PCB interconnection system parameter determination method and device

Abstract

The invention provides a PCB interconnection system parameter determination method comprising the following steps: obtaining first parameter information required by a to-be-designed PCB interconnection system, the first parameter information being used for limiting the structure and signal quality requirements of the to-be-designed PCB interconnection system; the parameter information is input into a first model, second design parameters of interconnection system design are output after operation of the first model, the first model is determined based on neural network training by using interconnection design information, and the interconnection design information is related to physical meanings represented by the first parameter information; wherein the second design parameters are used for constructing the PCB interconnection system, and the second design parameters are used for influencing the quality and speed of PCB internal signal transmission, signal transmission between PCB internal signals and onboard equipment, and signal transmission between the PCB and off-board equipment in the design of the PCB interconnection system. The invention further provides a PCB interconnection system parameter determination device.

Description

Technical Field

[0001] The present application relates to the technical field of PCB design, and in particular to a method for determining parameters of a PCB interconnection system and a device for determining parameters of a PCB interconnection system. Background Art

[0002] PCB is an important component of the server and a key material for supporting the operation of the server. The motherboard, backplane, power board and network card all use PCB. PCB design is an indispensable and important link. In electronic products, PCB must be connected with other components, which is the interconnection of PCB. The signal integrity of the interconnection system is an important factor that must be guaranteed in today's high-speed electronic product systems and PCB design. It directly determines the system signal quality and thus affects the correct transmission of data and the system bit error rate. The interconnection design of PCB involves three aspects: chip to PCB, PCB inside, PCB and external devices. The existing design technology uses simulation software to manually simulate the above three parts. That is, no matter which part, a large number of simulations are required for specific projects to determine the design parameters of the interconnection system. The workload is large, and it takes a lot of time and manpower. In addition, the simulation results often vary due to different simulation software and settings.

[0003] With the continuous shortening of product cycles of electronic products using PCBs, the improvement of product design quality and the enhancement of product performance, more and more scenarios require fast and high-quality interconnect system design. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method for determining parameters of a PCB interconnection system and a device for determining parameters of a PCB interconnection system.

[0005] The present application provides a method for determining parameters of a PCB interconnection system, comprising:

[0006] Acquire first parameter information required by the PCB interconnection system to be designed, where the first parameter information is used to define the structure and signal quality requirements of the PCB interconnection system to be designed;

[0007] Inputting the parameter information into a first model, and outputting a second design parameter of the interconnection system design after operation by the first model, wherein the first model is determined based on neural network training using interconnection design information, and the interconnection design information is related to the physical meaning represented by the first parameter information;

[0008] Among them, the second design parameter is used to construct a PCB interconnection system, and the second design parameter is used to affect the quality and speed of signal transmission within the PCB, signal transmission between the internal signal of the PCB and on-board devices, and signal transmission between the PCB and external devices in the design of the PCB interconnection system.

[0009] In some embodiments, the first parameter information includes at least one of the number of layers and insertion loss of the PCB.

[0010] In some embodiments, the second design parameter includes at least one of plate material type, line width, line spacing, impedance, and stacking structure.

[0011] In some embodiments, the first model includes an input layer, a hidden layer and an output layer, and the input layer, the hidden layer and the output layer are connected in sequence. The first parameter information obtains a first operation result after a first operation is performed on the input layer, and the first operation result obtains a second operation result after a second operation is performed on the hidden layer. The second operation result is used as the output result of the output layer, and the second operation result includes the second design parameter; wherein the first operation is determined by a first operation function, and the second operation is determined by a second operation function.

[0012] In some embodiments, the first model includes a trained RNN recurrent neural network model.

[0013] In some embodiments, the training method of the first model includes:

[0014] Obtain actual parameter information of multiple real PCB interconnection systems;

[0015] Using the actual parameter information as input and output of a training model for training;

[0016] Determine whether a preset condition is met, and if the preset condition is met, use the first model obtained by training as the PCB interconnection system design model;

[0017] The actual parameter information represents various design specifications required for a real PCB interconnection system, and the parameter information includes at least one of the number of PCB layers, insertion loss, and at least one of the board material type, line width, line spacing, impedance, and stacking structure.

[0018] In some embodiments, the parameter information is used as the input and output of the training model for training, including:

[0019] At least one of the number of layers and insertion loss of the PCB is used as an input layer parameter of the training model;

[0020] Using at least one of the plate material type, line width, line spacing, impedance and stacking as an output parameter of the training model;

[0021] The training model is trained based on the input layer parameters and the output layer parameters.

[0022] In some embodiments, training the training model based on the input layer parameters and the output layer parameters includes:

[0023] Based on the input layer, determine a first operation calculation method of the input value of the hidden layer of the training model;

[0024] Determine a second operation calculation method for the output layer of the training model based on the output value of the hidden layer;

[0025] In the process of training the training model, the undetermined parameters of each of the calculation methods are adjusted, and the undetermined parameters at least include the value of the weight matrix.

[0026] In some embodiments, the preset condition includes a threshold of a loss function, and the determining whether the preset condition is met, if the preset condition is met, training the first model as the PCB interconnection system design model, includes:

[0027] By judging whether the current calculated value of the loss function is less than a threshold value, if it is less than the threshold value, the training is stopped, and the first model obtained by training is used as the PCB interconnection system design model.

[0028] The present application provides a device for determining parameters of a PCB interconnection system, the device comprising:

[0029] An acquisition module, used for acquiring first parameter information required by the PCB interconnection system to be designed, wherein the first parameter information is used for defining the structure and signal quality requirements of the PCB interconnection system to be designed;

[0030] a first model, configured to input the first parameter information into a first model, and output a second design parameter of the interconnection system design after operation by the first model, wherein the first model is determined based on neural network training using interconnection design information, and the interconnection design information is related to a physical meaning represented by the first parameter information;

[0031] Among them, the second design parameter is used to construct a PCB interconnection system, and the second design parameter is used to affect the quality and speed of signal transmission within the PCB, signal transmission between the internal signal of the PCB and on-board devices, and signal transmission between the PCB and external devices in the design of the PCB interconnection system.

[0032] The method for determining the parameters of a PCB interconnection system provided by the present application, by inputting the first parameter information required by the PCB interconnection system to be designed into a trained first model, and obtaining the second design parameters required for the interconnection system design after the first model is operated, on the one hand, since the entire process is completed automatically and no manual simulation design is required, the workload of the designer can be saved, and on the other hand, since the first parameter information is used to limit the structure and signal quality requirements of the PCB interconnection system to be designed, and the first model is determined based on neural network training using the interconnection design information, the interconnection design information is related to the physical meaning represented by the first parameter information, which makes it possible to output the second design parameters of the interconnection system design after the first model is operated, so that the structure and signal quality requirements of the designed PCB interconnection system can be met. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic diagram of a method for determining parameters of a PCB interconnection system according to an embodiment of the present application;

[0034] Figure 2 This is a schematic diagram of the structure of a device for determining parameters of a PCB interconnection system according to an embodiment of the present application;

[0035] Figure 3 This is a schematic diagram of the first model structure of an embodiment of the present application.

[0036] Reference numerals:

[0037] 1000, PCB interconnection system parameter determination device; 1001, acquisition module; 1002, first model; 1100, bus; 1200, processor; 1300, memory; 1400, other circuits. DETAILED DESCRIPTION

[0038] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0039] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0040] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0041] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0042] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0043] Figure 1 A schematic diagram of a method for determining PCB interconnection system parameters according to an embodiment of the present application is shown. Figure 1 As shown, including:

[0044] S101, obtaining first parameter information required by the PCB interconnection system to be designed, where the first parameter information is used to define the structure and signal quality requirements of the PCB interconnection system to be designed;

[0045] S102, inputting parameter information into a first model, and outputting a second design parameter of the interconnection system design after operation by the first model, wherein the first model is determined based on neural network training using interconnection design information, and the interconnection design information is related to the physical meaning represented by the first parameter information;

[0046] The second design parameter is used to construct a PCB interconnection system, and the second design parameter is used to affect the quality and speed of signal transmission within the PCB, signal transmission between the internal signal of the PCB and on-board devices, and signal transmission between the PCB and external devices in the design of the PCB interconnection system.

[0047] The method for determining the parameters of a PCB interconnection system provided by the present application, by inputting the first parameter information required by the PCB interconnection system to be designed into a trained first model, and obtaining the second design parameters required for the interconnection system design after the first model is operated, on the one hand, since the entire process is completed automatically and no manual simulation design is required, the workload of the designer can be saved, and on the other hand, since the first parameter information is used to limit the structure and signal quality requirements of the PCB interconnection system to be designed, and the first model is determined based on neural network training using the interconnection design information, the interconnection design information is related to the physical meaning represented by the first parameter information, which makes it possible to output the second design parameters of the interconnection system design after the first model is operated, so that the structure and signal quality requirements of the designed PCB interconnection system can be met.

[0048] In some embodiments, the first parameter information includes at least one of the number of layers and insertion loss of the PCB.

[0049] For ease of understanding, examples are provided. Taking the number of PCB layers as an example as the first parameter, different PCB layers such as 4 layers, 8 layers, 10 layers, 12 layers, and more layers can be used. In addition, insertion loss can also be used as the first parameter, or both can be used as the first parameter.

[0050] In some embodiments, the second design parameter includes at least one of plate material type, line width, line spacing, impedance, and stacking.

[0051] In some embodiments, the first model includes an input layer, a hidden layer and an output layer, and the input layer, the hidden layer and the output layer are connected sequentially. The first parameter information obtains a first operation result after a first operation in the input layer, and the first operation result obtains a second operation result after a second operation in the hidden layer. The second operation result is used as the output result of the output layer, and the second operation result includes a second design parameter; wherein the first operation is determined by a first operation function, and the second operation is determined by a second operation function.

[0052] For easier understanding, examples are given below. Figure 3 As shown, the first model includes an input layer Input Layer, a hidden layer Hidden Layer and an output layer Output Layer, and the above layers are connected in sequence. The first parameter information X is used as the input information of the first model, and the first operation result S is obtained after the first operation in the input layer, and the first operation result S is obtained after the second operation in the hidden layer. The second operation result is used as the output result of the output layer. It should be noted that the first model is a model obtained by training. After training, the first operation method and the second operation method of the first model are both determined functions, that is, the first operation method f function, the second operation method g function and the matrices U, W and V required for the calculation of the two methods are all determined. Then, after the input parameter X is input into the first model, the required second design parameter can be obtained in the output layer. Among them, the first parameter information X can be, for example, the number of PCB layers and insertion loss, and the second design parameter can be, for example, one or more of the board material type, line width, line spacing, impedance and stacking structure, so that the second design parameter of the PCB interconnection system design can be obtained for product design.

[0053] In some embodiments, the first model includes a trained RNN recurrent neural network model. It should be noted that the first model of the present application is not limited to the RNN recurrent neural network model, and can also be other machine learning or deep learning models.

[0054] In some embodiments, the training method of the first model includes:

[0055] Obtain actual parameter information of multiple real PCB interconnection systems;

[0056] Use actual parameter information as input and output of the training model for training;

[0057] Determine whether a preset condition is met, and if the preset condition is met, use the first model obtained by training as a PCB interconnection system design model;

[0058] The actual parameter information represents various design specifications required for a real PCB interconnection system, and the parameter information includes at least one of the number of PCB layers, insertion loss, and at least one of the board material type, line width, line spacing, impedance, and stacking structure.

[0059] For ease of understanding, examples are provided. The first model of the present application is obtained through training. Before training the first model, the actual parameters of the real PCB interconnection system must first be used as sample information of the training data. For example, the parameters required by the real PCB interconnection system, such as the number of PCB layers, insertion loss, board material type, line width, line spacing, impedance and stacking structure, can be used. A part of them is used as the input parameter of the first model, and another part of them is used as the output parameter of the first model. Then, the input parameters and output parameters are used as the training data of the first model to start training the first model. During the training process, based on the preset conditions, it is determined whether the preset conditions are met according to the actual situation. If the preset conditions are met, the first model obtained through training is used as the PCB interconnection system design model.

[0060] In some embodiments, training the model using parameter information as input and output includes:

[0061] At least one of the number of layers and insertion loss of the PCB is used as an input layer parameter of the training model;

[0062] At least one of the plate material type, line width, line spacing, impedance and stacking structure is used as an output parameter of the training model;

[0063] The model is trained based on the input layer parameters and the output layer parameters.

[0064] For ease of understanding, examples are provided. For the parameters required by a real PCB interconnection system, during actual training, the input parameters may be one or two of the number of PCB layers and insertion loss, and the output parameters may be one or more of the board material type, line width, line spacing, impedance, and stacking structure. The first model trained with different types of input parameters and output parameters can adjust the type of input parameters according to actual needs during actual application to obtain the output required for design in order to perform PCB design. Taking the number of PCB layers as an example, when used as an input parameter, different PCB layers such as 4 layers, 8 layers, 10 layers, 12 layers, and more layers can be used, and interconnection system design solutions under different numbers of layers can be used as training design libraries. By analogy, the training design library is expanded with interconnection system design solutions under different numbers of layers of other buses, thus forming a large number of data samples.

[0065] In some embodiments, training the training model based on the input layer parameters and the output layer parameters includes:

[0066] Based on the input layer, a first operation calculation method for determining an input value of a hidden layer of a training model;

[0067] Determine a second operation calculation method for the output layer of the training model based on the output value of the hidden layer;

[0068] In the process of training the training model, the pending parameters of each calculation method are adjusted, and the pending parameters at least include the value of the weight matrix.

[0069] For easier understanding, examples are provided. Figure 3 In the first model shown, the input layer S has two nodes, representing two-dimensional inputs, which can be, for example, the number of PCB layers (x1) and insertion loss (x2). The hidden layer has n nodes, representing n-dimensional intermediate calculation data. The output layer has 5 nodes, representing 5-dimensional outputs, which can be, for example, board material type, line width, line spacing, impedance, and stacking. The input value S of the hidden layer is calculated by the parameter value X of the output layer through the first operation. Specifically, the first operation method for calculating the input value S of the hidden layer can be expressed as St=f(U*Xt+W*S t-1 ), the training process is an iterative calculation process, where U and W represent weight matrices, Xt represents the tth input value, and S t-1 represents the calculated value of the hidden layer at the t-1th time, St represents the calculated value of the hidden layer at the tth time, U and W have their own initial values, and the weight matrices U and W are adjusted after each iterative calculation. The input value o of the output layer is obtained by calculating the parameter value S of the hidden layer through the second operation. The second operation method can be expressed as O=g(V*St), that is, the calculation results of each node of the output layer are expressed as O1=g1(V*St), O2=g2(V*St), O3=g3(V*St), O4=g4(V*St), O5=g5(V*St), St represents the calculated value of the hidden layer at the tth iterative calculation, V represents a matrix with initial values, and V is adjusted after each iterative calculation.

[0070] In some embodiments, the preset condition includes a threshold of a loss function, and judging whether the preset condition is met, and if the preset condition is met, training the first model as a PCB interconnection system design model, including:

[0071] By judging whether the current calculated value of the loss function is less than a threshold value, if it is less than the threshold value, the training is stopped, and the first model obtained by training is used as the PCB interconnection system design model.

[0072] Specifically, the present application may use a sigmoid function as a loss function, and thereby set a certain threshold value. If the first model is in the training process, it is determined whether the current calculated value of the loss function is less than the threshold value. If it is less than the threshold value, the training is stopped, and the first model obtained by training is used as the PCB interconnection system design model. It should be noted that the loss function of the present application is not limited to the sigmoid function, and can be other mathematical calculation functions.

[0073] Figure 2 FIG. 1 shows a schematic diagram of a PCB interconnection system parameter determination device according to an embodiment of the present application. Figure 2 As shown, the device comprises:

[0074] An acquisition module 1001 is used to acquire first parameter information required by the PCB interconnection system to be designed, where the first parameter information is used to define the structure and signal quality requirements of the PCB interconnection system to be designed;

[0075] A first model 1002, for inputting first parameter information into a first model, and outputting second design parameters of the interconnection system design after operation by the first model, the first model being determined based on neural network training using interconnection design information, the interconnection design information being related to a physical meaning represented by the first parameter information;

[0076] The second design parameter is used to construct a PCB interconnection system, and the second design parameter is used to affect the quality and speed of signal transmission within the PCB, signal transmission between the internal signal of the PCB and on-board devices, and signal transmission between the PCB and external devices in the design of the PCB interconnection system.

[0077] It should be noted that the implementation details of each module of the PCB interconnection system parameter determination device provided in the present application are consistent with the PCB interconnection system parameter determination method, and will not be described one by one here.

[0078] The present application provides a method and device for determining PCB interconnection system parameters. Compared with the traditional PCB interconnection system design that uses simulation software, the above-mentioned output parameters (o1, o2, ..., o5) in the stacking structure can be automatically calculated without manual operation. Especially when there are a large number of PCB boards and multiple projects in parallel, after inputting the design parameters x1 and x2 using the scheme, other interconnection design parameters (o1, o2, ..., o5) can be quickly obtained through the trained neural network, which greatly improves the hardware design efficiency and saves a lot of simulation software operation time and labor costs.

[0079] The present application provides a method and device for determining PCB interconnection system parameters, which can also be called as an input interface for other hardware system designs. That is, the data trained by this scheme can be used as input for other subsequent signal integrity simulation parts such as time domain eye diagram simulation, and can also be extended to other hardware system designs such as power-on timing, functional simulation, etc., to accelerate hardware design time, promote simulation and design process in a modular form, and thus help hardware systems to be designed with high quality and efficiency.

[0080] Figure 2 An example diagram of the structure of a PCB interconnection system parameter determination device using a hardware implementation of a processing system is shown. The device may include corresponding modules for executing each or several steps in the above flowchart. Therefore, each step or several steps in the above flowchart may be executed by the corresponding module, and the device may include one or more modules in these modules. The module may be one or more hardware modules specially configured to execute the corresponding steps, or implemented by a processor configured to execute the corresponding steps, or stored in a computer-readable medium for implementation by a processor, or implemented by some combination.

[0081] The hardware structure can be implemented using a bus architecture. The bus architecture can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus 1100 connects various circuits including one or more processors 1200, memory 1300, and / or hardware modules together. The bus 1100 can also connect various other circuits 1400 such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0082] The bus 1100 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the figure only uses one connecting line, but does not mean that there is only one bus or one type of bus.

[0083] The processor 1200 may be a general purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof. The general purpose processor may be a microprocessor or any conventional processor.

[0084] Any process or method description in the flowchart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by a person skilled in the art of the technical field to which the embodiments of the present application belong. The processor performs the various methods and processes described above. For example, the method implementation in the present application can be implemented as a software program, which is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via a memory and / or a communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps in the method described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform one of the above methods in any other appropriate manner (e.g., by means of firmware).

[0085] The logic and / or steps represented in the flowchart or otherwise described herein may be embodied in any readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions on an instruction execution system, apparatus, or device), or in combination with such instruction execution systems, apparatuses, or devices.

[0086] For the purposes of this specification, a "readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use with or in conjunction with an instruction execution system, device or apparatus. More specific examples of readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), a fiber optic device, and a portable read-only memory (CDROM). In addition, the readable storage medium may even be paper or other suitable medium on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a memory.

[0087] It should be understood that the various parts of the present application can be implemented by hardware, software or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0088] A person skilled in the art may understand that all or part of the steps of implementing the above-mentioned implementation method may be completed by instructing related hardware through a program, and the program may be stored in a readable storage medium, which, when executed, includes one or a combination of the steps of the implementation method.

[0089] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a readable storage medium. The storage medium may be a read-only memory, a disk or an optical disk, etc.

[0090] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representations of the above terms are not necessarily the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments / methods or examples described in this specification and the features of the different embodiments / methods or examples, unless they are contradictory.

[0091] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0092] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present application, and are not intended to limit the scope of the present application. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present application.

Claims

1. A method for determining parameters of a PCB interconnection system, comprising: Acquire first parameter information required by the PCB interconnection system to be designed, where the first parameter information is used to define the structure and signal quality requirements of the PCB interconnection system to be designed; Inputting the parameter information into a first model, and outputting a second design parameter of the interconnection system design after operation by the first model, wherein the first model is determined based on neural network training using interconnection design information, and the interconnection design information is related to the physical meaning represented by the first parameter information; Among them, the second design parameter is used to construct a PCB interconnection system, and the second design parameter is used to affect the quality and speed of signal transmission within the PCB, signal transmission between the internal signal of the PCB and on-board devices, and signal transmission between the PCB and external devices in the design of the PCB interconnection system.

2. According to the method for determining parameters of a PCB interconnection system according to claim 1, the first parameter information includes at least one of the number of layers and insertion loss of the PCB.

3. According to the method for determining PCB interconnection system parameters as described in claim 1, the second design parameter includes at least one of plate material type, line width, line spacing, impedance and stacking structure.

4. The method for determining PCB interconnection system parameters according to claim 1, wherein the first model comprises an input layer, a hidden layer and an output layer, wherein the input layer, the hidden layer and the output layer are sequentially connected, wherein the first parameter information is subjected to a first operation at the input layer to obtain a first operation result, wherein the first operation result is subjected to a second operation at the hidden layer to obtain a second operation result, wherein the second operation result is used as an output result of the output layer, and the second operation result includes the second design parameter; wherein, The first operation is determined by a first operation function, and the second operation is determined by a second operation function.

5. The method for determining PCB interconnection system parameters according to claim 1, wherein the first model comprises a trained RNN recurrent neural network model.

6. The method for determining PCB interconnection system parameters according to claim 1, wherein the training method of the first model comprises: Obtain actual parameter information of multiple real PCB interconnection systems; Using the actual parameter information as input and output of a training model for training; Determine whether a preset condition is met, and if the preset condition is met, use the first model obtained by training as the PCB interconnection system design model; The actual parameter information represents various design specifications required for a real PCB interconnection system, and the parameter information includes at least one of the number of PCB layers, insertion loss, and at least one of the board material type, line width, line spacing, impedance, and stacking structure.

7. The training method according to claim 6, wherein the parameter information is used as the input and output of the training model for training, comprising: At least one of the number of layers and insertion loss of the PCB is used as an input layer parameter of the training model; Using at least one of the plate material type, line width, line spacing, impedance and stacking as an output parameter of the training model; The training model is trained based on the input layer parameters and the output layer parameters.

8. The training method according to claim 7, training the training model based on the input layer parameters and the output layer parameters, comprising: Based on the input layer, determine a first operation calculation method of the input value of the hidden layer of the training model; Determine a second operation calculation method for the output layer of the training model based on the output value of the hidden layer; In the process of training the training model, the undetermined parameters of each of the calculation methods are adjusted, and the undetermined parameters at least include the value of the weight matrix.

9. The training method according to claim 6, wherein the preset condition includes a threshold of a loss function, and the determining whether the preset condition is satisfied, if the preset condition is satisfied, using the first model obtained through training as the PCB interconnection system design model, comprises: By judging whether the current calculated value of the loss function is less than a threshold value, if it is less than the threshold value, the training is stopped, and the first model obtained by training is used as the PCB interconnection system design model.

10. A device for determining parameters of a PCB interconnection system, the device comprising: An acquisition module, used for acquiring first parameter information required by the PCB interconnection system to be designed, wherein the first parameter information is used for defining the structure and signal quality requirements of the PCB interconnection system to be designed; a first model, configured to input the first parameter information into a first model, and output a second design parameter of the interconnection system design after operation by the first model, wherein the first model is determined based on neural network training using interconnection design information, and the interconnection design information is related to a physical meaning represented by the first parameter information; Among them, the second design parameter is used to construct a PCB interconnection system, and the second design parameter is used to affect the quality and speed of signal transmission within the PCB, signal transmission between the internal signal of the PCB and on-board devices, and signal transmission between the PCB and external devices in the design of the PCB interconnection system.

Images