Printed circuit board quality monitoring method and device based on big data model

Abstract

The invention provides a printed circuit board quality monitoring method and device based on a big data model, and the method comprises the steps: generating a unique PCB quality identification code for a PCB in a production link; the PCB quality identification code is generated on the basis of the inner layer identification code, the outer layer identification code and the PCB product quality qualification identification code; the inner layer identification code is generated by searching a lamination structure of a product and associating identification codes of a plurality of core boards on the basis of a PCB inner layer quality model; the outer layer identification code is formed by adopting a through hole coding machine on the basis of the PCB outer layer quality model and is associated with the inner layer identification code; the PCB product quality qualification identification code is generated by a PCB product quality model.

Description

Technical Field

[0001] The present invention relates to the technical field of PCB production and quality inspection, and in particular to a printed circuit board quality monitoring method and device based on a big data model. Background Art

[0002] PCB (Printed Circuit Board) printed circuit boards are key electronic interconnect components in electronic products. Their production process is long and involves many steps. In the current industrial production field, they face problems such as unknown distribution of industrial equipment, lack of unified management of operating status, inability to know equipment operating efficiency, equipment failures relying on manual post-reporting, and difficulty in remote debugging and upgrading.

[0003] The characteristic of process manufacturing is that its production process is continuous and uninterrupted. Different equipment and processes need to be connected into a whole. It is a full-process multi-unit collaborative production method with high requirements for the reliability and real-time performance of management and control. Once an abnormality occurs in the production line and is not handled in time, the entire batch of products will fail, causing huge economic losses to the company.

[0004] The information collection platform fully leverages the latest information technology capabilities, including IoT connectivity, device protocol adaptation engines, object-oriented storage pools, and big data modeling. However, existing big data management faces challenges such as large and dispersed clusters, high resource utilization, numerous operational monitoring indicators, low data integration, significant data format variations, and complex and arduous data cleaning tasks. Summary of the Invention

[0005] Therefore, in response to the shortcomings and deficiencies of the existing technology, the present invention provides a method and device for monitoring the quality of printed circuit boards (PCBs) based on a big data model. This method is used to develop quality models for each module in the PCB production process for monitoring, ensuring PCB board quality, promoting the development of intelligent manufacturing and the digital economy, and accelerating the transformation and upgrading of enterprises. The present invention uses big data model technology to monitor the PCB production process, meeting the requirements for high efficiency, reliability, and real-time management and control of PCB product quality. This avoids the problem that if an abnormality in the production line is not promptly addressed, the entire batch of products will fail, resulting in huge economic losses to the enterprise. This helps promote intelligent manufacturing and the digital economy and accelerate the transformation and upgrading of enterprises.

[0006] The present invention specifically adopts the following technical solutions:

[0007] A method for monitoring the quality of printed circuit boards (PCBs) based on a big data model. In the production process, a unique PCB quality identification code is generated for the PCB. The PCB quality identification code is generated based on an inner layer identification code, an outer layer identification code, and a PCB product quality qualification identification code. The inner layer identification code is generated based on a PCB inner layer quality model by searching for the laminated structure of the product and associating the identification codes of multiple core boards. The outer layer identification code is formed using a through-hole coding machine based on the PCB outer layer quality model and is associated with the inner layer identification code. The PCB product quality qualification identification code is generated by the PCB product quality model.

[0008] Furthermore, the PCB inner layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB inner layer quality detection parameters and setting deviation values.

[0009] Furthermore, the PCB outer layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outer layer quality detection parameters and setting deviation values.

[0010] Furthermore, the PCB product quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outbound quality inspection parameters and setting deviation values.

[0011] Furthermore, the qualified rate data is obtained by collecting data during the PCB production process and updating it in real time.

[0012] Furthermore, the qualified rate data and their overall average values ​​used in the PCB inner layer quality model, PCB outer layer quality model and PCB product quality model are all set with corresponding thresholds. When any qualified rate data or overall average value is monitored to exceed the threshold, an alarm is triggered.

[0013] And, a printed circuit board quality monitoring device based on a big data model, used to generate a unique PCB quality identification code for the PCB during the production process; comprising:

[0014] The inner layer identification code generation module is used to generate the inner layer identification code by searching the laminate structure of the product based on the PCB inner layer quality model and correlating the identification codes of multiple core boards;

[0015] An outer layer identification code generation module is used to generate the outer layer identification code using a through-hole coding machine based on the PCB outer layer quality model and associate it with the inner layer identification code;

[0016] A PCB product quality qualified identification code generation module is used to generate the PCB product quality qualified identification code from the PCB product quality model;

[0017] The PCB quality identification code generation module is used to generate the PCB quality identification code based on the inner layer identification code, the outer layer identification code and the PCB product quality qualified identification code.

[0018] Furthermore, the PCB inner layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB inner layer quality detection parameters and setting deviation values;

[0019] The PCB outer layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outer layer quality detection parameters and setting deviation values;

[0020] The PCB product quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outbound quality inspection parameters and setting deviation values;

[0021] The qualified rate data is obtained by collecting data during the PCB production process and updating it in real time.

[0022] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the printed circuit board quality monitoring method based on a big data model as described above are implemented.

[0023] A non-transitory computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a printed circuit board quality monitoring method based on a big data model as described above.

[0024] Compared to existing technologies, the PCB identification codes generated by the present invention and its preferred embodiment are unique. For identification codes applied to the same product across different production processes, historical data can be used to monitor quality across each production process. This is more efficient and ensures product quality than existing technologies, facilitating accurate traceability of anomalies occurring at each stage of production. Using PCB identification codes for quality testing allows tracking and monitoring of the quality of each stage of the production process for the same PCB identification code. Each module quality model is configured with a threshold for the quality pass rate P. Accurately alerting any anomalies occurring during a production process can be generated, thus meeting quality testing requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0026] Figure 1 This is a flowchart for the overall implementation of the embodiment of the present invention.

[0027] Figure 2 This is a flow chart of PCB quality identification code generation and quality monitoring according to an embodiment of the present invention.

[0028] Figure 3 This is a platform framework diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the features and advantages of the present invention more clearly understood, the following embodiments are specifically described in detail with reference to the accompanying drawings.

[0030] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0032] like Figure 1 As shown, an embodiment of the present invention provides a printed circuit board quality monitoring solution based on a big data model. Its basic design includes providing a printed circuit board quality monitoring platform. Printed circuit board companies register their identities on the production monitoring platform, and the platform processes production data; the production monitoring platform establishes a PCB quality model library and configures quality models for each module in the PCB production process; the production monitoring platform monitors the quality models of each module in the PCB production process in real time to ensure the quality of the PCB boards.

[0033] The following further introduces the implementation of the detailed technical solution of the embodiment of the present invention through a preferred embodiment:

[0034] 1. The production monitoring platform collects data from the production process of printed circuit board enterprises, including the necessary process parameters of the entire production process, such as raw materials, cutting, inner layer circuits, lamination, drilling, outer layer dry film, outer layer circuit finished product testing, packaging, etc., as well as data on materials in the factory, process parameters, production process, packaging and shipment, as well as information records such as production equipment, operators, time points, and environmental data, and uploads them to the production monitoring platform;

[0035] 2. Printed circuit board companies register their identities on the production monitoring platform and fill in basic company information including certificate information, legal person information, contact information, and other information; and apply for user authority management, business management, and other permissions for the administrator.

[0036] 3. The production monitoring platform saves data from the production process and processes the production data, including protocol conversion, data storage, data compression, data standardization and other data processing;

[0037] 4. The data model and service module of the production monitoring platform formulates a PCB quality model library based on the PCB production process. The PCB quality model library includes three parts: PCB inner layer quality model, PCB outer layer quality model and PCB product quality model, among which:

[0038] The PCB inner layer quality model is mainly made for the steps of cutting, inner layer board dry film, exposure, SES, acid etching, dry film removal, blackening, and lamination;

[0039] The PCB outer layer quality model is mainly made for PTH, outer lamination, circuit etching, dry film removal, spraying, development, molding and other links;

[0040] PCB product quality model is mainly used to make PCB product quality models for finished products, testing, final inspection and other links;

[0041] The specific quality model parameters and quality inspection identification codes in this embodiment are shown in the following table (the process flow of each quality model and the quality inspection parameters can be modified, added or deleted according to the actual production environment):

[0042]

[0043]

[0044] The PCB product quality identification code is generated based on the inner layer identification code, outer layer identification code and PCB product quality qualified identification code.

[0045] The overall quality model is expressed as:

[0046] Right now:

[0047] Where: DT (t) NZ is the quality model for printed circuit boards; (t) is the inner layer quality model; WJ (t) is the outer mass model; CP (t) Product quality model.

[0048] 5. The service model and service module of the production monitoring platform formulate the quality model configuration quality pass rate of each module in the PCB production process.

[0049]

[0050] Where: P NZ(t)is the quality qualification rate of the inner layer quality model; W is the parameter weight; A(t) is the thermal conductivity qualification rate, B(t) is the high temperature resistance qualification rate, C(t) is the mechanical strength qualification rate, D(t) is the pH qualification rate, E(t) is the current density qualification rate, F(t) is the wiring qualification rate, G(t) is the hole position qualification rate, H(t) is the aperture qualification rate, I(t) is the hole spacing qualification rate, G(t) is the hole wall roughness qualification rate, K(t) is the pad qualification rate, and θ is the deviation value; (each parameter value can be adjusted or modified according to actual production conditions).

[0051]

[0052] Where: P WJ(t) is the quality pass rate of the outer layer quality model; W is the parameter weight; L(t) is the solderability pass rate, M(t) is the line tear strength pass rate, N(t) is the bending strength pass rate, O(t) is the section pass rate, P(t) is the S / M adhesion pass rate, Q(t) is the Gold (gold-plated layer) adhesion pass rate, R(t) is the thermal shock pass rate, S(t) is the ion contamination pass rate, T(t) is the impedance pass rate, and θ is the deviation value; (the values ​​of each parameter can be adjusted or modified according to actual production conditions)

[0053]

[0054] Where: P CP(t) is the quality pass rate of the product quality model; W is the parameter weight; U(t) is the audit pass rate, V(t) is the IQC / IPQC pass rate, W(t) is the S\M or gold surface peeling pass rate, X(t) is the scratch pass rate, Y(t) is the board surface foreign matter pass rate, Z(t) is the damage pass rate, etc., and θ is the deviation value; (each parameter value can be adjusted or modified according to actual production conditions)

[0055] 6. The service model and service module of the production monitoring platform formulate the quality model of each module to monitor the PCB production process. Each module quality model has its own threshold value for the quality pass rate P. Assuming that the threshold value of P is Q (the Q value is set according to the actual production situation), when the calculation steps of the quality pass rate P of each module quality model are repeated N times, the average value of the different results of the repeated N steps is calculated. The calculation formula for the average value of the parameter prediction value is:

[0056]

[0057] Among them, Z (t) The average value of P ij(t) Configure the quality pass rate P value for each module quality model, N is a constant. (t) >Q value, the quality is unqualified and the production monitoring platform system automatically alarms.(t) When <=Q value, the production monitoring platform system displays the information of each parameter (A~Z);

[0058] The specific quality inspection flow chart is as follows Figure 2 shown.

[0059] 7. The production monitoring platform monitors the quality models of each module in the PCB production process in real time to ensure the quality of PCB boards.

[0060] In this embodiment, the PCB identification code is unique. The identification codes applied to the same product at different production stages allow for quality testing of the same product at each stage of the production process, further ensuring product quality. Using the PCB identification code for quality testing allows for tracking and monitoring the quality of each step in the production process for the same PCB identification code. Each module quality model is configured with a threshold for the quality pass rate P to meet quality testing requirements.

[0061] The functions implemented in the above embodiments can be realized by embedding the IoT big data platform into the PCB production system. The overall architecture is as follows: Figure 3 shown.

[0062] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0063] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0066] The present invention is not limited to the above-mentioned optimal implementation mode. Anyone can derive various other forms of a printed circuit board quality monitoring method and device based on a big data model under the guidance of the present invention. All equivalent changes and modifications made within the scope of the patent application of the present invention should fall within the scope of the present invention.

Claims

1. A printed circuit board quality monitoring method based on a big data model, characterized by: During the production process, a unique PCB quality identification code is generated for the PCB; the PCB quality identification code is generated based on the inner layer identification code, the outer layer identification code and the PCB product quality qualified identification code; the inner layer identification code is generated based on the PCB inner layer quality model by searching the laminated structure of the product and associating the identification codes of multiple core boards; the outer layer identification code is formed using a through-hole coding machine based on the PCB outer layer quality model and is associated with the inner layer identification code; the PCB product quality qualified identification code is generated by the PCB product quality model.

2. The method for monitoring printed circuit board quality based on a big data model according to claim 1, characterized in that: The PCB inner layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB inner layer quality detection parameters and setting deviation values.

3. The method for monitoring printed circuit board quality based on a big data model according to claim 1, wherein: The PCB outer layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outer layer quality detection parameters and setting deviation values.

4. The method for monitoring printed circuit board quality based on a big data model according to claim 1, wherein: The PCB product quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outbound quality inspection parameters and setting deviation values.

5. A printed circuit board quality monitoring method based on a big data model according to any one of claims 2 to 4, characterized in that: The qualified rate data is obtained by collecting data during the PCB production process and updating it in real time.

6. A printed circuit board quality monitoring method based on a big data model according to any one of claim 5, characterized in that: The qualified rate data and their overall average values ​​used in the PCB inner layer quality model, PCB outer layer quality model and PCB product quality model are all set with corresponding thresholds. When any qualified rate data or overall average value is monitored to exceed the threshold, an alarm is activated.

7. A printed circuit board quality monitoring device based on a big data model, characterized in that: Used to generate a unique PCB quality identification code for PCBs during the production process; including: The inner layer identification code generation module is used to generate the inner layer identification code by searching the laminate structure of the product based on the PCB inner layer quality model and correlating the identification codes of multiple core boards; An outer layer identification code generation module is used to generate the outer layer identification code using a through-hole coding machine based on the PCB outer layer quality model and associate it with the inner layer identification code; A PCB product quality qualified identification code generation module is used to generate the PCB product quality qualified identification code from the PCB product quality model; The PCB quality identification code generation module is used to generate the PCB quality identification code based on the inner layer identification code, the outer layer identification code and the PCB product quality qualified identification code.

8. The printed circuit board quality monitoring device based on a big data model according to claim 7, characterized in that: The PCB inner layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB inner layer quality detection parameters and setting deviation values; The PCB outer layer quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outer layer quality detection parameters and setting deviation values; The PCB product quality model is constructed by assigning weights to the qualified rates corresponding to the PCB outbound quality inspection parameters and setting deviation values; The qualified rate data is obtained by collecting data during the PCB production process and updating it in real time.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the printed circuit board quality monitoring method based on a big data model as described in any one of claims 1 to 6 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the printed circuit board quality monitoring method based on a big data model as described in any one of claims 1 to 6 are implemented.

Images