used to find problems such as poor connection between processes and unreasonable resource allocation, which is convenient for the subsequent optimization of the shell manufacturing process. The present invention optimizes the shell manufacturing process according to the target defect index, the finished product defect degree, the strength compliance rate and the process coordination degree, and can improve the optimization efficiency of the shell manufacturing process. Therefore, a method and system for optimizing the preparation process of a communication module shell provided in an embodiment of the present invention can improve the optimization efficiency of the preparation process of a communication module shell. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic flow chart of a method for optimizing a manufacturing process of a communication module housing provided by an embodiment of the present invention;

[0067] Figure 2 A functional module diagram of a system for optimizing the manufacturing process of a communication module housing provided by one embodiment of the present invention.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0070] The embodiment of the present application provides a method for optimizing the preparation process of a communication module shell. In the embodiment of the present application, the execution subject of the method for optimizing the preparation process of a communication module shell includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for optimizing the preparation process of a communication module shell can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0071] Reference Figure 1 FIG. 1 is a flow chart of a method for optimizing the manufacturing process of a communication module housing provided by an embodiment of the present invention. In this embodiment, the method for optimizing the manufacturing process of a communication module housing includes steps S1-S4.

[0072] S1. Obtain a finished shell of a communication module shell and its corresponding shell application function, collect a shell appearance image corresponding to the finished shell, determine an appearance defect index corresponding to the finished shell based on the shell appearance image, analyze the correlation effect of the appearance defect index on the shell application function, and screen out a target defect index from the appearance defect index based on the correlation effect.

[0073] The present invention can obtain the type of appearance defect existing in the finished shell product by determining the appearance defect index corresponding to the finished shell product based on the shell appearance image, so as to facilitate the subsequent analysis of the type of defect affecting the finished shell product, wherein the communication module shell is a shell structure used to protect and accommodate key components such as electronic components and circuits inside the communication module, the shell application function is the corresponding use purpose of the communication module shell, the shell appearance image is an image obtained by collecting the appearance of the finished shell product, and the appearance defect index is the type of appearance defect corresponding to the finished shell product. Furthermore, the collection of the shell appearance image corresponding to the finished shell product can be achieved by an image collector, such as a camera.

[0074] As an embodiment of the present invention, the method of determining the appearance defect index corresponding to the shell finished product based on the shell appearance image includes: performing noise reduction processing on the shell appearance image to obtain a target appearance image, performing foreground extraction on the target appearance image to obtain a foreground appearance image, marking abnormal image areas in the foreground appearance image, performing feature extraction on the abnormal image area to obtain abnormal area features, and determining the appearance defect index corresponding to the shell finished product based on the abnormal area features.

[0075] Among them, the target appearance image is the image obtained after removing the noise interference in the shell appearance image, the foreground appearance image is the foreground shell image obtained after segmenting the background area in the target appearance image, the abnormal image area is the image area where there is an abnormality in the foreground appearance image, and the abnormal area feature is the abnormal representation of the abnormal image area.

[0076] Optionally, the noise reduction processing of the shell appearance image can be achieved by a low-pass filter; the foreground extraction of the target appearance image can be achieved by a threshold segmentation method; the marking of the abnormal image area in the foreground appearance image can be achieved by comparing it with the standard image, and if different areas appear in the image, they can be marked by using annotation tools, such as color annotation tools; the feature extraction of the abnormal image area can be achieved by a feature extraction algorithm, such as a grayscale co-occurrence matrix, an HSV model, etc.; the defect type corresponding to the abnormal area feature is queried to determine the appearance defect index corresponding to the shell finished product. The defect type corresponding to the abnormal area feature can be obtained by querying a mapping library. The mapping library is a mapping library formed by summarizing the correspondence between different abnormal area features and defect types through a large amount of sample data in advance.

[0077] By analyzing the correlation effect of the appearance defect index on the shell application function, the present invention can understand the degree of influence of the appearance defect index on the shell application function, thereby facilitating the screening of target defect indicators, wherein the correlation effect represents the correlation between the appearance defect index and the shell application function, and the target defect index is an indicator among the appearance defect indicators that has an influence on the shell application function.

[0078] As an embodiment of the present invention, the analysis of the association effect of the appearance defect index on the shell application function includes: querying the functional factors corresponding to the shell application function, collecting factor description information corresponding to the functional factors, extracting key factor information in the factor description information, calculating the similarity strength between the appearance defect index and the key factor information, and when the similarity strength is greater than a preset threshold, determining the association effect of the appearance defect index on the shell application function.

[0079] Among them, the functional factors are functional requirements corresponding to the application functions of the shell, such as transmission stability, protection performance, heat dissipation performance, installation adaptability, etc., the factor description information is a detailed description corresponding to the functional factors, the key factor information is important information in the factor description information, the similarity intensity indicates the degree of similarity between the appearance defect index and the key factor information, and the preset threshold can be 0.8, and can also be set according to the actual application scenario.

[0080] Optionally, the query of the functional factors corresponding to the shell application function can be achieved through human-computer interaction, such as querying from the Internet; the method for extracting key factor information in the factor description information can be achieved through a convolutional neural network; when the similarity intensity is greater than a preset threshold, it indicates that there is a correlation between the appearance defect index and the shell application function.

[0081] Further, as an optional embodiment of the present invention, the calculation of the similarity strength between the appearance defect index and the key factor information includes: respectively identifying the text characters in the appearance defect index and the key factor information to obtain defect indicator characters and factor information characters, respectively vectorizing the defect indicator characters and the factor information characters to obtain indicator character vectors and information character vectors, calculating the vector similarity coefficient between the indicator character vector and the information character vector, summing the vector similarity coefficients, and calculating the similarity strength between the appearance defect index and the key factor information.

[0082] Among them, the defect indicator character and the factor information character are respectively the text information in the appearance defect indicator and the key factor information, the indicator character vector and the information character vector are respectively the expression vectors corresponding to the defect indicator character and the factor information character, and the vector similarity coefficient represents the similarity between the indicator character vector and the information character vector.

[0083] Optionally, the recognition of the text characters in the appearance defect index and the key factor information can be achieved through OCR recognition technology; the vectorization processing of the defect indicator characters and the factor information characters can be achieved through the word2vec algorithm; the calculation of the vector similarity coefficient between the indicator character vector and the information character vector can be achieved through the cosine similarity algorithm; the similarity strength between the appearance defect index and the key factor information can be obtained by summing the vector similarity coefficient of each indicator in the appearance defect index.

[0084] S2. Sampling the shell finished product to obtain a first sampled finished product and a second sampled finished product, performing flaw detection on the first sampled finished product to obtain a sample flaw detection image, calculating the finished product defect degree corresponding to the shell finished product based on the sample flaw detection image, performing mechanical testing on the second sampled finished product, and collecting mechanical property data during the mechanical testing process, calculating the finished product strength value corresponding to the second sampled finished product based on the mechanical property data, and calculating the strength compliance rate corresponding to the shell finished product based on the finished product strength value.

[0085] The present invention calculates the finished product defect degree corresponding to the shell finished product based on the sample flaw detection image, so as to clarify the defect degree of the shell finished product and help determine whether the shell finished product meets the quality standards, wherein the first sampled finished product and the second sampled finished product are samples randomly sampled from the shell finished product, respectively, and are random variables in quantity, appearance, and production cycle, without fixed rules and inevitable associations, and the sample flaw detection image is an image of the first sampled finished product obtained by radiographic flaw detection, and further, the flaw detection of the first sampled finished product can be achieved by an X-ray flaw detector.

[0086] As an embodiment of the present invention, the method of calculating the finished product defect degree corresponding to the finished shell product based on the sample flaw detection image includes: performing grayscale processing on the sample flaw detection image to obtain a grayscale flaw detection image, constructing a grayscale histogram corresponding to the grayscale flaw detection image, setting a grayscale stretching threshold of the grayscale flaw detection image according to the grayscale histogram, calculating the stretched grayscale value corresponding to each pixel in the grayscale flaw detection image according to the grayscale stretching threshold, optimizing the grayscale flaw detection image according to the stretched grayscale value to obtain a target flaw detection image, identifying a defect display area in the target flaw detection image, extracting a defect quantization parameter corresponding to the defect display area, calculating a defect area corresponding to the defect display area according to the defect quantization parameter, and calculating the finished product defect degree corresponding to the finished shell product in combination with the defect area.

[0087] Among them, the grayscale histogram is the grayscale statistical graph corresponding to the sample flaw detection image, the grayscale stretching threshold is the grayscale stretching range corresponding to the grayscale flaw detection image, the stretched grayscale value is the grayscale value corresponding to each pixel in the grayscale flaw detection image after stretching optimization, the defect display area is the defect area with significant differences in the grayscale flaw detection image, the defect quantization parameter is the numerical description parameter of the defect display area, and the defect area is the size corresponding to the defect display area.

[0088] Optionally, the grayscale processing of the sample flaw detection image can be achieved by the average value method, calculating the color average of the three channels of each pixel in the sample flaw detection image to obtain the grayscale value, and replacing the pixel value with the grayscale value to obtain the grayscale flaw detection image; the grayscale value of each pixel in the grayscale flaw detection image can be counted, and a grayscale histogram corresponding to the grayscale flaw detection image can be constructed according to the grayscale value using a mapping tool, and the mapping tool includes a Visio mapping tool; the grayscale stretching threshold of the grayscale flaw detection image can be set by combining the grayscale range of the grayscale histogram, for example, the grayscale value of the defect is mainly concentrated between 50-100, and the discrete grayscale value is between 0-255, and the range of 50-100 can be selected as the grayscale stretching threshold; the identification of the defect display area in the target flaw detection image can be achieved by an edge detection method, such as the Sobel operator; the extraction of the defect quantization parameter corresponding to the defect display area can be achieved by It can be achieved by pixel counting method; the defect area corresponding to the defect display area can be calculated by selecting a suitable algorithm in combination with the shape of the area. For example, for a rectangle, it can be obtained according to the product of the length and width in the defect quantification parameter. If it is an irregular area, it can be calculated using the contour integral method. The calculation process of the finished product defect degree corresponding to the shell finished product is: calculate the sample area corresponding to the first sampled finished product, calculate the area ratio between the defect area and the sample area, obtain the sample defect rate corresponding to each sampled sample, count the number of samples of the first sampled finished product and the number of finished products of the shell finished product, combine the number of samples and the number of finished products, calculate the number ratio of the first sampled finished product, combine the sample defect rate and the number ratio, calculate the finished product defect degree corresponding to the shell finished product, and the formula is: finished product defect degree = (sample defect rate 1 + sample defect rate 2 + sample defect rate 3 +... + sample defect rate r) × number ratio.

[0089] Further, as an optional embodiment of the present invention, the stretching gray value corresponding to each pixel in the grayscale flaw detection image is calculated according to the grayscale stretching threshold, including: detecting the pixel gray value corresponding to each pixel in the grayscale flaw detection image, identifying the grayscale extreme value in the pixel grayscale value, combining the grayscale extreme value, the grayscale stretching threshold and the pixel grayscale value, and calculating the stretching gray value corresponding to each pixel in the grayscale flaw detection image by the following formula:

[0090]

[0091] Among them, A represents the stretched gray value corresponding to each pixel in the grayscale flaw detection image, It represents the gray value of the pixel corresponding to the ath pixel in the grayscale flaw detection image, a represents the pixel sequence number of the grayscale flaw detection image, and Respectively represent the starting value and ending value of the grayscale stretching threshold, and They represent the maximum and minimum values ​​in the grayscale extreme values ​​respectively.

[0092] Among them, the grayscale extreme values ​​are the maximum and minimum values ​​of the pixel grayscale values, which are 255 and 0. Furthermore, the pixel grayscale value corresponding to each pixel in the grayscale flaw detection image can be realized by a grayscale detection tool, and the grayscale detection tool is compiled by a script language.

[0093] The present invention can determine whether the second sampled finished product meets the specified strength standard by calculating the finished product strength value corresponding to the second sampled finished product based on the mechanical property data, thereby evaluating whether the strength quality of the second sampled finished product is qualified, so as to facilitate the optimization of subsequent manufacturing processes. The mechanical property data is the measurement results and recorded information during the mechanical testing of the second sampled finished product, and the flat strength value is the expression of the mechanical performance index corresponding to the second sampled finished product. Furthermore, the mechanical testing of the second sampled finished product can be achieved by a universal material testing machine; the collection of mechanical property data during the mechanical testing process can be achieved by sensors, such as force sensors.

[0094] As an embodiment of the present invention, the method of calculating the finished product strength value corresponding to the second sampled finished product based on the mechanical property data includes: identifying the mechanical property identifier corresponding to the mechanical property data, clustering the mechanical property data according to the mechanical property identifier to obtain clustered mechanical data, performing data optimization processing on the clustered mechanical data to obtain target clustered mechanical data, analyzing the mechanical index corresponding to the target clustered mechanical data, calculating the index strength value corresponding to the mechanical index based on the target clustered mechanical data, and calculating the finished product strength value corresponding to the second sampled finished product by combining the index strength value and the mechanical index.

[0095] Among them, the mechanical property identifier is the mechanical property corresponding to the mechanical property data, such as tension and pressure, the clustered mechanical data is the data obtained after the mechanical property data is classified according to the mechanical property identifier, the target clustered mechanical data is the data obtained after filtering the low-quality data in the clustered mechanical data, the mechanical indicator is the type corresponding to the target clustered mechanical data, such as tensile strength and yield strength, and the indicator strength value is the strength value corresponding to the mechanical indicator.

[0096] Optionally, the identification of the mechanical property identifier corresponding to the mechanical property data can be achieved through a keyword matching method; the clustering processing of the mechanical property data can be achieved through a clustering algorithm, such as a hierarchical clustering algorithm; the analysis of the mechanical indicators corresponding to the target clustering mechanical data can be achieved through a principal component analysis method; according to the specific type corresponding to the target clustering mechanical data, a suitable algorithm is selected to calculate the indicator strength value corresponding to the mechanical indicator, for example, the calculation formula for tensile strength is: tensile strength = maximum tensile force borne by the second sampled finished product before it breaks / stress cross-sectional area of ​​the second sampled finished product; the indicator weight value corresponding to the mechanical indicator is assigned, the indicator weight value and the corresponding indicator strength value are multiplied and summed to obtain the finished product strength value corresponding to the second sampled finished product. Furthermore, the assignment of indicator weight values ​​can be achieved through experimental data and statistical analysis. By performing statistical analysis on a large number of experimental data of similar materials, the degree of influence of different mechanical indicators on material failure or performance is observed, so as to determine the weight.

[0097] Further, as an optional embodiment of the present invention, the data optimization processing of the clustered mechanical data to obtain the target clustered mechanical data includes: measuring the amount of mechanical data of each category in the clustered mechanical data, and identifying the mechanical metric value in each category in the clustered mechanical data, combining the mechanical data amount and the mechanical metric value, and calculating the data quality score corresponding to the data in each category in the clustered mechanical data by the following formula:

[0098]

[0099] Among them, F represents the data quality score corresponding to the data in each category in the clustered mechanical data, q represents the amount of mechanical data in each category in the clustered mechanical data, and b represents the data sequence number in each category in the clustered mechanical data. represents the mechanical metric value corresponding to the bth data in the Hth category of the clustered mechanical data, H represents the category sequence number corresponding to the clustered mechanical data,

[0100] According to the data quality score, the cluster mechanical data is subjected to data optimization processing to obtain target cluster mechanical data.

[0101] Among them, the amount of mechanical data represents the total amount of data in each category in the clustered mechanical data, and the mechanical measurement value is the specific numerical value corresponding to the data in each category in the clustered mechanical data. Furthermore, the measurement of the amount of mechanical data in each category in the clustered mechanical data can be achieved by statistical methods; the identification of the mechanical measurement value in each category in the clustered mechanical data can be achieved by a recognition algorithm, and the recognition algorithm is compiled by JAVA language; the data optimization processing of the clustered mechanical data can be achieved according to the numerical value of the data quality score. For example, if the data quality score is lower than 0.6, it means that the corresponding data is low-quality data and can be filtered out.

[0102] The present invention calculates the strength compliance rate corresponding to the shell finished product based on the finished product strength value, so as to understand the degree of compliance of the shell finished product with respect to the strength of the drink. Further, the strength qualification rate of the finished product strength value and the standard strength value is calculated, and the quantity ratio of the second sampled finished products is calculated. The strength compliance rate corresponding to the shell finished product is calculated by combining the strength qualification rate and the quantity ratio, and the formula is: Strength compliance rate = (strength qualification rate 1 + strength qualification rate 2 + strength qualification rate 3 + ... + strength qualification rate y) × quantity ratio.

[0103] S3. Query the shell manufacturing process of the communication module shell, schedule the process manufacturing data and process usage resources corresponding to the shell manufacturing process, and calculate the process coordination degree between the shell manufacturing processes in combination with the process manufacturing data and the process usage resources.

[0104] The present invention calculates the process coordination degree between the shell manufacturing processes by combining the process manufacturing data and the process usage resources. The process coordination degree can be used to discover problems such as poor connection between processes and unreasonable resource allocation, which is convenient for subsequent optimization of the shell manufacturing process. The shell manufacturing process is the manufacturing process of the communication module shell, the process manufacturing data is the processing record data of the shell manufacturing process, the process usage resources are the resources used by the shell manufacturing process, and the process coordination degree indicates the degree of smooth connection between the shell manufacturing processes. Furthermore, the shell manufacturing process of the communication module shell can be obtained by querying the process file, and the process file includes a process flow chart; the scheduling of the process manufacturing data and process usage resources corresponding to the shell manufacturing process can be achieved through a corresponding control system, such as a programmable logic controller (PLC).

[0105] As an embodiment of the present invention, the process coordination degree between the shell manufacturing processes is calculated by combining the process manufacturing data and the process usage resources, including: identifying the predecessor process and the successor process of each process in the shell manufacturing process, determining the collaborative process in the shell manufacturing process by combining the predecessor process and the successor process, extracting the process processing cycle corresponding to the collaborative process from the process manufacturing data, calculating the cycle coordination degree corresponding to the collaborative process by combining the process processing cycle, and extracting the process resources corresponding to the collaborative process from the process usage resources, calculating the resource coordination degree corresponding to the collaborative process by combining the process resources, and calculating the process coordination degree between the shell manufacturing processes by combining the cycle coordination degree and the resource coordination degree.

[0106] Among them, the pre-process and the post-process are respectively the pre-preparation conditions for each process in the shell manufacturing process and the process that needs to be performed immediately after the completion of the process; the collaborative process is the processes that cooperate with each other in the shell manufacturing process; the process processing cycle is the processing time in the collaborative process; the cycle coordination degree indicates the degree of coordination of the collaborative processes in the cycle; the process resources are the resources utilized by the collaborative process; and the resource coordination degree indicates the degree of coordination of the collaborative processes in terms of resources.

[0107] Optionally, the preceding process and the following process of each process in the shell manufacturing process can be identified from the process flow chart; the collaborative process in the shell manufacturing process can be determined by combining the sequence between the preceding process and the following process; the calculation formula for the cycle coordination degree corresponding to the collaborative process is: time coordination degree = (start time of process 2 in the collaborative process - end time of process 1 in the collaborative process) / (processing time of process 2 in the collaborative process), for example, process 1 in the collaborative process ends at 9 am, process 2 in the collaborative process starts at 10 am, and process 3 in the collaborative process ends at 11 am. The processing time of process 2 is 2 hours, so: the start time of process 2 in the collaborative process is 10 am, the end time of process 1 in the collaborative process is 9 am, and the processing time of process 2 in the collaborative process is 2 hours. Substituting these times into the formula to calculate the time coordination can reflect the time coordination between process 1 in the collaborative process and process 2 in the collaborative process; the calculation principle of the resource coordination is the same as that of the time coordination, and no further details will be given here; the calculation formula for the process coordination between the shell manufacturing processes is: process coordination = (the cycle coordination + the resource coordination) / 2.

[0108] S4. Optimize the shell manufacturing process according to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree to obtain an optimized manufacturing process.

[0109] The present invention optimizes the shell manufacturing process according to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree, so as to improve the optimization efficiency of the shell manufacturing process. Optionally, the optimization processing steps of the shell manufacturing process are: respectively analyzing the causes corresponding to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree, and formulating corresponding processes to solve the problems according to the corresponding causes. For example, for the target defect index, analyze the possible process links and causes that lead to the defects, such as raw material problems, improper processing technology or operational errors. According to the finished product defect rate, judge the main defect types and corresponding process stages. For the case where the strength compliance rate is not high, study whether it is caused by factors such as insufficient material strength, improper heat treatment in the process or unreasonable structural design. Based on the level of the process coordination degree, find out the process combination with poor coordination, such as long waiting time, resource conflict and other problems. Combined with the problems analyzed above, formulate corresponding solutions. According to the solutions, optimize the shell manufacturing process to obtain an optimized manufacturing process.

[0110] The present invention determines the appearance defect index corresponding to the finished shell product based on the shell appearance image, and can obtain the appearance defect type existing in the finished shell product, so as to facilitate the subsequent analysis of the defect type that affects the finished shell product. The present invention calculates the finished product defect degree corresponding to the finished shell product based on the sample flaw detection image, and can clarify the defect degree of the finished shell product, which is helpful to determine whether the finished shell product meets the quality standard. The present invention calculates the process coordination degree between the shell manufacturing processes by combining the process manufacturing data and the process use resources. The process coordination degree can be used to find problems such as poor connection between processes and unreasonable resource allocation, which is convenient for the subsequent optimization of the shell manufacturing process. The present invention optimizes the shell manufacturing process according to the target defect index, the finished product defect degree, the strength compliance rate and the process coordination degree, and can improve the optimization efficiency of the shell manufacturing process. Therefore, a method for optimizing the preparation process of a communication module shell provided by an embodiment of the present invention can improve the optimization efficiency of the preparation process of a communication module shell.

[0111] like Figure 2 1 is a functional module diagram of a system for optimizing the manufacturing process of a communication module housing provided by an embodiment of the present invention.

[0112] The system 100 for optimizing the manufacturing process of a communication module housing according to the present invention can be installed in an electronic device. According to the functions to be implemented, the system 100 for optimizing the manufacturing process of a communication module housing can include a defect index screening module 101, a strength compliance rate calculation module 102, a process coordination degree calculation module 103 and a process optimization module 104. The module according to the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0113] In this embodiment, the functions of each module / unit are as follows:

[0114] The defect index screening module 101 is used to obtain a finished shell of a communication module shell, collect a shell appearance image corresponding to the finished shell, determine the appearance defect index corresponding to the finished shell based on the shell appearance image, analyze the correlation effect of the appearance defect index on the application function of the shell, and screen out a target defect index from the appearance defect index according to the correlation effect;

[0115] The strength compliance rate calculation module 102 is used to sample the shell finished product to obtain a first sampled finished product and a second sampled finished product, perform flaw detection on the first sampled finished product to obtain a sample flaw detection image, calculate the finished product defect degree corresponding to the shell finished product based on the sample flaw detection image, perform mechanical testing on the second sampled finished product, and collect mechanical property data during the mechanical testing process, calculate the finished product strength value corresponding to the second sampled finished product based on the mechanical property data, and calculate the strength compliance rate corresponding to the shell finished product based on the finished product strength value;

[0116] The process coordination degree calculation module 103 is used to query the shell manufacturing process of the communication module shell, schedule the process manufacturing data and process usage resources corresponding to the shell manufacturing process, and calculate the process coordination degree between the shell manufacturing processes in combination with the process manufacturing data and the process usage resources;

[0117] The process optimization module 104 is used to optimize the shell manufacturing process according to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree to obtain an optimized manufacturing process.

[0118] In detail, each module described in the system 100 for optimizing the manufacturing process of a communication module housing described in the embodiment of the present application is used in the same manner as described above. Figure 1 The same technical means as described in the method for optimizing the preparation process of the communication module housing can produce the same technical effects, which will not be repeated here.

[0119] In the several embodiments provided by the present invention, it should be understood that the provided methods and systems can be implemented in other ways. For example, the method embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for optimizing the manufacturing process of a communication module housing, characterized in that: The method comprises: Acquire a finished shell of a communication module shell, collect a shell appearance image corresponding to the finished shell, determine an appearance defect index corresponding to the finished shell based on the shell appearance image, analyze the correlation effect of the appearance defect index on the application function of the finished shell, and select a target defect index from the appearance defect index according to the correlation effect; The shell finished product is sampled to obtain a first sampled finished product and a second sampled finished product, wherein the first sampled finished product and the second sampled finished product are samples randomly sampled from the shell finished product, respectively, and are random variables in quantity, appearance, and production cycle, without fixed rules and inevitable associations; the first sampled finished product is subjected to flaw detection to obtain a sample flaw detection image; based on the sample flaw detection image, the finished product defect degree corresponding to the shell finished product is calculated; the second sampled finished product is subjected to mechanical testing, and mechanical property data during the mechanical testing process is collected; based on the mechanical property data, the finished product strength value corresponding to the second sampled finished product is calculated; based on the finished product strength value, the strength compliance rate corresponding to the shell finished product is calculated; Querying the shell manufacturing process of the communication module shell, scheduling the process manufacturing data and process usage resources corresponding to the shell manufacturing process, and calculating the process coordination degree between the shell manufacturing processes in combination with the process manufacturing data and the process usage resources; According to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree, the shell manufacturing process is optimized to obtain an optimized manufacturing process.

2. A method for optimizing the manufacturing process of a communication module housing according to claim 1, characterized in that: The determining, based on the shell appearance image, an appearance defect index corresponding to the shell finished product includes: Performing noise reduction processing on the shell appearance image to obtain a target appearance image; Performing foreground extraction on the target appearance image to obtain a foreground appearance image; marking abnormal image regions in the foreground appearance image; Extracting features from the abnormal image region to obtain features of the abnormal region; Based on the characteristics of the abnormal area, an appearance defect index corresponding to the shell finished product is determined.

3. A method for optimizing the manufacturing process of a communication module housing according to claim 1, characterized in that: The analyzing the correlation effect of the appearance defect index on the application function of the finished shell product includes: Querying the functional factors corresponding to the application functions of the finished shell product, and collecting factor description information corresponding to the functional factors; Extracting key factor information from the factor description information, and calculating the similarity strength between the appearance defect index and the key factor information; When the similarity strength is greater than a preset threshold, the correlation effect of the appearance defect index on the application function of the finished shell product is determined.

4. A method for optimizing the manufacturing process of a communication module housing according to claim 3, characterized in that: The calculating the similarity strength between the appearance defect index and the key factor information includes: Respectively identifying the text characters in the appearance defect index and the key factor information to obtain defect index characters and factor information characters; Performing vectorization processing on the defect indicator character and the factor information character respectively to obtain an indicator character vector and an information character vector; Calculating a vector similarity coefficient between the indicator character vector and the information character vector; The vector similarity coefficients are summed to obtain the similarity strength between the appearance defect index and the key factor information.

5. A method for optimizing the manufacturing process of a communication module housing according to claim 1, characterized in that: The step of calculating the finished product defect degree corresponding to the finished shell product according to the sample flaw detection image includes: Performing grayscale processing on the sample flaw detection image to obtain a grayscale flaw detection image, and constructing a grayscale histogram corresponding to the grayscale flaw detection image; According to the grayscale histogram, setting a grayscale stretching threshold of the grayscale flaw detection image; Calculating the stretched gray value corresponding to each pixel in the grayscale flaw detection image according to the grayscale stretching threshold; According to the stretched grayscale value, the grayscale flaw detection image is optimized to obtain a target flaw detection image; Identify the defect display area in the target flaw detection image, and extract defect quantification parameters corresponding to the defect display area; Calculating the defect area corresponding to the defect display area according to the defect quantification parameter; The finished product defect degree corresponding to the finished shell product is calculated in combination with the defect area.

6. A method for optimizing the manufacturing process of a communication module housing according to claim 5, characterized in that: The step of calculating the stretched gray value corresponding to each pixel in the grayscale flaw detection image according to the grayscale stretching threshold comprises: Detecting the pixel grayscale value corresponding to each pixel in the grayscale flaw detection image; Identifying grayscale extremes among the pixel grayscale values; Combining the grayscale extreme value, the grayscale stretching threshold and the pixel grayscale value, the stretching grayscale value corresponding to each pixel in the grayscale flaw detection image is calculated by the following formula: Among them, A represents the stretched gray value corresponding to each pixel in the grayscale flaw detection image, It represents the gray value of the pixel corresponding to the ath pixel in the grayscale flaw detection image, a represents the pixel sequence number of the grayscale flaw detection image, and Respectively represent the starting value and ending value of the grayscale stretching threshold, and They represent the maximum and minimum values ​​in the grayscale extreme values ​​respectively.

7. A method for optimizing the manufacturing process of a communication module housing according to claim 1, characterized in that: The step of calculating the finished product strength value corresponding to the second sampled finished product according to the mechanical property data includes: Identify the mechanical property identifier corresponding to the mechanical property data; According to the mechanical property identifier, clustering processing is performed on the mechanical property data to obtain clustered mechanical data; Performing data optimization processing on the cluster mechanical data to obtain target cluster mechanical data; Analyzing the mechanical indexes corresponding to the target cluster mechanical data; Calculating the index strength value corresponding to the mechanical index according to the target clustered mechanical data; The finished product strength value corresponding to the second sampled finished product is calculated by combining the index strength value and the mechanical index.

8. A method for optimizing the manufacturing process of a communication module housing according to claim 7, characterized in that: The step of performing data optimization processing on the cluster mechanical data to obtain target cluster mechanical data includes: Measuring the amount of mechanical data in each category of the clustered mechanical data, and identifying the mechanical metric value in each category of the clustered mechanical data; Combining the amount of mechanical data and the mechanical metric value, the data quality score corresponding to the data in each category in the clustered mechanical data is calculated by the following formula: Among them, F represents the data quality score corresponding to the data in each category in the clustered mechanical data, q represents the amount of mechanical data in each category in the clustered mechanical data, and b represents the data sequence number in each category in the clustered mechanical data. represents the mechanical metric value corresponding to the bth data in the Hth category of the clustered mechanical data, H represents the category sequence number corresponding to the clustered mechanical data, According to the data quality score, the cluster mechanical data is subjected to data optimization processing to obtain target cluster mechanical data.

9. A method for optimizing the manufacturing process of a communication module housing according to claim 1, characterized in that: The calculating the process coordination degree between the shell manufacturing processes by combining the process manufacturing data and the process usage resources includes: Identify the preceding and following steps of each step in the shell manufacturing process; Determine a coordinated process in the shell manufacturing process by combining the preceding process and the following process; Extracting the process processing cycle corresponding to the collaborative process from the process manufacturing data; In combination with the process processing cycle, the cycle coordination degree corresponding to the coordinated process is calculated; Extracting process resources corresponding to the collaborative process from the process usage resources; In combination with the process resources, calculating the resource coordination degree corresponding to the coordinated process; The process coordination degree between the shell manufacturing processes is calculated by combining the cycle coordination degree and the resource coordination degree.

10. A system for optimizing the manufacturing process of a communication module housing, characterized in that: The system comprises: A defect index screening module is used to obtain a finished shell of a communication module shell, collect a shell appearance image corresponding to the finished shell, determine an appearance defect index corresponding to the finished shell based on the shell appearance image, analyze the correlation effect of the appearance defect index on the application function of the finished shell, and screen out a target defect index from the appearance defect index according to the correlation effect; a strength compliance rate calculation module, used to perform sampling processing on the shell finished product to obtain a first sampled finished product and a second sampled finished product, perform flaw detection on the first sampled finished product to obtain a sample flaw detection image, calculate the finished product defect degree corresponding to the shell finished product based on the sample flaw detection image, perform mechanical testing on the second sampled finished product, and collect mechanical property data during the mechanical testing process, calculate the finished product strength value corresponding to the second sampled finished product based on the mechanical property data, and calculate the strength compliance rate corresponding to the shell finished product based on the finished product strength value; A process coordination degree calculation module is used to query the shell manufacturing process of the communication module shell, schedule the process manufacturing data and process usage resources corresponding to the shell manufacturing process, and calculate the process coordination degree between the shell manufacturing processes in combination with the process manufacturing data and the process usage resources; The process optimization module is used to optimize the shell manufacturing process according to the target defect index, the finished product defect rate, the strength compliance rate and the process coordination degree to obtain an optimized manufacturing process.