WO2019000892A1

WO2019000892A1 - Method and apparatus for predicting scrap rate for pcb order

Info

Publication number: WO2019000892A1
Application number: PCT/CN2017/120101
Authority: WO
Inventors: 宫立军; 邱醒亚; 张可
Original assignee: 广州兴森快捷电路科技有限公司; 深圳市兴森快捷电路科技股份有限公司; 宜兴硅谷电子科技有限公司
Priority date: 2017-06-29
Filing date: 2017-12-29
Publication date: 2019-01-03
Also published as: CN107506514B; CN107506514A

Abstract

A method and apparatus for predicting the scrap rate for a printed circuit board (PCB) order, the method comprising: acquiring a PCB order file of a PCB order for which scrap rate prediction is to be performed (S101); according to the PCB order file, determining parameters for the PCB order, the parameters comprising circuit board product information of a circuit board product corresponding to the PCB order (S102); according to the circuit board product information and a preset scrap rate calculation model, predicting the scrap rate for the PCB order (S103). By using the method and apparatus, scrap rate prediction for a PCB order may be achieved without manual intervention, and efficiency and accuracy in scrap rate prediction for a PCB order may also be improved.

Description

PCB order scrap rate prediction method and device

Technical field

The present invention relates to the field of PCB technology, and in particular, to a PCB order rejection rate prediction method and apparatus.

Background technique

PCB (Printed Circuit Board, printed circuit board, also known as printed circuit board) industry has many customers with PCB board source and random order, and PCB products have strong individuality, production parameters and process characteristics, and precision requirements. Higher characteristics. These characteristics lead to the easy occurrence of scrap in the PCB production process, so companies need to predict the scrap rate of PCB production.

The main influencing factors of PCB order scrap rate: Inevitably, there will be certain scrapping conditions in the PCB processing process, and the reasons for the product's unqualified scrapping include subjective factors and objective factors. The subjective factors mainly refer to the unreasonable design process of the man-made, the mistakes caused by the operation, etc., which can generally trace the responsible person directly. The objective factors are mainly due to the fact that the product requires a large number of processing parameters, complex processing characteristics, high process requirements, equipment processing capacity limitations and environmental uncertainty, resulting in a certain proportion of product scrapping in the process of manufacturing. Obviously, the more complex the product, the higher the accuracy requirements of the feature, the higher the difficulty in manufacturing under the condition that the manufacturing equipment is not improved, and the higher the scrap rate caused by objective reasons. The difficulty of fabrication is usually described by the extreme values (product parameters) of the manufacturing parameters of the PCB. The closer to the capability boundary, the higher the difficulty. The transcendence boundary may cause the scrap rate to rise rapidly. Similarly, the parameter range of one or several features processed in one process directly affects the scrap rate of the process.

In the traditional way, the PCB order scrap rate is mainly predicted by the production dispatcher to assess the difficulty of PCB manufacturing based on experience. This method has a large subjectivity, which may lead to inaccurate prediction and long time consumption.

Summary of the invention

In view of this, an object of the present invention is to provide a PCB order rejection rate prediction method and apparatus, a computer readable storage medium, and a computer device, which can predict the PCB order scrap rate without manual intervention, and can improve The efficiency and accuracy of PCB order scrap rate prediction.

In a first aspect, a method for predicting a PCB order scrap rate is provided, which includes:

Obtaining a PCB order file for a PCB order to be predicted for scrap rate;

Determining, according to the PCB order file, a parameter of the PCB order, where the parameter includes circuit board product information of a circuit board product corresponding to the PCB order;

Predicting the scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model.

With reference to the first aspect, in a possible implementation manner of the first aspect, the circuit board product information includes the number of layers, the number of plate plating times, the thickness of the finished board, the thickness of the minimum hole wall, the thickness ratio of the through holes, and the total number of holes , the total number of processes, the quantity of delivery, the historical yield, the area of the finished unit, whether it is plated with copper and nickel, whether it is plated with hard gold, whether there is gold finger, whether there is negative film plating, whether there is thinned copper, whether it is photoelectric plate, Whether it is a high-frequency board, whether it is required to meet the IPCIII standard, whether the line width spacing is less than a preset threshold value and a combination of all the parameter items or a plurality of parameter items.

In combination with the first aspect or some of the possible implementation manners described above, in a possible implementation manner of the first aspect, the foregoing scrap rate calculation model is:

R _scrapped =k ₁ *N _layers +k ₂ *T _plate +k ₃ *T _F-plate +k ₄ *S _ct-hw +k ₅ *R _th-dm +k ₆ *N _holes +k ₇ *N _{t -processes} -k ₈ *Q _delivery -k ₉ *Y _his +k ₁₀ *A _F-unit +k ₁₁ *W _plate1 +*k ₁₂ W _plate2 +k ₁₃ *W _chefs +k ₁₄ *W _n-plate +k ₁₅ *W _t-copper +k ₁₆ *W _p-panel +k ₁₇ *W _h-fq-board +k ₁₈ *W _IPCIII +k ₁₉ *W _L-width +k ₂₀ *N _press

Where R _scrapped indicates scrap rate, N _layers indicates number of layers, T _plate indicates plate plating times, T _F-plate indicates finished plate thickness, S _ct-hw indicates minimum hole wall thickness, and R _th-dm indicates through hole thickness Ratio, N _holes indicates the total number of holes, N _t-processes indicates the total number of flows, Q _delivery indicates the delivery quantity, Y _his indicates the historical yield, A _F-unit indicates the finished unit area, and W _plate1 indicates whether the _plate is plated with copper and nickel W _plate2 indicates whether to plate hard gold, W _chefs indicates whether there is gold finger, W _n-plate indicates whether there is negative plating, W _t-copper indicates whether there is thinned copper, W _p-panel indicates whether it is photoelectric plate, W _{h -fq-board} indicates whether it is a high frequency board, W _IPCIII indicates whether it is required to reach the IPCIII standard, W _L-width indicates whether the line width spacing is less than the preset threshold, N _press indicates the number of presses, k ₁ , k ₂ , k ₃ , k ₄ , k ₅ , k ₆ , k ₇ , k ₈ , k ₉ , k ₁₀ , k ₁₁ , k ₁₂ , k ₁₃ , k ₁₄ , k ₁₅ , k ₁₆ , k ₁₇ , k ₁₈ , k ₁₉ and k ₂₀ parameter term coefficient.

With reference to the first aspect or some possible implementations of the foregoing, in a possible implementation of the first aspect, k ₁ is 0.3347, k ₂ is 0.5837, k ₃ is 0.2654, k ₄ is 0.0118, and k ₅ is 0.1757. k ₆ is 0.00006001, k ₇ is 0.04282, k ₈ is 0.0002636, k ₉ is 0.05532, k ₁₀ is 42.07, k ₁₁ is 2.377, k ₁₂ is 0.828, k ₁₃ is 0.6899, k ₁₄ is 0.886, k ₁₅ is 0.6842. k ₁₆ is 0.2591, k ₁₇ is 0.3622, k ₁₈ is 0.4906, k ₁₉ is 0.4961, and k ₂₀ is 2.6278;

When the circuit board product pattern is plated with copper nickel gold, the value of W _plate1 is 1, otherwise 0; when the circuit board product is plated with hard gold, the value of W _plate2 is 1, otherwise 0; in the line When the board product has a gold finger, the value of W _chefs is 1, otherwise it is 0; when the circuit board product has negative film plating, the value of W _n-plate is 1, otherwise 0; in the circuit board product is reduced In the case of thin copper, the value of W _t-copper is 1, otherwise 0; when the circuit board product is a photovoltaic board, the value of W _p-panel is 1, otherwise 0; in the circuit board product is high frequency When the board is used, the value of W _h-fq-board is 1, otherwise it is 0; when the board product is required to meet the IPCIII standard, the value of W _IPCIII is 1, otherwise 0; the line width of the product line is less than When the threshold is preset, the value of W _L-width is 1, otherwise it is 0;

The preset threshold is 3.5 mils.

With reference to the first aspect or some of the foregoing possible implementation manners, in a possible implementation manner of the first aspect, the determining, by the CMP software server, the parameter that is determined by using the PCB order file The PCB order file is parsed to obtain the parameters of the PCB order.

In a second aspect, a PCB order rejection rate prediction apparatus is provided, including:

a file obtaining unit, configured to obtain a PCB order file of a PCB order to be predicted by the scrap rate;

An information analyzing unit, configured to determine, according to the PCB order file, a parameter of the PCB order, where the parameter includes circuit board product information of a circuit board product corresponding to the PCB order;

The scrap rate prediction unit is configured to predict a scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model.

With reference to the second aspect, in a possible implementation manner of the second aspect, the circuit board product information includes the number of layers, the number of plate plating times, the thickness of the finished board, the thickness of the minimum hole wall, the thickness ratio of the through holes, and the total Number of holes, total flow, delivery quantity, historical yield, finished unit area, whether copper or nickel plating, whether hard gold plating, whether there is gold finger, whether there is negative plating, whether there is thinned copper, whether it is photoelectric Whether the board, whether it is a high-frequency board, whether it is required to meet the IPCIII standard, whether the line width spacing is less than a preset threshold value and the number of presses, or a combination of a plurality of parameter items;

With reference to the second aspect, in a possible implementation manner of the second aspect, the foregoing retirement rate calculation model is:

With reference to the second aspect or some possible implementations of the foregoing, in a possible implementation of the second aspect, k ₁ is 0.3347, k ₂ is 0.5837, k ₃ is 0.2654, k ₄ is 0.0118, and k ₅ is 0.1757. k ₆ is 0.00006001, k ₇ is 0.04282, k ₈ is 0.0002636, k ₉ is 0.05532, k ₁₀ is 42.07, k ₁₁ is 2.377, k ₁₂ is 0.828, k ₁₃ is 0.6899, k ₁₄ is 0.886, k ₁₅ is 0.6842. k ₁₆ is 0.2591, k ₁₇ is 0.3622, k ₁₈ is 0.4906, k ₁₉ is 0.4961, and k ₂₀ is 2.6278;

The preset threshold is 3.5 mils.

In a third aspect, there is provided a computer readable storage medium having stored thereon a computer program for performing the steps of the PCB order scrap rate prediction method as described above when the program is executed by the processor.

A fourth aspect provides a computer device including a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the program to implement a PCB order scrap rate prediction method as described above A step of.

According to the solution of the present invention, the PCB order file of the PCB order for which the scrap rate prediction is to be performed is determined, and the parameter of the PCB order is determined according to the PCB order file, and the parameter includes the line of the circuit board product corresponding to the PCB order. The board product information predicts the scrap rate of the PCB order according to the board product information and a preset scrap rate calculation model. By adopting the solution of the invention, the prediction of the PCB order scrap rate can be realized without manual intervention, which can save labor cost and improve the efficiency and accuracy of the forecast.

DRAWINGS

1 is a schematic flowchart of an implementation process of a PCB order scrap rate prediction method according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a PCB order scrap rate prediction apparatus according to an embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the scope of the invention.

In one of the embodiments, a PCB order rejection rate prediction method is provided. As shown in FIG. 1, the PCB order scrap rate prediction method in this embodiment includes the following steps:

Step S101: Obtain a PCB order file of a PCB order to be predicted by the scrap rate;

Here, the PCB order file is a line graphic file that can be used to make a circuit board product.

Step S102: determining parameters of the PCB order according to the PCB order file, where the parameters include circuit board product information of the circuit board product corresponding to the PCB order;

Here, the circuit board product information includes parameter values corresponding to the respective parameter items of the circuit board product, and specifically includes which parameter item parameter values can be determined according to actual needs.

Step S103: predicting the scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model.

According to the solution of the present embodiment, after obtaining the PCB order file of the PCB order to be predicted by the scrap rate, determining the circuit board product information of the circuit board product corresponding to the PCB order according to the PCB order file, Predicting the scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model. With the solution of the embodiment, the prediction of the PCB order scrap rate can be realized without manual intervention, which can save labor cost and improve the efficiency and accuracy of the forecast.

In one embodiment, the above-mentioned circuit board product information includes the number of layers, the number of plate plating times, the thickness of the finished plate, the thickness of the minimum hole wall, the thickness ratio of the through holes, the total number of holes, the total number of processes, the quantity of delivery, and the history. Yield, finished unit area, whether it is plated with copper and nickel, whether it is plated with hard gold, whether there is gold finger, whether there is negative plating, whether there is thin copper, whether it is photovoltaic board, whether it is high frequency board, whether it is required to reach IPCIII Standard, whether the line width spacing is less than all the parameter items in the preset threshold value and the number of pressing times or a combination of multiple parameter items. The parameter items included in the board product information may be determined based on actual needs.

In a preferred embodiment, the product information of the circuit board includes the number of layers, the number of plate plating times, the thickness of the finished plate, the thickness of the minimum hole wall, the thickness ratio of the through holes, the total number of holes, the total number of processes, and the quantity of delivery. , historical yield, finished unit area, whether it is plated with copper and nickel gold, whether it is plated with hard gold, whether there is gold finger, whether there is negative film plating, whether there is thin copper, whether it is photoelectric plate, whether it is high frequency plate, whether it is required Meet the IPCIII standard, whether the line width spacing is less than the preset threshold and the number of presses. The parameter items included in the circuit board product information in this embodiment are comprehensive, and the prediction accuracy can be improved. Table 1 shows the parameters of a PCB order.

Table 1 Parameters of PCB Order

序号Serial number	参数项Parameter item	参数值Parameter value
11	层数Number of layers	22
22	板镀次数Plate plating times	11
33	成品板厚Finished board thickness	1.61.6
44	最小孔壁铜厚Minimum hole wall copper thickness	2020
55	通孔厚径比Through hole thickness to diameter ratio	66
66	总孔数Total number of holes	2156821568
77	总流程数Total number of processes	23twenty three
88	交货数量quantity of delivery	150150
99	历史良率Historical yield	94.17％94.17%
1010	成品单元面积Finished unit area	0.0050.005
1111	是否图镀铜镍金Whether the picture is plated with copper, nickel and gold	11
1212	是否电镀硬金Whether to plate hard gold	11
1313	是否有金手指Is there a golden finger?	00
1414	是否有负片电镀Is there a negative plating?	00
1515	是否有减薄铜Is there a thinned copper?	00
1616	是否光电板Whether photovoltaic panels	00
1717	是否高频板Whether high frequency board	00
1818	是否IPCIII标准Whether the IPCIII standard	00
1919	是否线宽间距小于3.5Whether the line width spacing is less than 3.5	00
2020	压合次数Number of presses	00

In one embodiment, the above-mentioned scrapping rate calculation model may be the number of layers, the number of plate plating times, the thickness of the finished plate, the minimum hole wall copper thickness, the through hole thickness to diameter ratio, the total number of holes, the total number of processes, and the number of deliveries. , historical yield, finished unit area, whether it is plated with copper and nickel gold, whether it is plated with hard gold, whether there is gold finger, whether there is negative film plating, whether there is thin copper, whether it is photoelectric plate, whether it is high frequency plate, whether it is required A combination of all parameter items or a plurality of parameter items in the IPCIII standard, whether the line width spacing is less than the preset threshold value and the number of presses is weighted and summed. Wherein, the weight coefficient of the two parameter items of the delivery quantity and the historical yield is a negative number, and the weight coefficient of the remaining parameter items is a positive number.

In a preferred embodiment, the above-mentioned scrap rate calculation model is the following formula (1):

The preset threshold can be set according to actual needs. Preferably, the predetermined threshold is 3.5 mils and 1 mil is equal to 25.4 microns.

It should be noted that the scrap rate calculation model in this embodiment considers various major influencing factors of the PCB scrap rate, and the prediction of the PCB order scrap rate based on the scheme of the embodiment can significantly improve the accuracy of the scrap rate prediction. However, it should be noted that the scrap rate calculation model is not limited to the formula (1). For example, when the parameter items included in the board product information are different, the scrap rate calculation model may have different forms.

In a preferred embodiment, when the rejection rate calculation model uses the formula (1), k ₁ is 0.3347, k ₂ is 0.5837, k ₃ is 0.2654, k ₄ is 0.0118, k ₅ is 0.1757, and k ₆ is 0.00006001, k ₇ is 0.04282, k ₈ is 0.0002636, k ₉ is 0.05532, k ₁₀ is 42.07, k ₁₁ is 2.377, k ₁₂ is 0.828, k ₁₃ is 0.6899, k ₁₄ is 0.886, k ₁₅ is 0.6842, k ₁₆ is 0.2591, k ₁₇ is 0.3622, k ₁₈ is 0.4906, k ₁₉ is 0.4961, and k ₂₀ is 2.6278;

The preset threshold is 3.5 mils.

With the solution of the embodiment, the accuracy of the prediction can be further improved.

Further, the units of the above-mentioned finished sheet thickness, minimum hole wall copper thickness, and finished unit area are respectively mm, micrometer, and square millimeter.

In one embodiment, the step of determining the parameter of the PCB order according to the PCB order file may include: parsing the PCB order file by a CAM (computer Aided Manufacturing) software server, Obtain the parameters of the PCB order.

Specifically, the PCB order file may be sent to the CAM software server, and the parameters of the PCB order returned by the CAM software server after parsing the PCB order file are received.

Since the CAM software server can quickly parse the parameters of the PCB order based on the PCB order file, the prediction efficiency can be further improved by adopting the scheme of the embodiment.

According to the PCB order scrap rate prediction method in the above embodiment, the present invention also provides a PCB order scrap rate prediction device. FIG. 2 is a schematic diagram showing the structure of a PCB order scrap rate prediction apparatus according to an embodiment of the present invention. As shown in FIG. 2, the PCB order scrap rate prediction apparatus of the present invention includes a file acquisition unit 201, an information analysis unit 202, and a scrap rate prediction unit 203, wherein:

a file obtaining unit 201, configured to acquire a PCB order file of a PCB order to be predicted by the scrap rate;

The information analyzing unit 202 is configured to determine, according to the PCB order file, a parameter of the PCB order, where the parameter includes circuit board product information of the circuit board product corresponding to the PCB order;

The scrap rate prediction unit 203 is configured to predict a scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model.

In one embodiment, the circuit board product information includes the number of layers, the number of plate plating times, the thickness of the finished plate, the thickness of the minimum hole wall, the thickness ratio of the through holes, the total number of holes, the total number of processes, the quantity of delivery, and the history. Yield, finished unit area, whether it is plated with copper and nickel, whether it is plated with hard gold, whether there is gold finger, whether there is negative plating, whether there is thin copper, whether it is photovoltaic board, whether it is high frequency board, whether it is required to reach IPCIII Standard, whether the line width spacing is less than all parameter items in the preset threshold value and the number of pressing times or a combination of multiple parameter items;

In one of the embodiments, the rejection rate calculation model is the formula (1) as above.

In one embodiment, k ₁ is 0.3347, k ₂ is 0.5837, k ₃ is 0.2654, k ₄ is 0.0118, k ₅ is 0.1757, k ₆ is 0.00006001, k ₇ is 0.04282, k ₈ is 0.0002636, k ₉ is 0.05532, k ₁₀ is 42.07, k ₁₁ is 2.377, k ₁₂ is 0.828, k ₁₃ is 0.6899, k ₁₄ is 0.886, k ₁₅ is 0.6842, k ₁₆ is 0.2591, k ₁₇ is 0.3622, k ₁₈ is 0.4906, k ₁₉ is 0.4961, k ₂₀ is 2.6278;

The preset threshold is 3.5 mils.

In one embodiment, the information analysis unit 202 may parse the PCB order file through the CAM software server to obtain parameters of the PCB order.

The description of the PCB order scrap rate prediction device provided by the embodiment of the present invention is similar to the description of the PCB order scrap rate prediction method described above, and has the beneficial effects of the above PCB order scrap rate prediction method, so as to save space, no further description is provided; Therefore, for the technical details not disclosed in the PCB order rejection rate prediction apparatus provided by the embodiment of the present invention, please refer to the description of the PCB order rejection rate prediction method provided above.

Based on the above-described embodiments, an embodiment further provides a computer readable storage medium having stored thereon a computer program that, when executed by the processor, implements the PCB order as described in any one of the above embodiments The steps of the scrap rate prediction method.

Based on the embodiments described above, an embodiment further provides a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the The steps of the PCB order scrap rate prediction method described in any of the above embodiments are implemented at the time of the program. The computer device may be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), an in-vehicle computer, a wearable device, and the like.

One of ordinary skill in the art can understand that all or part of the process of implementing the above embodiment method can be completed by a computer program to instruct related hardware, and the program can be stored in a non-volatile computer readable storage. In the medium, as in the embodiment of the invention, the program may be stored in a storage medium of the computer system and executed by at least one processor in the computer system to implement a flow comprising an embodiment of the methods as described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The technical features of the above-described embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be considered as the scope of this manual.

The above-described embodiments are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention. Therefore, the scope of the invention should be determined by the appended claims.

Claims

A method for predicting a scrap rate of a PCB order, comprising:

Obtaining a PCB order file for a PCB order to be predicted for scrap rate;

Determining, according to the PCB order file, a parameter of the PCB order, where the parameter includes circuit board product information of a circuit board product corresponding to the PCB order;

Predicting the scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model.
The PCB order scrap rate prediction method according to claim 1, wherein the circuit board product information comprises a number of layers, a plate plating time, a finished plate thickness, a minimum hole wall copper thickness, a through hole thickness to diameter ratio, and a total hole. Number, total number of processes, delivery quantity, historical yield, finished unit area, whether copper or nickel plating, whether hard gold plating, whether there is gold finger, whether there is negative plating, whether there is thin copper, whether it is photoelectric board Whether it is a high-frequency board, whether it is required to meet the IPCIII standard, whether the line width spacing is less than a preset threshold value and a combination of all the parameter items or a plurality of parameter items.
The method for presetting a PCB order scrap rate according to claim 2, wherein the scrap rate calculation model is:

R scrapped =k 1 *N layers +k 2 *T plate +k 3 *T F-plate +k 4 *S ct-hw +k 5 *R th-dm +k 6 *N holes

+k 7 *N t-processes -k 8 *Q delivery -k 9 *Y his +k 10 *A F-unit +k 11 *W plate1 +*k 12 W plate2

+k 13 *W chefs +k 14 *W n-plate +k 15 *W t-copper +k 16 *W p-panel +k 17 *W h-fq-board

+k 18 *W IPCIII +k 19 *W L-width +k 20 *N press

Where R scrapped indicates scrap rate, N layers indicates number of layers, T plate indicates plate plating times, T F-plate indicates finished plate thickness, S ct-hw indicates minimum hole wall thickness, and R th-dm indicates through hole thickness Ratio, N holes indicates the total number of holes, N t-processes indicates the total number of flows, Q delivery indicates the delivery quantity, Y his indicates the historical yield, A F-unit indicates the finished unit area, and W plate1 indicates whether the plate is plated with copper and nickel W plate2 indicates whether to plate hard gold, W chefs indicates whether there is gold finger, W n-plate indicates whether there is negative plating, W t-copper indicates whether there is thinned copper, W p-panel indicates whether it is photoelectric plate, W h -fq-board indicates whether it is a high frequency board, W IPCIII indicates whether it is required to reach the IPCIII standard, W L-width indicates whether the line width spacing is less than the preset threshold, N press indicates the number of presses, k 1 , k 2 , k 3 , k 4 , k 5 , k 6 , k 7 , k 8 , k 9 , k 10 , k 11 , k 12 , k 13 , k 14 , k 15 , k 16 , k 17 , k 18 , k 19 and k 20 parameter term coefficient.
The method for presetting a PCB order scrap rate according to claim 3, wherein:

k 1 is 0.3347, k 2 is 0.5837, k 3 is 0.2654, k 4 is 0.0118, k 5 is 0.1757, k 6 is 0.00006001, k 7 is 0.04282, k 8 is 0.0002636, k 9 is 0.05532, and k 10 is 42.07. k 11 is 2.377, k 12 is 0.828, k 13 is 0.6899, k 14 is 0.886, k 15 is 0.6842, k 16 is 0.2591, k 17 is 0.3622, k 18 is 0.4906, k 19 is 0.4961, k 20 is 2.6278;

When the circuit board product pattern is plated with copper nickel gold, the value of W plate1 is 1, otherwise 0; when the circuit board product is plated with hard gold, the value of W plate2 is 1, otherwise 0; in the line When the board product has a gold finger, the value of W chefs is 1, otherwise it is 0; when the circuit board product has negative film plating, the value of W n-plate is 1, otherwise 0; in the circuit board product is reduced In the case of thin copper, the value of W t-copper is 1, otherwise 0; when the circuit board product is a photovoltaic board, the value of W p-panel is 1, otherwise 0; in the circuit board product is high frequency When the board is used, the value of W h-fq-board is 1, otherwise it is 0; when the board product is required to meet the IPCIII standard, the value of W IPCIII is 1, otherwise 0; the line width of the product line is less than When the threshold is preset, the value of W L-width is 1, otherwise it is 0;

The preset threshold is 3.5 mils.
The method for presetting a PCB order scrap rate according to any one of claims 1 to 4, wherein the determining the parameter of the PCB order according to the PCB order file comprises: placing the PCB order through a CAM software server The file is parsed to obtain the parameters of the PCB order.
A PCB order scrap rate prediction device, comprising:

a file obtaining unit, configured to obtain a PCB order file of a PCB order to be predicted by the scrap rate;

An information analyzing unit, configured to determine, according to the PCB order file, a parameter of the PCB order, where the parameter includes circuit board product information of a circuit board product corresponding to the PCB order;

The scrap rate prediction unit is configured to predict a scrap rate of the PCB order according to the circuit board product information and a preset scrap rate calculation model.
The PCB order scrap rate prediction device according to claim 6, wherein:

The circuit board product information includes the number of layers, plate plating times, finished plate thickness, minimum hole wall copper thickness, through hole thickness to diameter ratio, total number of holes, total number of processes, delivery quantity, historical yield, finished unit area, Whether it is plated with copper-nickel gold, whether it is plated with hard gold, whether there is gold finger, whether there is negative plate plating, whether there is thinned copper, whether it is a photovoltaic plate, whether it is a high-frequency plate, whether it is required to meet the IPCIII standard, whether the line width is less than a combination of all parameter items or a plurality of parameter items in the preset threshold value and the number of presses;

R scrapped =k 1 *N layers +k 2 *T plate +k 3 *T F-plate +k 4 *S ct-hw +k 5 *R th-dm +k 6 *N holes

+k 7 *N t-processes -k 8 *Q delivery -k 9 *Y his +k 10 *A F-unit +k 11 *W plate1 +*k 12 W plate2

+k 13 *W chefs +k 14 *W n-plate +k 15 *W t-copper +k 16 *W p-panel +k 17 *W h-fq-board

+k 18 *W IPCIII +k 19 *W L-width +k 20 *N press

Where R scrapped indicates scrap rate, N layers indicates number of layers, T plate indicates plate plating times, T F-plate indicates finished plate thickness, S ct-hw indicates minimum hole wall thickness, and R th-dm indicates through hole thickness Ratio, N holes indicates the total number of holes, N t-processes indicates the total number of flows, Q delivery indicates the delivery quantity, Y his indicates the historical yield, A F-unit indicates the finished unit area, and W plate1 indicates whether the plate is plated with copper and nickel W plate2 indicates whether to plate hard gold, W chefs indicates whether there is gold finger, W n-plate indicates whether there is negative plating, W t-copper indicates whether there is thinned copper, W p-panel indicates whether it is photoelectric plate, W h -fq-board indicates whether it is a high frequency board, W IPCIII indicates whether it is required to reach the IPCIII standard, W L-width indicates whether the line width spacing is less than the preset threshold, N press indicates the number of presses, k 1 , k 2 , k 3 , k 4 , k 5 , k 6 , k 7 , k 8 , k 9 , k 10 , k 11 , k 12 , k 13 , k 14 , k 15 , k 16 , k 17 , k 18 , k 19 and k 20 parameter term coefficient.
The PCB order scrap rate preset device according to claim 7, wherein:

k 1 is 0.3347, k 2 is 0.5837, k 3 is 0.2654, k 4 is 0.0118, k 5 is 0.1757, k 6 is 0.00006001, k 7 is 0.04282, k 8 is 0.0002636, k 9 is 0.05532, and k 10 is 42.07. k 11 is 2.377, k 12 is 0.828, k 13 is 0.6899, k 14 is 0.886, k 15 is 0.6842, k 16 is 0.2591, k 17 is 0.3622, k 18 is 0.4906, k 19 is 0.4961, k 20 is 2.6278;

When the circuit board product pattern is plated with copper nickel gold, the value of W plate1 is 1, otherwise 0; when the circuit board product is plated with hard gold, the value of W plate2 is 1, otherwise 0; in the line When the board product has a gold finger, the value of W chefs is 1, otherwise it is 0; when the circuit board product has negative film plating, the value of W n-plate is 1, otherwise 0; in the circuit board product is reduced In the case of thin copper, the value of W t-copper is 1, otherwise 0; when the circuit board product is a photovoltaic board, the value of W p-panel is 1, otherwise 0; in the circuit board product is high frequency When the board is used, the value of W h-fq-board is 1, otherwise it is 0; when the board product is required to meet the IPCIII standard, the value of W IPCIII is 1, otherwise 0; the line width of the product line is less than When the threshold is preset, the value of W L-width is 1, otherwise it is 0;

The preset threshold is 3.5 mils.
A computer readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor to implement the steps of the PCB order scrap rate prediction method according to any one of claims 1-5.
A computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the program to implement the method of any one of claims 1-5 The steps of the PCB order scrap rate prediction method.