CN109871978B - PCB order qualification rate prediction method and device and readable storage medium - Google Patents
PCB order qualification rate prediction method and device and readable storage medium Download PDFInfo
- Publication number
- CN109871978B CN109871978B CN201811624966.7A CN201811624966A CN109871978B CN 109871978 B CN109871978 B CN 109871978B CN 201811624966 A CN201811624966 A CN 201811624966A CN 109871978 B CN109871978 B CN 109871978B
- Authority
- CN
- China
- Prior art keywords
- pcb
- qualification rate
- order
- model
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
Abstract
The invention discloses a PCB order qualification rate prediction method, a device and a readable storage medium, wherein the method comprises the following steps: acquiring structural information of a PCB; analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB; acquiring historical parameter data related to PCB qualification rate; performing big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor; establishing a PCB qualification rate model according to the influence factors of the PCB qualification rate and the corresponding weights; and calculating the qualification rate of the order of the PCB according to the order structure of the PCB and combining the qualification rate model of the PCB. According to the order structure of the PCB, the qualification rate of the order of the PCB is calculated by combining the qualification rate model of the PCB, when the predicted qualification rate is low, the production is identified in advance, necessary resources are input, and when the actual qualification rate of the production does not reach the standard, the theoretical qualification rate of the order can be formulated, and the traction production is improved.
Description
Technical Field
The invention relates to the technical field of PCBs, in particular to a PCB order qualification rate prediction method and device and a readable storage medium.
Background
The PCB (Printed Circuit Board, printed circuit board, also called printed circuit board) industry has the characteristics of multiple customer sources, strong order randomness of the PCB, and the PCB product has the characteristics of strong individuation, multiple manufacturing parameters and process characteristics, high precision requirement and the like. These features lead to the easy rejection of PCB production processes, and therefore
Aiming at the qualification rate of PCB products, the main problems are as follows:
(1) The order adding and throwing ratio is too dependent on experience
A. It is difficult to consider factors comprehensively by empirically determining the addition amount. The strategy is extensive, the subjectivity is strong, the ultra-projection/few-projection volatility is large, and the balance and the global optimization are difficult;
B. experience feeding is adopted, and the super-production product occupies the factory productivity, so that equipment resource load is increased, energy is wasted, and meanwhile, the purchasing raw materials, logistics, stock and scrapping treatment cost is increased;
C. and the small amount of investment also causes the need of additional investment, thereby increasing the difficulty and the production cost of planned scheduling.
(2) Difficulty order prenatal planning deletion
A. After the difficult order enters a factory, the production cannot identify the difficult order as a low-yield order in advance due to lack of a qualification rate early warning mechanism, so that the order lacks necessary resource investment, effective prenatal planning is not performed, and the rejection rate of the difficult order is high.
(3) Yield target without traction
A. The true qualification rate of an order of a certain model cannot be accurately identified, when the actual qualification rate of the order is lower than the theoretical qualification rate, the due theoretical qualification rate cannot be given, the current formulated qualification rate is determined to have no referential property, and the target traction performance is not strong.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent. It is, therefore, an object of the present invention to provide a PCB order qualification rate prediction method, apparatus, and readable storage medium that facilitate the improvement of the effectiveness of production management.
The technical scheme adopted by the invention is as follows:
in a first aspect, the present invention provides a method for predicting the qualification rate of a PCB order, comprising:
acquiring structural information of a PCB;
analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB;
acquiring historical parameter data related to PCB qualification rate;
performing big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor;
establishing a PCB qualification rate model according to the influence factors of the PCB qualification rate and the corresponding weights;
and calculating the qualification rate of the order of the PCB according to the order structure of the PCB and combining the qualification rate model of the PCB.
Further, it also includes: and acquiring the actual PCB qualification rate, acquiring scrapping data when the actual PCB qualification rate does not reach the theoretical value of the PCB order qualification rate, and analyzing the influence factors corresponding to scrapping exceeding standards.
Further, the acquiring historical parameter data related to the PCB qualification rate includes: and extracting relevant parameter data of the PCB order qualification rate from the ERP system through a pre-written query statement, wherein the query statement is written according to a pre-determined parameter range.
Further, the impact factors include the qualification rate of each process of PCB production.
Further, the calculation formula of the qualification rate model of the PCB is as follows: y=f (Y1, Y2, y3.. Yn), where Y1, y2.. Yn represents the yield of each process.
Further, a process qualification rate calculation model is established, wherein a formula of the process calculation model is y=A1x1+A2x2+A3x … +Anxn, wherein xn represents An influence factor of each step of a process, and An represents a weight corresponding to each step factor.
In a second aspect, the present invention provides a PCB order qualification rate prediction apparatus, comprising:
the first acquisition module is used for acquiring the structural information of the PCB;
the first analysis module is used for analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB;
the second acquisition module is used for acquiring historical parameter data related to the PCB qualification rate;
the second analysis module is used for carrying out big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor;
the model creation module is used for creating a qualification rate model of the PCB according to the influence factors of the qualification rate of the PCB and the corresponding weights;
and the calculation module is used for calculating the qualification rate of the order of the PCB according to the order structure of the PCB and combining the qualification rate model of the PCB.
Further, the system also comprises a feedback module which is used for obtaining the actual PCB qualification rate, obtaining scrapping data when the actual PCB qualification rate does not reach the theoretical value of the PCB order qualification rate, and analyzing the influence factors corresponding to scrapping exceeding standards.
Further, the second obtaining module extracts relevant parameter data of the PCB order qualification rate from the ERP system through a pre-written query statement, wherein the query statement is written according to a pre-determined parameter range.
In a third aspect, the present invention provides a computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor performs the steps of the PCB order qualification rate prediction method described above.
The beneficial effects of the invention are as follows:
according to the invention, through analyzing the structural information of the PCB and the historical parameter data related to the PCB qualification rate, a PCB qualification rate model is established, the qualification rate of the order of the PCB is calculated according to the order structure of the PCB and by combining the PCB qualification rate model, when the predicted qualification rate is lower, the production is identified in advance, necessary resources are input, and prenatal planning measures are formulated, when the actual qualification rate of the production does not reach the standard, the theoretical qualification rate of the order can be formulated, and the production improvement is pulled.
Drawings
FIG. 1 is a flow chart of a PCB order yield prediction method in an embodiment of the invention.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
As shown in fig. 1, which illustrates a PCB order qualification rate prediction method, the method includes:
acquiring structural information of a PCB;
analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB;
acquiring historical parameter data related to PCB qualification rate;
performing big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor;
parameter data related to PCB yield calculations may first be extracted from each PCB history order, the related parameter data comprising parameter values of related parameters to each PCB yield calculation; and (3) primarily screening the related parameter data, excluding data which does not meet the quality requirement (or called garbage data mainly comprising incomplete data and error data), wherein the obtained residual data is the initial parameter data.
Establishing a PCB qualification rate model according to the influence factors of the PCB qualification rate and the corresponding weights; the calculation formula of the qualification rate model of the PCB is as follows: y=f (Y1, Y2, y3.. Yn). Where y1, y2 … yn represent each of the influencing factors, preferably, the influencing factors include the qualification rate of each process of PCB production, such as drilling process qualification rate, inner layer pattern qualification rate, lamination qualification rate, drilling qualification rate. . . Surface treatment qualification rate, profile treatment qualification rate, and the like.
And (3) establishing a process qualification rate calculation model, wherein the formula of the process calculation model is y=A1x1+A2x2+A3x … +Anxn, wherein xn represents the influence factors of each step of the process, and An represents the weight corresponding to each step factor. By further refining on the basis of the order-level budget model and establishing a process-level qualification rate calculation prediction model, the accuracy of prediction can be further improved.
Preferably, the drilling procedure qualification rate model is obtained by carrying out data arrangement on the drilling procedure qualification rate data according to the corresponding influence factors and then carrying out big data analysis:
the qualification rate calculation formula of the drilling procedure is as follows: y1= =a1×resin drilled hole+a2×stepped hole+a3×back drilled hole+a4×deep drilled hole+a5×tapped hole+a6×number of holes+a7×minimum hole diameter+a8×minimum distance from hole to conductor+a9×deep ratio+a10×high speed/high frequency material+a11×drilled hole+a12×core drilled hole+a13×core drilled hole.
According to the order structure of the PCB, the qualification rate of the order of the PCB is calculated by combining the qualification rate model of the PCB, background parameters and a factory process equipment capacity library (comprising qualification rate data of each procedure) are automatically grabbed to obtain the theoretical qualification rate level of the PCB, and meanwhile, the due qualification rate level of all orders of a factory can be output. Relevant parametric data for PCB order yield is extracted from an ERP (Enterprise Resource Planning ) system by pre-written query statements written according to a pre-determined range of parameters.
Further as a preferred embodiment, it further comprises: and acquiring the actual PCB qualification rate, acquiring scrapping data when the actual PCB qualification rate does not reach the theoretical value of the PCB order qualification rate, and analyzing the influence factors corresponding to scrapping exceeding standards.
According to the invention, according to an order structure, the weight of each factor is identified according to the model by combining the order qualification rate given by the qualification rate prediction model, and meanwhile, turning points corresponding to the reduction of the factor qualification rate are identified and used as boundary points of process capability, further, process capability parameters are determined, when the predicted qualification rate is lower, the production is identified in advance, necessary resources are input, and prenatal planning measures are formulated, and according to the order structure, when the actual qualification rate of the production does not reach the standard, the theoretical qualification rate of the order can be formulated.
A PCB order qualification rate prediction apparatus, comprising:
the first acquisition module is used for acquiring the structural information of the PCB;
the first analysis module is used for analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB;
the second acquisition module is used for acquiring historical parameter data related to the PCB qualification rate;
the second analysis module is used for carrying out big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor;
the model creation module is used for creating a qualification rate model of the PCB according to the influence factors of the qualification rate of the PCB and the corresponding weights;
and the calculation module is used for calculating the qualification rate of the order of the PCB according to the order structure of the PCB and combining the qualification rate model of the PCB.
Further as a preferred embodiment, the system further comprises a feedback module for acquiring the actual PCB qualification rate, acquiring scrapping data when the actual PCB qualification rate does not reach the theoretical value of the PCB order qualification rate, and analyzing the influence factor corresponding to scrapping exceeding.
Further as a preferred embodiment, the second obtaining module extracts relevant parameter data of the PCB order qualification rate from the ERP system through a pre-written query statement, wherein the query statement is written according to a pre-determined parameter range.
Based on the embodiments described above, there is also provided in one embodiment a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the PCB order qualification rate prediction method described above.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are included in the scope of the present invention as defined in the appended claims.
Claims (9)
1. A PCB order qualification rate prediction method is characterized by comprising the following steps:
acquiring structural information of a PCB;
analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB;
acquiring historical parameter data related to PCB qualification rate;
performing big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor;
establishing a PCB qualification rate model according to the influence factors of the PCB qualification rate and the corresponding weights;
according to the order structure of the PCB, and combining the qualification rate model of the PCB, calculating the qualification rate of the order of the PCB;
the PCB order qualification rate prediction method further comprises the following steps: and acquiring the actual PCB qualification rate, acquiring scrapping data when the actual PCB qualification rate does not reach the theoretical value of the PCB order qualification rate, and analyzing the influence factors corresponding to scrapping exceeding standards.
2. The PCB order yield prediction method of claim 1, wherein the obtaining historical parameter data related to PCB yield comprises:
and extracting relevant parameter data of the PCB order qualification rate from the ERP system through a pre-written query statement, wherein the query statement is written according to a pre-determined parameter range.
3. The PCB order yield prediction method of claim 1, wherein the impact factor comprises a yield of each process of PCB production.
4. The PCB order yield prediction method of claim 3, wherein the calculation formula of the PCB yield model is: y=f (Y1, Y2, y3.. Yn), where Y1, y2.. Yn represents the yield of each process.
5. The method of claim 4, wherein a process qualification rate calculation model is established, the process calculation model having a formula of y=a1x1+a2x2+a3x … +anxn, wherein xn represents a process step influencing factor and An represents a weight corresponding to each step factor.
6. A PCB order qualification rate prediction apparatus, comprising:
the first acquisition module is used for acquiring the structural information of the PCB;
the first analysis module is used for analyzing the structural information of the PCB to obtain a qualification rate influence factor of the PCB;
the second acquisition module is used for acquiring historical parameter data related to the PCB qualification rate;
the second analysis module is used for carrying out big data analysis on the historical parameter data to obtain the weight of the PCB qualification rate influence factor;
the model creation module is used for creating a qualification rate model of the PCB according to the influence factors of the qualification rate of the PCB and the corresponding weights;
the calculation module is used for calculating the qualification rate of the order of the PCB according to the order structure of the PCB and combining the qualification rate model of the PCB;
the PCB order qualification rate predicting device is also used for obtaining the actual PCB qualification rate, obtaining scrapping data when the actual PCB qualification rate does not reach the theoretical value of the PCB order qualification rate, and analyzing the influence factors corresponding to scrapping exceeding standards.
7. The PCB order qualification rate predicting apparatus of claim 6, further comprising a feedback module configured to obtain an actual PCB qualification rate, obtain discard data when the actual PCB qualification rate fails to reach a theoretical value of the PCB order qualification rate, and analyze an impact factor corresponding to discard exceeding a standard.
8. The PCB order qualification rate prediction apparatus of claim 6, wherein the second obtaining module extracts the related parameter data of the PCB order qualification rate from the ERP system through a pre-written query statement, wherein the query statement is written according to a pre-determined parameter range.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the PCB order qualification rate prediction method of one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624966.7A CN109871978B (en) | 2018-12-28 | 2018-12-28 | PCB order qualification rate prediction method and device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624966.7A CN109871978B (en) | 2018-12-28 | 2018-12-28 | PCB order qualification rate prediction method and device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109871978A CN109871978A (en) | 2019-06-11 |
| CN109871978B true CN109871978B (en) | 2023-07-18 |
Family
ID=66917323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811624966.7A Active CN109871978B (en) | 2018-12-28 | 2018-12-28 | PCB order qualification rate prediction method and device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871978B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598383B (en) * | 2020-04-03 | 2024-03-15 | 广州兴森快捷电路科技有限公司 | Method, system and storage medium for predicting qualification rate influence degree of PCB order |
| CN112348229A (en) * | 2020-10-12 | 2021-02-09 | 上海微亿智造科技有限公司 | Product yield prediction method and prediction system based on industrial big data |
| CN113610414A (en) * | 2021-08-13 | 2021-11-05 | 深圳市巨力方视觉技术有限公司 | PCB (printed Circuit Board) management and control method and device based on machine vision and computer readable medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107065795A (en) * | 2017-03-27 | 2017-08-18 | 深圳崇达多层线路板有限公司 | The automatic charging method and its system of a kind of multi-varieties and small-batch pcb board |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920863A (en) * | 2005-08-22 | 2007-02-28 | 力晶半导体股份有限公司 | Real time management system for production management and yield analytical integration and processing method thereof |
| US8707221B2 (en) * | 2011-12-29 | 2014-04-22 | Flextronics Ap, Llc | Circuit assembly yield prediction with respect to manufacturing process |
| CN106777652B (en) * | 2016-12-09 | 2019-12-17 | 中冶赛迪工程技术股份有限公司 | method for predicting air permeability of blast furnace |
| CN107506514B (en) * | 2017-06-29 | 2020-07-28 | 广州兴森快捷电路科技有限公司 | Method and device for predicting rejection rate of PCB (printed circuit board) order |
| CN108364085B (en) * | 2018-01-02 | 2020-12-15 | 拉扎斯网络科技（上海）有限公司 | Takeout delivery time prediction method and device |
| CN108416470B (en) * | 2018-02-11 | 2020-11-17 | 广州兴森快捷电路科技有限公司 | Method for predicting yield of circuit board |
| CN108830492B (en) * | 2018-06-22 | 2022-02-08 | 成都博宇科技有限公司 | Method for determining spot-check merchants based on big data |
-
2018
- 2018-12-28 CN CN201811624966.7A patent/CN109871978B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107065795A (en) * | 2017-03-27 | 2017-08-18 | 深圳崇达多层线路板有限公司 | The automatic charging method and its system of a kind of multi-varieties and small-batch pcb board |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109871978A (en) | 2019-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871978B (en) | PCB order qualification rate prediction method and device and readable storage medium | |
| CN110024097B (en) | Semiconductor manufacturing yield prediction system and method based on machine learning | |
| Ghosh et al. | Data mining driven DMAIC framework for improving foundry quality–a case study | |
| US10611086B2 (en) | System and method for evaluating additive manufacturing index | |
| CN110321658B (en) | Method and device for predicting plate performance | |
| CN110991739A (en) | Construction method and prediction method of industry electric quantity demand prediction model | |
| US10824498B2 (en) | Quantification of failure using multimodal analysis | |
| Harris et al. | A multivariate control chart for autocorrelated tool wear processes | |
| Bodendorf et al. | A machine learning approach to estimate product costs in the early product design phase: a use case from the automotive industry | |
| Lee et al. | Development of a predictive and preventive maintenance demonstration system for a semiconductor etching tool | |
| CN107506515B (en) | Method and device for constructing calculation model of PCB (printed Circuit Board) adding rate | |
| Papakostas et al. | An approach for adaptability modeling in manufacturing–analysis using chaotic dynamics | |
| CN110096820B (en) | Method for predicting residual life of k/n (G) system when unit life obeys Weibull distribution | |
| Borodavko et al. | Role of artificial intelligence in supply chain | |
| CN107506514A (en) | PCB order scrappage Forecasting Methodologies and device | |
| JP2009245043A (en) | Method and device for supporting line production management | |
| JP2006350883A (en) | Demand prediction value automatic determination system using knowledge database, demand prediction value automatic determination program used therefor, and storage medium storing its program | |
| Burduk | Stability analysis of the production system using simulation models | |
| CN107506842A (en) | PCB orders add throwing rate Forecasting Methodology and device | |
| US20190205804A1 (en) | Information processing device, information processing method and computer readable medium | |
| CN114918581A (en) | Welding parameter processing method and device, storage medium and processor | |
| Frye et al. | Adaptive scheduling through machine learning-based process parameter prediction | |
| Wickel et al. | How to build up an Engineering Change dependency model based on past change data? | |
| CN113723637A (en) | Economic repair level analysis method and system for ship maintenance system | |
| CN112700050A (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station |
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 |