A product quality detection method for an intelligent manufacturing production line

Abstract

This invention discloses a product quality inspection method for intelligent manufacturing production lines, belonging to the field of product quality inspection. The method includes: constructing a production process library and determining the quality inspection indicators for each production process; determining the time sequence of each production process and obtaining the correlation between each production process based on its quality inspection indicators; during production, after the m-th production process is completed, inspecting the current semi-finished product to obtain the quality inspection indicator values; comparing the quality inspection indicator values ​​of the current semi-finished product with the standard thresholds of the quality inspection indicators for the m-th production process; if any quality inspection indicator is unqualified, the current semi-finished product is judged as a failed product and eliminated from the production line; and updating the standard thresholds of the relevant quality inspection indicators for the preceding production processes based on the quality inspection results of the current semi-finished product in the (1-m)-th production processes. This invention solves the problem of wasted productivity caused by the inability of existing methods to adaptively adjust quality inspection indicator thresholds based on specific working conditions.

Description

Technical Field

[0001] The present invention belongs to the field of product quality inspection, and particularly relates to a product quality inspection method for an intelligent manufacturing production line. Background Art

[0002] In the wave of the global manufacturing industry accelerating towards intelligent transformation, intelligent manufacturing production lines are gradually becoming the core carriers of industrial upgrading. This production mode integrating automation, digitalization, and intelligent technologies has greatly improved production efficiency and flexibility, driving the manufacturing industry towards the direction of "flexible, efficient, and precise". However, while pursuing production efficiency, product quality control faces unprecedented challenges, and the traditional quality inspection system has become difficult to adapt to the development needs of intelligent manufacturing.

[0003] In the field of quality control of intelligent production lines, traditional quality inspection methods have played an important role in ensuring product quality. Currently, most intelligent production lines use a method of setting fixed quality inspection thresholds for quality control. In each process, specific quality inspection index thresholds are preset in advance. Products are detected for various indicators through detection devices such as sensors. If the detection results are within the preset threshold range, the product is determined to be qualified in this process inspection and can enter the next process; if it exceeds the threshold range, it is determined to be unqualified. For example, in the chip mounting process of electronic device manufacturing, a fixed threshold is set for the position accuracy of component mounting, and the deviation between the actual mounting position of the component and the standard position is measured through a vision inspection system to determine whether the mounting is qualified.

[0004] This existing method based on fixed quality inspection thresholds has certain advantages. On the one hand, its operation is relatively simple and direct, easy to understand and implement. The staff on the production line can quickly master the quality inspection standards and processes, reducing training costs and time. In some production scenarios with relatively stable processes and little change in product quality requirements, fixed thresholds can efficiently complete quality inspection work, ensuring the continuity and high efficiency of production. On the other hand, fixed thresholds can ensure the consistency of product quality to a certain extent. As long as the production process is stable and quality inspection is carried out according to the established thresholds, it can ensure that the produced products meet the pre-set quality standards and meet the basic quality requirements of the market for products.

[0005] However, this method also has significant drawbacks. First, fixed quality inspection thresholds lack adaptability to complex and changing factors during the production process. Fluctuations in the production environment, such as changes in temperature and humidity, gradual aging and wear of equipment, and subtle differences between batches of raw materials, can all lead to changes in product quality characteristics, but fixed thresholds cannot be adjusted accordingly. In the food processing industry, changes in ambient temperature and humidity affect indicators such as the moisture content of food. If the quality inspection thresholds are fixed, products that were originally qualified may be mistakenly judged as unqualified when the environment changes, or unqualified products may not be detected. Second, there are inter-process interactions. Even if the quality inspection indicators of the current process meet the standards, it may affect the quality inspection indicators of subsequent processes, leading to the final product being unqualified. However, because fixed thresholds cannot be dynamically adjusted according to this relationship between processes, it is difficult to screen out potential unqualified products in the early stages of production, resulting in wasted resources and reduced production efficiency in subsequent processes. In addition, fixed thresholds cannot fully utilize the large amount of data generated during the production process. In the era of intelligent manufacturing, massive amounts of quality inspection data have accumulated on production lines, but the fixed threshold method fails to deeply mine and analyze this data to optimize and improve quality inspection standards. Summary of the Invention

[0006] To address the aforementioned shortcomings in existing technologies, this invention provides a product quality inspection method for intelligent manufacturing production lines, which solves the problem of wasted productivity caused by the inability to adaptively adjust quality inspection index thresholds based on specific working conditions in existing methods.

[0007] To achieve the above-mentioned objectives, the technical solution adopted by this invention is: a product quality inspection method for an intelligent manufacturing production line, comprising:

[0008] Based on the product manufacturing process, a production process library is constructed, and the quality inspection indicators for each production process in the production process library are determined.

[0009] Determine the timing of each production process, and based on the quality inspection indicators of each production process, obtain the degree of correlation between each production process;

[0010] Initialize the standard thresholds for each quality inspection indicator in each production process;

[0011] During production, after the m-th production process is completed, the current semi-finished product is tested to obtain the quality inspection index values ​​of the current semi-finished product.

[0012] The quality inspection index values ​​of the current semi-finished product are compared with the standard threshold values ​​of the quality inspection index values ​​of the m-th production process. When there is a quality inspection index that is not up to standard, the current semi-finished product is judged as a defective product and is eliminated from the production line. Based on the quality inspection results of the current semi-finished product in the (1-m)-th production process, the standard threshold values ​​of the relevant quality inspection index values ​​of the preceding production process are updated.

[0013] The beneficial effects of this invention are as follows: by constructing the correlation between various production processes, the production quality of each production process is correlated, the standard threshold of the quality inspection indicators of each production process is dynamically adjusted, and semi-finished products that are likely to fail later are eliminated in the early stage, which can reduce the consumption of the production line.

[0014] Furthermore, the acquisition of the correlation between various production processes specifically involves:

[0015] Based on the time sequence of each production process, construct a production process association matrix:

[0016]

[0017] in, For the production process correlation matrix; This is a self-related term for the first production process; For the first production process to the second Related items in the production process; For the first Self-related terms in the production process; This represents the total number of production processes, which are numbered sequentially based on time sequence. It is a zero matrix;

[0018] Perform several production line simulations to obtain datasets of various quality inspection indicators for each production process;

[0019] Set the correlation degree of each correlation item in the production process correlation matrix to 1;

[0020] Based on the quality inspection index datasets for each production process, calculate the first... The production process of the first Dao production process The degree of correlation; among which, and All are production process indexes. .

[0021] The beneficial effects of the above-mentioned further scheme are as follows: the production process correlation matrix is ​​a triangular matrix, which integrates the time sequence into the description of the production process pair, and makes a preliminary judgment on the influence relationship, that is, the preceding process affects the subsequent process, which facilitates the subsequent solution of the specific degree of influence.

[0022] Furthermore, the calculation The degree of correlation is as follows:

[0023] Get the Quality control indicators for the production process:

[0024]

[0025] in, For the first A set of quality inspection indicators for the production process; For the first The first quality inspection indicator in the production process; For the first The second quality inspection indicator for the production process; For the first The first production process One quality inspection indicator; For the first The total number of quality inspection indicators for each production process;

[0026] Get the Quality control indicators for the production process:

[0027]

[0028] in, For the first A set of quality inspection indicators for the production process; For the first The first quality inspection indicator in the production process; For the first The second quality inspection indicator for the production process; For the first The first production process One quality inspection indicator; For the first The total number of quality inspection indicators for each production process;

[0029] According to the quality inspection index set and quality inspection indicator set To determine the impact on quality inspection indicators:

[0030] From the set of quality inspection indicators Select quality inspection indicator B from the set of quality inspection indicators. Select quality inspection indicator C;

[0031] Based on the datasets of quality inspection indicators for each production process, the changing trends of quality inspection indicator B and quality inspection indicator C are depicted in the same line graph with the production line simulation round as the horizontal axis and the quality inspection indicator value as the vertical axis.

[0032] If quality inspection indicator B and quality inspection indicator C are of the same type, calculate the degree of convergence of changes in quality inspection indicator B and quality inspection indicator C:

[0033]

[0034] in, The degree of convergence of changes in quality inspection indicator B and quality inspection indicator C; For quality inspection indicator B The simulation reached the [number]th [number]. The trend of the simulation is as follows: rising is 1, remaining flat is 0, and falling is -1. For quality inspection indicator C The simulation reached the [number]th [number]. The trend of the simulation is as follows: rising is 1, remaining flat is 0, and falling is -1. This represents the total number of simulations. For simulation index; This function determines whether two parameters have the same trend of change; if they do, the value is 1, otherwise it is 0.

[0035] If quality inspection indicator B and quality inspection indicator C are of different types, calculate the degree of divergence between the changes in quality inspection indicator B and quality inspection indicator C:

[0036]

[0037] in, The degree of divergence between the changes in quality inspection indicators B and C; This function determines whether the changing trends of two parameters are opposite; if they are the same, the value is 1, otherwise it is 0.

[0038] When the degree of convergence or divergence of change is greater than the change threshold, determine the first... The quality inspection index C of the production process is subject to the first The quality control index B of the production process is affected; otherwise, the judgment is made. The quality inspection index C of the production process is not affected by the first The impact of quality control index B on the production process;

[0039] Duplicate quality inspection indicators affect the judgment process; obtaining the set of quality inspection indicators is crucial. Various quality inspection indicators and quality inspection indicator sets The influence relationship of various quality inspection indicators; and based on the set of quality inspection indicators. Various quality inspection indicators and quality inspection indicator sets The influence relationships of various quality inspection indicators are analyzed to construct a set of quality inspection indicators. Quality inspection indicator set The path of influence;

[0040] According to the quality inspection index set Quality inspection indicator set Influence path, calculation The degree of correlation.

[0041] The beneficial effects of the above-mentioned further scheme are as follows: by continuously conducting simulations, the changing trend of subsequent indicators when the preceding indicators change, the degree of convergence and divergence can be judged, and the data can be filtered according to the change threshold, which can make up for the errors caused by data collection mistakes or accidental events.

[0042] Furthermore, the indicator types include positive indicators and negative indicators; the positive indicators are those with higher values ​​indicating better quality; the negative indicators are those with higher values ​​indicating worse quality.

[0043] The beneficial effect of the above-mentioned further scheme is that the classification of indicator types prepares for the subsequent adjustment of standard thresholds.

[0044] Furthermore, the set of quality inspection indicators Quality inspection indicator set The expression for the influence path is:

[0045]

[0046] in, For quality inspection indicator set Quality inspection indicator set The path of influence; For the first The first production process One quality inspection indicator; For the first Impact of production process The set of quality inspection indicators; For the first Index of quality inspection indicators for production processes.

[0047] The beneficial effect of the above-mentioned further scheme is: to obtain the factors in the preceding process that affect each quality inspection index of the current process, so as to prepare for the calculation of the degree of influence in the subsequent process.

[0048] Furthermore, the aforementioned The expression for the degree of association is:

[0049]

[0050]

[0051] in, for The degree of correlation; For the first Quality inspection indicators for the production process of the first stage The degree of influence of the first quality inspection indicator in the production process; For the first Quality inspection indicators for the production process of the first stage The degree of influence of the second quality inspection indicator in the production process; For the first Quality inspection indicators for the production process of the first stage The first production process The degree of influence of each quality inspection indicator; For the first Quality inspection indicators for production processes The degree of impact; For the first The first production process One quality inspection indicator; for The first quality inspection indicator in China The degree of impact; For the first Impact of production process The set of quality inspection indicators; for The second quality inspection indicator in China The degree of impact; for The Middle Each quality inspection indicator The degree of impact; for Middle Each quality inspection indicator The degree of impact; for The total number of elements; This is the normalization function; for The weights; for The Middle Each quality inspection indicator The numerical value affects the mean; This represents the total number of simulations. For simulation index; for No. The simulation reached the [number]th [number]. Normalized values ​​of numerical changes from the simulation; for The Middle The first quality inspection indicator The simulation reached the [number]th [number]. Normalized values ​​of numerical changes from the simulation; for The Middle Each quality inspection indicator The numerical value affects the mean; and All The quality inspection index in the document.

[0052] The beneficial effects of the above-mentioned further scheme are as follows: the degree of correlation is used to describe the degree of influence of the influencing factors in the preceding process on the quality inspection indicators of the current process. In actual calculation, the data measurement thresholds for different indicators may be different. Therefore, normalization can unify the degree of variation into a standard, making the calculation of the degree of influence more accurate.

[0053] Furthermore, the relevant quality inspection indicators of the preceding production process are the quality inspection indicators that affect the current unqualified quality inspection indicators of the semi-finished product in each of the preceding production processes, which are determined based on the influence path.

[0054] The beneficial effect of the above-mentioned further scheme is that it prepares for the subsequent update of the standard threshold.

[0055] Furthermore, the standard thresholds for the relevant quality inspection indicators of the preceding production process are specifically as follows:

[0056] If the non-conforming quality inspection indicator of the current semi-finished product is an independent indicator item, keep the standard thresholds of all quality inspection indicators in the preceding production process unchanged; otherwise, update the standard thresholds of the relevant quality inspection indicators in the preceding production process.

[0057]

[0058] in, For the first Impact of production process Quality inspection indicator set The first in The updated standard thresholds for each quality inspection indicator; for The quality inspection index in the document; For the first Impact of production process The set of quality inspection indicators; For the first The first production process One quality inspection indicator; This is an index of non-compliant quality inspection indicators for the current semi-finished products; For the first Updated standard threshold values ​​for each quality inspection indicator; for The first in The standard thresholds for each quality inspection indicator before the update; For the first The quality inspection indicator for the first The degree of influence of each quality inspection indicator; for Each quality inspection indicator in China affects the first The average degree of influence of each quality inspection indicator; This is a threshold adjustment coefficient used to balance the deviation of the influence degree distribution; This is the scaling factor used to control the parameter tuning step size; for The value; for The standard threshold; For use in judgment and The first in If a quality inspection indicator is a binary parameter of the same type, it is 1; otherwise, it is 0. for Minimum value constraint; for Maximum value constraint.

[0059] The beneficial effects of the above-mentioned further scheme are as follows: when adjusting the standard threshold, the threshold constraints of the indicator items are taken into account, which is more in line with the actual working conditions. At the same time, the degree of influence of the influencing factors on the non-compliant indicators is taken into account during the adjustment, which makes the adjustment more accurate.

[0060] Furthermore, the independent indicator item is a quality inspection indicator item that has no influence relationship with any quality inspection indicator of any preceding production process.

[0061] The beneficial effects of the above-mentioned further solutions are: eliminating special indicator items, fully considering the correlation of process indicators, and avoiding erroneous adjustments. Attached Figure Description

[0062] Figure 1 This is a flowchart of the method of the present invention.

[0063] Figure 2 This is a line graph showing the trend of indicator changes in an embodiment of the present invention. Detailed Implementation

[0064] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0065] like Figure 1 As shown, in one embodiment of the present invention, a product quality inspection method for a smart manufacturing production line includes:

[0066] Based on the product manufacturing process, a production process library is constructed, and the quality inspection indicators for each production process in the production process library are determined.

[0067] Determine the timing of each production process, and based on the quality inspection indicators of each production process, obtain the degree of correlation between each production process;

[0068] Initialize the standard thresholds for each quality inspection indicator in each production process;

[0069] During production, after the m-th production process is completed, the current semi-finished product is tested to obtain the quality inspection index values ​​of the current semi-finished product.

[0070] The quality inspection index values ​​of the current semi-finished product are compared with the standard threshold values ​​of the quality inspection index values ​​of the m-th production process. When there is a quality inspection index that is not up to standard, the current semi-finished product is judged as a defective product and is eliminated from the production line. Based on the quality inspection results of the current semi-finished product in the (1-m)-th production process, the standard threshold values ​​of the relevant quality inspection index values ​​of the preceding production process are updated.

[0071] In this embodiment, before implementation, it is necessary to analyze the massive amount of data accumulated in the production line to determine whether there is a correlation between each process and each indicator. If there is a correlation, the threshold of the preceding correlated quality inspection indicator is determined based on the feedback of the quality inspection indicators in the subsequent process and is adjusted accordingly, so as to screen out potential unqualified products in the early stage.

[0072] The process of obtaining the correlation between various production processes specifically involves:

[0073] Based on the time sequence of each production process, construct a production process association matrix:

[0074]

[0075] in, For the production process correlation matrix; This is a self-related term for the first production process; For the first production process to the second Related items in the production process; For the first Self-related terms in the production process; This represents the total number of production processes, which are numbered sequentially based on time sequence. It is a zero matrix;

[0076] Perform several production line simulations to obtain datasets of various quality inspection indicators for each production process;

[0077] Set the correlation degree of each correlation item in the production process correlation matrix to 1;

[0078] Based on the quality inspection index datasets for each production process, calculate the first... The production process of the first Dao production process The degree of correlation; among which, and All are production process indexes. .

[0079] In this embodiment, we focus on the impact of preceding production processes on subsequent production processes. Therefore, the production process correlation matrix is ​​a triangular matrix, taking into account the temporal relationship.

[0080] The calculation The degree of correlation is as follows:

[0081] Get the Quality control indicators for the production process:

[0082]

[0083] in, For the first A set of quality inspection indicators for the production process; For the first The first quality inspection indicator in the production process; For the first The second quality inspection indicator for the production process; For the first The first production process One quality inspection indicator; For the first The total number of quality inspection indicators for each production process;

[0084] Get the Quality control indicators for the production process:

[0085]

[0086] in, For the first A set of quality inspection indicators for the production process; For the first The first quality inspection indicator in the production process; For the first The second quality inspection indicator for the production process; For the first The first production process One quality inspection indicator; For the first The total number of quality inspection indicators for each production process;

[0087] According to the quality inspection index set and quality inspection indicator set To determine the impact on quality inspection indicators:

[0088] From the set of quality inspection indicators Select quality inspection indicator B from the set of quality inspection indicators. Select quality inspection indicator C;

[0089] Based on the quality inspection index datasets for each production process, and with the production line simulation rounds as the x-axis and the quality inspection index values ​​as the y-axis, the changing trends of quality inspection index B and quality inspection index C are depicted in the same line graph (e.g., ...). Figure 2 (as shown)

[0090] If quality inspection indicator B and quality inspection indicator C are of the same type, calculate the degree of convergence of changes in quality inspection indicator B and quality inspection indicator C:

[0091]

[0092] in, The degree of convergence of changes in quality inspection indicator B and quality inspection indicator C; For quality inspection indicator B The simulation reached the [number]th [number]. The trend of the simulation is as follows: rising is 1, remaining flat is 0, and falling is -1. For quality inspection indicator C The simulation reached the [number]th [number]. The trend of the simulation is as follows: rising is 1, remaining flat is 0, and falling is -1. This represents the total number of simulations. For simulation index; This function determines whether two parameters have the same trend of change; if they do, the value is 1, otherwise it is 0.

[0093] If quality inspection indicator B and quality inspection indicator C are of different types, calculate the degree of divergence between the changes in quality inspection indicator B and quality inspection indicator C:

[0094]

[0095] in, The degree of divergence between the changes in quality inspection indicators B and C; This function determines whether the changing trends of two parameters are opposite; if they are the same, the value is 1, otherwise it is 0.

[0096] When the degree of convergence or divergence of change is greater than the change threshold, determine the first... The quality inspection index C of the production process is subject to the first The quality control index B of the production process is affected; otherwise, the judgment is made. The quality inspection index C of the production process is not affected by the first The impact of quality control index B on the production process;

[0097] Duplicate quality inspection indicators affect the judgment process; obtaining the set of quality inspection indicators is crucial. Various quality inspection indicators and quality inspection indicator sets The influence relationship of various quality inspection indicators; and based on the set of quality inspection indicators. Various quality inspection indicators and quality inspection indicator sets The influence relationships of various quality inspection indicators are analyzed to construct a set of quality inspection indicators. Quality inspection indicator set The path of influence;

[0098] According to the quality inspection index set Quality inspection indicator set Influence path, calculation The degree of correlation.

[0099] The indicator types include positive indicators and negative indicators; the positive indicators are those with higher values, indicating better quality; the negative indicators are those with higher values, indicating worse quality.

[0100] In this embodiment, not all indicators are correlated in actual working conditions, so it is necessary to analyze the changing trends of the quality inspection indicators of the preceding and subsequent processes.

[0101] The quality inspection index set Quality inspection indicator set The expression for the influence path is:

[0102]

[0103] in, For quality inspection indicator set Quality inspection indicator set The path of influence; For the first The first production process One quality inspection indicator; For the first Impact of production process The set of quality inspection indicators; For the first Index of quality inspection indicators for production processes.

[0104] The The expression for the degree of association is:

[0105]

[0106]

[0107] in, for The degree of correlation; For the first Quality inspection indicators for the production process of the first stage The degree of influence of the first quality inspection indicator in the production process; For the first Quality inspection indicators for the production process of the first stage The degree of influence of the second quality inspection indicator in the production process; For the first Quality inspection indicators for the production process of the first stage The first production process The degree of influence of each quality inspection indicator; For the first Quality inspection indicators for production processes The degree of impact; For the first The first production process One quality inspection indicator; for The first quality inspection indicator in China The degree of impact; For the first Impact of production process The set of quality inspection indicators; for The second quality inspection indicator in China The degree of impact; for The Middle Each quality inspection indicator The degree of impact; for The Middle Each quality inspection indicator The degree of impact; for The total number of elements; This is the normalization function; for The weights; for The Middle Each quality inspection indicator The numerical value affects the mean; This represents the total number of simulations. For simulation index; for No. The simulation reached the [number]th [number]. Normalized values ​​of numerical changes from the simulation; for The Middle The first quality inspection indicator The simulation reached the [number]th [number]. Normalized values ​​of numerical changes from the simulation; for The Middle Each quality inspection indicator The numerical value affects the mean; and All The quality inspection index in the document.

[0108] In this embodiment, the summation and average of the results of dividing the changes of two indices that have an influencing relationship in each simulation are performed. In a single division, when the change of index 1 is d1 and the change of index 2 is d2, since the indices are expressed in different ways—some are counted as natural numbers and some as percentages—normalization is required before dividing the two to obtain the proportional relationship between the changes of index 1 and index 2. The summation and average of multiple calculations expresses this proportional relationship more accurately.

[0109] The relevant quality inspection indicators of the preceding production process are the quality inspection indicators that affect the current unqualified quality inspection indicators of the semi-finished product in each of the preceding production processes, which are determined based on the influence path.

[0110] The standard thresholds for the relevant quality inspection indicators of the preceding production process are specifically as follows:

[0111] If the non-conforming quality inspection indicator of the current semi-finished product is an independent indicator item, keep the standard thresholds of all quality inspection indicators in the preceding production process unchanged; otherwise, update the standard thresholds of the relevant quality inspection indicators in the preceding production process.

[0112]

[0113] in, For the first Impact of production process Quality inspection indicator set The first in The updated standard thresholds for each quality inspection indicator; for The quality inspection index in the document; For the first Impact of production process The set of quality inspection indicators; For the first The first production process One quality inspection indicator; This is an index of non-compliant quality inspection indicators for the current semi-finished products; For the first Updated standard threshold values ​​for each quality inspection indicator; for The first in The standard thresholds for each quality inspection indicator before the update; For the first The quality inspection indicator for the first The degree of influence of each quality inspection indicator; for Each quality inspection indicator in China affects the first The average degree of influence of each quality inspection indicator; This is a threshold adjustment coefficient used to balance the deviation of the influence degree distribution; This is the scaling factor used to control the parameter tuning step size; for The value; for The standard threshold; For use in judgment and The first in If a quality inspection indicator is a binary parameter of the same type, it is 1; otherwise, it is 0. for Minimum value constraint; for Maximum value constraint.

[0114] In this embodiment, when a defective product occurs in a subsequent process, in order to avoid the adjustment of the indicators exceeding the range and to avoid concentrating the control risk on a single indicator, it is necessary to adjust the indicators that affect all preceding processes. With this adjustment method, the adjustment of the threshold of each indicator will be very small.

[0115] During the adjustment process, through parameters To mitigate risk, the expected adjustment for non-conforming indicators can be calculated by dividing the sum of the impacts of all relevant quality control indicators from preceding production processes on the non-conforming indicators. ;in, This represents the expected adjustment amount for non-compliant indicators; For the preceding number The degree of influence of production processes on non-conforming indicators.

[0116] In this embodiment, in actual implementation, sometimes to be on the safe side and to reduce adjustment risks, the adjustment ratio is multiplied by a coefficient greater than 0 and less than 1 for control.

[0117] The independent indicator item is a quality inspection indicator item that has no influence relationship with any quality inspection indicator of any preceding production process.

Claims

1. A product quality inspection method for an intelligent manufacturing production line, characterized in that, include: Based on the product manufacturing process, a production process library is constructed, and the quality inspection indicators for each production process in the production process library are determined. The timing of each production process is determined, and the degree of correlation between each production process is obtained based on the quality inspection indicators of each production process; specifically, obtaining the degree of correlation between each production process involves: Based on the time sequence of each production process, construct a production process association matrix: in, For the production process correlation matrix; This is a self-related term for the first production process; For the first production process to the second Related items in the production process; For the first Self-related terms in the production process; This represents the total number of production processes, which are numbered sequentially based on time sequence. It is a zero matrix; Perform several production line simulations to obtain datasets of various quality inspection indicators for each production process; Set the correlation degree of each correlation item in the production process correlation matrix to 1; Based on the quality inspection index datasets for each production process, calculate the first... The production process of the first Dao production process The degree of correlation; among which, and All are production process indexes. The calculation The degree of correlation is as follows: Get the Quality control indicators for the production process: in, For the first A set of quality inspection indicators for the production process; For the first The first quality inspection indicator in the production process; For the first The second quality inspection indicator for the production process; For the first The first production process One quality inspection indicator; For the first The total number of quality inspection indicators for each production process; Get the Quality control indicators for the production process: in, For the first A set of quality inspection indicators for the production process; For the first The first quality inspection indicator in the production process; For the first The second quality inspection indicator for the production process; For the first The first production process One quality inspection indicator; For the first The total number of quality inspection indicators for each production process; According to the quality inspection index set and quality inspection indicator set To determine the impact on quality inspection indicators: From the set of quality inspection indicators Select quality inspection indicator B from the set of quality inspection indicators. Select quality inspection indicator C; Based on the datasets of quality inspection indicators for each production process, the changing trends of quality inspection indicator B and quality inspection indicator C are depicted in the same line graph with the production line simulation round as the horizontal axis and the quality inspection indicator value as the vertical axis. If quality inspection indicator B and quality inspection indicator C are of the same type, calculate the degree of convergence of changes in quality inspection indicator B and quality inspection indicator C: in, The degree of convergence of changes in quality inspection indicator B and quality inspection indicator C; For quality inspection indicator B The simulation reached the [number]th [number]. The trend of the simulation is as follows: rising is 1, remaining flat is 0, and falling is -1. For quality inspection indicator C The simulation reached the [number]th [number]. The trend of the simulation is as follows: rising is 1, remaining flat is 0, and falling is -1. This represents the total number of simulations. For simulation index; This function determines whether two parameters have the same trend of change; if they do, the value is 1, otherwise it is 0. If quality inspection indicator B and quality inspection indicator C are of different types, calculate the degree of divergence between the changes in quality inspection indicator B and quality inspection indicator C: in, The degree of divergence between quality inspection indicators B and C; This function determines whether the changing trends of two parameters are opposite; if they are the same, the value is 1, otherwise it is 0. When the degree of convergence or divergence of change is greater than the change threshold, determine the first... The quality inspection index C of the production process is subject to the first The quality control index B of the production process is affected; otherwise, the judgment is made. The quality control index C of the production process is not affected by the first The impact of quality control index B on the production process; Duplicate quality inspection indicators affect the judgment process; obtaining the set of quality inspection indicators is crucial. Various quality inspection indicators and quality inspection indicator sets The influence relationship of various quality inspection indicators; and based on the set of quality inspection indicators. Various quality inspection indicators and quality inspection indicator sets The influence relationships of various quality inspection indicators are analyzed to construct a set of quality inspection indicators. Quality inspection indicator set The path of influence; According to the quality inspection index set Quality inspection indicator set Influence path, calculation The degree of correlation; Initialize the standard thresholds for each quality inspection indicator in each production process; During production, after the m-th production process is completed, the current semi-finished product is tested to obtain the quality inspection index values ​​of the current semi-finished product. The quality inspection index values ​​of the current semi-finished product are compared with the standard threshold values ​​of the quality inspection index values ​​of the m-th production process. When there is a quality inspection index that is not up to standard, the current semi-finished product is judged as a defective product and is eliminated from the production line. Based on the quality inspection results of the current semi-finished product in the (1-m)-th production process, the standard threshold values ​​of the relevant quality inspection index values ​​of the preceding production process are updated.

2. The product quality inspection method for the intelligent manufacturing production line according to claim 1, characterized in that, The indicator types include positive indicators and negative indicators; the positive indicators are those with higher values, indicating better quality; the negative indicators are those with higher values, indicating worse quality.

3. The product quality inspection method for the intelligent manufacturing production line according to claim 1, characterized in that, The quality inspection index set Quality inspection indicator set The expression for the influence path is: in, For quality inspection indicator set Quality inspection indicator set The path of influence; For the first The first production process One quality inspection indicator; For the first Impact of production process The set of quality inspection indicators; For the first Index of quality inspection indicators for production processes.

4. The product quality inspection method for the intelligent manufacturing production line according to claim 1, characterized in that, The The expression for the degree of association is: in, for The degree of correlation; For the first Quality inspection indicators for the production process of the first stage The degree of influence of the first quality inspection indicator in the production process; For the first Quality inspection indicators for the production process of the first stage The degree of influence of the second quality inspection indicator in the production process; For the first Quality inspection indicators for the production process of the first stage The first production process The degree of influence of each quality inspection indicator; For the first Quality inspection indicators for production processes The degree of impact; For the first The first production process One quality inspection indicator; for The first quality inspection indicator in China The degree of impact; For the first Impact of production process The set of quality inspection indicators; for The second quality inspection indicator in China The degree of impact; for The Middle Each quality inspection indicator The degree of impact; for The Middle Each quality inspection indicator The degree of impact; for The total number of elements; This is the normalization function; for The weights; for The Middle Each quality inspection indicator The numerical value affects the mean; This represents the total number of simulations. For simulation index; for No. The simulation reached the [number]th [number]. Normalized values ​​of numerical changes from the simulation; for The Middle The first quality inspection indicator The simulation reached the [number]th [number]. Normalized values ​​of numerical changes from the simulation; for The Middle Each quality inspection indicator The numerical value affects the mean; and All The quality inspection index in the document.

5. The product quality inspection method for the intelligent manufacturing production line according to claim 1, characterized in that, The relevant quality inspection indicators of the preceding production process are the quality inspection indicators that affect the current unqualified quality inspection indicators of the semi-finished product in each of the preceding production processes, which are determined based on the influence path.

6. The product quality inspection method for the intelligent manufacturing production line according to claim 1, characterized in that, The standard thresholds for the relevant quality inspection indicators of the preceding production process are specifically as follows: If the non-conforming quality inspection indicator of the current semi-finished product is an independent indicator item, keep the standard thresholds of all quality inspection indicators in the preceding production process unchanged; otherwise, update the standard thresholds of the relevant quality inspection indicators in the preceding production process. in, For the first Impact of production process Quality inspection indicator set The first in The updated standard thresholds for each quality inspection indicator; for The quality inspection index in the document; For the first Impact of production process The set of quality inspection indicators; For the first The first production process One quality inspection indicator; This is an index of non-compliant quality inspection indicators for the current semi-finished products; For the first Updated standard threshold values ​​for each quality inspection indicator; for The first in The standard thresholds for each quality inspection indicator before the update; For the first The quality inspection indicator for the first The degree of influence of each quality inspection indicator; for Each quality inspection indicator in China affects the first The average degree of influence of each quality inspection indicator; This is a threshold adjustment coefficient used to balance the deviation of the influence degree distribution; This is the scaling factor used to control the parameter tuning step size; for The value; for The standard threshold; For use in judgment and The first in If a quality inspection indicator is a binary parameter of the same type, it is 1; otherwise, it is 0. for Minimum value constraint; for Maximum value constraint.

7. The product quality inspection method for the intelligent manufacturing production line according to claim 6, characterized in that, The independent indicator item is a quality inspection indicator item that has no influence relationship with any quality inspection indicator of any preceding production process.

Images