LCP millimeter wave radar circuit board processing control method and device

Abstract

The embodiment of the invention provides an LCP millimeter wave radar circuit board processing control method and device. The method comprises the steps that LCP material parameters, spraying material parameters and FR4 material parameters are acquired; preset hole machining parameters are obtained, and machining technology and defect parameters in the preset hole machining parameters are extracted; forming a data set by the LCP material parameters, the spraying material parameters, the FR4 material parameters and the processing technology and defect parameters; inputting the data set into a neural network model for training to obtain a trained neural network model; new LCP material parameters, spraying material parameters and FR4 material parameters are input into the trained neural network model, and output preset hole machining parameters are obtained; according to the preset hole machining parameters, spraying and drilling operation of the millimeter wave radar circuit board is carried out; the processing defects of burrs, curled edges and the like of the circuit board are avoided, the processing and manufacturing yield is improved, and the problems that materials cannot be completely cut off easily when a CNC forming milling cutter is used for processing and cutting, and curled edges and burrs are caused when the milling cutter pulls LCP materials are solved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a LCP millimeter wave radar circuit board processing control method and a LCP millimeter wave radar circuit board processing control device, a computer device and a storage medium. Background Art

[0002] With the trend of automobile intelligence and autonomous driving, vehicle-mounted millimeter-wave radar has ushered in rapid development. The importance of high-frequency circuit board materials of printed circuit boards in 77GHz automotive radar applications; in the high-frequency band, although many new circuit board materials have been developed, they are not all suitable for such high-frequency use; recently, it has been proposed to use liquid crystal polymer (LCP) materials for microwave and millimeter-wave RF front-end circuit integration and packaging. As a new material, LCP has lower loss than other materials and is very suitable for manufacturing microwave and millimeter-wave equipment, so it has good application prospects; due to the characteristics of LCP materials, during the CNC molding process of the circuit board manufacturing process, the edge of the LCP material board is prone to curling, burrs and other undesirable phenomena, such as Figure 1 As shown, it affects the size and appearance of the finished product. Summary of the invention

[0003] In view of the above problems, the present embodiment is proposed to provide a LCP millimeter wave radar circuit board processing control device, a computer device and a storage medium that overcome the above problems or at least partially solve the above problems.

[0004] In order to solve the above problems, this embodiment discloses a LCP millimeter wave radar circuit board processing control method, including:

[0005] Obtain LCP material parameters, spray material parameters and FR4 material parameters;

[0006] Acquire preset hole processing parameters, and extract processing technology and defect parameters from the preset hole processing parameters;

[0007] The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set;

[0008] Inputting the data set into a neural network model for training to obtain a trained neural network model;

[0009] Inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters;

[0010] The millimeter wave radar circuit board is sprayed and drilled according to the preset hole processing parameters.

[0011] Preferably, the LCP material parameters include density self-enhancement parameters, the spraying material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters;

[0012] The processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion dimensions;

[0013] The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set, including:

[0014] The density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size are combined into a six-element data set, and the six-element data set is divided into a six-element training set and a six-element verification set.

[0015] Preferably, the millimeter wave radar circuit board includes a two-layer structure, and the two-layer structure includes an LCP material layer and an FR4 material layer;

[0016] The spraying and drilling operations of the millimeter wave radar circuit board according to the preset hole processing parameters include:

[0017] Controlling the device to perform a drilling operation of a preset depth of the LCP material layer according to the liquid crystal layer depth parameter to obtain a millimeter wave radar circuit board with preliminary drilling;

[0018] Obtain the corresponding milling cutter speed and feed speed according to the milling cutter temperature parameters;

[0019] According to the milling cutter rotation speed and feed speed control, the millimeter wave radar circuit board control device for preliminary drilling performs a through-hole drilling operation on the FR4 material layer to obtain a millimeter wave radar circuit board containing through holes.

[0020] Preferably, inputting the data set into a neural network model for training to obtain a trained neural network model comprises:

[0021] Inputting the six-element training set into the neural network model for training to obtain a neural network model to be verified;

[0022] Inputting the six-element verification set into the neural network model to be verified, adjusting the model parameters, and obtaining a preliminary neural network model;

[0023] The six-element training set is input into the preliminary neural network model, and the model parameters are adjusted again until the iteration is completed to obtain a trained neural network model.

[0024] Preferably, the method further comprises:

[0025] The millimeter-wave radar circuit board including the through-hole is subjected to electrical testing, organic solderability protection film generation, and appearance inspection operations to complete the processing of the millimeter-wave radar circuit board.

[0026] Preferably, the step of obtaining the corresponding milling cutter rotation speed and feed speed according to the milling cutter temperature parameter includes:

[0027] The milling cutter temperature parameter in the preset hole processing parameters, as well as the historical milling cutter rotation speed and the historical feed speed are fitted to obtain a milling cutter temperature rotation speed curve and a milling cutter temperature feed speed curve;

[0028] The milling cutter temperature rotation speed curve and the milling cutter temperature feed speed curve are queried according to the milling cutter temperature parameter to obtain the corresponding milling cutter rotation speed and feed speed.

[0029] The embodiment of the present invention discloses a LCP millimeter wave radar circuit board processing control device, comprising:

[0030] Parameter acquisition module, used to obtain LCP material parameters, spray material parameters and FR4 material parameters;

[0031] An extraction module, used to obtain preset hole processing parameters and extract processing technology and defect parameters from the preset hole processing parameters;

[0032] A composition module, used for composing the LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters into a data set;

[0033] A training module, used for inputting the data set into a neural network model for training to obtain a trained neural network model;

[0034] An input module, used for inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters;

[0035] The processing module is used to perform spraying and drilling operations on the millimeter wave radar circuit board according to the preset hole processing parameters.

[0036] Preferably, the LCP material parameters include density self-enhancement parameters, the spray material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters; the processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling protrusion size;

[0037] The component modules include:

[0038] The composition submodule is used to form a six-element data set by combining the density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size, and divide the six-element data set into a six-element training set and a six-element verification set.

[0039] This embodiment also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned steps of LCP millimeter wave radar circuit board processing control when executing the computer program.

[0040] This embodiment also discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned steps of LCP millimeter-wave radar circuit board processing control are implemented.

[0041] This embodiment includes the following advantages:

[0042] The LCP millimeter-wave radar circuit board processing control method in the embodiment of the present invention includes: obtaining LCP material parameters, spray material parameters and FR4 material parameters; obtaining preset hole processing parameters, extracting processing technology and defect parameters in the preset hole processing parameters; forming a data set with the LCP material parameters, spray material parameters and FR4 material parameters and processing technology and defect parameters; inputting the data set into a neural network model for training to obtain a trained neural network model; inputting new LCP material parameters, spray material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters; performing spraying and drilling operations on the millimeter-wave radar circuit board according to the preset hole processing parameters; avoiding processing defects such as burrs and curling of circuit boards, improving processing yield, and solving the problem that it is difficult to completely cut off the material during CNC forming milling cutter processing and cutting, and the milling cutter pulls the LCP material to cause curling and burrs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solution in the present embodiment, the following briefly introduces the drawings required for use in the description of the embodiment. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 It is a schematic diagram of a circuit board manufacturing process and effect in the prior art;

[0045] Figure 2 This is a flowchart of the steps of an embodiment of a LCP millimeter wave radar circuit board processing control method of this embodiment;

[0046] Figure 3This is a schematic diagram of a circuit board manufacturing process and effect in an embodiment of the present invention;

[0047] Figure 4 This is a structural block diagram of an embodiment of an LCP millimeter wave radar circuit board processing control device of this embodiment;

[0048] Figure 5 The diagram is a diagram of the internal structure of a computer device according to an embodiment. DETAILED DESCRIPTION

[0049] In order to make the technical problems, technical solutions and beneficial effects solved by this embodiment more clearly understood, this embodiment is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] In a core concept of an embodiment of the present invention, different material parameters and processing parameters are combined into a data set, and the data set is trained with an intelligent prediction model to obtain a trained intelligent prediction model, and then subsequent new data is input into the trained intelligent prediction model to obtain predicted processing parameters. According to the material characteristics, the optimal processing parameters (mainly in terms of preset hole processing depth) can be further selected to avoid processing defects such as burrs and curling of circuit boards, improve the processing yield, and solve the problem that it is difficult to completely cut off the material during CNC molding milling cutter processing and cutting, and the milling cutter pulls the LCP material to cause curling and burrs; further, according to previous historical data, mainly historical milling cutter speed and historical feed speed data, and predicted temperature data, fit is performed to obtain two different curves, and the corresponding milling cutter speed and feed speed are queried according to the curves, and processing is performed according to the above data to further obtain accurate processing data and improve the processing yield.

[0051] The LCP millimeter wave radar circuit board processing control method provided in this embodiment can be applied to an application environment including a terminal and a server. Among them, the terminal communicates with the server through a network. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The terminal is connected to a variety of semiconductor devices, and the embodiment of the present invention does not impose too many restrictions on this.

[0052] Reference Figure 2 , shows a flowchart of a method for controlling the processing of an LCP millimeter-wave radar circuit board according to the present embodiment, which may specifically include the following steps:

[0053] Step 101, obtaining LCP material parameters, spraying material parameters and FR4 material parameters;

[0054] In an embodiment of the present invention, the terminal may be a terminal connected to a variety of semiconductor devices, and the semiconductor devices may include a variety of semiconductor devices, such as material pre-baking equipment, inner layer imaging equipment, etching equipment, drilling equipment, electroplating equipment, browning equipment, etc. The embodiment of the present invention does not impose too many restrictions on the types of semiconductor devices; the terminal and the connected server can control the above-mentioned semiconductor devices to perform corresponding processing operations on various semiconductor materials.

[0055] Specifically applied to the embodiment of the present invention, LCP material parameters, spray material parameters and FR4 material parameters are obtained; the LCP material parameters refer to various material characteristic parameters of liquid crystal polymer (Liquid Crystal Polymer); and the spray material parameters refer to various material characteristic parameters sprayed after drilling of semiconductor materials; FR4 material parameters refer to comprehensive material characteristic parameters of composite materials (FR4) made of epoxy resin, filler, glass fiber and other materials;

[0056] For example, the LCP material parameters include a density self-enhancement parameter, the spray material parameters include a protective film thickness, and the FR4 material parameters include a flame retardant loss parameter; the density self-enhancement parameter may refer to a parameter obtained by comprehensively calculating the density parameter and the self-enhancement parameter of the LCP material. Specifically, the density parameter and the self-enhancement parameter may be divided according to preset levels to obtain corresponding level values, and the level values ​​of multiple material parameters may be calculated according to different weighting coefficients to obtain the density self-enhancement parameter; for example, if the density parameter is 1.365 g / cm3; and the self-enhancement parameter may directly use the preset level as a parameter, and the preset levels corresponding to the two parameters may be calculated according to the weighting coefficient to obtain the density self-enhancement parameter. For example, if the level of the self-enhancement parameter is level 6, and the level corresponding to the density parameter is level 7, and the weighting coefficients are divided into 0.3 and 0.7, then the density self-enhancement parameter is: the level of the self-enhancement parameter (6)*0.3+the level of the density parameter (7)*0.6 is equal to 6, and a corresponding relationship between various parameters and preset levels is established for easy query.

[0057] It should be noted that the above density parameters can be converted into corresponding preset levels according to the level division method set according to actual conditions, such as being divided into different levels according to different density ranges from high to low. For example, the density range is: 1.0-1.2g / cm 3 Grade 6, 1.2-1.4g / cm 3It is level 7. The above-mentioned level division is only an example of an embodiment of the present invention. The level division can also be performed in other ways. The embodiment of the present invention does not impose too many restrictions on this. In addition, the corresponding range can be obtained according to the level to obtain the numerical range. In the embodiment of the present invention, training is performed through a small range of values, which does not require too much model computing power, improves the computing efficiency of the artificial model, and reduces the cost of model training.

[0058] Similarly, the flame retardant loss parameter in the FR4 material parameters refers to the parameter obtained by comprehensively calculating the flame retardant parameters and loss parameters of the FR4 material; the calculation method can refer to the calculation method of the above-mentioned density self-enhancement parameter, and the embodiment of the present invention does not impose too many restrictions on this; for example, ordinary loss: loss parameter ≥ 0.02, then the level is 1; medium loss: 0.01<loss parameter<0.02, then the level is 2; 0.005<low loss<0.01, then the level is 3; ultra-low loss board <0.005, then the level is 4; flame retardant parameters can be directly divided into levels, such as level 1 and level 2. The higher the level, the better the flame retardant effect. The two levels are then calculated according to different weighting coefficients to obtain the flame retardant loss parameters.

[0059] The spray material parameters include the protective film thickness, which refers to a single parameter of the thickness of the spray material sprayed in the circuit board. The single parameter can be trained with a parameter value instead of a level value. On the basis of improving the calculation efficiency of the artificial model through the above operation, it helps to improve the accuracy of training.

[0060] Step 102, obtaining preset hole processing parameters, and extracting processing technology and defect parameters from the preset hole processing parameters;

[0061] In an embodiment of the present invention, preset hole processing parameters can also be obtained, and the preset hole processing parameters refer to parameters related to preset holes in the processing technology of the circuit board; they may include liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion dimensions; specifically, the liquid crystal layer depth parameters refer to the hole depth of laser pre-processing of the LCP material layer, and the milling cutter temperature parameters refer to the temperature change of the milling cutter and the feed speed during the processing of the LCP material layer and the FR4 material layer. The embodiment of the present invention does not impose too many restrictions on this; in addition, the curling edge protrusion dimension refers to the protruding dimensions of processing defects such as burrs and curling; the above three parameters of liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion dimensions may refer to processing technology and defect parameters.

[0062] Step 103, forming a data set with the LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters;

[0063] Further applied to the embodiment of the present invention, the LCP material parameters, spray material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set, including: the density self-enhancement parameters, protective film thickness, flame retardant loss parameters, liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion size are combined into a six-element data set, and the six-element data set is divided into a six-element training set and a six-element verification set.

[0064] The six parameters of density self-enhancement parameter, protective film thickness, flame retardant loss parameter, liquid crystal layer depth parameter, milling cutter temperature parameter and curling edge protrusion size constitute a data set, and the data set can be divided into a six-element training set and a six-element verification set; for example, an example of the data set can be: (density self-enhancement parameter 1, protective film thickness 1, flame retardant loss parameter 1, liquid crystal layer depth parameter 1, milling cutter temperature parameter 1, curling edge protrusion size 1), (density self-enhancement parameter 2, protective film thickness 2, flame retardant loss parameter 2, liquid crystal layer depth parameter 2, milling cutter temperature parameter 2, curling edge protrusion size 2), and model training is performed through multivariate data to improve prediction accuracy.

[0065] In the embodiment of the present invention, six parameters including density self-enhancement parameter, protective film thickness, flame retardant loss parameter, liquid crystal layer depth parameter, milling cutter temperature parameter and curling edge protrusion size are processed by data cleaning, such as consistency check or processing of invalid values ​​and missing values. The embodiment of the present invention does not impose excessive restrictions on this.

[0066] Step 104, inputting the data set into a neural network model for training to obtain a trained neural network model;

[0067] Furthermore, the above-mentioned data set is input into the neural network model for training to obtain a trained neural network model; specifically, the data set is input into the neural network model for training to obtain a trained neural network model, including: inputting the six-element training set into the neural network model for training to obtain a neural network model to be verified; inputting the six-element verification set into the neural network model to be verified, adjusting the model parameters, and obtaining a preliminary neural network model; inputting the six-element training set into the preliminary neural network model again, and adjusting the model parameters again until the iteration is completed to obtain a trained neural network model. In the embodiment of the present invention, the initial neural network model is first adjusted by the training set. After the data set is input, the neural network model to be verified is obtained; further, the verification neural network model is tested through the six-element verification set. Specifically, when the model output result is inconsistent with the result of the six-element verification set, the model coefficient is further adjusted to obtain a preliminary neural network model to improve the accuracy of the output result. In an embodiment of the present invention, the six-element training set needs to be input into the preliminary neural network model again, and the model parameters are adjusted again until the iteration is completed to obtain the trained neural network model. After inputting the six-element training set and the six-element verification set in sequence, the six-element training set is input again for training, and the model is further corrected, which can effectively improve the accuracy of model training.

[0068] Regarding the type of neural network model, it can be other supervised neural network models, such as recursive neural network, etc., or an unsupervised neural network model can be used to implement the functions of the embodiments of the present invention. It is only necessary to obtain the data to be input into the model. The unsupervised neural network model can include K-means algorithm model, hierarchical clustering algorithm model, PCA principal component analysis model, etc. The embodiments of the present invention do not impose too many restrictions on this.

[0069] Step 105, inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters;

[0070] Furthermore, after obtaining the trained neural network model, the new LCP material parameters, spray material parameters and FR4 material parameters are input into the trained neural network model to obtain the output preset hole processing parameters, that is, the density self-enhancement parameters, protective film thickness, and flame retardant loss parameters are input into the trained neural network model to obtain the output preset hole processing parameters: liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion size.

[0071] In an embodiment of the present invention, when the output milling cutter temperature parameters and curling protrusion size are greater than the predicted temperature threshold or the predicted size threshold, it means that the LCP material parameters, the spray material parameters and the FR4 material parameters cannot achieve the effect of controlling burrs and curling. At this time, it is necessary to return to the step of obtaining the LCP material parameters, the spray material parameters and the FR4 material parameters and re-collect the data.

[0072] Step 106: performing spraying and drilling operations on the millimeter wave radar circuit board according to the preset hole processing parameters.

[0073] When the preset hole processing parameters meet the conditions, the spraying and drilling operations of the millimeter wave radar circuit board are performed according to the preset hole processing parameters.

[0074] Specifically, the spraying and drilling operations of the millimeter-wave radar circuit board according to the preset hole processing parameters include: the millimeter-wave radar circuit board includes a two-layer structure, and the two-layer structure includes an LCP material layer and an FR4 material layer; according to the liquid crystal layer depth parameter, the device is controlled to perform a drilling operation of a preset depth of the LCP material layer to obtain a millimeter-wave radar circuit board with preliminary drilling; according to the milling cutter temperature parameter, the corresponding milling cutter speed and feed speed are obtained; according to the milling cutter speed and feed speed, the control device of the millimeter-wave radar circuit board with preliminary drilling is controlled to perform a through-hole drilling operation on the FR4 material layer, that is, CNC milling cutter forming, to obtain a millimeter-wave radar circuit board containing through holes.

[0075] like Figure 3 As shown, first, according to the liquid crystal layer depth parameter, the control device performs a preliminary drilling operation of the preset depth of the LCP material layer. Specifically, a millimeter-wave radar circuit board with preliminary drilling can be obtained by laser forming; then, the corresponding milling cutter speed and feed speed are obtained according to the milling cutter temperature parameter; according to the milling cutter speed and feed speed, the control device of the millimeter-wave radar circuit board with preliminary drilling is controlled to perform a through-hole drilling operation on the FR4 material layer to obtain a millimeter-wave radar circuit board containing through holes, that is, various milling processing processes can be performed by a CNC milling cutter, and the embodiments of the present invention do not impose too many restrictions on this.

[0076] It should be noted that after obtaining the millimeter-wave radar circuit board with preliminary drilling, the spraying operation of a preset time can be performed on the millimeter-wave radar circuit board with preliminary drilling according to the thickness control device of the protective film. Regarding the specific material of the spraying operation, it can be a variety of lubricants, and the embodiment of the present invention does not impose too many restrictions on this.

[0077] Specifically applied to the embodiment of the present invention, the corresponding milling cutter speed and feed speed are obtained according to the milling cutter temperature parameters, including: fitting the milling cutter temperature parameters in the preset hole processing parameters, and the historical milling cutter speeds and historical feed speeds, respectively, to obtain a milling cutter temperature speed curve and a milling cutter temperature feed speed curve; querying the milling cutter temperature speed curve and the milling cutter temperature feed speed curve according to the milling cutter temperature parameters to obtain the corresponding milling cutter speed and feed speed; in the embodiment of the present invention, the temperature speed curve and the temperature feed speed curve are established by fitting, and the corresponding milling cutter speed and feed speed can be conveniently queried through the two curves, thereby improving the processing efficiency.

[0078] Regarding the data fitting method, the embodiment of the present invention can perform fitting through linear regression, quadratic regression, nonlinear least squares fitting, spline interpolation and other methods, and the embodiment of the present invention does not impose too many restrictions on this.

[0079] Specifically applied to the embodiment of the present invention, the method also includes: performing electrical testing on the millimeter-wave radar circuit board containing through holes, generating an organic solder preservative film, and performing appearance inspection operations to complete the processing of the millimeter-wave radar circuit board. It should be noted that the millimeter-wave radar circuit board may also include other operations before or after the spraying and drilling operations, such as stacking operations, pressing operations, electroplating operations, outer layer image etching operations, solder mask operations, gold deposition operations, thermosetting text operations, molding operations, electrical testing operations, etc. The embodiment of the present invention does not impose too many restrictions on this.

[0080] The LCP millimeter-wave radar circuit board processing control method in the embodiment of the present invention includes: obtaining LCP material parameters, spray material parameters and FR4 material parameters; obtaining preset hole processing parameters, extracting processing technology and defect parameters in the preset hole processing parameters; forming a data set with the LCP material parameters, spray material parameters and FR4 material parameters and processing technology and defect parameters; inputting the data set into a neural network model for training to obtain a trained neural network model; inputting new LCP material parameters, spray material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters; performing spraying and drilling operations on the millimeter-wave radar circuit board according to the preset hole processing parameters; avoiding processing defects such as burrs and curling of circuit boards, improving processing yield, and solving the problem that it is difficult to completely cut off the material during CNC forming milling cutter processing and cutting, and the milling cutter pulls the LCP material to cause curling and burrs.

[0081] It should be noted that, for the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that this embodiment is not limited by the order of the actions described, because according to this embodiment, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by this embodiment.

[0082] Reference Figure 4 , shows a structural block diagram of an embodiment of an LCP millimeter wave radar circuit board processing control device of this embodiment, which may specifically include the following modules:

[0083] Parameter acquisition module 301, used to acquire LCP material parameters, spraying material parameters and FR4 material parameters;

[0084] An extraction module 302 is used to obtain preset hole processing parameters and extract processing technology and defect parameters from the preset hole processing parameters;

[0085] A composition module 303 is used to combine the LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters into a data set;

[0086] A training module 304 is used to input the data set into a neural network model for training to obtain a trained neural network model;

[0087] An input module 305 is used to input new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters;

[0088] The processing module 306 is used to perform spraying and drilling operations on the millimeter wave radar circuit board according to the preset hole processing parameters.

[0089] Preferably, the LCP material parameters include density self-enhancement parameters, the spray material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters; the processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling protrusion size;

[0090] The component modules include:

[0091] The composition submodule is used to form a six-element data set by combining the density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size, and divide the six-element data set into a six-element training set and a six-element verification set.

[0092] Preferably, the millimeter wave radar circuit board includes a two-layer structure, and the two-layer structure includes an LCP material layer and an FR4 material layer;

[0093] The processing module comprises:

[0094] A pre-drilling submodule, used to control the device to perform a drilling operation of a preset depth of the LCP material layer according to the liquid crystal layer depth parameter, so as to obtain a millimeter-wave radar circuit board with preliminary drilling;

[0095] The acquisition submodule is used to obtain the corresponding milling cutter rotation speed and feed speed according to the milling cutter temperature parameters;

[0096] The drilling submodule is used to control the millimeter-wave radar circuit board control device for preliminary drilling to perform a through-hole drilling operation on the FR4 material layer according to the milling cutter rotation speed and feed speed, so as to obtain a millimeter-wave radar circuit board containing through holes.

[0097] Preferably, the input module comprises:

[0098] A training set input submodule, used for inputting the six-element training set into the neural network model for training to obtain a neural network model to be verified;

[0099] A verification set input submodule, used to input the six-element verification set into the neural network model to be verified, adjust the model parameters, and obtain a preliminary neural network model;

[0100] The iterative submodule is used to input the six-element training set into the preliminary neural network model, and adjust the model parameters again until the iteration is completed to obtain the trained neural network model.

[0101] Preferably, the device further comprises:

[0102] Other processing modules are used to perform electrical testing, generate organic solder paste, and perform appearance inspection operations on the millimeter-wave radar circuit board containing through holes to complete the processing of the millimeter-wave radar circuit board.

[0103] Preferably, the acquisition submodule is used to include:

[0104] A fitting submodule, for fitting the milling cutter temperature parameter in the preset hole processing parameters, and the historical milling cutter rotation speed and the historical feed speed, respectively, to obtain a milling cutter temperature rotation speed curve and a milling cutter temperature feed speed curve;

[0105] The query submodule is used to query the milling cutter temperature rotation speed curve and the milling cutter temperature feed speed curve according to the milling cutter temperature parameter to obtain the corresponding milling cutter rotation speed and feed speed.

[0106] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0107] For the specific definition of the LCP millimeter-wave radar circuit board processing control device, please refer to the definition of the LCP millimeter-wave radar circuit board processing control method above, which will not be repeated here. Each module in the above-mentioned LCP millimeter-wave radar circuit board processing control device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0108] The LCP millimeter-wave radar circuit board processing control device provided above can be used to execute the LCP millimeter-wave radar circuit board processing control method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0109] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for simulating daylighting is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0110] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0112] Obtain LCP material parameters, spray material parameters and FR4 material parameters;

[0113] Acquire preset hole processing parameters, and extract processing technology and defect parameters from the preset hole processing parameters;

[0114] The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set;

[0115] Inputting the data set into a neural network model for training to obtain a trained neural network model;

[0116] Inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters;

[0117] The millimeter wave radar circuit board is sprayed and drilled according to the preset hole processing parameters.

[0118] Preferably, the LCP material parameters include density self-enhancement parameters, the spraying material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters;

[0119] The processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion dimensions;

[0120] The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set, including:

[0121] The density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size are combined into a six-element data set, and the six-element data set is divided into a six-element training set and a six-element verification set.

[0122] Preferably, the millimeter wave radar circuit board includes a two-layer structure, and the two-layer structure includes an LCP material layer and an FR4 material layer;

[0123] The spraying and drilling operations of the millimeter wave radar circuit board according to the preset hole processing parameters include:

[0124] Controlling the device to perform a drilling operation of a preset depth of the LCP material layer according to the liquid crystal layer depth parameter to obtain a millimeter wave radar circuit board with preliminary drilling;

[0125] Obtain the corresponding milling cutter speed and feed speed according to the milling cutter temperature parameters;

[0126] According to the milling cutter rotation speed and feed speed control, the millimeter wave radar circuit board control device for preliminary drilling performs a through-hole drilling operation on the FR4 material layer to obtain a millimeter wave radar circuit board containing through holes.

[0127] Preferably, inputting the data set into a neural network model for training to obtain a trained neural network model comprises:

[0128] Inputting the six-element training set into the neural network model for training to obtain a neural network model to be verified;

[0129] Inputting the six-element verification set into the neural network model to be verified, adjusting the model parameters, and obtaining a preliminary neural network model;

[0130] The six-element training set is input into the preliminary neural network model, and the model parameters are adjusted again until the iteration is completed to obtain a trained neural network model.

[0131] Preferably, the method further comprises:

[0132] The millimeter-wave radar circuit board including the through-hole is subjected to electrical testing, organic solderability protection film generation, and appearance inspection operations to complete the processing of the millimeter-wave radar circuit board.

[0133] Preferably, the step of obtaining the corresponding milling cutter rotation speed and feed speed according to the milling cutter temperature parameter includes:

[0134] The milling cutter temperature parameter in the preset hole processing parameters, as well as the historical milling cutter rotation speed and the historical feed speed are fitted to obtain a milling cutter temperature rotation speed curve and a milling cutter temperature feed speed curve;

[0135] The milling cutter temperature rotation speed curve and the milling cutter temperature feed speed curve are queried according to the milling cutter temperature parameter to obtain the corresponding milling cutter rotation speed and feed speed.

[0136] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0137] Obtain LCP material parameters, spray material parameters and FR4 material parameters;

[0138] Acquire preset hole processing parameters, and extract processing technology and defect parameters from the preset hole processing parameters;

[0139] The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set;

[0140] Inputting the data set into a neural network model for training to obtain a trained neural network model;

[0141] Inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters;

[0142] The millimeter wave radar circuit board is sprayed and drilled according to the preset hole processing parameters.

[0143] Preferably, the LCP material parameters include density self-enhancement parameters, the spraying material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters;

[0144] The processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion dimensions;

[0145] The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set, including:

[0146] The density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size are combined into a six-element data set, and the six-element data set is divided into a six-element training set and a six-element verification set.

[0147] Preferably, the millimeter wave radar circuit board includes a two-layer structure, and the two-layer structure includes an LCP material layer and an FR4 material layer;

[0148] The spraying and drilling operations of the millimeter wave radar circuit board according to the preset hole processing parameters include:

[0149] Controlling the device to perform a drilling operation of a preset depth of the LCP material layer according to the liquid crystal layer depth parameter to obtain a millimeter wave radar circuit board with preliminary drilling;

[0150] Obtain the corresponding milling cutter speed and feed speed according to the milling cutter temperature parameters;

[0151] According to the milling cutter rotation speed and feed speed control, the millimeter wave radar circuit board control device for preliminary drilling performs a through-hole drilling operation on the FR4 material layer to obtain a millimeter wave radar circuit board containing through holes.

[0152] Preferably, inputting the data set into a neural network model for training to obtain a trained neural network model comprises:

[0153] Inputting the six-element training set into the neural network model for training to obtain a neural network model to be verified;

[0154] Inputting the six-element verification set into the neural network model to be verified, adjusting the model parameters, and obtaining a preliminary neural network model;

[0155] The six-element training set is input into the preliminary neural network model, and the model parameters are adjusted again until the iteration is completed to obtain a trained neural network model.

[0156] Preferably, the method further comprises:

[0157] The millimeter-wave radar circuit board including the through-hole is subjected to electrical testing, organic solderability protection film generation, and appearance inspection operations to complete the processing of the millimeter-wave radar circuit board.

[0158] Preferably, the step of obtaining the corresponding milling cutter rotation speed and feed speed according to the milling cutter temperature parameter includes:

[0159] The milling cutter temperature parameter in the preset hole processing parameters, as well as the historical milling cutter rotation speed and the historical feed speed are fitted to obtain a milling cutter temperature rotation speed curve and a milling cutter temperature feed speed curve;

[0160] The milling cutter temperature rotation speed curve and the milling cutter temperature feed speed curve are queried according to the milling cutter temperature parameter to obtain the corresponding milling cutter rotation speed and feed speed.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0162] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0163] Those skilled in the art will appreciate that the embodiments of the present embodiment may be provided as methods, devices, or computer program products. Therefore, the present embodiment may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present embodiment may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0164] The present embodiment is described with reference to the flowchart and / or block diagram of the apparatus, terminal device (system), and computer program product according to the present embodiment. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0165] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction method, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0166] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0167] Although the preferred embodiment of the present embodiment has been described, other changes and modifications may be made to these embodiments once those skilled in the art have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiment and all changes and modifications falling within the scope of the present embodiment.

[0168] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the existence of other identical elements in the process, device, article or terminal device including the elements.

[0169] The above is a detailed introduction to a LCP millimeter-wave radar circuit board processing control method and a LCP millimeter-wave radar circuit board processing control device, a computer device and a storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A LCP millimeter wave radar circuit board processing control method, characterized in that: include: Obtain LCP material parameters, spray material parameters and FR4 material parameters; Acquire preset hole processing parameters, and extract processing technology and defect parameters from the preset hole processing parameters; The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set; Inputting the data set into a neural network model for training to obtain a trained neural network model; Inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters; The millimeter wave radar circuit board is sprayed and drilled according to the preset hole processing parameters.

2. The method according to claim 1, characterized in that: The LCP material parameters include density self-enhancement parameters, the spray material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters; The processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion dimensions; The LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters are combined into a data set, including: The density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size are combined into a six-element data set, and the six-element data set is divided into a six-element training set and a six-element verification set.

3. The method according to claim 2, characterized in that The millimeter wave radar circuit board includes a two-layer structure, and the two-layer structure includes an LCP material layer and an FR4 material layer; The spraying and drilling operations of the millimeter wave radar circuit board according to the preset hole processing parameters include: Controlling the device to perform a drilling operation of a preset depth of the LCP material layer according to the liquid crystal layer depth parameter to obtain a millimeter wave radar circuit board with preliminary drilling; Obtain the corresponding milling cutter speed and feed speed according to the milling cutter temperature parameters; According to the milling cutter rotation speed and feed speed control, the millimeter wave radar circuit board control device for preliminary drilling performs a through-hole drilling operation on the FR4 material layer to obtain a millimeter wave radar circuit board containing through holes.

4. The method according to claim 2, characterized in that: The step of inputting the data set into a neural network model for training to obtain a trained neural network model comprises: Inputting the six-element training set into the neural network model for training to obtain a neural network model to be verified; Inputting the six-element verification set into the neural network model to be verified, adjusting the model parameters, and obtaining a preliminary neural network model; The six-element training set is input into the preliminary neural network model, and the model parameters are adjusted again until the iteration is completed to obtain a trained neural network model.

5. The method according to claim 3, characterized in that: The method further comprises: The millimeter-wave radar circuit board including the through-hole is subjected to electrical testing, organic solderability protection film generation, and appearance inspection operations to complete the processing of the millimeter-wave radar circuit board.

6. The method according to claim 3, characterized in that The method of obtaining the corresponding milling cutter rotation speed and feed speed according to the milling cutter temperature parameter includes: The milling cutter temperature parameter in the preset hole processing parameters, as well as the historical milling cutter rotation speed and the historical feed speed are fitted to obtain a milling cutter temperature rotation speed curve and a milling cutter temperature feed speed curve; The milling cutter temperature rotation speed curve and the milling cutter temperature feed speed curve are queried according to the milling cutter temperature parameter to obtain the corresponding milling cutter rotation speed and feed speed.

7. A LCP millimeter wave radar circuit board processing control device, characterized in that: include: Parameter acquisition module, used to obtain LCP material parameters, spray material parameters and FR4 material parameters; An extraction module, used to obtain preset hole processing parameters and extract processing technology and defect parameters from the preset hole processing parameters; A composition module, used for composing the LCP material parameters, spraying material parameters, FR4 material parameters, processing technology and defect parameters into a data set; A training module, used for inputting the data set into a neural network model for training to obtain a trained neural network model; An input module, used for inputting new LCP material parameters, spraying material parameters and FR4 material parameters into the trained neural network model to obtain output preset hole processing parameters; The processing module is used to perform spraying and drilling operations on the millimeter wave radar circuit board according to the preset hole processing parameters.

8. The device according to claim 7, characterized in that The LCP material parameters include density self-enhancement parameters, the spray material parameters include protective film thickness, and the FR4 material parameters include flame retardant loss parameters; the processing technology and defect parameters include liquid crystal layer depth parameters, milling cutter temperature parameters and curling edge protrusion size; The component modules include: The composition submodule is used to form a six-element data set by combining the density self-enhancement parameter, the protective film thickness, the flame retardant loss parameter, the liquid crystal layer depth parameter, the milling cutter temperature parameter and the curling edge protrusion size, and divide the six-element data set into a six-element training set and a six-element verification set.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the LCP millimeter-wave radar circuit board processing control method described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the LCP millimeter-wave radar circuit board processing control method described in any one of claims 1 to 6 are implemented.

Images