Multi-layer rigid-flex circuit board pressing control method and multi-layer rigid-flex circuit board pressing control system

Abstract

The invention relates to a lamination control method and system for a multilayer rigid-flex circuit board, relates to the field of data processing, and provides a lamination control method and system for the multilayer rigid-flex circuit board, which comprises the following steps of: partitioning pressure and temperature according to a pressing plate lamination log by utilizing a hierarchical clustering partitioning technology; the pressure and temperature distribution conditions of the pressing plate in different areas can be accurately identified; temperature field simulation is carried out through the pressure and temperature time sequence information of the target subarea, the temperature distribution condition of the multilayer rigid-flexible circuit board can be monitored and predicted in real time, and when the temperature field time sequence information is consistent with the standard, a pressing plate is controlled to execute pressing control through the pressure and temperature time sequence information, so that the pressing efficiency is improved. And the lamination quality of the multilayer rigid-flexible circuit board is remarkably improved, so that the technical problems of large temperature and pressure fluctuation and non-uniform distribution caused by the problems of material heat-conducting property difference, multilayer interface heat transfer lag, pressing plate abrasion and the like are effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method and system for controlling the lamination of a multi-layer rigid-flex printed circuit board. Background Art

[0002] In the field of electronic manufacturing, multi-layer rigid-flex printed circuit boards are widely used in various complex electronic devices due to their combination of the stability of rigid boards and the flexibility of flexible boards. In the manufacturing process, the lamination process is one of the key links. Pressure and temperature are applied to the multi-layer printed circuit board through a press plate to achieve interlayer bonding. Traditional lamination control methods mainly rely on preset temperature and pressure parameters, which are usually set based on experience and have large fluctuations during the lamination process.

[0003] On the one hand, there are significant differences in the thermal conductivity of rigid materials and flexible materials, resulting in different heat transfer rates between different material layers; on the other hand, after the multi-layer boards are stacked, the heat needs to penetrate more interfaces, causing the inner layer temperature to lag behind the outer layer. These factors lead to large fluctuations in temperature and pressure; in addition, during long-term use, the press plate will have uneven pressure and temperature distribution due to wear, further increasing the difficulty of controlling the temperature and pressure of the multi-layer rigid-flex printed circuit board. At present, there is a lack of refined temperature and pressure control solutions for the lamination of multi-layer rigid-flex printed circuit boards in the market, and it is difficult to meet the requirements of high-quality lamination.

[0004] Most of the current existing lamination control methods stay at setting temperature and control schemes according to manual experience, lacking precise and effective control schemes, resulting in the technical problems of inaccurate temperature and pressure control during the lamination of multi-layer rigid-flex printed circuit boards, which affects the use effect of the lamination of multi-layer rigid-flex printed circuit boards. Summary of the Invention

[0005] In view of the technical problems in the prior art that the temperature and pressure control during the lamination of multi-layer rigid-flex printed circuit boards is not precise, which affects the use effect of the lamination of multi-layer rigid-flex printed circuit boards, the present invention provides a method and system for controlling the lamination of multi-layer rigid-flex printed circuit boards to solve this problem.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In a first aspect, the present invention provides a method for controlling the lamination of a multi-layer rigid-flex printed circuit board, including:

[0008] Performing hierarchical clustering partitioning on the press plate pressure according to the press plate lamination log to obtain a press plate pressure partition;

[0009] Performing hierarchical clustering partitioning on the press plate temperature according to the press plate lamination log to obtain a press plate temperature partition;

[0010] Taking the intersection of the press plate pressure partition and the press plate temperature partition to obtain a press plate target partition;

[0011] Receive pressure timing information and temperature timing information, perform frequent temperature and pressure statistics according to the target partition of the press plate, and obtain the target partition pressure timing information and the target partition temperature timing information;

[0012] Based on the target partition pressure timing information and the target partition temperature timing information, perform a temperature field simulation on the multi-layer rigid-flex printed circuit board geometry to obtain temperature field timing information;

[0013] When the temperature field timing information is consistent with the standard temperature field timing information, control the press plate to perform lamination control according to the pressure timing information and the temperature timing information.

[0014] In a second aspect, the present invention provides a lamination control system for a multi-layer rigid-flex printed circuit board, including:

[0015] A press plate pressure partition template for performing hierarchical clustering partitioning of the press plate pressure according to the press plate lamination log to obtain the press plate pressure partition;

[0016] A press plate temperature partition module for performing hierarchical clustering partitioning of the press plate temperature according to the press plate lamination log to obtain the press plate temperature partition;

[0017] A press plate target partition module for taking the intersection of the press plate pressure partition and the press plate temperature partition to obtain the press plate target partition;

[0018] A pressure and temperature timing information module for receiving pressure timing information and temperature timing information, performing frequent temperature and pressure statistics according to the target partition of the press plate, and obtaining the target partition pressure timing information and the target partition temperature timing information;

[0019] A temperature field timing information module for performing a temperature field simulation on the multi-layer rigid-flex printed circuit board geometry based on the target partition pressure timing information and the target partition temperature timing information to obtain the temperature field timing information;

[0020] A lamination control module for controlling the press plate to perform lamination control according to the pressure timing information and the temperature timing information when the temperature field timing information is consistent with the standard temperature field timing information.

[0021] The beneficial effects of the present invention are as follows: The present invention provides a method and system for controlling the lamination of a multi-layer rigid-flex printed circuit board. Compared with the traditional lamination control method that sets the temperature and control scheme based on manual experience, by using the hierarchical clustering partition technology, the pressure and temperature are partitioned according to the lamination log of the press plate, which can accurately identify the pressure and temperature distribution of the press plate in different regions, and effectively solve the problem of uneven distribution caused by the wear of the press plate. By taking the intersection to obtain the target partition of the press plate and combining the pressure time series information and temperature time series information for frequent temperature and pressure statistics, the accuracy of temperature and pressure control is further refined. Through the temperature field simulation using the pressure and temperature time series information of the target partition, the temperature distribution of the multi-layer rigid-flex printed circuit board can be monitored and predicted in real time, and compared with the standard temperature field time series information to ensure that the temperature field during lamination meets the expectations. When the temperature field time series information is consistent with the standard, the press plate is controlled to perform lamination control through the pressure and temperature time series information, thereby effectively solving the problems of large temperature and pressure fluctuations and uneven distribution caused by differences in material thermal conductivity, heat transfer lag at the multi-layer interface, and wear of the press plate, significantly improving the lamination quality of the multi-layer rigid-flex printed circuit board, and solving the technical problem of refined temperature and pressure control for the lamination of multi-layer rigid-flex printed circuit boards. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 FIG. is a schematic flow chart of a method for controlling the lamination of a multi-layer rigid-flex printed circuit board provided by the present invention;

[0023] Figure 2 FIG. is a schematic structural diagram of a system for controlling the lamination of a multi-layer rigid-flex printed circuit board provided by the present invention.

[0024] Reference numerals: Press plate pressure partition template 11, press plate temperature partition module 12, press plate target partition module 13, pressure and temperature time series information module 14, temperature field time series information module 15, lamination control module 16. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present invention.

[0026] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0027] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0028] Embodiment 1:

[0029] As Figure 1 shown, an embodiment of the present invention provides a method for controlling the lamination of a multi-layer rigid-flex printed circuit board. The method specifically includes the following steps:

[0030] S10: Perform hierarchical clustering partitioning of the press lamination pressure based on the press lamination log to obtain the press lamination pressure partition;

[0031] Further, performing hierarchical clustering partitioning of the press lamination pressure based on the press lamination log to obtain the press lamination pressure partition, and executing step S10 includes:

[0032] S11: Obtain the starting geometry and the target geometry of the multi-layer rigid-flex circuit board geometry;

[0033] Further, the press lamination log refers to a file recording various parameters and states during the lamination of the multi-layer rigid-flex circuit board by the press, including information such as time, pressure, temperature, position, etc.; hierarchical clustering partitioning refers to a data processing method that groups data points into clusters with similar characteristics by calculating the similarity or distance between data points and organizes them in a hierarchical structure; the starting geometry and the target geometry refer to the starting geometry being the initial shape and size of the circuit board before lamination, and the target geometry being the final shape and size that the circuit board is expected to reach after lamination; the temperature time series recording information refers to the data recording the change of temperature over time during the lamination process; the pressure distribution recording information refers to the information recording the pressure distribution of the press in different regions during the lamination process.

[0034] S12: Retrieve the press bonding log of the target position number press plate that meets the starting geometric body and the target geometric body;

[0035] S13: Extract the first pressure distribution record information with the same temperature time series record information to the Nth pressure distribution record information from the press bonding log of the press plate;

[0036] S14: Perform hierarchical clustering partitioning of the press plate pressure based on the first pressure distribution record information to the Nth pressure distribution record information to obtain the press plate pressure partition.

[0037] Exemplarily, obtain the starting geometric body and the target geometric body of the multi-layer rigid-flexible circuit board geometry: Assume that the starting geometric body of the multi-layer rigid-flexible circuit board is a multi-layer stack with a thickness of 1.5 mm, including 3 rigid layers and 2 flexible layers, and the target geometric body is a flat circuit board with a thickness of 1.2 mm, and each layer is tightly combined.

[0038] Retrieve the press bonding log of the target position number press plate that meets the starting geometric body and the target geometric body, and retrieve the historical press bonding log of the target position number press plate from the database of the press bonding equipment. Assume that the retrieved press bonding log records the following data:

[0039] Time Temperature (°C) Pressure (MPa) Position (x,y) 0s 150 0.5 (0,0) 10s 150 0.6 (10,10) 20s 150 0.7 (20,20) 30s 150 0.8 (30,30) 40s 150 0.9 (40,40) 50s 150 1.0 (50,50)

[0040] Extract the first pressure distribution record information with the same temperature time series record information to the Nth pressure distribution record information from the press bonding log of the press plate. Assume that the temperature time series record information is 150 °C, and extract the corresponding pressure distribution record information:

[0041] Time Pressure (MPa) Position (x,y) 0s 0.5 (0,0) 10s 0.6 (10,10) 20s 0.7 (20,20) 30s 0.8 (30,30) 40s 0.9 (40,40) 50s 1.0 (50,50)

[0042] Perform hierarchical clustering partitioning of the press plate pressure based on the first pressure distribution record information to the Nth pressure distribution record information to obtain the press plate pressure partition, and use the hierarchical clustering algorithm to partition the extracted pressure distribution record information. Assume that the Euclidean distance is used as the similarity measure, and calculate the distance matrix between each point:

[0043] Coordinate point (0,0) (10,10) (20,20) (30,30) (40,40) (50,50) (0,0) 0 14.14 28.28 42.43 56.57 70.71 (10,10) 14.14 0 14.14 28.28 42.43 56.57 (20,20) 28.28 14.14 0 14.14 28.28 42.43 (30,30) 42.43 28.28 14.14 0 14.14 28.28 (40,40) 56.57 42.43 28.28 14.14 0 14.14 (50,50) 70.71 56.57 42.43 28.28 14.14 0

[0044] According to the hierarchical clustering algorithm, divide these points into multiple partitions. Assume that the final division is into 3 partitions:

[0045] Partition 1: (0,0), (10,10)

[0046] Partition 2: (20,20), (30,30)

[0047] Partition 3: (40,40), (50,50)

[0048] Further, based on the first pressure distribution record information up to the Nth pressure distribution record information, perform platen pressure hierarchical clustering partitioning to obtain platen pressure partitioning. Performing step S14 includes:

[0049] S141: Perform neighborhood hierarchical clustering analysis on the first pressure distribution record information to obtain the first pressure distribution partitioning;

[0050] S142: Until performing neighborhood hierarchical clustering analysis on the Nth pressure distribution record information to obtain the Nth pressure distribution partitioning;

[0051] S143: Perform pairwise enumeration evaluation of distribution similarity on the first pressure distribution partitioning up to the Nth pressure distribution partitioning to obtain a number of partitioning similarities;

[0052] S144: According to the number of partitioning similarities, perform outlier distribution partitioning deletion on the first pressure distribution partitioning up to the Nth pressure distribution partitioning to obtain a concentrated pressure distribution partitioning, and take the intersection of the concentrated pressure distribution partitioning as the platen pressure partitioning.

[0053] Exemplarily, perform neighborhood hierarchical clustering analysis on the first pressure distribution record information to obtain the first pressure distribution partitioning. Assume the first pressure distribution record information is as follows:

[0054] Time Pressure (MPa) Position (x,y) 0s 0.5 (0,0) 10s 0.6 (10,10) 20s 0.7 (20,20)

[0055] Use neighborhood hierarchical clustering analysis to calculate the similarity of each data point within the local neighborhood. Assume the Euclidean distance is used as the similarity metric, and the calculation results are as follows:

[0056] The distance between (0, 0) and (10, 10) is 14.14

[0057] The distance between (10, 10) and (20, 20) is 14.14

[0058] According to the hierarchical clustering algorithm, divide these points into 2 partitions:

[0059] Partition 1.1: (0, 0), (10, 10)

[0060] Partition 1.2: (20, 20)

[0061] Perform neighborhood hierarchical clustering analysis on the Nth pressure distribution record information to obtain the Nth pressure distribution partitioning. Assume the Nth pressure distribution record information is as follows:

[0062] Time Pressure (MPa) Position (x,y) 30s 0.8 (30,30) 40s 0.9 (40,40) 50s 1.0 (50,50)

[0063] Using neighborhood hierarchical clustering analysis, calculate the similarity of each data point within its local neighborhood. Assuming Euclidean distance as the similarity metric, the calculation results are as follows:

[0064] The distance between (30, 30) and (40, 40) is 14.14

[0065] The distance between (40, 40) and (50, 50) is 14.14

[0066] According to the hierarchical clustering algorithm, divide these points into 2 partitions:

[0067] Partition N.1: (30, 30), (40, 40)

[0068] Partition N.2: (50, 50)

[0069] Perform pairwise enumeration and evaluation of the distribution similarity for the first pressure distribution partition to the Nth pressure distribution partition to obtain several partition similarities. Calculate the similarity between partition 1.1 and partition N.1. Assuming the average value of the pressure values is used as the similarity evaluation criterion:

[0070] The average pressure value of partition 1.1 is 0.55

[0071] The average pressure value of partition N.1 is 0.85

[0072] Calculate the similarity:

[0073] Similarity = |0.55 - 0.85| = 0.3

[0074] Similarly, calculate the similarities between other partitions:

[0075] The similarity between partition 1.2 and partition N.2 = |0.7 - 1.0| = 0.3

[0076] Based on the several partition similarities, delete the outlier distribution partitions for the first pressure distribution partition to the Nth pressure distribution partition to obtain concentrated pressure distribution partitions, and take the intersection of the concentrated pressure distribution partitions, which is set as the platen pressure partition

[0077] According to the similarity evaluation results, assume that partitions with a similarity greater than 0.2 are considered outlier partitions and need to be deleted. Therefore:

[0078] The similarity between partition 1.1 and partition N.1 is 0.3, delete partition 1.1 and partition N.1

[0079] The similarity between partition 1.2 and partition N.2 is 0.3, delete partition 1.2 and partition N.2

[0080] After screening, the partitions that remain are:

[0081] Concentrated pressure distribution partition: None

[0082] Since all partitions have been deleted, it means that no partition with similar pressure distribution characteristics can be found under the current data. At this time, the similarity threshold can be adjusted. For example, the threshold can be increased to 0.4 and the screening can be performed again.

[0083] Assume that after adjustment, the similarities of partition 1.2 and partition N.2 meet the requirements and are retained. Take the intersection of these two partitions as the platen pressure partition:

[0084] Platen pressure partition: (20, 20), (50, 50)

[0085] Furthermore, pairwise enumeration and evaluation of the distribution similarities of the first pressure distribution partition to the Nth pressure distribution partition are performed to obtain several partition similarities. Performing step S143 includes:

[0086] S1431: Connect the centers of the first pressure distribution partition to obtain a first pattern;

[0087] S1432: Connect the centers of the second pressure distribution partition to obtain a second pattern;

[0088] S1433: Calculate the similarity between the first pattern and the second pattern to obtain a first partition similarity and add it to the several partition similarities.

[0089] Exemplarily, connect the centers of the first pressure distribution partition to obtain a first pattern. Assume the first pressure distribution partition is as follows:

[0090] Partition 1.1: (0, 0), (10, 10)

[0091] Partition 1.2: (20, 20)

[0092] Calculate the center position of each partition:

[0093] The center position of partition 1.1 is: ((0 + 10) / 2, (0 + 10) / 2) = (5, 5)

[0094] The center position of partition 1.2 is: (20, 20)

[0095] Connect these center positions to form a first pattern. Assume the first pattern is a simple line segment connecting the points (5, 5) and (20, 20).

[0096] Connect the centers of the second pressure distribution partition to obtain a second pattern. Assume the second pressure distribution partition is as follows:

[0097] Partition N.1: (30, 30), (40, 40)

[0098] Partition N.2: (50, 50)

[0099] Calculate the central position of each partition:

[0100] The central position of Partition N.1 is: ((30 + 40) / 2, (30 + 40) / 2) = (35, 35)

[0101] The central position of Partition N.2 is: (50, 50)

[0102] Connect these central positions to form a second pattern. Assume the second pattern is a simple line segment connecting the points (35, 35) and (50, 50).

[0103] Calculate the similarity between the first pattern and the second pattern to obtain the first partition similarity and add it to the several partition similarities.

[0104] To calculate the similarity between two patterns, a shape matching algorithm can be used. Assume a simple contour similarity calculation method is adopted to evaluate the similarity by comparing geometric features such as the lengths and angles of the two patterns.

[0105] The length of the first pattern: The distance from (5, 5) to (20, 20) is

[0106] The length of the second pattern: The distance from (35, 35) to (50, 50) is

[0107] The lengths of the two patterns are the same, but their positions are different. Assume the similarity calculation formula is: Similarity = 1 / (1 + distance difference)

[0108] Calculate the distance between the central points of the two patterns:

[0109] The central point of the first pattern is: ((5 + 20) / 2, (5 + 20) / 2) = (12.5, 12.5)

[0110] The central point of the second pattern is: ((35 + 50) / 2, (35 + 50) / 2) = (42.5, 42.5)

[0111] The distance between the central points is:

[0112] Calculate the similarity:

[0113] Add this similarity to the several partition similarities.

[0114] Through the above embodiments, the pressure plate is divided into multiple pressure zones, and by calculating the pattern similarity of different zones, the zones with similar pressure distribution characteristics are screened out. This method can effectively identify the pressure change law of the pressure plate in different regions. Especially in the case of uneven pressure distribution caused by the wear of the pressure plate, it can accurately locate the problem area. The finally obtained pressure zones of the pressure plate can provide a refined zoning basis for subsequent pressing control, thus effectively solving the problem of uneven pressure distribution caused by the wear of the pressure plate and achieving the technical effect of improving the pressing quality of multi-layer rigid-flexible printed circuit boards.

[0115] S20: Perform hierarchical clustering partitioning of the pressure plate temperature according to the pressure plate pressing log to obtain the pressure plate temperature zones;

[0116] Furthermore, to obtain the hierarchical clustering partitioning of the pressure plate temperature is the same as to obtain the hierarchical clustering partitioning of the pressure plate pressure, and step S10 is executed.

[0117] S30: Take the intersection of the pressure plate pressure zones and the pressure plate temperature zones to obtain the target zones of the pressure plate;

[0118] Furthermore, execute step S143 to obtain the target zones of the pressure plate.

[0119] S40: Receive the pressure time series information and the temperature time series information, and perform temperature-pressure frequency statistics according to the target zones of the pressure plate to obtain the target zone pressure time series information and the target zone temperature time series information. Executing step S40 includes:

[0120] S41: Constrained by the multi-layer rigid-flexible printed circuit board model and the service life of the press, collect the first partition temperature time series information set to the Mth partition temperature time series information set that meet the pressure time series information and the temperature time series information, and the first partition pressure time series information set to the Mth partition pressure time series information set;

[0121] S42: Perform the simultaneous moment median evaluation on the first partition temperature time series information set to the Mth partition temperature time series information set and the first partition pressure time series information set to the Mth partition pressure time series information set respectively to obtain the target zone pressure time series information and the target zone temperature time series information.

[0122] Exemplarily, collect the first partition temperature time series information set to the Mth partition temperature time series information set that meet the pressure time series information and the temperature time series information, and the first partition pressure time series information set to the Mth partition pressure time series information set. Assume the following constraint conditions for the multi-layer rigid-flexible printed circuit board model and the service life of the press:

[0123] Circuit board model: Model A

[0124] Service life of the press: 2 years

[0125] Collect the pressure and temperature time series information that meets the above conditions from the database of the lamination equipment. Suppose the collected data is as follows:

[0126] Partition Time (s) Pressure (MPa) Temperature (°C) 1.1 0 0.5 150 1.1 10 0.6 150 1.1 20 0.7 150 1.2 0 0.8 150 1.2 10 0.9 150 1.2 20 1.0 150 N.1 0 0.6 150 N.1 10 0.7 150 N.1 20 0.8 150 N.2 0 0.9 150 N.2 10 1.0 150 N.2 20 1.1 150

[0127] Classify this data into the first partition temperature time series information set, the first partition pressure time series information set, until the Mth partition temperature time series information set and the Mth partition pressure time series information set respectively.

[0128] Perform the simultaneous moment central value evaluation on the first partition temperature time series information set until the Mth partition temperature time series information set, and the first partition pressure time series information set until the Mth partition pressure time series information set respectively, to obtain the target partition pressure time series information and the target partition temperature time series information.

[0129] Perform the simultaneous moment central value evaluation on the temperature and pressure time series information of each partition. Taking partition 1.1 and partition N.1 as examples, calculate the central value (such as the average value) at each time point.

[0130]

[0131] Calculate the simultaneous moment central value:

[0132] Time 0s:

[0133] Average pressure: (0.5 + 0.6) / 2 = 0.55 MPa

[0134] Average temperature: (150 + 150) / 2 = 150 °C

[0135] Time 10s:

[0136] Average pressure: (0.6 + 0.7) / 2 = 0.65 MPa

[0137] Average temperature: (150 + 150) / 2 = 150 °C

[0138] Time 20s:

[0139] Average pressure: (0.7 + 0.8) / 2 = 0.75 MPa

[0140] Average temperature: (150 + 150) / 2 = 150 °C

[0141] Take these central values as the pressure time series information and temperature time series information of the target partition.

[0142] Through the above steps, the refined frequent statistics of the temperature and pressure of the target area of the pressing plate are realized. By collecting the pressure and temperature time-series information that meets specific conditions and conducting the centralized value evaluation at the same moment, the pressure and temperature time-series information of the target area can be accurately obtained. These information provide important data support for subsequent pressing control, contribute to the realization of refined temperature control in the pressing of multi-layer rigid-flexible printed circuit boards, and thus effectively solve the problems of large temperature and pressure fluctuations and uneven distribution caused by differences in material thermal conductivity, heat transfer lag at multi-layer interfaces, and wear of the pressing plate, significantly improving the pressing quality of multi-layer rigid-flexible printed circuit boards.

[0143] S50: Based on the target area pressure time-series information and the target area temperature time-series information, perform a temperature field simulation on the multi-layer rigid-flexible printed circuit board geometry to obtain the temperature field time-series information;

[0144] Further, based on the target area pressure time-series information and the target area temperature time-series information, performing a temperature field simulation on the multi-layer rigid-flexible printed circuit board geometry to obtain the temperature field time-series information, the execution of step S50 includes:

[0145] S51: Based on the target area of the pressing plate, construct a pressing plate grid topology. Combine it with the multi-layer rigid-flexible printed circuit board grid body, and perform topological twinning based on a graph neural network to build the architecture of the geometry temperature field fitting model. Among them, the input node of the geometry temperature field fitting model architecture is the target area of the pressing plate, the input data of any area is the pressure time-series information and the temperature time-series information, the output node is the grid temperature field of the multi-layer rigid-flexible printed circuit board grid body, and the multi-layer rigid-flexible printed circuit board grid body will change from the starting grid body to the target grid body at a preset shrinking speed;

[0146] S52: Constrained by the multi-layer rigid-flexible printed circuit board model and the pressing machine model, collect the pressure time-series record information, temperature time-series record information, and the first multi-layer rigid-flexible printed circuit board geometry temperature field time-series record information with a service duration less than or equal to the service duration threshold, and train the geometry temperature field fitting model architecture to obtain the temperature field fitting base model;

[0147] S53: Constrained by the multi-layer rigid-flexible printed circuit board model and the pressing machine position number, collect the target area pressure time-series record information, target area temperature time-series record information, and the second multi-layer rigid-flexible printed circuit board geometry temperature field time-series record information, train the temperature field fitting base model to obtain the temperature field fitting model, and perform a temperature field simulation on the multi-layer rigid-flexible printed circuit board geometry based on the target area pressure time-series information and the target area temperature time-series information to obtain the temperature field time-series information.

[0148] Exemplarily, a pressing plate grid topology is constructed, combined with a multi-layer rigid-flexible printed circuit board grid body, and topology twins are generated based on a graph neural network to build a geometric body temperature field fitting model architecture. Assume the grid topologies of the pressing plate and the multi-layer rigid-flexible printed circuit board are as follows:

[0149] Pressing plate grid topology: The pressing plate is divided into 4 partitions, and each partition contains several grid units.

[0150] Multi-layer rigid-flexible printed circuit board grid body: The circuit board is divided into several grid units, and each grid unit corresponds to a temperature value.

[0151] Based on the graph neural network for topology twinning, the pressing plate grid topology is mapped with the circuit board grid body to form a topology twin relationship. The model architecture is as follows:

[0152] Input node: The target partition of the pressing plate, and the input data for each partition is pressure time series information and temperature time series information.

[0153] Output node: The temperature field distribution of the multi-layer rigid-flexible printed circuit board grid body.

[0154] Constrained by the multi-layer rigid-flexible printed circuit board model and the laminator model, pressure time series record information, temperature time series record information, and the first multi-layer rigid-flexible printed circuit board geometric body temperature field time series record information with a service life less than or equal to the service life threshold are collected to train the geometric body temperature field fitting model architecture, and a temperature field fitting base model is obtained. Assume the collected data is as follows:

[0155] Circuit board model: Model A

[0156] Laminator model: Model B

[0157] Service life threshold: 2 years

[0158] The collected training data is as follows:

[0159]

[0160] Use this data to train the geometric body temperature field fitting model architecture to obtain a temperature field fitting base model.

[0161] Constrained by the multi-layer rigid-flexible printed circuit board model and the laminator position number, target partition pressure time series record information, target partition temperature time series record information, and the second multi-layer rigid-flexible printed circuit board geometric body temperature field time series record information are collected to train the temperature field fitting base model to obtain a temperature field fitting model. Assume the collected target partition data is as follows:

[0162]

[0163]

[0164] Use these data to train the temperature field fitting base model to obtain the temperature field fitting model.

[0165] Furthermore, the data model training is specifically as follows:

[0166] Initialize the model parameters. Before the training starts, it is necessary to initialize the parameters of the model. For different models, the initialization methods are also different. For example, in a neural network, small random values are usually used to initialize the weights to break symmetry and enable the model to learn normally.

[0167] Define the loss function. The loss function is used to measure the difference between the predicted value and the true value of the model. For classification problems, the commonly used loss function is the cross-entropy loss function; for regression problems, the commonly used loss function is the mean squared error loss function. For example, in a binary classification problem, the cross-entropy loss function can be expressed as:

[0168]

[0169] where y is the true label, is the probability predicted by the model, and N is the number of samples.

[0170] Select an optimization algorithm. The optimization algorithm is used to adjust the parameters of the model according to the loss function to minimize the loss value. Common optimization algorithms include the gradient descent algorithm, stochastic gradient descent algorithm (SGD), mini-batch gradient descent algorithm, Adam algorithm, etc.

[0171] Taking the stochastic gradient descent algorithm as an example, it calculates the gradient using only one sample each time and then updates the model parameters. This method has a fast calculation speed but may cause large fluctuations in the loss value during the training process. The mini-batch gradient descent algorithm calculates the gradient using a batch of samples each time, which can balance the calculation speed and stability.

[0172] Iterative training. During the training process, the model will iterate continuously, and the parameters of the model will be updated according to the optimization algorithm in each iteration. In each iteration, the model will receive the input data, calculate the predicted value through forward propagation, then calculate the loss value through the loss function, and finally calculate the gradient through backpropagation and update the parameters.

[0173] The number of iterations is usually determined by hyperparameters (such as the maximum number of iterations) or convergence conditions (such as the loss value no longer decreasing significantly). For example, when training a simple linear regression model, it may only take dozens of iterations to converge; while for a complex deep learning model, it may take thousands or even tens of thousands of iterations.

[0174] Further, based on the target partition pressure time series information and the target partition temperature time series information, a temperature field simulation is performed on the multi-layer rigid-flexible printed circuit board geometry to obtain temperature field time series information. Assume that the input target partition pressure and temperature time series information are as follows:

[0175]

[0176] Use the trained temperature field fitting model for simulation to obtain temperature field time series information:

[0177] Time (s) Temperature field of circuit board (°C) 0 [150,150,150] 10 [150,150,150] 20 [150,150,150]

[0178] Through the above steps, the temperature field simulation of the multi-layer rigid-flexible printed circuit board geometry is realized. By constructing the topological twin relationship between the press plate grid topology and the multi-layer rigid-flexible printed circuit board grid body, and using the graph neural network for the training and simulation of the temperature field fitting model, the temperature field time series information of the multi-layer rigid-flexible printed circuit board can be accurately obtained. These information provide important data support for the subsequent lamination control, contribute to the realization of the refined temperature control of the multi-layer rigid-flexible printed circuit board lamination, and thus effectively solve the problems of large temperature-pressure volatility and uneven distribution caused by differences in material thermal conductivity, heat transfer lag at the multi-layer interface, and press plate wear, etc., and significantly improve the lamination quality of the multi-layer rigid-flexible printed circuit board.

[0179] S60: When the temperature field time series information is consistent with the standard temperature field time series information, control the press plate to perform lamination control according to the pressure time series information and the temperature time series information.

[0180] Further, when the temperature field time series information is inconsistent with the standard temperature field time series information, update the pressure time series information and the temperature time series information, obtain the updated pressure time series information and the updated temperature time series information to perform loop analysis, and at the same time store the pressure time series information and the temperature time series information as the temperature field intervention medium. The execution of step S60 includes:

[0181] S61: When the number of temperature field intervention media is greater than or equal to the intervention medium number threshold, use the deviation parameter between the temperature field intervention medium and the standard temperature field intervention medium as the fitness function to obtain the first temperature field intervention medium, the second temperature field intervention medium, and the third temperature field intervention medium with the fitness from small to large.

[0182] S62: Aim at simultaneously reducing the three deviation parameters with the first temperature field intervention medium, the second temperature field intervention medium, and the third temperature field intervention medium, update the other temperature field intervention media, and obtain the extended pressure time series information and the extended temperature time series information to perform loop analysis.

[0183] Exemplarily, when the temperature field timing information is inconsistent with the standard temperature field timing information, update the pressure timing information and the temperature timing information to obtain updated pressure timing information and updated temperature timing information, perform loop analysis, and at the same time store the pressure timing information and the temperature timing information as the temperature field intervention medium. Assume the standard temperature field timing information is as follows:

[0184] Time (s) Standard temperature field (°C) 0 [150,150,150] 10 [150,150,150] 20 [150,150,150]

[0185] The temperature field timing information obtained by simulation is as follows:

[0186] Time (s) Simulated temperature field (°C) 0 [148,148,148] 10 [149,149,149] 20 [151,151,151]

[0187] Since the simulated temperature field is inconsistent with the standard temperature field, the pressure and temperature timing information needs to be updated. Assume the updated pressure and temperature timing information is as follows:

[0188] Time (s) Updated pressure (MPa) Updated temperature (°C) 0 0.56 151 10 0.66 151 20 0.76 151

[0189] Use the updated information to re - simulate the temperature field to obtain new temperature field timing information:

[0190] Time (s) Updated temperature field (°C) 0 [149,149,149] 10 [150,150,150] 20 [152,152,152]

[0191] Store the updated pressure and temperature timing information as the temperature field intervention medium.

[0192] When the number of temperature field intervention media is greater than or equal to the intervention medium number threshold, use the deviation parameter between the temperature field intervention medium and the standard temperature field intervention medium as the fitness function to obtain the first temperature field intervention medium, the second temperature field intervention medium, and the third temperature field intervention medium with the fitness values from small to large. Assume the intervention medium number threshold is 3, and the stored temperature field intervention media are as follows:

[0193]

[0194] Use the deviation parameter between the temperature field intervention medium and the standard temperature field intervention medium as the fitness function to calculate the fitness of each intervention medium. Sort the intervention media in ascending order of fitness and select the first three intervention media:

[0195] The first temperature field intervention medium: number 2, deviation parameter 1;

[0196] The second temperature field intervention medium: number 1, deviation parameter 2;

[0197] The third temperature field intervention medium: number 3, deviation parameter 3.

[0198] With the goal of simultaneously reducing the three deviation parameters of the first temperature field intervention medium, the second temperature field intervention medium, and the third temperature field intervention medium, other temperature field intervention media are updated, and loop analysis is performed on the obtained extended pressure time series information and extended temperature time series information. Assume that the temperature field intervention medium numbered 4 needs to be updated. According to the deviation parameter adjustment strategy of the first three intervention media, the intervention medium numbered 4 is updated:

[0199]

[0200]

[0201] Use the updated pressure and temperature time series information to re - perform the temperature field simulation to obtain the extended temperature field time series information:

[0202] Time (s) Expanded temperature field (°C) 0 [149,149,149] 10 [150,150,150] 20 [151,151,151]

[0203] Through the above steps, the update and optimization of the temperature field intervention medium are achieved. By storing the pressure and temperature time series information of each simulation and evaluating with the deviation parameter as the fitness function, the pressure and temperature time series information can be gradually adjusted to make the simulated temperature field closer to the standard temperature field. This method can effectively solve the temperature field deviation problem caused by inaccurate initial parameters or environmental changes, further improve the temperature control accuracy of the multilayer rigid - flexible printed circuit board lamination, and ensure the lamination quality.

[0204] Embodiment 2:

[0205] As Figure 2 shown, based on the same inventive concept as the lamination control method for a multilayer rigid - flexible printed circuit board provided in Embodiment 1, the present invention embodiment also provides a lamination control system for a multilayer rigid - flexible printed circuit board. The explanation of the lamination control method for a multilayer rigid - flexible printed circuit board in Embodiment 1 also applies to the lamination control system for a multilayer rigid - flexible printed circuit board. The system includes:

[0206] The platen pressure partition template 11 is used to perform platen pressure hierarchical clustering partition according to the platen lamination log to obtain the platen pressure partition;

[0207] The platen temperature partition module 12 is used to perform platen temperature hierarchical clustering partition according to the platen lamination log to obtain the platen temperature partition;

[0208] The platen target partition module 13 is used to take the intersection of the platen pressure partition and the platen temperature partition to obtain the platen target partition;

[0209] The pressure and temperature timing information module 14 is configured to receive pressure timing information and temperature timing information, perform frequent temperature and pressure statistics according to the target partition of the pressing plate, and obtain target partition pressure timing information and target partition temperature timing information;

[0210] The temperature field timing information module 15 is configured to perform temperature field simulation on the multi-layer rigid-flex printed circuit board geometry based on the target partition pressure timing information and the target partition temperature timing information, and obtain temperature field timing information;

[0211] The pressing control module 16 is configured to, when the temperature field timing information is consistent with the standard temperature field timing information, control the pressing plate to perform pressing control according to the pressure timing information and the temperature timing information.

[0212] Furthermore, the pressing plate pressure partition template 11 is further configured to:

[0213] Obtain the starting geometry and the target geometry of the multi-layer rigid-flex printed circuit board geometry;

[0214] Retrieve the pressing log of the target position number pressing plate that satisfies the starting geometry and the target geometry;

[0215] Extract the first pressure distribution record information with the same temperature timing record information to the Nth pressure distribution record information from the pressing log of the pressing plate;

[0216] Perform hierarchical clustering partitioning of the pressing plate pressure based on the first pressure distribution record information to the Nth pressure distribution record information to obtain the pressing plate pressure partition.

[0217] Furthermore, the pressing plate pressure partition template 11 is further configured to:

[0218] Perform neighborhood hierarchical clustering analysis on the first pressure distribution record information to obtain the first pressure distribution partition;

[0219] Until neighborhood hierarchical clustering analysis is performed on the Nth pressure distribution record information to obtain the Nth pressure distribution partition;

[0220] Perform pairwise enumeration evaluation of the distribution similarity of the first pressure distribution partition to the Nth pressure distribution partition to obtain a number of partition similarities;

[0221] According to the number of partition similarities, perform outlier distribution partition deletion on the first pressure distribution partition to the Nth pressure distribution partition to obtain a concentrated pressure distribution partition, and take the intersection of the concentrated pressure distribution partitions as the pressing plate pressure partition.

[0222] Furthermore, the pressing plate pressure partition template 11 is further configured to:

[0223] Connect the center lines of the partitioned areas of the first pressure distribution to obtain the first pattern;

[0224] Connect the center lines of the partitioned areas of the second pressure distribution to obtain the second pattern;

[0225] Calculate the similarity between the first pattern and the second pattern to obtain the first partition similarity, and add it to the several partition similarities.

[0226] Furthermore, the platen temperature partition module 12 and the platen target partition module 13 can execute the platen pressure partition module 11.

[0227] Furthermore, the pressure and temperature timing information module 14 is also used for:

[0228] Constrained by the multi-layer rigid-flexible circuit board model and the service life of the laminator, collect the first partition temperature timing information set to the Mth partition temperature timing information set that meets the pressure timing information and the temperature timing information, and the first partition pressure timing information set to the Mth partition pressure timing information set;

[0229] Perform a simultaneous moment median evaluation on the first partition temperature timing information set to the Mth partition temperature timing information set and the first partition pressure timing information set to the Mth partition pressure timing information set respectively, to obtain the target partition pressure timing information and the target partition temperature timing information.

[0230] Furthermore, the temperature field timing information module 15 is also used for:

[0231] Based on the platen target partition, construct a platen grid topology, combine it with the multi-layer rigid-flexible circuit board grid body, perform topological twinning based on the graph neural network, and build a geometric body temperature field fitting model architecture. Among them, the input node of the geometric body temperature field fitting model architecture is the platen target partition, the input data of any partition is the pressure timing information and the temperature timing information, the output node is the grid temperature field of the multi-layer rigid-flexible circuit board grid body, and the multi-layer rigid-flexible circuit board grid body will change from the starting grid body to the target grid body at a preset shrinking speed;

[0232] Constrained by the multi-layer rigid-flexible circuit board model and the laminator model, collect the pressure timing record information, temperature timing record information and the first multi-layer rigid-flexible circuit board geometric body temperature field timing record information with a service life less than or equal to the service life threshold, and train the geometric body temperature field fitting model architecture to obtain the temperature field fitting base model;

[0233] Constrained by the model number of the multi-layer rigid-flexible printed circuit board and the press-fitting machine position number, collect the target partition pressure time-series record information, the target partition temperature time-series record information, and the second multi-layer rigid-flexible printed circuit board geometry temperature field time-series record information, train the temperature field fitting base model, obtain the temperature field fitting model, and simulate the temperature field of the multi-layer rigid-flexible printed circuit board geometry based on the target partition pressure time-series information and the target partition temperature time-series information to obtain the temperature field time-series information.

[0234] Further, the press-fitting control module 16 is further configured to:

[0235] When the temperature field time-series information is inconsistent with the standard temperature field time-series information, update the pressure time-series information and the temperature time-series information to obtain the updated pressure time-series information and the updated temperature time-series information, perform loop analysis, and simultaneously store the pressure time-series information and the temperature time-series information as the temperature field intervention medium;

[0236] When the number of temperature field intervention media is greater than or equal to the intervention medium number threshold, use the deviation parameter between the temperature field intervention medium and the standard temperature field intervention medium as the fitness function to obtain the first temperature field intervention medium, the second temperature field intervention medium, and the third temperature field intervention medium with increasing fitness from small to large;

[0237] Aim at simultaneously reducing the three deviation parameters of the first temperature field intervention medium, the second temperature field intervention medium, and the third temperature field intervention medium, update the other temperature field intervention media to obtain the extended pressure time-series information and the extended temperature time-series information, and perform loop analysis.

[0238] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailedly described in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0239] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0240] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded computers, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0241] These computer program instructions can 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, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0242] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0243] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic inventive concept.

[0244] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A multi-layer rigid-flexible circuit board lamination control method, characterized in that: include: According to the platen pressing log, the platen pressure is hierarchically clustered and partitioned to obtain the platen pressure partition; Perform platen temperature hierarchical clustering partitioning according to the platen pressing log to obtain platen temperature partitioning; Taking the intersection of the platen pressure partition and the platen temperature partition to obtain the platen target partition; Receiving pressure timing information and temperature timing information, performing temperature and pressure frequent statistics according to the target partition of the pressing plate, and obtaining target partition pressure timing information and target partition temperature timing information; Based on the target partition pressure timing information and the target partition temperature timing information, a temperature field simulation is performed on the multi-layer rigid-flexible circuit board geometry to obtain the temperature field timing information; When the temperature field timing information is consistent with the standard temperature field timing information, the pressing plate is controlled to perform pressing control according to the pressure timing information and the temperature timing information.

2. The method according to claim 1, characterized in that According to the platen pressing log, the platen pressure hierarchical clustering partition is performed to obtain the platen pressure partition, including: Get the starting geometry and target geometry of the multi-layer rigid-flexible circuit board; Retrieve the platen pressing log of the target position platen that satisfies the starting geometry and the target geometry; Extracting the first pressure distribution record information to the Nth pressure distribution record information having the same temperature timing record information from the pressing plate pressing log; Based on the first pressure distribution record information to the Nth pressure distribution record information, platen pressure hierarchical clustering and partitioning are performed to obtain platen pressure partitions.

3. The method according to claim 2, characterized in that Performing platen pressure hierarchical clustering partitioning based on the first pressure distribution record information to the Nth pressure distribution record information to obtain platen pressure partitions, including: Performing neighborhood hierarchical clustering analysis on the first pressure distribution record information to obtain first pressure distribution partitions; Until the Nth pressure distribution record information is subjected to neighborhood hierarchical clustering analysis to obtain the Nth pressure distribution partition; Performing distribution similarity enumeration evaluation on the first pressure distribution partition to the Nth pressure distribution partition in pairs to obtain a plurality of partition similarities; According to the similarities of the several partitions, outlier distribution partitions are deleted from the first pressure distribution partition to the Nth pressure distribution partition to obtain concentrated pressure distribution partitions, and the intersection of the concentrated pressure distribution partitions is taken and set as the pressure plate pressure partition.

4. The method according to claim 3, characterized in that Performing distribution similarity enumeration evaluation on the first pressure distribution partition to the Nth pressure distribution partition in pairs to obtain a plurality of partition similarities, including: Connecting the centers of the first pressure distribution partitions to obtain a first pattern; Connecting the centers of the second pressure distribution zones to obtain a second pattern; The similarity between the first pattern and the second pattern is calculated to obtain a first partition similarity, which is added to the plurality of partition similarities.

5. The method according to claim 1, characterized in that Receiving pressure timing information and temperature timing information, performing temperature and pressure frequent statistics according to the target partition of the pressure plate, and obtaining target partition pressure timing information and target partition temperature timing information, including: Taking the model of the multi-layer rigid-flexible circuit board and the service life of the laminating machine as constraints, collecting the first partition temperature timing information set until the Mth partition temperature timing information set that satisfies the pressure timing information and the temperature timing information, and the first partition pressure timing information set until the Mth partition pressure timing information set; The first partition temperature timing information set to the Mth partition temperature timing information set, and the first partition pressure timing information set to the Mth partition pressure timing information set are respectively evaluated at the same time to obtain the target partition pressure timing information and the target partition temperature timing information.

6. The method according to claim 1, characterized in that Based on the target partition pressure timing information and the target partition temperature timing information, a temperature field simulation is performed on the multi-layer rigid-flexible circuit board geometry to obtain the temperature field timing information, including: Based on the target partition of the pressure plate, the pressure plate grid topology is constructed, combined with the multi-layer rigid-flexible circuit board grid body, topological twinning is performed based on the graph neural network, and a geometric body temperature field fitting model architecture is built, wherein the input node of the geometric body temperature field fitting model architecture is the pressure plate target partition, the input data of any partition is the pressure timing information and the temperature timing information, and the output node is the grid temperature field of the multi-layer rigid-flexible circuit board grid body, and the multi-layer rigid-flexible circuit board grid body will change from the starting grid body to the target grid body according to the preset shrinking speed; Taking the model of multi-layer rigid-flexible circuit board and the model of laminating machine as constraints, the pressure time series record information, temperature time series record information and the temperature field time series record information of the geometric body of the first multi-layer rigid-flexible circuit board with a service time less than or equal to the service time threshold are collected, and the geometric body temperature field fitting model architecture is trained to obtain the temperature field fitting base model; Taking the multi-layer rigid-flexible circuit board model and pressing machine position number as constraints, the target partition pressure timing record information, the target partition temperature timing record information and the second multi-layer rigid-flexible circuit board geometric body temperature field timing record information are collected, the temperature field fitting base model is trained, and the temperature field fitting model is obtained. Based on the target partition pressure timing information and the target partition temperature timing information, the temperature field of the multi-layer rigid-flexible circuit board geometry is simulated to obtain the temperature field timing information.

7. The method according to claim 1, characterized in that Also includes: When the temperature field timing information is inconsistent with the standard temperature field timing information, the pressure timing information and the temperature timing information are updated to obtain updated pressure timing information and updated temperature timing information for loop analysis, and the pressure timing information and the temperature timing information are stored as temperature field intervention media; When the number of temperature field intervention media is greater than or equal to the intervention medium number threshold, the deviation parameter between the temperature field intervention medium and the standard temperature field intervention medium is used as the fitness function to obtain the first temperature field intervention medium, the second temperature field intervention medium and the third temperature field intervention medium with fitness from small to large; With the goal of simultaneously reducing the three deviation parameters of the first temperature field intervention medium, the second temperature field intervention medium and the third temperature field intervention medium, other temperature field intervention media are updated to obtain expansion pressure timing information and expansion temperature timing information to perform cyclic analysis.

8. A multi-layer rigid-flexible circuit board pressing control system, characterized in that: The system is used to execute the method according to any one of claims 1 to 7, and the system comprises: The platen pressure partition template is used to perform platen pressure hierarchical clustering partitioning according to the platen pressing log to obtain the platen pressure partition; The platen temperature partitioning module is used to perform platen temperature hierarchical clustering partitioning according to the platen pressing log to obtain the platen temperature partitioning; A platen target partitioning module, used for taking the intersection of the platen pressure partition and the platen temperature partition to obtain a platen target partition; A pressure and temperature timing information module is used to receive pressure timing information and temperature timing information, perform temperature and pressure frequent statistics according to the target partition of the pressing plate, and obtain target partition pressure timing information and target partition temperature timing information; A temperature field timing information module is used to perform temperature field simulation on a multi-layer rigid-flexible circuit board geometry based on the target partition pressure timing information and the target partition temperature timing information to obtain temperature field timing information; The pressing control module is used to control the pressing plate to perform pressing control according to the pressure timing information and the temperature timing information when the temperature field timing information is consistent with the standard temperature field timing information.

Images