Production optimization method and system for anylayer core board layer

Abstract

The invention provides a production optimization method and system for an anylayer core board layer, and relates to the field of equipment manufacturing, the characteristics (such as the size, the material and the batch number) of a core board and the processing parameters (such as the PTH linear speed, the copper deposition liquid concentration, the temperature, the current density and the spraying pressure) of the core board are used as input, and the compatibility requirements of the core board and horizontal line equipment are automatically analyzed, so that the production optimization of the core board layer is realized. Key parameters such as the thickness, the strength and the connection mode of the adaptive band plate are generated; then, the band plates are accurately screened based on the calculation result, physical coupling of the band plates and the core plate is achieved through the pressing plate clamp, and a rigidity-enhanced integrated structure is formed; in the process, equipment adjustment does not need to be manually intervened, the problems of core plate bending, plate clamping and the like can be effectively solved only through parameterized matching and intelligent transmission assistance, and finally stable transmission and smooth production of the ultrathin core plate in the complex electroplating process are ensured.

Description

Technical Field

[0001] This application relates to the field of equipment manufacturing, and more particularly, in the embodiments of this application, it relates to a production optimization method and system for an anylayer core board layer. Background Art

[0002] With the rapid development of electronic devices towards thinner, lighter, and higher-density directions, the anylayer high-density interconnect board (anylayer HDI) has become an important development direction in the field of high-end printed circuit boards due to its advantages in miniaturization and high integration. However, the thickness of the anylayer core board layer is usually extremely thin (0.051 mm - 0.076 mm), far lower than the adaptation range of traditional circuit board production equipment. In horizontal line processes (such as desmearing, horizontal electroless copper plating PTH line, etc.), ultra-thin core boards are prone to problems such as board warping and jamming due to insufficient mechanical strength, severely restricting production efficiency and yield. Existing technologies mostly alleviate such problems by adjusting equipment parameters or optimizing process conditions, but limited by the inherent design of the equipment, it is difficult to fundamentally solve the compatibility contradiction between the core board and the line drive system. In addition, traditional methods lack dynamic matching analysis of core board characteristics and process parameters, resulting in insufficient generality and adaptability of the solutions.

[0003] Therefore, a production optimization solution for the anylayer core board layer is desired. Summary of the Invention

[0004] To solve the above technical problems, this application is proposed. Embodiments of this application provide a production optimization method and system for an anylayer core board layer, which take core board characteristics (such as size, material, and batch number) and process parameters (such as PTH line speed, electroless copper plating solution concentration, temperature, current density, and spray pressure) as inputs, and generate key parameters such as the thickness, strength, and connection method of the adapted carrier board by automatically analyzing the compatibility requirements between the core board and the horizontal line equipment. Subsequently, based on the calculation results, the carrier board is accurately selected, and the physical coupling between the carrier board and the core board is achieved through a press clamp to form a rigidly enhanced integrated structure. This process does not require manual intervention in equipment adjustment, and only through parameterized matching and intelligent drive assistance, problems such as core board warping and jamming can be effectively suppressed, ultimately ensuring the stable transmission and smooth production of ultra-thin core boards in complex electroplating processes.

[0005] According to one aspect of this application, a production optimization method for an anylayer core board layer is provided, which includes:

[0006] Obtain core board parameters and horizontal line parameters;

[0007] Based on the core board parameters and horizontal line parameters, determine the tape board parameters, including: performing feature domain mapping on the core board parameters and horizontal line parameters to obtain a set of structured mapping representations of the core board parameters and structured mapping representations of the horizontal line parameter items; determining the tape board parameters based on the cross-modal feature domain dynamic response analysis results between the set of structured mapping representations of the core board parameters and the set of structured mapping representations of the horizontal line parameter items;

[0008] Based on the tape board parameters, select a tape board with suitable parameters;

[0009] Control the press plate clamp to connect the tape board and the core board to form an integrated structure.

[0010] According to another aspect of the present application, there is provided a production optimization system for an anylayer core board layer, which includes:

[0011] A parameter acquisition module for acquiring core board parameters and horizontal line parameters;

[0012] A tape board parameter determination module for determining tape board parameters based on the core board parameters and horizontal line parameters, wherein the tape board parameter determination module is used to: perform feature domain mapping on the core board parameters and horizontal line parameters to obtain a set of structured mapping representations of the core board parameters and a set of structured mapping representations of the horizontal line parameter items; determine the tape board parameters based on the cross-modal feature domain dynamic response analysis results between the set of structured mapping representations of the core board parameters and the set of structured mapping representations of the horizontal line parameter items;

[0013] A tape board selection module for selecting a tape board with suitable parameters based on the tape board parameters;

[0014] A connection module for controlling the press plate clamp to connect the tape board and the core board to form an integrated structure.

[0015] Compared with the prior art, a production optimization method and system for an anylayer core board layer provided by the present application take the core board characteristics (such as size, material, and batch number) and process parameters (such as PTH line speed, copper deposition solution concentration, temperature, current density, and spray pressure) as inputs, automatically analyze the compatibility requirements between the core board and the horizontal line equipment, and generate key parameters such as the thickness, strength, and connection method of the adapted tape board. Subsequently, based on the calculation results, the tape board is accurately screened, and the physical coupling between the tape board and the core board is realized through the press plate clamp to form a rigid enhanced integrated structure. This process does not require manual intervention in equipment adjustment, and only through parametric matching and intelligent transmission assistance, problems such as core board warping and carding can be effectively suppressed, and finally the stable transmission and smooth production of the ultra-thin core board in the complex electroplating process can be ensured. Description of the Drawings

[0016] The above and other objects, features, and advantages of the present application will become more apparent by describing the embodiments of the present application in more detail with reference to the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. They are used together with the embodiments of the present application to explain the present application and do not constitute a limitation to the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flowchart of a production optimization method for an anylayer core board layer according to an embodiment of the present application.

[0018] Figure 2 It is a flowchart of determining the strip board parameters based on the core board parameters and the horizontal line parameters in the production optimization method for an anylayer core board layer according to an embodiment of the present application.

[0019] Figure 3 It is a schematic diagram of data flow for determining the strip board parameters based on the core board parameters and the horizontal line parameters in the production optimization method for an anylayer core board layer according to an embodiment of the present application.

[0020] Figure 4 It is a flowchart of determining the strip board parameters based on the cross-modal feature domain dynamic response analysis result between the set of structured mapping characterizations of core board parameters and the set of structured mapping characterizations of horizontal line parameter items in the production optimization method for an anylayer core board layer according to an embodiment of the present application.

[0021] Figure 5 It is a flowchart of performing parameter cross-modal inter-feature dynamic response analysis on the set of structured mapping encoded vectors of core board parameters and the set of structured mapping encoded vectors of horizontal line parameter items to obtain the core board parameter-horizontal board parameter dynamic query response encoded vector as the cross-modal feature domain dynamic response analysis result in the production optimization method for an anylayer core board layer according to an embodiment of the present application.

[0022] Figure 6 It is a system block diagram of a production optimization system for an anylayer core board layer according to an embodiment of the present application. Detailed Embodiments

[0023] Hereinafter, various exemplary embodiments, features, and aspects of the present application will be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0024] The special term "exemplary" here means "serving as an example, embodiment, or illustrative". Any embodiment described as "exemplary" here does not have to be construed as superior or better than other embodiments.

[0025] In addition, to better illustrate the present application, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present application can be implemented without some specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art are not described in detail so as to highlight the gist of the present application.

[0026] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot 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 such features. In the description of the present application, "a plurality of" means two or more unless otherwise specifically defined.

[0027] As electronic devices develop towards being thinner, lighter, and having higher density, the anylayer high-density interconnect board (anylayer HDI) has become an important development direction for high-end printed circuit boards due to its advantages of miniaturization and high integration. However, the thickness of the anylayer core board is relatively thin (0.051 mm to 0.076 mm), which is lower than the adaptation range of traditional equipment. In the horizontal line process, the ultra-thin core board is prone to problems such as warping and jamming due to insufficient mechanical strength, affecting production efficiency and yield. Existing technologies alleviate this problem by adjusting equipment parameters or optimizing processes, but due to the limitations of equipment design, it is difficult to fundamentally solve the compatibility problem between the core board and the wire body transmission system, and there is a lack of dynamic matching analysis of the core board characteristics and process parameters, resulting in insufficient adaptability of the solution.

[0028] To address the above technical problems, in the technical solution of the present application, a production optimization method for the anylayer core board layer is proposed. Before the core board enters the production of the horizontal line (such as electroplating processes like desmear, PTH line, etc.), the thin board tape is connected to the core board by using a pressing plate clamp. By utilizing the thicker feature of the tape, the core board is driven to move on the horizontal line body, enabling the originally thinner and easily bendable and jammed core board to smoothly pass through the horizontal line. In addition, by introducing tape-assisted transmission and parameterized dynamic response technology, deep adaptation between the core board and the horizontal line process is achieved to ensure the stable transmission of the ultra-thin core board in the horizontal line, ultimately improving the smooth production of the anylayer core board layer in the horizontal line. Specifically, Figure 1 is a flowchart of the production optimization method for the anylayer core board layer according to an embodiment of the present application. As Figure 1As shown, the production optimization method for the anylayer core board layer according to the embodiments of the present application includes: S110, obtaining core board parameters and horizontal line parameters; S120, determining the strip board parameters based on the core board parameters and the horizontal line parameters; S130, selecting a strip board with adapted parameters based on the strip board parameters; S140, controlling the pressing plate clamp to connect the strip board and the core board to form an integrated structure. That is, aiming at the transmission problem of the ultra-thin anylayer core board layer in the horizontal line production, a production optimization scheme based on dynamic feature analysis is proposed. Taking the core board characteristics (such as size, material, and batch number) and process parameters (such as PTH line speed, copper deposition solution concentration, temperature, current density, and spray pressure) as inputs, by automatically analyzing the compatibility requirements between the core board and the horizontal line equipment, key parameters such as the thickness, strength, and connection method of the adapted strip board are generated. Subsequently, based on the calculation results, the strip board is accurately selected, and the physical coupling between the strip board and the core board is realized through the pressing plate clamp to form an integrated structure with enhanced rigidity. This process does not require manual intervention in equipment adjustment. Only through parameterized matching and intelligent transmission assistance, problems such as core board warping and jamming can be effectively suppressed, and finally, the stable transmission and smooth production of the ultra-thin core board in the complex electroplating process can be ensured.

[0029] In the above production optimization method for the anylayer core board layer, in step 110, core board parameters and horizontal line parameters are obtained. Specifically, in the embodiments of the present application, the core board parameters include size, material, and batch number; the horizontal line parameters include PTH line speed, copper deposition solution concentration, temperature, current density, and spray pressure. It should be understood that the core board parameters include the basic characteristics of the core board, including but not limited to its size, material, and batch number. Among them, the size information provides a specific description of the physical size of the core board, which helps to evaluate its transmission stability in the horizontal line and the possible deformation risks it may face; the material determines the basic mechanical properties of the core board, such as bending strength and ductility, which are crucial for preventing the core board from being damaged in the complex electroplating process; and the batch number is associated with historical production data, which can be used to trace the manufacturing conditions and past performance of this batch of core boards, thereby assisting in predicting possible problems in the current batch. To achieve the accurate collection of the above parameters, in the technical solution of the present application, a laser rangefinder is used to measure the core board size, a material analyzer is used to determine its specific material composition, and an enterprise resource planning system (ERP) is used to record and track batch information. On the other hand, the horizontal line parameters mainly include PTH line speed, copper deposition solution concentration, temperature, current density, and spray pressure. Among them, the PTH line speed affects the transmission rate of the core board on the production line, and thus determines the length of time each core board undergoes chemical treatment; the copper deposition solution concentration is directly related to the uniformity and thickness of the copper layer deposited on the surface of the core board; the change in temperature can not only change the physical properties of the copper deposition solution, but also affect the thermal expansion coefficient of the core board itself, thereby indirectly affecting its shape stability; the current density is one of the key factors controlling the electroplating rate, and too high a current density may cause local overheating and lead to core board deformation; finally, the spray pressure is responsible for ensuring the uniform distribution of the chemical solution throughout the treatment process, avoiding local untreated or over-treated situations. For the measurement of these parameters, the present application uses a sensor network to monitor and record relevant data in real time, such as temperature sensors, flow meters, and tension sensors, to ensure that all key indicators can be accurately captured and recorded.

[0030] In the above production optimization method for the anylayer core board layer, in step 120, based on the core board parameters and horizontal line parameters, the strip board parameters are determined. It should be understood that considering that relying solely on core board parameters or horizontal line parameters cannot provide sufficient information to optimize the strip board parameters. Among them, the core board parameters provide basic information about the characteristics of the core board itself, but lack an understanding of the specific conditions in the actual production environment; while the horizontal line parameters, although describing the process conditions, do not fully consider the physical characteristics of the core board itself. By combining the core board parameters and horizontal line parameters for analysis, it is possible to more comprehensively understand the interaction between the two, more accurately quantify the bending resistance requirements of the core board under specific process conditions, and dynamically match the optimal strip board configuration accordingly.

[0031] Figure 2 It is a flowchart for determining strip parameters based on core board parameters and horizontal line parameters in the production optimization method for an anylayer core board layer according to an embodiment of the present application. Figure 3 It is a schematic diagram of data flow for determining strip parameters based on core board parameters and horizontal line parameters in the production optimization method for an anylayer core board layer according to an embodiment of the present application. As Figure 2 and Figure 3 shown, in step 120, based on the core board parameters and the horizontal line parameters, determining the strip parameters includes: S121, performing feature domain mapping on the core board parameters and the horizontal line parameters to obtain a set of structured mapping characterizations of the core board parameters and a set of structured mapping characterizations of the horizontal line parameter items; S122, determining the strip parameters based on the cross-modal feature domain dynamic response analysis result between the set of structured mapping characterizations of the core board parameters and the set of structured mapping characterizations of the horizontal line parameter items.

[0032] In an embodiment of the present application, step S121, performing feature domain mapping on the core board parameters and the horizontal line parameters to obtain a set of structured mapping characterizations of the core board parameters and a set of structured mapping characterizations of the horizontal line parameter items, includes: S1211, performing structured mapping on the core board parameters to obtain a structured mapping encoding vector of the core board parameters as the structured mapping characterization of the core board parameters;

[0033] S1212, performing structured mapping on each parameter item in the horizontal line parameters to obtain a set of structured mapping encoding vectors of the horizontal line parameter items as the set of structured mapping characterizations of the horizontal line parameter items.

[0034] Specifically, in step S1211, the core board parameters are structurally mapped to obtain a structurally mapped coding vector of the core board parameters as a structural mapping representation of the core board parameters. It should be understood that considering the production process of the existing anylayer core board layer, since the core board is extremely thin (0.051 mm to 0.076 mm) and the horizontal line process parameters are complex (such as the PTH line speed, the concentration of the electroless copper solution, etc.), it is difficult for traditional methods to dynamically analyze the multi-dimensional correlation relationship between the core board characteristics and the equipment parameters. Therefore, in the technical solution of this application, the core board parameters are further structurally mapped to obtain a structurally mapped coding vector of the core board parameters. It is worth mentioning that since the core board parameters (such as size, material, batch number) are essentially discrete, heterogeneous, and non-standard data forms, directly inputting them into the analysis model will result in feature redundancy or information loss. Through the structural mapping technology, the physical attributes of the core board are transformed into a unified coding vector. For example, the material type is quantified as the bending strength coefficient, the size is mapped to the geometric topology feature, and the batch number is associated with the historical production data, etc., so as to construct a high-dimensional mathematical representation that can be directly processed by the algorithm. The purpose of this process is to eliminate the noise interference of the original data and extract the implicit physical laws (such as the coupling relationship between the mechanical properties of thin plates and the process conditions) at the same time, providing standardized input features for the subsequent dynamic response analysis network. Finally, through the generation of the structured coding vector, the system can accurately quantify the bending demand of the core board in the horizontal line drive, and dynamically match the optimal tape configuration in combination with the process parameters, significantly improving the adaptation accuracy. For example, for a certain batch of ultra-thin core boards, due to the difference in material ductility, the warping threshold is reduced. After structural mapping, this characteristic can be directly reflected by the coding vector, thereby triggering targeted optimization of the tape thickness and connection strength, avoiding the blindness of traditional empirical debugging, fundamentally solving the problems such as carding and deformation of the core board in the electroplating process, and realizing the synchronous optimization of the yield and production cost.

[0035] Specifically, in step S1212, each parameter item in the horizontal line parameters is structurally mapped to obtain a set of structurally mapped encoding vectors of the horizontal line parameter items as a set of structural mappings of the horizontal line parameter items. It should be understood that considering the significant differences in the physical meanings and numerical ranges of the horizontal line process parameters (such as the PTH line speed, the concentration of the copper deposition solution, the temperature, the current density, and the spray pressure), for example, the line speed is directly related to the transmission time, the concentration of the copper deposition solution affects the plating uniformity, and the temperature fluctuation may cause material deformation. These parameters are not only diverse in type, but also have a non-linear coupling relationship with each other (such as an increase in temperature may cause a change in the viscosity of the copper deposition solution, which in turn affects the spray pressure distribution). Traditional methods usually independently adjust a single parameter and it is difficult to comprehensively capture the comprehensive impact of the multi-parameter synergistic effect on the core board transmission stability. Therefore, each parameter item in the horizontal line parameters is further structurally mapped to obtain a set of structurally mapped encoding vectors of the horizontal line parameter items, where the horizontal line parameters include the PTH line speed, the concentration of the copper deposition solution, the temperature, the current density, and the spray pressure. This can transform discrete and heterogeneous process parameters (such as the numerical line speed, the categorical variable spray mode, and the dynamically changing temperature curve) into a unified high-dimensional mathematical representation, eliminate the dimension difference and data redundancy, and construct an associated feature space between the parameters. For example, the concentration of the copper deposition solution is mapped to the ion mobility coefficient, the temperature gradient is transformed into the thermal stress distribution function, and the spray pressure is associated with the hydrodynamic model, etc. The purpose of this process is to provide a standardized input basis for the non-linear cross-modal analysis network, enabling the model to deeply explore the implicit laws between the parameters (such as the dynamic relationship between the current density and the core board deformation threshold under high temperature conditions), so as to accurately quantify the constraints of the horizontal line process on the core board transmission. Finally, through the generation of the set of structurally mapped encoding vectors of the horizontal line parameter items, the system can dynamically analyze the matching requirements between the carrier board and the core board in a complex process environment. For example, when the concentration of the copper deposition solution increases and the plating thickness increases, the encoding vector will automatically reflect the impact of this change on the surface friction of the core board and trigger a targeted optimization of the connection strength of the carrier board, avoiding the matching deviation caused by ignoring the parameter interaction in the traditional empirical debugging. This not only improves the robustness of the carrier board parameter matching, but also significantly reduces the risk of core board jamming caused by process fluctuations, providing a quantifiable and scalable technical support for the efficient and stable production of ultra-thin anylayer core boards in the horizontal line.

[0036] Figure 4 FIG. is a flowchart for determining the carrier board parameters based on the dynamic response analysis results of the cross-modal feature domain between the structural mapping representation of the core board parameters and the set of structural mapping representations of the horizontal line parameter items in the production optimization method for the anylayer core board layer according to the embodiment of the present application. As Figure 4As shown, in the embodiment of the present application, in step S122, the strip parameters are determined based on the cross-modal feature domain dynamic response analysis result between the set of structured mapping characterizations of core board parameters and the set of structured mapping characterizations of horizontal line parameter items, including: S1221, performing parameter cross-modal feature dynamic response analysis on the set of structured mapping encoding vectors of core board parameters and the set of structured mapping encoding vectors of horizontal line parameter items to obtain a core board parameter-horizontal board parameter dynamic query response encoding vector as the cross-modal feature domain dynamic response analysis result; S1222, decoding the features of the core board parameter-horizontal board parameter dynamic query response encoding vector to obtain the strip parameters.

[0037] Figure 5 It is a flowchart for performing parameter cross-modal feature dynamic response analysis on the set of structured mapping encoding vectors of core board parameters and the set of structured mapping encoding vectors of horizontal line parameter items in the production optimization method for an anylayer core board layer according to an embodiment of the present application to obtain a core board parameter-horizontal board parameter dynamic query response encoding vector as the cross-modal feature domain dynamic response analysis result. As Figure 5As shown, in the embodiment of the present application, in step S1221, parameter cross-modal feature dynamic response analysis is performed on the set of core board parameter structured mapping coding vectors and horizontal line parameter item structured mapping coding vectors to obtain a core board parameter-horizontal board parameter dynamic query response coding vector as the cross-modal feature domain dynamic response analysis result, including: S1221-1, performing responsiveness analysis of non-linear decision-making on each horizontal line parameter item structured mapping coding vector in the set of core board parameter structured mapping coding vectors and horizontal line parameter item structured mapping coding vectors to obtain a set of core board parameter-horizontal board parameter decision point state implicit coding vectors; S1221-2, constructing a Laplacian matrix of the set of core board parameter-horizontal board parameter decision point state implicit coding vectors to obtain a core board parameter-horizontal board parameter decision point state Laplacian matrix; S1221-3, performing spectral decomposition on the core board parameter-horizontal board parameter decision point state Laplacian matrix to obtain a set of core board parameter-horizontal board parameter decision point core component coding vectors; S1221-4, performing adaptive fusion on the set of core board parameter-horizontal board parameter decision point core component coding vectors to obtain a core board parameter-horizontal board parameter dynamic query response coding vector. It should be understood that since the core board parameters (such as size, material) and the horizontal line parameters (such as PTH line speed, copper deposition solution concentration) belong to two types of heterogeneous modal data of physical characteristics and process environment, their interaction relationship has the characteristics of strong non-linearity, high dimension and dynamic coupling. For example, the correlation between the thermal expansion coefficient of the core board material and the temperature fluctuation of the horizontal line needs to be described by a complex physical model, and traditional methods are difficult to quantify the comprehensive impact of the two on the core board drive stability due to the lack of a cross-modal feature fusion mechanism. Therefore, in the technical solution of the present application, parameter cross-modal feature dynamic response analysis is further performed on the set of core board parameter structured mapping coding vectors and horizontal line parameter item structured mapping coding vectors to obtain a core board parameter-horizontal board parameter dynamic query response coding vector. This is because although the set of core board parameter structured mapping coding vectors and horizontal line parameter item structured mapping coding vectors after structured mapping has eliminated the dimensional difference of the original data, the implicit correlation between the core board and the horizontal line parameters (such as the gradient effect of current density on the surface stress distribution of the core board) still exists in the high-dimensional feature space, and the cooperative action law of cross-modal features needs to be mined through non-linear modeling. Through parameter cross-modal feature dynamic response analysis, a graph structure can be constructed using the decision point state implicit coding, the local correlation between parameters can be captured through the neighborhood matrix (such as the dynamic threshold relationship between the copper deposition solution concentration and the core board deformation in a high-temperature environment), and the cross-modal global structure features can be extracted by the spectral decomposition of the Laplacian matrix (such as the long-range constraint relationship between the material bending strength and the spray pressure). The purpose is to map the originally separated core board characteristics and process conditions to a unified spectral domain space, and generate a dynamic query response coding vector through adaptive fusion. This vector not only compresses the redundant information of the high-dimensional data, but also accurately represents the matching requirements of the core board and the horizontal line parameters in a low-dimensional form.For example, when the horizontal line speed increases and causes a sudden change in the force on the core board, the core component encoding extracted by spectral decomposition can dynamically reflect the non-linear balance relationship between the connection strength of the belt board and the transmission time. Furthermore, optimized belt board parameters are generated through adaptive weight allocation. In terms of execution effect, this method breaks through the limitations of traditional single-modal analysis, enabling the system to real-time analyze the transmission constraint conditions under the coupling action of multiple parameters. For example, for a certain batch of ultra-thin core boards, the system can predict the potential impact of the change in the viscosity of the copper deposition solution on the friction coefficient of the core board through cross-modal analysis, and accordingly adjust the belt board thickness and the connection method of the pressing plate clamp to avoid the risk of board jamming caused by unmodeled parameter interaction. This not only improves the accuracy and robustness of the belt board adaptation, but also significantly reduces the negative impact of process fluctuations on the yield, providing quantifiable and scalable intelligent decision-making support for the efficient and stable production of anylayer core boards in complex electroplating processes.

[0038] Specifically, in step S1221-1, perform a responsiveness analysis of non-linear decision-making on each horizontal line parameter structured mapping encoding vector in the set of the core board parameter structured mapping encoding vector and the horizontal line parameter item structured mapping encoding vector to obtain a set of implicit encoding vectors of the core board parameter-horizontal board parameter decision point state, which is expressed by the core board parameter-horizontal board parameter non-linear decision response analysis formula as:

[0039] V 2 ={v 21 ,v 22 ,...,v 2i ,...,v 2n}

[0040]

[0041] V 1,2 ={v 1,21 ,v 1,22 ,...,v 1,2i ,...,v 1,2n}

[0042] Among them, V 2 is the set of horizontal line parameter item structured mapping encoding vectors, v 21 , v 22 , v 2i and v 2n are respectively the 1st, 2nd, i-th and n-th horizontal line parameter item structured mapping encoding vectors in the set of horizontal line parameter item structured mapping encoding vectors, V 1 is the core board parameter structured mapping encoding vector, is matrix multiplication, W i and b i are respectively v 2iThe corresponding decision response weight matrix and decision response bias vector, sigmoid is the activation function, v 1,21 , v 1,22 , v 1,2i , v 1,2j and v 1,2n are respectively the 1st, 2nd, ith, jth and nth core board parameter - horizontal board parameter decision point state implicit coding vectors in the set of core board parameter - horizontal board parameter decision point state implicit coding vectors, and V 1,2 is the set of core board parameter - horizontal board parameter decision point state implicit coding vectors. It should be understood that due to the strong non - linear coupling relationship between the core board parameter structured mapping coding vector and the horizontal line parameter item structured mapping coding vector, it is difficult for traditional linear models to capture the dynamic interaction of multiple parameters. In the technical solution of this application, by introducing the responsiveness analysis of non - linear decision - making, the system constructs a decision response function between parameters using a deep neural network, maps physical parameters to a high - dimensional hidden space, and realizes feature decoupling and decision boundary reconstruction in this space. The essence of this analysis is to transform the bending resistance requirements of the core board and the process constraint conditions into a quantifiable decision response state through the dynamic modeling of feature interaction, providing an adaptability evaluation benchmark for subsequent cross - modal feature fusion. In this way, by constructing the hidden space of the decision response state of both through significant non - linear mapping and interaction between features, the originally linearly inseparable parameter combinations form recognizable distribution patterns in the hidden space, effectively separating the originally indistinguishable features and simplifying the complex decision boundary. Moreover, through the dynamic representation of the decision response state, the impact of parameter perturbations on the transmission stability of the core board can be predicted in real - time. For example, when the concentration of the electroless copper plating solution suddenly changes, the hidden space representation can immediately reflect the change trend of the plating friction coefficient, thereby driving the adaptive adjustment of the belt plate parameters.

[0043] In the embodiment of this application, in step S1221 - 2, constructing the Laplacian matrix of the core board parameter - horizontal board parameter decision point state for the set of core board parameter - horizontal board parameter decision point state implicit coding vectors includes: S1221 - 21, calculating the core board parameter - horizontal board parameter decision point state class neighborhood matrix based on the set of core board parameter - horizontal board parameter decision point state implicit coding vectors; S1221 - 22, calculating the core board parameter - horizontal board parameter decision point state class degree matrix based on the set of core board parameter - horizontal board parameter decision point state implicit coding vectors; S1221 - 23, calculating the core board parameter - horizontal board parameter decision point state Laplacian matrix based on the core board parameter - horizontal board parameter decision point state class neighborhood matrix and the core board parameter - horizontal board parameter decision point state class degree matrix.

[0044] Specifically, in step S1221-21, based on the set of implicit coding vectors of the core board parameter-horizontal board parameter decision point states, calculate the core board parameter-horizontal board parameter decision point state class neighborhood matrix, which is expressed by the core board parameter-horizontal board parameter decision point state class neighborhood calculation formula as:

[0045]

[0046] where, ||·|| 2 is the two-norm of the calculation vector, arccosh is the inverse hyperbolic cosine function, A 11 , A n1 , A 1n , A ij and A nn are the eigenvalues at each position in the core board parameter-horizontal board parameter decision point state class neighborhood matrix respectively, and A is the core board parameter-horizontal board parameter decision point state class neighborhood matrix. It should be understood that by calculating the core board parameter-horizontal board parameter decision point state class neighborhood matrix, the system maps the implicit coding vectors of the core board parameter-horizontal board parameter decision point states generated by the non-linear decision response analysis into a graph structure, and uses the adjacency relationship to explicitly express the local topological features in the data manifold. The construction of the core board parameter-horizontal board parameter decision point state class neighborhood matrix is essentially a discretization approximation of the data manifold structure, so as to transform the complex associations in the high-dimensional parameter space into the node connection strength in the graph theory framework, where the eigenvalue of each element quantifies the state similarity of the corresponding decision point under process constraints. After executing this step, the originally scattered parameter response patterns are reconstructed into a graph structure with clear geometric meaning, providing an analyzable topological basis for subsequent spectral decomposition, enabling the system to capture the long-range dependence relationship between parameters through graph embedding. In the technical solution of this application, the eigenvalues at each position in the core board parameter-horizontal board parameter decision point state class neighborhood matrix reflect the state semantic correlation degree between the corresponding two core board parameter-horizontal board parameter decision points. In this way, the accuracy of the process adaptation is improved, so that when the system faces abnormal working conditions such as sudden changes in the concentration of the electroless copper plating solution, it can quickly identify the key influencing factors through the graph structure and adjust the tape connection strategy, effectively suppressing the risk of core board warping.

[0047] Specifically, in step S1221-22, based on the set of implicit coding vectors of the core board parameter-horizontal board parameter decision point states, calculate the core board parameter-horizontal board parameter decision point state class degree matrix, which is expressed by the core board parameter-horizontal board parameter decision point state class degree calculation formula as:

[0048]

[0049] where, is the square of the calculation vector one-norm, n is the number of vectors in V 1,2 minus one, D 1, D i and D n i and n are the eigenvalues at various positions on the diagonal of the core board parameter - horizontal board parameter decision point state degree matrix, and D is the core board parameter - horizontal board parameter decision point state degree matrix. It should be understood that by calculating the core board parameter - horizontal board parameter decision point state degree matrix, the system transforms the local connection strength between the core board parameter - horizontal board parameter decision point state implicit coding vectors into a node centrality index in the form of a diagonal matrix. The diagonal elements quantify the topological weight of each core board parameter - horizontal board parameter decision point in the parameter association network through the statistical mean of the squared distance of the one - norm, reflecting the "importance" and "centrality" of the node in the graph structure. The construction of the core board parameter - horizontal board parameter decision point state degree matrix is essentially to establish a dynamic evaluation system for process parameter influence factors, enabling the subsequent core board parameter - horizontal board parameter decision point state Laplacian matrix to adaptively distinguish key parameter nodes (such as strongly correlated nodes of current density on core board deformation) from secondary nodes according to the connection strength of the nodes, so as to more accurately reflect the internal structural characteristics of the data. In particular, in the technical solution of this application, the eigenvalues at various positions on the diagonal of the core board parameter - horizontal board parameter decision point state degree matrix are used to represent the stacking situation of the implicit correlation degrees between each core board parameter - horizontal board parameter decision point and all other core board parameter - horizontal board parameter decision points.

[0050] Specifically, in steps S1221 - 23, based on the core board parameter - horizontal board parameter decision point state neighborhood matrix and the core board parameter - horizontal board parameter decision point state degree matrix, calculate the core board parameter - horizontal board parameter decision point state Laplacian matrix, which is expressed by the core board parameter - horizontal board parameter decision point state Laplacian calculation formula as:

[0051] L = D - A

[0052] where L is the core board parameter - horizontal board parameter decision point state Laplacian matrix. It should be understood that by calculating the core board parameter - horizontal board parameter decision point state Laplacian matrix based on the core board parameter - horizontal board parameter decision point state neighborhood matrix and the core board parameter - horizontal board parameter decision point state degree matrix, the graph structure of parameter association is transformed into a mathematical object under the spectral analysis framework. Its essence is to map the complex associations between process parameters to the frequency domain space through graph signal processing theory. The eigenvalues and eigenvectors of the core board parameter - horizontal board parameter decision point state Laplacian matrix contain rich information about the graph spectrum. The eigenvalues reflect the frequency components of the graph signal, and the eigenvectors form the basis functions for graph signal processing. Specifically, high - frequency features correspond to local parameter mutations (such as the impact of instantaneous fluctuations in current density on core board stress), and low - frequency features reflect global process constraints (such as the long - term effect of temperature gradient on coating uniformity).

[0053] Specifically, in step S1221-3, perform spectral decomposition on the Laplacian matrix of the core board parameter-horizontal board parameter decision point state to obtain a set of core board parameter-horizontal board parameter decision point core component coding vectors, which is expressed by the core board parameter-horizontal board parameter spectral decomposition formula as follows:

[0054]

[0055] where Spectral Decomposition(L) is the operation of performing spectral decomposition on L, U is the core board parameter-horizontal board parameter eigenmatrix, that is, a set of core board parameter-horizontal board parameter decision point core component coding vectors, x 1 , x 2 , x i and x k are the 1st, 2nd, ith, and kth core board parameter-horizontal board parameter decision point core component coding vectors in the set of core board parameter-horizontal board parameter decision point core component coding vectors respectively, diag(λ 1 , λ 2 , …, λ i …, λ k ) is a core board parameter-horizontal board parameter eigenvalue diagonal matrix with elements λ 1 , λ 2 , λ i and λ k on the diagonal, λ 1 , λ 2 , λ i and λ k are the eigenvalues corresponding to x 1 , x 2 , x i and x k respectively, and Λ is the core board parameter-horizontal board parameter eigenvalue diagonal matrix. It should be understood that the Laplacian matrix of the core board parameter-horizontal board parameter decision point state generated through structured mapping and cross-modal feature domain dynamic response analysis carries the implicit correlation information between heterogeneous data. However, it is difficult to capture its internal patterns and key influencing factors directly using the original high-dimensional data. Therefore, spectral decomposition technology is used to decompose the Laplacian matrix of the core board parameter-horizontal board parameter decision point state, converting it into the form of eigenvalues and eigenvectors, where the eigenvalues reflect the importance of different frequency components, and the eigenvectors provide the basis functions for describing these components. This operation enables the system to strip off high-frequency noise components and retain the core features reflecting global process constraints.

[0056] Preferably, in another example of the present application, in step S1221-3, spectral decomposition is performed on the Laplacian matrix of the core board parameter-horizontal board parameter decision point state to obtain a set of core board parameter-horizontal board parameter decision point core component coding vectors, including: S1221-31, performing matrix topology optimization based on cut-cycle space closure on the Laplacian matrix of the core board parameter-horizontal board parameter decision point state to obtain an optimized Laplacian matrix of the core board parameter-horizontal board parameter decision point state;

[0057] S1221-32, performing spectral decomposition on the optimized Laplacian matrix of the core board parameter-horizontal board parameter decision point state to obtain a set of core board parameter-horizontal board parameter decision point core component coding vectors.

[0058] In step S1221-31, matrix topology optimization based on cut-cycle space closure is performed on the Laplacian matrix of the core board parameter-horizontal board parameter decision point state to obtain an optimized Laplacian matrix of the core board parameter-horizontal board parameter decision point state. It should be understood that due to the limit point representation of each core board parameter-horizontal board parameter decision point state in the node graph structure, the Laplacian matrix of the core board parameter-horizontal board parameter decision point state is the union representation of all limit points of a set in the topological space, and in this case, a topological closure operator can be applied to perform a more robust topological feature representation on the Laplacian matrix of the core board parameter-horizontal board parameter decision point state.

[0059] Specifically, first use generalized inverse matrix operations to extract the connected domain characteristics of the core board parameter-horizontal board parameter decision point state class neighborhood matrix and the core board parameter-horizontal board parameter decision point state class degree matrix, that is, let:

[0060]

[0061] Then the matrix M 1 and M 2 can respectively represent the cut space and the cycle space of the Laplacian matrix L of the core board parameter-horizontal board parameter decision point state. Thus, the Laplacian matrix of the core board parameter-horizontal board parameter decision point state is optimized through cut space closure and cycle space closure, expressed as:

[0062]

[0063] In this way, global structure invariants in the structural information of the graph are extracted through generalized inverse-driven closure reconstruction, making the spectral domain topological feature expression ability of the Laplacian matrix L of the core board parameter-horizontal board parameter decision point state more robust.

[0064] Next, in step S1221-32, spectral decomposition is performed on the Laplacian matrix of the optimized core board parameter-horizontal board parameter decision point state to obtain a set of core board parameter-horizontal board parameter decision point core component coding vectors. It should be understood that by decomposing the Laplacian matrix of the optimized core board parameter-horizontal board parameter decision point state into eigenvalues and eigenvectors through spectral decomposition technology, the system maps the parameter correlation network to the spectral domain space, where the eigenvector corresponding to the smallest eigenvalue carries the essential structural information of the data manifold. This process is essentially a non-linear dimensionality reduction by stripping high-frequency noise components through mathematical orthogonal transformation. For example, it eliminates the interference of instantaneous fluctuations in current density on the core board stress model and retains the stable correlation pattern between temperature gradient and material thermal expansion coefficient. The generated set of core board parameter-horizontal board parameter decision point core component coding vectors, as a low-dimensional embedding representation of the parameter correlation network, captures the key structural information of the data and provides a condensed feature representation for dynamic query response, enabling the system to quickly analyze the key influence paths under complex working conditions such as sudden changes in the concentration of the electroless copper plating solution.

[0065] Specifically, in step S1221-4, adaptive fusion is performed on the set of core board parameter-horizontal board parameter decision point core component coding vectors to obtain a core board parameter-horizontal board parameter dynamic query response coding vector, which is expressed by the core board parameter-horizontal board parameter dynamic query response adaptive fusion formula as:

[0066]

[0067] where AF(U) is the adaptive fusion operation on U, W i and b i are the fusion weight matrix and fusion bias vector corresponding to x i respectively, softmax is the softmax function, is the core board parameter-horizontal board parameter scoring weight vector corresponding to x i a i is the core board parameter-horizontal board parameter weight value corresponding to x i mask is the masking operation, τ is the preset threshold, w i is the core board parameter-horizontal board parameter masking weight value corresponding to x i v fIt is the core board parameter - horizontal board parameter dynamic query response coding vector. It should be understood that considering the contradiction between feature redundancy and context dependence still exists in the low - dimensional core board parameter - horizontal board parameter decision point core component coding vector extracted by spectral decomposition. Therefore, through adaptive fusion, the complementary information of multiple core board parameter - horizontal board parameter decision point core component coding vectors is integrated and dynamically adjusted according to specific tasks, so as to achieve the collaborative optimization of multi - source information. In specific implementation, through an attention - driven model or a gated function system, a parameter correlation evaluation framework is constructed to quantify the influence factor weights of each coding vector on specific process tasks. This process uses a context - aware weight assignment mechanism to focus on key feature dimensions in real - time (such as the vector related to the coefficient of thermal expansion in the scenario of sudden change in current density), and suppresses the interference of unnecessary parameters. Adaptive fusion is not just weighted summation, but learning context - related feature combination strategies, enabling the core board parameter - horizontal board parameter dynamic query response coding vector to best adapt to different query inputs and state changes. Dynamic feature recombination breaks through the limitations of traditional linear superposition, establishes a feature coupling strategy adaptable to process states, enables the generated core board parameter - horizontal board parameter dynamic query response coding vector to accurately match the parameter matching requirements under different process conditions, and finally outputs a process optimization feature representation with high discrimination and anti - interference ability.

[0068] Specifically, in step S1222, the core board parameter - horizontal board parameter dynamic query response coding vector is decoded for features to obtain the tape board parameters. It should be understood that since the core board parameter - horizontal board parameter dynamic query response coding vector, as a low - dimensional representation in the spectral domain, can only reflect the global requirements of the core board's adaptation to the horizontal line process, the specific parameters of the tape board need to reverse - analyze the quantitative indicators of physical meaning from these abstract features. For example, the coding vector may imply the dynamic balance relationship between the bending strength of the core board and the PTH line speed, but it needs to be decoded to convert it into a millimeter - level value of the tape board thickness. Based on this, in the technical solution of this application, the core board parameter - horizontal board parameter dynamic query response coding vector is further decoded for features to obtain the tape board parameters. Through accurate parameter restoration, the system can dynamically generate the optimal configuration plan for the tape board according to the characteristics of different batches of core boards (such as abnormal ductility of a certain batch of materials) and real - time process fluctuations (such as sudden increase in the concentration of copper deposition solution). For example, during a certain production, there is an abnormal fluctuation in current density. The decoder quickly adjusts the distribution density of the tape board connection points by analyzing the current - stress correlation features in the coding vector, avoiding the fracture of the core board caused by local stress concentration. This not only makes the tape board adaptation plan highly interpretable and operable, but also significantly reduces the trial - and - error cost of manual debugging, providing a closed - loop optimization ability for zero - defect production of the anylayer core board layer in complex electroplating processes.

[0069] In the above production optimization method for the anylayer core board layer, in step 130, based on the tape parameters, select a tape with suitable parameters. It should be understood that the tape parameters include key indicators such as thickness, strength, and connection method. These parameters are directly related to the performance of the tape in the actual production environment and its supporting role for the core board. For example, the thickness of the tape determines its mechanical strength and rigidity, thus affecting its bending resistance in horizontal line transmission; the strength of the tape reflects its ability to resist deformation, which is crucial for preventing the core board from deforming during complex electroplating processes; and the connection method determines the coupling effect between the tape and the core board, directly affecting the physical coupling strength and stability between the two. Therefore, accurately obtaining and understanding the tape parameters is of fundamental significance for the subsequent selection process. After determining the tape parameters, the next step is to select the most suitable option from numerous candidate tapes based on these parameters. Specifically, in order to find the tape that best suits the current production requirements, a comprehensive evaluation of each option in the tape library must be carried out, which includes detailed measurement and analysis of its thickness, strength, and connection method. For example, when evaluating the tape thickness, not only the nominal value needs to be considered, but also its consistency needs to be confirmed through actual measurement; when evaluating the tape strength, it is necessary to verify whether its bending and tensile strengths meet the requirements through material mechanics tests; and when evaluating the connection method, it is necessary to confirm its reliability under specific process conditions through simulation experiments or actual application tests. To achieve the above goals, a series of advanced detection tools and technical means are usually adopted. For example, a laser rangefinder can be used to accurately measure the thickness of the tape to ensure that it meets the calculated thickness requirements; a material analyzer can be used to determine the specific material composition of the tape and evaluate its strength through mechanical tests; and devices such as tension sensors and strain gauges can be used to monitor the stress distribution of the tape in the actual production environment in real time to ensure that it can maintain stable performance during complex electroplating processes. In addition, computer-aided design (CAD) software and finite element analysis (FEA) technology can be used to perform virtual simulation on the tape to predict its performance under specific process conditions in advance, thereby further improving the accuracy and efficiency of the selection process. Another important aspect is the compatibility and coupling effect between the tape and the core board. Although the tape parameters have been calculated and optimized in detail, in actual applications, it is still necessary to verify its matching effect with a specific batch of core boards through experiments. This is because even for core boards of the same specification, due to material differences or different manufacturing processes, their performances in actual production may also have slight differences. Therefore, when selecting a tape, it is also necessary to conduct targeted tests in combination with specific application scenarios to ensure that the coupling strength and stability between the tape and the core board reach the best state. For example, by simulating the working conditions in the actual production environment, dynamic tests can be carried out on the combination of the tape and the core board to observe its performance at different speeds, temperatures, and current densities, thereby further optimizing the tape selection scheme.

[0070] In the above production optimization method for the anylayer core board layer, in step 140, control the press clamp to connect the tape and the core board to form an integrated structure. It should be understood that the press clamp is a specially designed device for firmly bonding the tape and the core board under specific pressure and temperature conditions. Its working principle is based on the application of mechanical pressure. By applying uniform and controllable pressure, the contact surfaces between the tape and the core board are closely fitted, thus forming a stable physical coupling. This coupling can not only improve the overall mechanical strength of the core board but also ensure its good flatness and stability during complex electroplating processes. Specifically, the process of controlling the press clamp to connect the tape and the core board generally includes the following aspects: First is the preparation work. Ensure that the surfaces of the tape and the core board are clean and free of contamination, and perform appropriate pretreatment on them, such as cleaning, drying, etc., to remove surface impurities and oil stains to ensure the quality of subsequent connections. Secondly, it is necessary to adjust the working parameters of the press clamp according to the calculated tape parameters and core board parameters, including the magnitude of pressure, temperature setting, and time control, etc. These parameters directly affect the quality of the connection and must be precisely adjusted to achieve the best state. For example, in some cases, a higher temperature helps to improve the adhesion performance between the tape and the core board, but too high a temperature may cause material deformation or damage; similarly, appropriate pressure can ensure the close fitting of the two, but too much pressure may cause the core board to crack or the tape to deform. Next, enter the actual operation stage, and precisely control the action of the press clamp through an automated control system. In a modern production environment, advanced sensor technologies and intelligent control systems are usually adopted to monitor and adjust the working state of the press clamp in real time. For example, pressure sensors can be used to monitor the magnitude of the pressure applied to the tape and the core board in real time, and automatically adjust the force of the press clamp according to the feedback information to ensure that it is always within the best range; temperature sensors can measure the temperature change in the connection area in real time and perform dynamic adjustment through a closed-loop control system to prevent the occurrence of too high or too low temperature. In actual operation, the specific steps of controlling the press clamp to connect the tape and the core board are as follows: First, place the pre-prepared tape and core board on the working platform of the press clamp and ensure that their positions are accurately aligned. Then, start the press clamp to gradually apply the predetermined pressure and temperature conditions. During the whole process, the system will continuously monitor the changes of various parameters and make fine adjustments according to the actual situation. For example, if it is detected that the pressure distribution in a certain area is uneven, the system will automatically adjust the posture of the press clamp or increase local pressure compensation to ensure the uniformity and consistency of the overall connection. When the predetermined time is reached, the press clamp will gradually release the pressure and allow the connected integrated structure to cool and take shape. During this period, the system still needs to continue monitoring the temperature change to prevent internal stress concentration or crack generation in the material due to too fast cooling speed. To further improve the connection quality, some auxiliary measures and technical means can also be adopted.For example, coating a special adhesive or conductive adhesive on the contact surface between the carrier plate and the core plate can significantly enhance the adhesion performance of the two. Especially under high temperature and high pressure conditions, this adhesive can form stronger chemical bonds, thereby improving the stability of the overall structure. In addition, advanced technologies such as laser welding or ultrasonic welding can be used to achieve a more precise connection effect without affecting the material properties. These methods can not only improve the connection strength but also reduce the damage to the material itself and extend the service life of the product.

[0071] In a specific embodiment of the present application, by adding a thin plate carrier plate fixture before the production process flow, it is ensured that the core plate can be smoothly transported on the horizontal line, thereby effectively reducing production anomalies and improving the product yield. This method specifically includes steps such as secondary outer layer laser, desmearing, blind via AOI inspection, secondary outer layer PTH, etc., and uses a press plate clamp to connect the carrier plate and the core plate to make them integrated, further ensuring the smoothness of the production process. This method is not only easy to install and disassemble but also significantly reduces the frequency of problems occurring during the production process, which is of great significance for improving the manufacturing efficiency and quality of any layer high-density interconnect boards (anylayer HDI).

[0072] In summary, the production optimization method for the anylayer core plate layer based on the embodiments of the present application is elucidated. It takes the core plate characteristics (such as size, material, and batch number) and process parameters (such as PTH line speed, copper plating solution concentration, temperature, current density, and spray pressure) as inputs, and by automatically analyzing the compatibility requirements between the core plate and the horizontal line equipment, generates key parameters such as the thickness, strength, and connection method of the adapted carrier plate. Subsequently, based on the calculation results, the carrier plate is accurately selected, and the physical coupling between the carrier plate and the core plate is achieved through a press plate clamp to form a rigid enhanced integrated structure. This process does not require manual intervention in equipment adjustment. Only through parametric matching and intelligent transmission assistance can problems such as core plate warping and jamming be effectively suppressed, and finally, the stable transmission and smooth production of the ultra-thin core plate in the complex electroplating process can be ensured.

[0073] Figure 6 It is a system block diagram of the production optimization system for the anylayer core plate layer according to the embodiments of the present application. As Figure 6As shown, the production optimization system 100 for the anylayer core board layer according to an embodiment of the present application includes: a parameter acquisition module 110, configured to acquire core board parameters and horizontal line parameters; a strip board parameter determination module 120, configured to determine strip board parameters based on the core board parameters and the horizontal line parameters, wherein the strip board parameter determination module is configured to: perform feature domain mapping on the core board parameters and the horizontal line parameters to obtain a set of structured mapping representations of the core board parameters and a set of structured mapping representations of the horizontal line parameter items; determine the strip board parameters based on the cross-modal feature domain dynamic response analysis result between the set of structured mapping representations of the core board parameters and the set of structured mapping representations of the horizontal line parameter items; a strip board selection module 130, configured to select a strip board with adapted parameters based on the strip board parameters; and a connection module 140, configured to control a press plate clamp to connect the strip board and the core board to form an integrated structure.

[0074] Here, those skilled in the art can understand that the specific operations of each step in the above production optimization system for the anylayer core board layer have been introduced in detail in the description of the production optimization method for the anylayer core board layer with reference to Figures 1 to 5 above, and thus, the repeated description thereof will be omitted.

[0075] As described above, the production optimization system 100 for the anylayer core board layer according to an embodiment of the present application can be implemented in various terminal devices. In one example, the production optimization system 100 for the anylayer core board layer can be integrated into the terminal device as a software module and / or a hardware module. For example, the production optimization system 100 for the anylayer core board layer can be a software module in the operating system of the terminal device, or can be an application program developed for the terminal device; of course, the production optimization system 100 for the anylayer core board layer can also be one of the many hardware modules of the terminal device.

[0076] Alternatively, in another example, the production optimization system 100 for the anylayer core board layer and the terminal device can also be separate devices, and the production optimization system 100 for the anylayer core board layer can be connected to the terminal device through a wired and / or wireless network and transmit and interact information in accordance with a predefined data format.

[0077] In summary, a production optimization system for an anylayer core board layer based on the embodiments of the present application is elucidated. It takes core board characteristics (such as size, material, and batch number) and process parameters (such as PTH line speed, copper deposition solution concentration, temperature, current density, and spray pressure) as inputs. By automatically analyzing the compatibility requirements between the core board and the horizontal line equipment, it generates key parameters such as the thickness, strength, and connection method of the adapter carrier board. Subsequently, based on the calculation results, the carrier board is accurately selected, and the physical coupling between the carrier board and the core board is achieved through the press plate clamp, forming a rigidly enhanced integrated structure. This process does not require manual intervention for equipment adjustment. Only through parametric matching and intelligent transmission assistance, problems such as core board warping and jamming can be effectively suppressed, ultimately ensuring the stable transmission and smooth production of ultra-thin core boards in complex electroplating processes.

[0078] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules is only a logical function division, and there can be other division methods in actual implementation.

[0079] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Additionally, in various embodiments of the present invention, the functional modules can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of a combination of hardware and software functional modules.

[0080] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0081] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention. Any associated drawing marks in the claims should not be regarded as limiting the claimed rights.

[0082] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular form does not exclude the plural form. A plurality of units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The terms such as "second" are used to denote names and do not denote any particular order.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit of the technical solutions of the present invention.

Claims

1. A production optimization method for anylayer core layer, characterized in that: include: Get core plate parameters and horizontal line parameters; Based on the core plate parameters and the horizontal line parameters, determining the strip plate parameters, including: performing feature domain mapping on the core plate parameters and the horizontal line parameters to obtain a set of core plate parameter structured mapping representations and horizontal line parameter item structured mapping representations; determining the strip plate parameters based on a cross-modal feature domain dynamic response analysis result between the core plate parameter structured mapping representations and the set of horizontal line parameter item structured mapping representations; Based on the strip plate parameters, selecting a strip plate with matching parameters; The control plate clamp connects the strip plate and the core plate to form an integrated structure.

2. The production optimization method for anylayer core layer according to claim 1, characterized in that: The core board parameters include size, material and batch number; the horizontal line parameters include PTH line speed, copper plating solution concentration, temperature, current density and spray pressure.

3. The production optimization method for anylayer core layer according to claim 2, characterized in that: The core plate parameters and the horizontal line parameters are mapped to feature domains to obtain a set of core plate parameter structured mapping representations and horizontal line parameter item structured mapping representations, including: Performing structured mapping on the core panel parameters to obtain a core panel parameter structured mapping encoding vector as the core panel parameter structured mapping representation; Perform structured mapping on each parameter item in the horizontal line parameters to obtain a set of structured mapping encoding vectors of the horizontal line parameter items as a set of structured mapping representations of the horizontal line parameter items.

4. The production optimization method for anylayer core layer according to claim 3, characterized in that: Determining the strip plate parameters based on the cross-modal feature domain dynamic response analysis results between the core plate parameter structured mapping representation and the set of horizontal line parameter item structured mapping representations includes: Performing parameter cross-modal feature dynamic response analysis on the set of the core panel parameter structured mapping coding vector and the horizontal line parameter item structured mapping coding vector to obtain a core panel parameter-horizontal panel parameter dynamic query response coding vector as the cross-modal feature domain dynamic response analysis result; The core panel parameter-horizontal panel parameter dynamic query response encoding vector is feature decoded to obtain the strip panel parameters.

5. The production optimization method for anylayer core layer according to claim 4, characterized in that: Performing parameter cross-modal feature dynamic response analysis on the set of the core panel parameter structured mapping encoding vector and the horizontal line parameter item structured mapping encoding vector to obtain a core panel parameter-horizontal panel parameter dynamic query response encoding vector as the cross-modal feature domain dynamic response analysis result, including: Performing nonlinear decision responsiveness analysis on each horizontal line parameter item structured mapping coding vector in the set of the core panel parameter structured mapping coding vector and the horizontal line parameter item structured mapping coding vector to obtain a set of core panel parameter-horizontal panel parameter decision point state implicit coding vectors; Constructing the Laplace matrix of the set of implicit coding vectors of the core plate parameter-horizontal plate parameter decision point state to obtain the core plate parameter-horizontal plate parameter decision point state Laplace matrix; Performing spectral decomposition on the core plate parameter-horizontal plate parameter decision point state Laplace matrix to obtain a set of core plate parameter-horizontal plate parameter decision point core component encoding vectors; The set of the core panel parameter-horizontal panel parameter decision point core component coding vectors is adaptively fused to obtain the core panel parameter-horizontal panel parameter dynamic query response coding vector.

6. The production optimization method for anylayer core layer according to claim 5, characterized in that: Constructing a core board parameter-horizontal board parameter decision point state Laplace matrix of the set of core board parameter-horizontal board parameter decision point state implicit coding vectors, including: Based on the set of implicit coding vectors of the core board parameter-horizontal board parameter decision point states, a core board parameter-horizontal board parameter decision point state class neighborhood matrix is ​​calculated; Based on the set of implicit coding vectors of the core board parameter-horizontal board parameter decision point states, calculating the core board parameter-horizontal board parameter decision point state class matrix; Based on the core panel parameter-horizontal panel parameter decision point state class neighborhood matrix and the core panel parameter-horizontal panel parameter decision point state class degree matrix, the core panel parameter-horizontal panel parameter decision point state Laplace matrix is ​​calculated.

7. The production optimization method for anylayer core layer according to claim 6, characterized in that: The core plate parameter-horizontal plate parameter decision point state Laplace matrix is ​​spectrally decomposed to obtain a set of core plate parameter-horizontal plate parameter decision point core component encoding vectors, including: Performing matrix topology optimization based on cut-cycle space closure on the core plate parameter-horizontal plate parameter decision point state Laplace matrix to obtain an optimized core plate parameter-horizontal plate parameter decision point state Laplace matrix; The optimized core panel parameter-horizontal panel parameter decision point state Laplace matrix is ​​spectrally decomposed to obtain a set of core component coding vectors of the core panel parameter-horizontal panel parameter decision point.

8. A production optimization system for anylayer core layer, characterized in that: include: A parameter acquisition module is used to obtain core board parameters and horizontal line parameters; A strip plate parameter determination module is used to determine the strip plate parameters based on the core plate parameters and the horizontal line parameters, wherein the strip plate parameter determination module is used to: perform feature domain mapping on the core plate parameters and the horizontal line parameters to obtain a set of structured mapping representations of core plate parameters and structured mapping representations of horizontal line parameter items; determine the strip plate parameters based on a cross-modal feature domain dynamic response analysis result between the set of structured mapping representations of core plate parameters and structured mapping representations of horizontal line parameter items; A strip board selection module, used for selecting a strip board with matching parameters based on the strip board parameters; The connection module is used to control the pressure plate clamp to connect the strip plate and the core plate to form an integrated structure.

9. The production optimization system for anylayer core layer according to claim 8, characterized in that: The core board parameters include size, material and batch number; the horizontal line parameters include PTH line speed, copper plating solution concentration, temperature, current density and spray pressure.

Images