CN116611679A - Electronic component production data management system and method based on artificial intelligence - Google Patents
Electronic component production data management system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN116611679A CN116611679A CN202310902304.6A CN202310902304A CN116611679A CN 116611679 A CN116611679 A CN 116611679A CN 202310902304 A CN202310902304 A CN 202310902304A CN 116611679 A CN116611679 A CN 116611679A
- Authority
- CN
- China
- Prior art keywords
- deviation
- value
- data
- production
- electronic component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 196
- 238000000034 method Methods 0.000 title claims abstract description 145
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 34
- 238000013523 data management Methods 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000007726 management method Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims description 56
- 239000011159 matrix material Substances 0.000 claims description 44
- 238000012545 processing Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000012797 qualification Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 229910021421 monocrystalline silicon Inorganic materials 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 230000002087 whitening effect Effects 0.000 claims description 3
- 238000012986 modification Methods 0.000 abstract description 4
- 230000004048 modification Effects 0.000 abstract description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000012937 correction Methods 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an electronic component production data management system and method based on artificial intelligence, and belongs to the technical field of electronic component production data management. The system comprises a production process flow list management module, a deviation value early warning module, an artificial intelligent analysis module, a data marking module and an electronic component production regulation module; the output end of the production procedure flow list management module is connected with the input end of the deviation value early warning module; the output end of the deviation value early warning module is connected with the input end of the artificial intelligent analysis module; the output end of the artificial intelligent analysis module is connected with the input end of the data marking module; and the output end of the data marking module is connected with the input end of the electronic component production adjusting module. The invention can analyze the subsequent influence in an artificial intelligence mode based on the preamble deviation in the production process of the electronic components, unify the flow modification parameters and improve the working efficiency.
Description
Technical Field
The invention relates to the technical field of electronic component production data management, in particular to an electronic component production data management system and method based on artificial intelligence.
Background
The electronic component is a finished product which does not change the molecular composition during factory production and processing. The integrated circuit is a special electronic component, and is one of the most important electronic components at present, and the integrated circuit is a device with a certain function, which is formed by integrating elements such as a transistor, a resistor, a capacitor and the like on a silicon substrate by adopting a special process. Small scale integrated circuits typically include basic logic gates, flip-flops, registers, decoders, drivers, counters, shaping circuits, programmable logic devices, microprocessors, singlechips, DSPs, etc.
In the production process of integrated circuits, each process generally comprises a plurality of processes, each process has a test standard, in the current industry production, generally after each process is finished, if a correction deviation is found, the production parameters of the next process are adjusted to ensure that the deviation can be reduced when the next process is finished, but in practice, the influence of a plurality of deviations is usually shown after a plurality of processes, the influence of the smaller deviation on the actual working condition is not great, and at present, the analysis of the initial deviation and the influence of the initial deviation on the subsequent production are lacked, so that the work is heavy and the efficiency is low.
Disclosure of Invention
The invention aims to provide an electronic component production data management system and method based on artificial intelligence, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an electronic component production data management method based on artificial intelligence, the method comprises the following steps:
s1, acquiring an electronic component production process flow, marking each production process as a data node, and acquiring an electronic component production process standard value of each data node, wherein the standard value refers to a system qualification test value of the electronic component production process;
s2, acquiring an actual value of the initial data node, calculating a deviation value formed by the actual value and a standard value, setting a deviation threshold value, if the deviation value is not higher than the deviation threshold value, carrying out a next production process queue, and if the deviation value is higher than the deviation value, alarming to an administrator port; s3, acquiring a normal deviation value and a deviation influence value of each data node under historical data, wherein the normal deviation value refers to a deviation value of an adjacent next process when a previous process ends with a standard value, and the deviation influence value refers to a deviation value of an adjacent next process when the previous process ends with the deviation value, so as to construct a deviation analysis model between the adjacent production processes;
s4, obtaining deviation values of initial data nodes in different batches, generating deviation values of all subsequent production procedures according to a deviation analysis model, and marking a production line and the data nodes corresponding to the deviation threshold value exceeding the first occurrence if the deviation value of any subsequent production procedure exceeds the set deviation threshold value;
s5, collecting the marked times of the data nodes, sequencing the data nodes according to the sequence from more to less, adjusting production queues of different batches, constructing a set of production lines marked by the same data node, and adjusting corresponding data node parameters when electronic component production is carried out on the production lines in the set, so as to ensure that deviation values output by all the production lines in the set meet deviation thresholds.
According to the above technical solution, the deviation value refers to an absolute value of a difference between an actual value and a standard value, and the method includes the steps of: monocrystalline silicon wafer manufacturing, IC design, photomask manufacturing, IC testing and packaging, after each procedure is finished, obtaining each actual parameter of the electronic component, and calculating an output deviation value according to the following mode:
wherein P represents an offset value;representing the actual value of the electronic component parameter i; />Representing the standard value of the electronic component parameter i; n represents the total amount of parameters of the electronic components involved in the test.
In the above technical solution, a calculation manner of the deviation value is provided, and because each actual parameter of the electronic component may be different from the standard value, the deviation value is actually calculated by using a deviation sum, and in the actual calculation process, a sum average value may also be adopted.
According to the above technical solution, the deviation analysis model includes: acquiring a normal deviation value and a deviation influence value of each data node under historical data, wherein the normal deviation value is marked as W, and the deviation influence value is marked as M;
selecting j groups of normal deviation values from the historical data, calculating the average value of the normal deviation values and marking the average value as W avc The method comprises the steps of carrying out a first treatment on the surface of the Selecting T groups of deviation influence values under the same process and the deviation value of the previous process corresponding to the deviation influence values, and calculating the deviation influence value and W avc The difference value of the two components is combined with the deviation value of the last procedure corresponding to the deviation influence value to form a combined queue [ W ] K ,M K ]The method comprises the steps of carrying out a first treatment on the surface of the Wherein W is K The deviation value of the previous process corresponding to the deviation influence value is indicated; m is M K Index deviation influence value and W avc A difference between them; k refers to a serial number label, and the value range is [1, T]；
Obtaining T groups of combined queues to form a data matrix:
calculating a covariance matrix for the data matrix R:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing a covariance matrix; />Representing an inverse matrix;
for covariance matrix Q, use the eigen equationWherein->Is characteristic value (I)>Is a unit matrix; calculated to obtainCharacteristic value->The method comprises the steps of carrying out a first treatment on the surface of the Each characteristic value +.>Substitution of the characteristic equation +.>Obtaining a corresponding characteristic vector x under each characteristic value; in the technical scheme, the data matrix is in a multi-dimensional form, the data are mutually influenced, the direct analysis can lead to data overfitting, the data result is chaotic, the data is required to be reduced to a one-dimensional level for processing, the data matrix is converted by utilizing the characteristic value and the characteristic vector, the next layer of data after the conversion is analyzed, and the prediction deviation of the current process can be correspondingly obtained according to the available previous process deviation. In the calculation process of each procedure, the initial deviation is actually generated, and each subsequent previous procedure deviation is a predicted deviation adopting a preamble.
Sorting the characteristic values from large to small, selecting the largest L characteristic vectors, and then respectively taking the corresponding characteristic vectors as row vectors to form a characteristic vector matrix F; wherein L is a constant set for the system, and the total number of the corresponding feature vectors does not exceed T when L is satisfied;
multiplying the data matrix R by the first row of the eigenvector matrix F to output a converted data matrix R1；
Outputting data in gray prediction mode according to the data in the data matrix R1As the next converted data value of the current process;
the method comprises the following specific steps:
data processing is carried out on the data in the data matrix R1 to generate R2 and R3 data sets; the data processing comprises gray accumulation and immediate mean value, wherein R2 is a gray accumulated data set, and R3 is a data set which is immediately adjacent to the mean value on the basis of R2;
wherein the method comprises the steps ofThe calculation includes:
wherein e represents a natural logarithm;the development coefficient and the ash action quantity in the whitening differential equation of R2 are respectively; according to the calculated->Is fed back to the data matrix R according to the formed combined queue W T+1 Output M T+1 Calculate M T+1 And W is equal to avc And as a deviation value under the current process.
According to the above technical solution, in step S4, further includes:
forming a current process deviation value corresponding to the deviation value of each production process based on the previous process according to the deviation analysis model;
obtaining the deviation values of initial data nodes in different batches, sequentially generating the deviation values of all subsequent production processes according to a deviation analysis model, and marking a production line and the data nodes corresponding to the deviation threshold value exceeding for the first time if the deviation value of any subsequent production process exceeds the set deviation threshold value.
An electronic component production data management system based on artificial intelligence, the system comprising: the system comprises a production process flow list management module, a deviation value early warning module, an artificial intelligent analysis module, a data marking module and an electronic component production adjusting module;
the production procedure list management module is used for acquiring the production procedure of the electronic component, marking each production procedure as a data node and acquiring the standard value of the production procedure of the electronic component of each data node; the deviation value early warning module is used for acquiring an actual value of the initial data node, calculating a deviation value formed by the actual value and a standard value, setting a deviation threshold, carrying out a next production process queue if the deviation threshold is not higher than the deviation threshold, and alarming to an administrator port if the deviation threshold is higher than the deviation value; the artificial intelligent analysis module is used for acquiring the normal deviation value and the deviation influence value of each data node under the historical data and constructing a deviation analysis model between adjacent production procedures; the data marking module is used for obtaining the deviation values of the initial data nodes in different batches, generating the deviation values of all subsequent production procedures according to the deviation analysis model, and marking the production line and the data nodes corresponding to the deviation threshold value exceeding the first occurrence if the deviation value of any subsequent production procedure exceeds the set deviation threshold value; the electronic component production regulation module is used for collecting the marked times of the data nodes, sequencing the data nodes according to the sequence from more to less, regulating the production queues of different batches, constructing a set of production lines marked by the same data node, regulating corresponding data node parameters when the production lines in the set are used for producing electronic components, and ensuring that the deviation values output by all the production lines in the set meet the deviation threshold;
the output end of the production procedure flow list management module is connected with the input end of the deviation value early warning module; the output end of the deviation value early warning module is connected with the input end of the artificial intelligent analysis module; the output end of the artificial intelligent analysis module is connected with the input end of the data marking module; and the output end of the data marking module is connected with the input end of the electronic component production adjusting module.
According to the technical scheme, the production procedure flow list management module comprises a flow marking unit and a standard value processing unit;
the flow marking unit is used for obtaining the flow of the production procedure of the electronic component and marking each production procedure as a data node; the standard value processing unit is used for obtaining the standard value of the electronic component production process of each data node, and the standard value refers to the system qualification test value of the electronic component production process;
the output end of the flow marking unit is connected with the input end of the standard value processing unit.
According to the technical scheme, the deviation value early-warning module comprises a calculating unit and a data early-warning unit;
the calculating unit is used for obtaining the actual value of the initial data node and calculating the deviation value formed by the actual value and the standard value; the data early warning unit is used for setting a deviation threshold, if the deviation threshold is not higher than the deviation threshold, carrying out the next production process queue, and if the deviation threshold is higher than the deviation value, alarming to an administrator port;
the output end of the computing unit is connected with the input end of the data early warning unit.
According to the technical scheme, the artificial intelligence analysis module comprises an artificial intelligence analysis unit and a model construction unit;
the artificial intelligence analysis unit is used for acquiring a normal deviation value and a deviation influence value of each data node under the historical data, wherein the normal deviation value refers to a deviation value of an adjacent next process when a previous process ends with a standard value, and the deviation influence value refers to a deviation value of the adjacent next process when the previous process ends with the deviation value; the model construction unit constructs a deviation analysis model between adjacent production procedures based on the normal deviation value and the deviation influence value under the historical data;
the output end of the artificial intelligence analysis unit is connected with the input end of the model building unit.
According to the technical scheme, the data marking module comprises a data acquisition unit and a node marking unit;
the data acquisition unit is used for acquiring deviation values of initial data nodes in different batches; the node marking unit generates deviation values of all subsequent production procedures according to the deviation analysis model, and marks the production line and the data node corresponding to the deviation threshold value when the deviation value of any subsequent production procedure exceeds the set deviation threshold value;
the output end of the data acquisition unit is connected with the input end of the node marking unit.
According to the technical scheme, the electronic component production adjusting module comprises a sequencing unit and an adjusting unit;
the sorting unit is used for collecting the marked times of the data nodes and sorting the data nodes according to the sequence from more to less; the adjusting unit is used for adjusting production queues of different batches, constructing a set of production lines with the same data node marked, adjusting corresponding data node parameters when electronic component production is carried out on the production lines in the set, and ensuring that deviation values output by all the production lines in the set meet deviation thresholds;
the output end of the sequencing unit is connected with the input end of the adjusting unit.
Compared with the prior art, the invention has the following beneficial effects: the invention can solve the problem of multiple correction in the current industry production, analyze the initial deviation of the production process, propose the influence of the initial deviation on the subsequent production, analyze the subsequent influence in an artificial intelligence form based on the preamble deviation in the production process of electronic components, collect the production lines with the same influence, unify the flow modification parameters and improve the working efficiency.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic flow chart of an electronic component production data management system and method based on artificial intelligence.
Description of the embodiments
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, in a first embodiment, an electronic component production data management method based on artificial intelligence is provided, an electronic component production process flow is obtained, each production process is marked as a data node, and an electronic component production process standard value of each data node is obtained, wherein the standard value refers to a system qualification test value of the electronic component production process; acquiring an actual value of an initial data node, calculating a deviation value formed by the actual value and a standard value, setting a deviation threshold, if the deviation threshold is not higher than the deviation threshold, carrying out a next production process queue, and if the deviation threshold is higher than the deviation value, alarming to an administrator port;
the deviation value refers to an absolute value of a difference between an actual value and a standard value, and in this embodiment, integrated circuit production is taken as an example: the method comprises the following steps: monocrystalline silicon wafer manufacturing, IC design, photomask manufacturing, IC testing and packaging, after each procedure is finished, obtaining each actual parameter of the electronic component, and calculating an output deviation value according to the following mode:
wherein P represents an offset value;representing the actual value of the electronic component parameter i; />Representing the standard value of the electronic component parameter i; n represents the total amount of parameters of the electronic components involved in the test;
building a deviation analysis model:
acquiring a normal deviation value and a deviation influence value of each data node under historical data, wherein the normal deviation value is marked as W, and the deviation influence value is marked as M;
selecting j groups of normal deviation values from the historical data, calculating the average value of the normal deviation values and marking the average value as W avc The method comprises the steps of carrying out a first treatment on the surface of the Selecting T groups of deviation influence values under the same process and the deviation value of the previous process corresponding to the deviation influence values, and calculating the deviation influence value and W avc Difference between, binding pairThe deviation value of the previous process to which the deviation influence value should be applied forms a combined queue [ W ] K ,M K ]The method comprises the steps of carrying out a first treatment on the surface of the Wherein W is K The deviation value of the previous process corresponding to the deviation influence value is indicated; m is M K Index deviation influence value and W avc A difference between them; k refers to a serial number label, and the value range is [1, T]；
Obtaining T groups of combined queues to form a data matrix:
calculating a covariance matrix for the data matrix R:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing a covariance matrix; />Representing an inverse matrix;
for covariance matrix Q, use the eigen equationWherein->Is characteristic value (I)>Is a unit matrix; calculating to obtain characteristic value->The method comprises the steps of carrying out a first treatment on the surface of the Each characteristic value +.>Substitution of the characteristic equation +.>Obtaining a corresponding characteristic vector x under each characteristic value; the feature values are ordered from big to small, the largest L of the feature values are selected,then, respectively taking the corresponding eigenvectors as row vectors to form an eigenvector matrix F; wherein L is a constant set for the system, and the total number of the corresponding feature vectors does not exceed T when L is satisfied;
multiplying the data matrix R by the first row of the eigenvector matrix F to output a converted data matrix R1；
Outputting data in gray prediction mode according to the data in the data matrix R1As the next converted data value of the current process;
the method comprises the following specific steps:
data processing is carried out on the data in the data matrix R1 to generate R2 and R3 data sets; the data processing comprises gray accumulation and immediate mean value, wherein R2 is a gray accumulated data set, and R3 is a data set which is immediately adjacent to the mean value on the basis of R2;
wherein the method comprises the steps ofThe calculation includes:
wherein e represents a natural logarithm;the development coefficient and the ash action quantity in the whitening differential equation of R2 are respectively;
according to calculationsIs fed back to the data matrix R according to the formed combined queue W T+1 Output M T+1 Calculate M T+1 And W is equal to avc And as a deviation value under the current process.
Forming a current process deviation value corresponding to the deviation value of each production process based on the previous process according to the deviation analysis model;
obtaining the deviation values of initial data nodes in different batches, sequentially generating the deviation values of all subsequent production processes according to a deviation analysis model, and marking a production line and the data nodes corresponding to the deviation threshold value exceeding for the first time if the deviation value of any subsequent production process exceeds the set deviation threshold value. The method comprises the steps of collecting the marked times of data nodes, sequencing the data nodes according to the sequence from more to less, adjusting production queues of different batches, constructing a set of production lines marked by the same data node, and adjusting corresponding data node parameters when electronic component production is carried out on the production lines in the set, so that the deviation values output by all the production lines in the set are ensured to meet a deviation threshold.
In a second embodiment, an electronic component production data management system based on artificial intelligence is provided, the system including: the system comprises a production process flow list management module, a deviation value early warning module, an artificial intelligent analysis module, a data marking module and an electronic component production adjusting module;
the production procedure list management module is used for acquiring the production procedure of the electronic component, marking each production procedure as a data node and acquiring the standard value of the production procedure of the electronic component of each data node; the deviation value early warning module is used for acquiring an actual value of the initial data node, calculating a deviation value formed by the actual value and a standard value, setting a deviation threshold, carrying out a next production process queue if the deviation threshold is not higher than the deviation threshold, and alarming to an administrator port if the deviation threshold is higher than the deviation value; the artificial intelligent analysis module is used for acquiring the normal deviation value and the deviation influence value of each data node under the historical data and constructing a deviation analysis model between adjacent production procedures; the data marking module is used for obtaining the deviation values of the initial data nodes in different batches, generating the deviation values of all subsequent production procedures according to the deviation analysis model, and marking the production line and the data nodes corresponding to the deviation threshold value exceeding the first occurrence if the deviation value of any subsequent production procedure exceeds the set deviation threshold value; the electronic component production regulation module is used for collecting the marked times of the data nodes, sequencing the data nodes according to the sequence from more to less, regulating the production queues of different batches, constructing a set of production lines marked by the same data node, regulating corresponding data node parameters when the production lines in the set are used for producing electronic components, and ensuring that the deviation values output by all the production lines in the set meet the deviation threshold;
the output end of the production procedure flow list management module is connected with the input end of the deviation value early warning module; the output end of the deviation value early warning module is connected with the input end of the artificial intelligent analysis module; the output end of the artificial intelligent analysis module is connected with the input end of the data marking module; and the output end of the data marking module is connected with the input end of the electronic component production adjusting module.
The production procedure flow list management module comprises a flow marking unit and a standard value processing unit;
the flow marking unit is used for obtaining the flow of the production procedure of the electronic component and marking each production procedure as a data node; the standard value processing unit is used for obtaining the standard value of the electronic component production process of each data node, and the standard value refers to the system qualification test value of the electronic component production process;
the output end of the flow marking unit is connected with the input end of the standard value processing unit.
The deviation value early warning module comprises a calculation unit and a data early warning unit;
the calculating unit is used for obtaining the actual value of the initial data node and calculating the deviation value formed by the actual value and the standard value; the data early warning unit is used for setting a deviation threshold, if the deviation threshold is not higher than the deviation threshold, carrying out the next production process queue, and if the deviation threshold is higher than the deviation value, alarming to an administrator port;
the output end of the computing unit is connected with the input end of the data early warning unit.
The artificial intelligence analysis module comprises an artificial intelligence analysis unit and a model construction unit;
the artificial intelligence analysis unit is used for acquiring a normal deviation value and a deviation influence value of each data node under the historical data, wherein the normal deviation value refers to a deviation value of an adjacent next process when a previous process ends with a standard value, and the deviation influence value refers to a deviation value of the adjacent next process when the previous process ends with the deviation value; the model construction unit constructs a deviation analysis model between adjacent production procedures based on the normal deviation value and the deviation influence value under the historical data;
the output end of the artificial intelligence analysis unit is connected with the input end of the model building unit.
The data marking module comprises a data acquisition unit and a node marking unit;
the data acquisition unit is used for acquiring deviation values of initial data nodes in different batches; the node marking unit generates deviation values of all subsequent production procedures according to the deviation analysis model, and marks the production line and the data node corresponding to the deviation threshold value when the deviation value of any subsequent production procedure exceeds the set deviation threshold value;
the output end of the data acquisition unit is connected with the input end of the node marking unit.
The electronic component production adjusting module comprises a sequencing unit and an adjusting unit;
the sorting unit is used for collecting the marked times of the data nodes and sorting the data nodes according to the sequence from more to less; the adjusting unit is used for adjusting production queues of different batches, constructing a set of production lines with the same data node marked, adjusting corresponding data node parameters when electronic component production is carried out on the production lines in the set, and ensuring that deviation values output by all the production lines in the set meet deviation thresholds;
the output end of the sequencing unit is connected with the input end of the adjusting unit.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An electronic component production data management method based on artificial intelligence is characterized in that: the method comprises the following steps:
s1, acquiring an electronic component production process flow, marking each production process as a data node, and acquiring an electronic component production process standard value of each data node, wherein the standard value refers to a system qualification test value of the electronic component production process;
s2, acquiring an actual value of the initial data node, calculating a deviation value formed by the actual value and a standard value, setting a deviation threshold value, if the deviation value is not higher than the deviation threshold value, carrying out a next production process queue, and if the deviation value is higher than the deviation value, alarming to an administrator port;
s3, acquiring a normal deviation value and a deviation influence value of each data node under historical data, wherein the normal deviation value refers to a deviation value of an adjacent next process when a previous process ends with a standard value, and the deviation influence value refers to a deviation value of an adjacent next process when the previous process ends with the deviation value, so as to construct a deviation analysis model between the adjacent production processes;
s4, obtaining deviation values of initial data nodes in different batches, generating deviation values of all subsequent production procedures according to a deviation analysis model, and marking a production line and the data nodes corresponding to the deviation threshold value exceeding the first occurrence if the deviation value of any subsequent production procedure exceeds the set deviation threshold value;
s5, collecting the marked times of the data nodes, sequencing the data nodes according to the sequence from more to less, adjusting production queues of different batches, constructing a set of production lines marked by the same data node, and adjusting corresponding data node parameters when electronic component production is carried out on the production lines in the set, so as to ensure that deviation values output by all the production lines in the set meet deviation thresholds.
2. The electronic component production data management method based on artificial intelligence according to claim 1, wherein: the deviation value refers to an absolute value of a difference between an actual value and a standard value, and the method comprises the following steps of: monocrystalline silicon wafer manufacturing, IC design, photomask manufacturing, IC testing and packaging, after each procedure is finished, obtaining each actual parameter of the electronic component, and calculating an output deviation value according to the following mode:wherein P represents an offset value; />Representing the actual value of the electronic component parameter i; />Representing the standard value of the electronic component parameter i; n represents the total amount of parameters of the electronic components involved in the test.
3. An electronic component production data management method based on artificial intelligence according to claim 2, characterized in that: the bias analysis model includes: acquiring a normal deviation value and a deviation influence value of each data node under historical data, wherein the normal deviation value is marked as W, and the deviation influence value is marked as M;
selecting j groups of normal deviation values from the historical data, calculating the average value of the normal deviation values and marking the average value as W avc The method comprises the steps of carrying out a first treatment on the surface of the Selecting T groups of deviation influence values under the same process and the deviation value of the previous process corresponding to the deviation influence values, and calculating the deviation influence value and W avc The difference value of the two components is combined with the deviation value of the last procedure corresponding to the deviation influence value to form a combined queue [ W ] K ,M K ]The method comprises the steps of carrying out a first treatment on the surface of the Wherein W is K The deviation value of the previous process corresponding to the deviation influence value is indicated; m is M K Index deviation influence value and W avc A difference between them; k refers to a serial number label, and the value range is [1, T]；
Obtaining T groups of combined queues to form a data matrix:
calculating a covariance matrix for the data matrix R: />Wherein (1)>Representing a covariance matrix; />Representing an inverse matrix; for covariance matrix Q, use the characteristic equation +.>Wherein->Is characteristic value (I)>Is a unit matrix; calculating to obtain characteristic value->The method comprises the steps of carrying out a first treatment on the surface of the Each characteristic value +.>Substitution of the characteristic equation +.>In x=0, a corresponding feature vector x under each feature value is obtained;
sorting the characteristic values from large to small, selecting the largest L characteristic vectors, and then respectively taking the corresponding characteristic vectors as row vectors to form a characteristic vector matrix F; wherein L is a constant set for the system, and the total number of the corresponding feature vectors does not exceed T when L is satisfied; multiplying the data matrix R by the first row of the eigenvector matrix F to output a converted data matrix R1；
Outputting data in gray prediction mode according to the data in the data matrix R1As the next converted data value of the current process;
the method comprises the following specific steps:
data processing is carried out on the data in the data matrix R1 to generate R2 and R3 data sets; the data processing comprises gray accumulation and immediate mean value, wherein R2 is a gray accumulated data set, and R3 is a data set which is immediately adjacent to the mean value on the basis of R2;
wherein the method comprises the steps ofThe calculation includes: />Wherein e represents a natural logarithm; />Development coefficients in the whitening differential equation for R2, respectively, ashAn amount of action;
according to calculationsIs fed back to the data matrix R according to the formed combined queue W T+1 Output M T+1 Calculate M T+1 And W is equal to avc And as a deviation value under the current process.
4. An electronic component production data management method based on artificial intelligence according to claim 3, wherein: in step S4, further comprising:
forming a current process deviation value corresponding to the deviation value of each production process based on the previous process according to the deviation analysis model; obtaining the deviation values of initial data nodes in different batches, sequentially generating the deviation values of all subsequent production processes according to a deviation analysis model, and marking a production line and the data nodes corresponding to the deviation threshold value exceeding for the first time if the deviation value of any subsequent production process exceeds the set deviation threshold value.
5. An electronic component production data management system based on artificial intelligence, which is characterized in that: the system comprises: the system comprises a production process flow list management module, a deviation value early warning module, an artificial intelligent analysis module, a data marking module and an electronic component production adjusting module;
the production procedure list management module is used for acquiring the production procedure of the electronic component, marking each production procedure as a data node and acquiring the standard value of the production procedure of the electronic component of each data node; the deviation value early warning module is used for acquiring an actual value of the initial data node, calculating a deviation value formed by the actual value and a standard value, setting a deviation threshold, carrying out a next production process queue if the deviation threshold is not higher than the deviation threshold, and alarming to an administrator port if the deviation threshold is higher than the deviation value; the artificial intelligent analysis module is used for acquiring the normal deviation value and the deviation influence value of each data node under the historical data and constructing a deviation analysis model between adjacent production procedures; the data marking module is used for obtaining the deviation values of the initial data nodes in different batches, generating the deviation values of all subsequent production procedures according to the deviation analysis model, and marking the production line and the data nodes corresponding to the deviation threshold value exceeding the first occurrence if the deviation value of any subsequent production procedure exceeds the set deviation threshold value; the electronic component production regulation module is used for collecting the marked times of the data nodes, sequencing the data nodes according to the sequence from more to less, regulating the production queues of different batches, constructing a set of production lines marked by the same data node, regulating corresponding data node parameters when the production lines in the set are used for producing electronic components, and ensuring that the deviation values output by all the production lines in the set meet the deviation threshold;
the output end of the production procedure flow list management module is connected with the input end of the deviation value early warning module; the output end of the deviation value early warning module is connected with the input end of the artificial intelligent analysis module; the output end of the artificial intelligent analysis module is connected with the input end of the data marking module; and the output end of the data marking module is connected with the input end of the electronic component production adjusting module.
6. An artificial intelligence based electronic component production data management system according to claim 5, wherein: the production procedure flow list management module comprises a flow marking unit and a standard value processing unit;
the flow marking unit is used for obtaining the flow of the production procedure of the electronic component and marking each production procedure as a data node; the standard value processing unit is used for obtaining the standard value of the electronic component production process of each data node, and the standard value refers to the system qualification test value of the electronic component production process;
the output end of the flow marking unit is connected with the input end of the standard value processing unit.
7. An artificial intelligence based electronic component production data management system according to claim 5, wherein: the deviation value early warning module comprises a calculation unit and a data early warning unit;
the calculating unit is used for obtaining the actual value of the initial data node and calculating the deviation value formed by the actual value and the standard value; the data early warning unit is used for setting a deviation threshold, if the deviation threshold is not higher than the deviation threshold, carrying out the next production process queue, and if the deviation threshold is higher than the deviation value, alarming to an administrator port;
the output end of the computing unit is connected with the input end of the data early warning unit.
8. An artificial intelligence based electronic component production data management system according to claim 5, wherein: the artificial intelligence analysis module comprises an artificial intelligence analysis unit and a model construction unit;
the artificial intelligence analysis unit is used for acquiring a normal deviation value and a deviation influence value of each data node under the historical data, wherein the normal deviation value refers to a deviation value of an adjacent next process when a previous process ends with a standard value, and the deviation influence value refers to a deviation value of the adjacent next process when the previous process ends with the deviation value; the model construction unit constructs a deviation analysis model between adjacent production procedures based on the normal deviation value and the deviation influence value under the historical data;
the output end of the artificial intelligence analysis unit is connected with the input end of the model building unit.
9. An artificial intelligence based electronic component production data management system according to claim 5, wherein: the data marking module comprises a data acquisition unit and a node marking unit;
the data acquisition unit is used for acquiring deviation values of initial data nodes in different batches; the node marking unit generates deviation values of all subsequent production procedures according to the deviation analysis model, and marks the production line and the data node corresponding to the deviation threshold value when the deviation value of any subsequent production procedure exceeds the set deviation threshold value;
the output end of the data acquisition unit is connected with the input end of the node marking unit.
10. An artificial intelligence based electronic component production data management system according to claim 5, wherein: the electronic component production adjusting module comprises a sequencing unit and an adjusting unit;
the sorting unit is used for collecting the marked times of the data nodes and sorting the data nodes according to the sequence from more to less; the adjusting unit is used for adjusting production queues of different batches, constructing a set of production lines with the same data node marked, adjusting corresponding data node parameters when electronic component production is carried out on the production lines in the set, and ensuring that deviation values output by all the production lines in the set meet deviation thresholds;
the output end of the sequencing unit is connected with the input end of the adjusting unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310902304.6A CN116611679B (en) | 2023-07-21 | 2023-07-21 | Electronic component production data management system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310902304.6A CN116611679B (en) | 2023-07-21 | 2023-07-21 | Electronic component production data management system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116611679A true CN116611679A (en) | 2023-08-18 |
| CN116611679B CN116611679B (en) | 2024-01-16 |
Family
ID=87676903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310902304.6A Active CN116611679B (en) | 2023-07-21 | 2023-07-21 | Electronic component production data management system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116611679B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108490902A (en) * | 2018-04-24 | 2018-09-04 | 长春北方化工灌装设备股份有限公司 | Control parameter based on successive type production task reviews one's lessons by oneself normal operation method |
| CN109697571A (en) * | 2018-12-28 | 2019-04-30 | 龙岩烟草工业有限责任公司 | Product quality analysis method, apparatus and storage medium |
| CN115328054A (en) * | 2022-08-23 | 2022-11-11 | 大连优米兴创信息软件开发有限公司 | Intelligent manufacturing industrial software debugging system based on cloud computing |
| CN115421982A (en) * | 2022-09-28 | 2022-12-02 | 惠州市华达通气体制造股份有限公司 | Industrial production data backup method and device and server |
| CN116295172A (en) * | 2023-05-15 | 2023-06-23 | 湖南隆深氢能科技有限公司 | Method, system, terminal equipment and storage medium for detecting membrane electrode production line |
| CN116341771A (en) * | 2023-05-30 | 2023-06-27 | 江苏鹏润电缆科技有限公司 | Intelligent optimization method and system for low-temperature-resistant cable production process |
| CN116339262A (en) * | 2023-03-30 | 2023-06-27 | 昆山名禾精密模具有限公司 | Numerical control processing production quality monitoring system based on artificial intelligence |
-
2023
- 2023-07-21 CN CN202310902304.6A patent/CN116611679B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108490902A (en) * | 2018-04-24 | 2018-09-04 | 长春北方化工灌装设备股份有限公司 | Control parameter based on successive type production task reviews one's lessons by oneself normal operation method |
| CN109697571A (en) * | 2018-12-28 | 2019-04-30 | 龙岩烟草工业有限责任公司 | Product quality analysis method, apparatus and storage medium |
| CN115328054A (en) * | 2022-08-23 | 2022-11-11 | 大连优米兴创信息软件开发有限公司 | Intelligent manufacturing industrial software debugging system based on cloud computing |
| CN115421982A (en) * | 2022-09-28 | 2022-12-02 | 惠州市华达通气体制造股份有限公司 | Industrial production data backup method and device and server |
| CN116339262A (en) * | 2023-03-30 | 2023-06-27 | 昆山名禾精密模具有限公司 | Numerical control processing production quality monitoring system based on artificial intelligence |
| CN116295172A (en) * | 2023-05-15 | 2023-06-23 | 湖南隆深氢能科技有限公司 | Method, system, terminal equipment and storage medium for detecting membrane electrode production line |
| CN116341771A (en) * | 2023-05-30 | 2023-06-27 | 江苏鹏润电缆科技有限公司 | Intelligent optimization method and system for low-temperature-resistant cable production process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116611679B (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110609531A (en) | Workshop scheduling method based on digital twin | |
| CN111428201B (en) | Prediction method for time series data based on empirical mode decomposition and feedforward neural network | |
| US20090185493A1 (en) | Hierarchical and Incremental Multivariate Analysis for Process Control | |
| CN110008551B (en) | Resistance model and extraction method thereof | |
| DE102017111926A1 (en) | Process control circuit and method for controlling a processing arrangement | |
| CN111177970B (en) | Multi-stage semiconductor process virtual metering method based on Gaussian process and convolutional neural network | |
| DE112007000868T5 (en) | Timed moving average filter | |
| US7873501B2 (en) | Crack growth evaluation apparatus, crack growth evaluation method, and recording medium recording crack growth evaluation program | |
| CN101424919A (en) | Rescheduling and deciding system for semi-conductor manufacturing system | |
| CN107909216A (en) | A kind of part actual production period forecasting method | |
| CN116611679B (en) | Electronic component production data management system and method based on artificial intelligence | |
| CN111126499A (en) | Secondary clustering-based power consumption behavior pattern classification method | |
| Lee | Artificial intelligence-based sampling planning system for dynamic manufacturing process | |
| DE60208236T2 (en) | METHOD AND DEVICE FOR PLANNING MANUFACTURING UNITS BASED ON UNIT AND TOOL CONDITIONS | |
| CN112395558B (en) | Improved unbalanced data mixed sampling method suitable for historical fault data of intelligent electric meter | |
| US20020156603A1 (en) | Modeling tool with controlled capacity | |
| Graf et al. | The problem of unsuspected serial correlations | |
| CN112598259A (en) | Capacity measuring method and device and computer readable storage medium | |
| Wang et al. | Simulation-based real-time production control with different classes of residence time constraints | |
| CN115705545A (en) | Method and apparatus for evaluating throughput of semiconductor device | |
| EP0620526A1 (en) | Method and apparatus for estimating unknown numeric quantity | |
| CN116384715B (en) | Robot operation and maintenance management method of digital robot industrial chain | |
| CN113591398B (en) | Intelligent operation batch method and device based on deep reinforcement learning and electronic equipment | |
| Kwong et al. | Modeling manufacturing processes using fuzzy regression with the detection of outliers | |
| Lin et al. | Predecessor-set technique for reliability evaluation of a stochastic manufacturing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |