Intelligent DES production line

Abstract

The invention provides an intelligent DES production line. Products are pretreated through a pretreatment production line; the copper thickness detection and board separation equipment detects the copper thickness of each position of an upper board surface and a lower board surface of a product, performs classification according to different board thickness ranges, and transmits detection classification data to the data processing center; the data processing center receives the product information of the product, and outputs a corresponding target production parameter through a pre-trained big data model based on the product information; wherein the product information comprises the detection classification data and dry film thickness and circuit related data received from an exposure machine; the DES production line receives the target production parameters, carries out parameter adjustment based on the target production parameters and then carries out production work on products; the detection equipment is used for detecting and re-checking the line width and the line distance of products produced by the DES production line; and when the detection recheck is passed, a detection recheck result is fed back to the data processing center for storage, or when the detection recheck is not passed, the detection recheck result is reported to the data processing center for parameter optimization. Therefore, the etching process can be optimized, the precision and the flexibility are improved, and errors caused by manual intervention are reduced; the production efficiency is improved; and the rejection rate of the first plate is reduced.

Description

Technical Field

[0001] The present invention relates to the field of printed circuit board manufacturing, and particularly to an intelligent DES production line. Background Art

[0002] In the printed circuit board industry, products are small in quantity and diverse in variety, and each product has its own different parameters. For enterprises, how to find the best parameters for manufacturing products in a short time highly depends on the experience of senior personnel. In addition, the PCB manufacturing process is diverse and lengthy. When encountering any situation of poor quality, exploring the faulty link also highly depends on the judgment of senior personnel. Over time, with the market demand for high quality and high efficiency, the pressure and workload of senior personnel are becoming increasingly heavy, making it difficult to focus on thinking about deeper process and operation improvement strategies.

[0003] The current industry pain points include the following: 1. The first board must be confirmed every 12 - 24 hours for the same part number; 2. Frequent switching of part numbers for small batches of multiple part numbers on carrier boards and sample boards; 3. Process technicians adjust parameters entirely based on experience, and at the same time are affected by people's experience and emotions, without data storage, unable to ensure the selection of the optimal solution, and the quality fluctuates greatly; 4. For high - requirement boards, process engineers need to repeatedly verify parameters, affecting production capacity and efficiency.

[0004] Therefore, there is an urgent need to improve the existing DES (Developing Etching Stripping) production line. Summary of the Invention

[0005] Aiming at the above - mentioned defects, the purpose of the present invention is to provide an intelligent DES production line, which can improve production efficiency and reduce the scrap rate of the first board.

[0006] To achieve the above purpose, the present invention provides an intelligent DES production line, including:

[0007] A pre - treatment production line for pre - treating products;

[0008] A copper thickness detection and board - splitting device for detecting the copper thickness at each position on the upper and lower surfaces of the product, classifying according to different board - thickness ranges, and transmitting the detection and classification data to a data processing center;

[0009] The data processing center is used to receive the product information of the product and output corresponding target production parameters based on the product information through a pre - trained big - data model; wherein, the product information includes the detection and classification data and the dry - film thickness and circuit - related data received from the exposure machine.

[0010] The DES production line is used to receive the target production parameters, and based on the target production parameters, adjust the parameters and then carry out the production work on the product; wherein, the target production parameters at least include compensation etching working parameters, working line speed, working temperature, chemical solution concentration, and working spraying pressure;

[0011] The detection device is used to detect and review the line width and line pitch of the product produced by the DES production line; and when the detection and review are passed, the detection and review results are fed back to the data processing center for storage, or when the detection and review are not passed, the detection and review results are reported to the data processing center for parameter optimization.

[0012] Optionally, it further includes a chemical solution detection instrument, which is used to monitor the chemical solution data of the DES production line in real time and feed it back to the data processing center.

[0013] Optionally, the pre-trained big data model is a neural network model based on deep learning, and its training data includes historical production parameters, product defect types and corresponding copper thickness, dry film thickness, and circuit data; and the big data model optimizes the parameter prediction accuracy in real time through a dynamic update mechanism.

[0014] Optionally, the DES production line is provided with an adaptive control module for spot spraying of etching solution, and the adaptive control module automatically controls the spot spraying according to the difference in the copper thickness distribution before etching of the product.

[0015] Optionally, the data processing center is provided with an abnormal warning module, and the abnormal warning module is used to generate a warning prompt message when the monitored classification data and / or AOI detection results exceed the preset threshold.

[0016] Optionally, the pre-treatment production line is specifically used to carry out substrate cutting, substrate cleaning, and surface roughening on the product.

[0017] The intelligent DES production line described in the present invention preprocesses products through a pretreatment production line; the copper thickness detection and board splitting equipment detects the copper thickness at each position on the upper and lower surfaces of the product and classifies them according to different board thickness ranges, and transmits the detected classification data to the data processing center; the data processing center receives the product information of the product and outputs corresponding target production parameters based on the product information through a pre-trained big data model; wherein, the product information includes the detected classification data and the dry film thickness and circuit-related data received from the exposure machine; the DES production line receives the target production parameters and adjusts the parameters based on the target production parameters and then carries out the production work on the product; the detection equipment is used to detect and verify the line width and line pitch of the products produced by the DES production line; and when the detection and verification are passed, the detection and verification results are fed back to the data processing center for storage, or when the detection and verification are not passed, the detection and verification results are reported to the data processing center for parameter optimization. That is, the present invention can realize the intelligent optimization of production parameters and the closed-loop control of product quality by integrating big data analysis, adaptive control and real-time detection technologies. Brief Description of the Drawings

[0018] Figure 1 It is a schematic diagram of the connection relationship of the intelligent DES production line provided in the first embodiment of the present invention. Detailed Description of the Embodiments

[0019] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0020] It should be noted that the references to "one embodiment", "embodiment", "example embodiment", etc. in this specification mean that the described embodiment may include specific features, structures or characteristics, but not every embodiment must include these specific features, structures or characteristics. In addition, such expressions do not refer to the same embodiment. Further, when combining an embodiment to describe specific features, structures or characteristics, it has been shown that it is within the knowledge of those skilled in the art to combine such features, structures or characteristics into other embodiments whether or not explicitly described.

[0021] Before describing the various embodiments of the present application in detail, first briefly describe the technical concept of the present application: Currently, the traditional DES production line has the following problems: 1. Parameter adjustment depends on manual experience, and etching parameters (such as line speed, temperature, and chemical solution concentration) need to be set manually, which is likely to lead to poor product consistency due to human errors; 2. Detection lag, key indicators such as copper thickness and line width need to be sampled offline, and production parameters cannot be adjusted in real time based on feedback; 3. Uncontrollable chemical solution consumption, lack of dynamic regulation in the etching solution spraying, resulting in waste of chemical solutions; 4. Historical data is not systematically stored, making it difficult to quickly locate the root cause of defects. In response to this, the present invention provides an intelligent DES production line with self-learning and self-optimization capabilities. Through the collaboration of intelligent devices and big data model prediction, it realizes full-flow automatic parameter adjustment and quality closed-loop control, improving production efficiency and product yield. The following describes the specific principle of the intelligent DES production line of the present application in combination with specific embodiments.

[0022] Figure 1 Figure 4 shows an intelligent DES production line provided by an embodiment of the present invention, which includes a pre-treatment production line 10, a copper thickness detection and board splitting device 20, a data processing center 30, an exposure machine 40, a DES production line 50, and a detection device 60; among them:

[0023] The pre-treatment production line 10 is used to pre-treat the product; the pre-treatment production line 10 of this embodiment is specifically used to perform substrate cutting, substrate cleaning, and surface roughening on the product; that is, through the pre-treatment production line 10, substrate cutting, cleaning, and surface roughening are performed to provide a standardized substrate for subsequent processes.

[0024] The copper thickness detection and board splitting device 20 is used to detect the copper thickness at each position on the upper and lower surfaces of the product and classify according to different board thickness ranges, and transmit the detection and classification data to the data processing center; for example, a non-contact sensor can be used to detect the copper thickness at different positions on the upper and lower surfaces of the product substrate, and automatically classify according to a preset board thickness range (such as <10μm, 10 - 20μm, >20μm); then the detection and classification data is uploaded to the data processing center 30 in real time.

[0025] The data processing center 30 is used to receive the product information of the product, and the product information includes the detection and classification data uploaded from the copper thickness detection and board splitting device 20 and the dry film thickness and circuit-related data received from the exposure machine 40; then, based on the received product information, the corresponding target production parameters are output through a pre-trained big data model; specifically, the data processing center 30 inputs the received product information into the big data model to obtain the target production parameters output by the model. The target production parameters are the optimal solution parameters given by the analysis of the big data model, no longer relying on process engineers, reducing manual parameter adjustment, effectively saving the first board time and reducing the scrap rate of the first board.

[0026] Among them, the exposure machine 40 transmits the dry film thickness and line-related data to the data processing center 30, and the line-related data is data such as the line working height of the line layout; the product information specifically includes information such as copper thickness, line width, line pitch, dry film thickness, and line layout.

[0027] The DES production line 50 is used to receive the target production parameters, and based on the target production parameters, adjust the parameters and then carry out the production work on the product; among them, the target production parameters at least include compensation etching work parameters, working line speed, working temperature, chemical solution concentration, and working spray pressure; the compensation etching work parameters are applied to the compensation etching section of the DES production line 50 to control the individual compensation spray time of each nozzle according to the thickness of each board and the copper thickness distribution, and eliminate the copper thickness difference on the board surface; the DES production line 50 adjusts the parameters for production according to the target production parameters provided by the data processing center 30, and the product is transmitted to the detection device 60 after being produced by the DES production line 50.

[0028] The detection device 60 is used to detect and review the line width and line pitch of the product produced by the DES production line 50; and when the detection and review are passed, the detection and review results are fed back to the data processing center 30 for storage, or when the detection and review are not passed, the detection and review results are reported to the data processing center 30 for parameter optimization. In an optional embodiment, the detection device 60 can use optical imaging technology to review the line width and line pitch, compare the monitoring results with the preset values, so as to determine whether they meet the requirements. If they do not meet the requirements, it means that the detection and review results are not passed, otherwise it means that the detection and review results are passed.

[0029] The detection device 60 is an AOI or other detection device capable of measuring line width and line pitch.

[0030] Further, after receiving the unqualified data fed back by the detection device 60, the data processing center 30 automatically analyzes the reasons according to the fed-back data, optimizes the relevant parameters, and then sends the parameters to the DES production line 50.

[0031] This embodiment further includes a chemical solution detection instrument 70, which is used to monitor the chemical solution data of the DES production line in real time and feed it back to the data processing center 30; the chemical solution data can be data such as etching solution concentration, PH value, and impurity content, and the data is fed back to the data processing center 30 to dynamically correct the corresponding chemical solution ratio.

[0032] The pre-trained big data model is a neural network model based on deep learning (such as a convolutional neural network), and its training data includes historical production parameters, product defect types, and corresponding copper thickness, dry film thickness, and line data; and the big data model optimizes the parameter prediction accuracy in real time through a dynamic update mechanism. Specifically, the model optimizes the prediction accuracy in real time through the correlation analysis of historical production parameters, defect types (such as over-etching, residual copper) and corresponding copper thickness / dry film data.

[0033] In this embodiment, machine learning and deep learning algorithms are used to monitor and adjust the etching conditions in real time to ensure that each board meets the optimal requirements.

[0034] In an optional implementation, the DES production line 50 is provided with an adaptive control module for spot spraying of the etching solution. The adaptive control module performs automatic spot spraying control according to the difference in the copper thickness distribution before product etching; that is, the adaptive control module adjusts the spot spraying position and flow rate of the etching solution according to the difference in copper thickness distribution to ensure etching uniformity; among them, the difference in copper thickness distribution is analyzed and determined by the data processing center 30 based on product information and then statistically recorded in the target production parameters; specifically in implementation, the adaptive control module can control the nozzle to increase the spraying frequency in the local high copper thickness area. The adaptive control module can also dynamically adjust the flow rate and heating power of the liquid circulation system according to the chemical solution concentration and working temperature in the target production parameters, and adjust the nozzle opening based on the feedback value of the spraying pressure to achieve etching uniformity.

[0035] Furthermore, the data processing center 30 is provided with an abnormal warning module, and the abnormal warning module is used to generate a warning prompt message when the monitored classification data and / or the AOI detection result exceeds a preset threshold.

[0036] To sum up, the intelligent DES production line described in the present invention preprocesses the product through the preprocessing production line; the copper thickness detection and board splitting equipment detects the copper thickness at each position on the upper and lower surfaces of the product and classifies according to different board thickness ranges, and transmits the detected classification data to the data processing center; the data processing center receives the product information of the product and outputs the corresponding target production parameters based on the product information through a pre-trained big data model; among them, the product information includes the detected classification data and the dry film thickness and circuit-related data received from the exposure machine; the DES production line receives the target production parameters, and performs parameter adjustment based on the target production parameters and then carries out production work on the product; the detection equipment is used to detect and review the line width and line pitch of the product produced by the DES production line; and when the detection and review are passed, the detection and review result is fed back to the data processing center for storage, or when the detection and review are not passed, the detection and review result is reported to the data processing center for parameter optimization. That is, the present invention can realize the intelligent optimization of production parameters and the closed-loop control of product quality through the integration of big data analysis, adaptive control and real-time detection technologies.

[0037] Certainly, the present invention may also have many other embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art can make various corresponding changes and deformations according to the present invention, but these corresponding changes and deformations should all fall within the protection scope of the appended claims of the present invention.

Claims

1. An intelligent DES production line, characterized in that: Included are: Pre-treatment production line, used to pre-treat products; Copper thickness detection and board separation equipment, used to detect the copper thickness of the upper and lower board surfaces of the product and classify them according to different board thickness ranges, and transmit the detection and classification data to the data processing center; The data processing center is used to receive product information of the product and output corresponding target production parameters through a pre-trained big data model based on the product information; wherein the product information includes the detection classification data and the dry film thickness and circuit-related data received from the exposure machine; The DES production line is used to receive the target production parameters and perform production work on the product after adjusting the parameters based on the target production parameters; wherein the target production parameters at least include compensation etching working parameters, working line speed, working temperature, chemical concentration and working spray pressure; The detection equipment is used to detect and verify the line width and line spacing of the products produced by the DES production line; and when the detection review is passed, the detection review result is fed back to the data processing center for storage, or when the detection review is not passed, the detection review result is reported to the data processing center for parameter optimization.

2. The intelligent DES production line according to claim 1 is characterized in that: It also includes a medicine liquid detection instrument, which is used to monitor the medicine liquid data of the DES production line in real time and feed it back to the data processing center.

3. The intelligent DES production line according to claim 1 is characterized in that: The pre-trained big data model is a neural network model based on deep learning, and its training data includes historical production parameters, product defect types and corresponding copper thickness, dry film thickness, and circuit data; and the big data model optimizes parameter prediction accuracy in real time through a dynamic update mechanism.

4. The intelligent DES production line according to claim 1 is characterized in that: The DES production line is provided with an adaptive control module for etching liquid spot spraying, and the adaptive control module performs automatic spot spraying control according to the difference in copper thickness distribution of the product before etching.

5. The intelligent DES production line according to claim 1 is characterized in that: The data processing center is provided with an abnormal warning module, and the abnormal warning module is used to generate warning prompt information when the monitoring classification data and / or the AOI detection result exceeds a preset threshold.

6. The intelligent DES production line according to claim 1, characterized in that: The pre-processing production line is specifically used for performing substrate cutting, substrate cleaning and board surface roughening on the product.

Images