CN110610052A - PCB automatic wiring system and method - Google Patents
PCB automatic wiring system and method Download PDFInfo
- Publication number
- CN110610052A CN110610052A CN201910892545.0A CN201910892545A CN110610052A CN 110610052 A CN110610052 A CN 110610052A CN 201910892545 A CN201910892545 A CN 201910892545A CN 110610052 A CN110610052 A CN 110610052A
- Authority
- CN
- China
- Prior art keywords
- module
- wiring
- information
- rule
- evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Design And Manufacture Of Integrated Circuits (AREA)
Abstract
The application provides a PCB automatic wiring system and a method, wherein the system comprises: the device comprises a schematic diagram module, a multiplexing processing module, an automatic rule module and an AI wiring module; the schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module; the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning the wiring rules of the circuit board diagrams; the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules. The method and the device can improve the accuracy and wiring efficiency of automatic wiring.
Description
Technical Field
The present application relates to the field of integrated circuit technologies, and in particular, to a PCB automatic wiring system and method.
Background
Wiring is a key step in PCB (Printed Circuit Board) design, and functions to connect components together by wires to realize specific functions. Traditional PCB design flow needs to spend a large amount of time at processes such as schematic diagram design, PCB overall arrangement, after automatic wiring process, still needs to carry out manual adjustment, and whole process automation degree is not high, and most work is accomplished by the manual work, and is inefficient. For the PCB with complex structure, multiple layers and multiple types of components, the automatic wiring result is difficult to meet the requirement of electrical performance.
The existing PCB design software mainly comprises three parts, namely a schematic diagram part, a PCB part and a simulation part, which are connected through a network table. The automatic PCB wiring part generally adopts traditional wiring algorithms such as a maze algorithm, a line exploration method and the like, the algorithms occupy large storage space during operation, the calculation amount is large, the efficiency is low, and a satisfactory effect is difficult to achieve when the PCB with a complex structure is processed.
Disclosure of Invention
The application aims to provide a PCB automatic wiring system and a method so as to relieve the technical problems of low wiring efficiency and poor wiring effect in the prior art.
The embodiment of the application provides an automatic wiring system of PCB, and the system includes: the device comprises a schematic diagram module, a multiplexing processing module, an automatic rule module and an AI wiring module;
the schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information;
the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module;
the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning the wiring rules of the circuit board diagrams;
the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules.
Further, the automatic rule module is further configured to extract rule information from the netlist, and input the rule information and a user preset rule into the rule generation model, so that the rule generation model outputs a wiring rule corresponding to each functional module.
Further, the AI wiring module includes: the system comprises a wiring model generation module, a wiring module and a post-processing module;
and the AI wiring module is also used for performing layout matching on the module information corresponding to each function module and performing rule matching on the wiring rules corresponding to each function module through the wiring model generation module, generating target wiring models corresponding to each function module respectively, calling the wiring modules corresponding to each target wiring model to perform wiring operation, and outputting a wiring result through the post-processing module.
Further, the system further comprises: an evaluation module; the evaluation module comprises an evaluation model generated by deep learning of a plurality of circuit wiring rules and layout information;
the AI wiring module is also used for sending the current wiring information to the evaluation module in real time through the post-processing module;
and the evaluation module is used for evaluating the current wiring information through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
Further, the system further comprises: a simulation module;
the multiplexing processing module is also used for extracting the simulation model and the simulation parameter corresponding to each functional module from the netlist and sending the simulation model and the simulation parameter corresponding to each functional module to the simulation module;
the AI wiring module is also used for sending the wiring information to the simulation module after the automatic wiring is finished; the wiring information includes: line width, line length, position, via hole;
and the simulation module simulates the PCB after wiring is finished based on the simulation model, the simulation parameters and the wiring information corresponding to each functional module to obtain a simulation result.
Further, the AI wiring module is also used for sending the current wiring information to the evaluation module;
the automatic rule module is also used for sending the wiring rule to the evaluation module;
the simulation module is also used for sending the simulation result to the evaluation module;
and the evaluation module is also used for evaluating the current wiring information, the wiring rule and the simulation result through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
Further, the simulation module comprises: the circuit comprises an information processing module, a circuit analysis module and a display module;
the information processing module is used for carrying out comprehensive processing according to the simulation model, the simulation parameters and the wiring result, generating a global model of the PCB and sending the global model to the circuit analysis module;
the circuit analysis module is used for carrying out circuit analysis on the global model and sending a circuit analysis result to the display module;
and the display module is used for displaying the circuit analysis result and outputting the simulation result.
Further, the circuit analysis module includes: the circuit dynamic analysis module and the circuit transient analysis module.
The embodiment of the application also provides an automatic PCB wiring method, which is applied to an automatic PCB wiring system, wherein the automatic PCB wiring system comprises: the device comprises a schematic diagram module, a multiplexing processing module, an automatic rule module and an AI wiring module; the method comprises the following steps:
the schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information;
the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module;
the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning the wiring rules of the circuit board diagrams;
the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules.
Further, the PCB automatic wiring system further includes: an evaluation module; the evaluation module comprises an evaluation model generated by deep learning of a plurality of circuit wiring rules and layout information; the method further comprises the following steps:
the AI wiring module is also used for sending the current wiring information to the evaluation module in real time;
and the evaluation module is used for evaluating the current wiring information through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
The PCB automatic wiring system and the method provided by the embodiment of the application can realize a high-efficiency automatic wiring process through the combined action of the schematic diagram module, the multiplexing processing module, the automatic rule module and the AI wiring module in the system. The schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information; the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module; the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the automatic rule module comprises a rule generation model obtained by deep learning of wiring rules of a plurality of circuit board diagrams; the AI wiring module comprises a wiring model obtained after deep learning of a plurality of functional modules and wiring rules, and the automatic rule module and the AI wiring module comprise the model obtained after deep learning, so that the accuracy of automatic wiring and the wiring efficiency can be improved.
Drawings
In order to more clearly illustrate the detailed description of the present application or the technical solutions in the prior art, the drawings needed to be used in the detailed description of the present application or the prior art description will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow diagram of a conventional PCB design of the prior art;
FIG. 2 is a prior art PCB design software block diagram;
fig. 3 is a block diagram of an automatic PCB routing system according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of another PCB automatic routing system provided by an embodiment of the present application;
fig. 5 is a schematic diagram illustrating an operation of an automatic rule module in an automatic PCB routing system according to an embodiment of the present disclosure;
fig. 6 is a schematic diagram illustrating an operation of an AI wiring module in an automatic PCB wiring system according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram illustrating an operation of a multiplexing processing module in an automatic PCB routing system according to an embodiment of the present disclosure;
fig. 8 is a schematic diagram illustrating an operation of a simulation module in an automatic PCB routing system according to an embodiment of the present disclosure;
fig. 9 is a schematic diagram illustrating an operation of an evaluation module in an automatic PCB routing system according to an embodiment of the present disclosure;
FIG. 10 is a diagram of a prior art PCB component layout;
fig. 11 is a layout diagram of a PCB component according to an embodiment of the present application;
FIG. 12 is a functional block diagram of a PCB provided by an embodiment of the present application;
fig. 13 is a flowchart of an automatic PCB routing method according to an embodiment of the present application.
Detailed Description
The technical solutions of the present application will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The wiring is a key step in the design of the PCB, and the function of the wiring is to connect components together through wires to realize specific functions. In PCB design, it is often desirable to use automatic routing to improve efficiency and save time. Fig. 1 is a flow of a conventional PCB design.
Traditional PCB design flow needs to spend a large amount of time at processes such as schematic diagram design, PCB overall arrangement, behind automatic wiring process, still needs to carry out manual adjustment as required, and whole process automation degree is not high, and most work is accomplished by the manual work, and is inefficient. For the PCBs with complex structures, multiple layers and multiple component types, the automatic wiring result is often difficult to meet the requirements. Meanwhile, electrical properties (such as frequency, electromagnetic compatibility, etc.) are not considered sufficiently in the wiring process, which may cause the completed PCB to be difficult to meet.
The existing PCB design software block diagram is shown in FIG. 2, and mainly comprises three parts, namely a schematic diagram part, a PCB part and a simulation part, which are connected through a network table. The automatic PCB wiring part generally adopts traditional wiring algorithms such as a maze algorithm, a line exploration method and the like, the algorithms occupy large storage space during operation, the calculation amount is large, the efficiency is low, and a satisfactory effect is difficult to achieve when the PCB with a complex structure is processed.
Based on this, the embodiment of the application provides an automatic wiring system and method for a PCB, so as to alleviate the technical problems of low wiring efficiency and poor wiring effect in the prior art.
To facilitate understanding of the present embodiment, a detailed description will be given of an automatic PCB wiring system disclosed in the embodiments of the present application.
Fig. 3 is a block diagram of an automatic PCB routing system according to an embodiment of the present application, where the system includes: a schematic diagram module 31, a multiplexing processing module 32, an automatic rule module 33, and an AI (Artificial Intelligence) wiring module 34.
The schematic block 31 is connected to the multiplexing block 32 and the automatic rule block 33, and the multiplexing block 32 and the automatic rule block 33 are connected to the AI wiring block 34.
The schematic diagram module 31 is configured to generate a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information; the multiplexing processing module 32 is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module; an automatic rule module 33, configured to generate a routing rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning the wiring rules of the circuit board diagrams; an AI wiring module 34 for performing automatic wiring according to the module information and wiring rules corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules.
In specific implementation, the schematic diagram module 31 has a main function of drawing a circuit schematic diagram and generating a netlist corresponding to the circuit schematic diagram, and different from a conventional netlist, the netlist further includes layout and rule information of each functional module in the schematic diagram besides component attribute information and electrical connection relation. In this embodiment, the multiplexing processing module 32 functions to extract module information corresponding to each functional module in the schematic circuit diagram from the netlist, such as: layout information, routing information, and device parameters of the module.
The automatic rule module 33 and the AI wiring module 34 each include a model obtained by deep learning of a sample, for example, the automatic rule module 33 includes a rule generation model obtained by deep learning of wiring rules of a plurality of circuit board diagrams; specifically, the rule generation model is generated as a result of deep learning, the data source of the rule generation model is a large number of circuit board diagrams, different circuit rules are learned and classified in an unsupervised learning mode, and finally a model capable of generating corresponding rules for each type of circuit is generated. The AI wiring module 34 includes a wiring model obtained by deep learning a plurality of function modules and wiring rules. The wiring model is also a deep learning result, the training main process is similar to the rule generation model, the learning process mainly trains the optimal wiring model according to the input module and the rule, and the optimal wiring result can be achieved through the wiring model. Further, automatic generation of rules and automatic wiring processes can be realized, for example, the automatic rule module 33 generates wiring rules corresponding to each functional module according to the netlist and the user preset rules; the AI wiring module 34 performs automatic wiring based on the module information and wiring rules corresponding to the respective function modules.
In the automatic wiring system of the PCB, the automatic rule module and the AI wiring module respectively comprise a model obtained after deep learning, so that the accuracy and the wiring efficiency of automatic wiring can be improved.
In another preferred embodiment, there is provided a block diagram of another PCB automatic wiring system, as shown in fig. 4, in addition to including a schematic diagram module 41, a multiplexing processing module 42, an automatic rule module 43 and an AI wiring module 44 similar to the previous embodiment, further including: an evaluation module 45 and a simulation module 46.
The schematic diagram module 41 is connected to the multiplexing processing module 42 and the automatic rule module 43, the multiplexing processing module 42 and the automatic rule module 43 are connected to the AI wiring module 44, the multiplexing processing module 42 is further connected to the simulation module 46, the automatic rule module 43 is further connected to the evaluation module 45, the simulation module 46 is further connected to the evaluation module 45, and the simulation module 46 and the evaluation module 45 are connected to the AI wiring module 44. The evaluation module 45 includes an evaluation model generated by deep learning a plurality of circuit wiring rules and layout information. The generation of the evaluation model is also the result of deep learning, and in the training process, the corresponding evaluation model is extracted by analyzing a large amount of circuit rules and layout information, and the optimization is achieved through testing, correction and improvement.
In this embodiment, the automatic rule module 43 is further configured to extract rule information from the netlist, and input the rule information and a user preset rule into the rule generation model, so that the rule generation model outputs a wiring rule corresponding to each functional module.
Specifically, referring to fig. 5, the function of the automatic rule module 43 is to interpret the netlist, the layout and some necessary rules set by human, that is, the rules preset by the user, and then to calculate the specific routing rule for the specific input. In addition to extracting rules from the netlist, the user may also add custom rules for a particular module, all of which are processed by an automatic rules module 43 to generate quantized routing rules for provision to the AI routing module 44 for processing.
Further, the AI routing module 44 may further specifically include: the device comprises a wiring model generation module, a wiring module and a post-processing module. The AI wiring module 44 is further configured to perform layout matching on module information corresponding to each function module and rule matching on wiring rules corresponding to each function module through the wiring model generation module, generate target wiring models corresponding to each function module, call the wiring module corresponding to each target wiring model to perform wiring operation, and output a wiring result through the post-processing module.
The AI wiring module 44 may be further configured to send the current wiring information to the evaluation module 45 in real time through the post-processing module; and the evaluation module 45 is used for evaluating the current wiring information through the evaluation model and returning the evaluation information to the AI wiring module 44, so that the AI wiring module 44 modifies the wiring model based on the evaluation information and performs the wiring operation again until the evaluation information meets the preset evaluation requirement.
The AI wiring module 44 may further send wiring information to the simulation module 46 after the automatic wiring is completed; the wiring information includes: line width, line length, position, via hole; the simulation module 46 may simulate the PCB after the wiring is completed based on the simulation model, the simulation parameters, and the wiring information corresponding to each functional module, so as to obtain a simulation result.
In another preferred embodiment, the AI wiring module 44 may further send the current wiring information to the evaluation module 45; an automatic rule module 43, further configured to send the wiring rule to the evaluation module 45; the simulation module 46 is further configured to send the simulation result to the evaluation module 45; and the evaluation module 45 is further configured to evaluate the current wiring information, the wiring rule and the simulation result through the evaluation model, and return the evaluation information to the AI wiring module 44, so that the AI wiring module 44 modifies the wiring model based on the evaluation information and performs the wiring operation again until the evaluation information meets the preset evaluation requirement.
In a preferred aspect of the present embodiment, the simulation module 46 includes: the device comprises an information processing module, a circuit analysis module and a display module.
The information processing module is used for carrying out comprehensive processing according to the simulation model, the simulation parameters and the wiring result, generating a global model of the PCB and sending the global model to the circuit analysis module; the circuit analysis module is used for carrying out circuit analysis on the global model and sending a circuit analysis result to the display module; and the display module is used for displaying the circuit analysis result and outputting the simulation result. The circuit analysis module includes: the circuit dynamic analysis module and the circuit transient analysis module.
Specifically, fig. 6 shows an operation schematic diagram of the AI wiring module 44 provided in the embodiment of the present application. The AI routing module 44 routes the PCB using an iterative method, where the routing unit is a module and not a component. The AI wiring module 44 has three input sources, respectively from the multiplexing processing module 42, the automatic rule module 43, and the evaluation module 45. The AI wiring module 44 generates a wiring model after performing layout matching and rule matching on the information of the input source, calls the wiring module to perform wiring, and outputs information to the evaluation module 45 every time one or more steps are performed, the evaluation module 45 evaluates the current wiring to obtain feedback information, and then sends the feedback information back to the AI wiring module 44 to correct the wiring model, and the steps are repeated in such a way until all wiring is completed.
In the case where the system includes the simulation module 46, the multiplexing processing module 42 may further include another function, extract the simulation model and the simulation parameter corresponding to each functional module from the netlist, and send the simulation model and the simulation parameter corresponding to each functional module to the simulation module 46.
As shown in fig. 7, the main function of the multiplexing processing module 42 is to extract information of all functional modules from the netlist and perform overall processing on the information to obtain overall information of the PCB and simulation model information, respectively. The PCB integrity information includes the layout of the module, traces within the module, parameters of devices within the module, etc., some of which will be passed to the subsequent AI routing module 44 as an information input. The simulation model information contains the simulation model and simulation parameters for each individual module, which typically contain the recorded results of the simulation and testing of the module in a complex environment, which are necessary for simulation module 46.
Referring to fig. 8, the main function of the simulation module 46 is to simulate the PCB after the wiring is completed to check whether the design requirements are satisfied. The input information of the simulation module 46 comes from the multiplexing processing module 42 and the AI wiring module 44, respectively. The multiplexing processing module 42 provides a simulation model and simulation parameters inside the module, the AI wiring module 44 provides related information of wiring, such as line width, line length, position, via hole, etc., and the information is synthesized by the information processing module to generate a global model of the PCB and transmitted to the circuit analysis part. The circuit analysis part comprises transient analysis and steady-state analysis, the analysis result is processed and then visually displayed, the running state of the whole circuit can be comprehensively known through simulation, the part which does not meet the design requirement can be fed back to the evaluation function, the part is transmitted to the wiring module through the evaluation function, the current wiring is modified, and if the simulation result meets the requirement, the whole wiring process is finished.
As shown in fig. 9, the main function of the evaluation module 45 is to establish an evaluation model, perform global evaluation on the current wiring result, and output evaluation information to the AI wiring module 44 to improve the wiring result of the AI wiring module 44 until the design requirement is satisfied. The input sources are three, respectively, rules input from the automatic rules module 43, simulation results from the simulation module 46, and wiring information from the AI wiring module 44.
Compared with the existing PCB wiring system, the automatic PCB wiring system provided by the embodiment of the application has the following advantages:
1. the reusability is high. When a new PCB is designed, a large number of existing modules can be used for designing the new PCB;
2. the wiring efficiency is high. The wiring objects of the wiring module are not individual components, but individual modules, so that the calculation scale and the calculation time are greatly reduced;
3. the reliability is high. The elements constituting the module can be examined in detail to confirm an optimum combination, and high reliability can be achieved while improving efficiency.
The automatic rule module, the AI wiring module and the evaluation module adopt the deep learning idea, realize corresponding functions through the training of a large amount of data, and ensure good electrical performance while wiring.
In addition, the embodiment of the application also adopts the design idea of the modularized PCB, which is mainly embodied in the following two aspects:
1. modularization of wiring system software
As described above, the wiring system is designed as 6 modules, each module performs a specific function, and information exchange is performed between the modules through data streams.
Modularization of PCB layout
In the conventional PCB layout, the components are taken as units, as shown in fig. 10, and if a group of components with specific functions is divided into a module, the PCB can be seen as being composed of a great number of modules, which greatly reduces the difficulty of layout, as shown in fig. 11.
For each functional module, it needs to be designed reasonably to meet the requirements of modular PCB design, as shown in fig. 12: the PCB functional module mainly comprises four parts, namely a schematic diagram part, a PCB part, a simulation model part and a rule part. The schematic diagram part comprises schematic diagrams and connection relations of all components forming the module, and input and output interfaces; the PCB part comprises the encapsulation and electrical connection of components forming the module; the simulation model comprises a simulation model and data of wiring and electrical characteristics inside the module; the rules section contains the principles that the module should follow when making connections with other modules.
Based on the above automatic PCB wiring system, an embodiment of the present application further provides an automatic PCB wiring method, where the method is applied to an automatic PCB wiring system, and the automatic PCB wiring system includes: the device comprises a schematic diagram module, a multiplexing processing module, an automatic rule module and an AI wiring module; the method comprises the following steps, as shown in fig. 13:
step S101, a schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information;
step S102, a multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module;
step S103, an automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning the wiring rules of the circuit board diagrams;
step S104, an AI wiring module, which is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules.
Further, the PCB automatic wiring system further includes: an evaluation module; the evaluation module comprises an evaluation model generated by deep learning of a plurality of circuit wiring rules and layout information; the above method further comprises the steps of:
the AI wiring module is used for sending the current wiring information to the evaluation module in real time;
and the evaluation module is used for evaluating the current wiring information through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
In another embodiment, the system further comprises: a simulation module; the above method further comprises the steps of:
the multiplexing processing module is used for extracting the simulation model and the simulation parameter corresponding to each functional module from the netlist and sending the simulation model and the simulation parameter corresponding to each functional module to the simulation module;
the AI wiring module is used for sending the wiring information to the simulation module after the automatic wiring is finished; the wiring information includes: line width, line length, position, via hole;
and the simulation module is used for simulating the PCB after wiring is finished based on the simulation model, the simulation parameters and the wiring information corresponding to each functional module to obtain a simulation result.
In a preferred embodiment, the automatic rule module is further configured to extract rule information from the netlist, and input the rule information and a user preset rule into the rule generation model, so that the rule generation model outputs a routing rule corresponding to each functional module.
The AI wiring module includes: the system comprises a wiring model generation module, a wiring module and a post-processing module; and the AI wiring module is also used for performing layout matching on the module information corresponding to each function module and performing rule matching on the wiring rules corresponding to each function module through the wiring model generation module, generating target wiring models corresponding to each function module respectively, calling the wiring modules corresponding to each target wiring model to perform wiring operation, and outputting a wiring result through the post-processing module.
The method further comprises the following steps:
the AI wiring module is also used for sending the current wiring information to the evaluation module;
the automatic rule module is also used for sending the wiring rule to the evaluation module;
the simulation module is also used for sending the simulation result to the evaluation module;
and the evaluation module is also used for evaluating the current wiring information, the wiring rule and the simulation result through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
The simulation module comprises: the circuit comprises an information processing module, a circuit analysis module and a display module; the information processing module is used for carrying out comprehensive processing according to the simulation model, the simulation parameters and the wiring result, generating a global model of the PCB and sending the global model to the circuit analysis module; the circuit analysis module is used for carrying out circuit analysis on the global model and sending a circuit analysis result to the display module; and the display module is used for displaying the circuit analysis result and outputting the simulation result. Wherein, the circuit analysis module includes: the circuit dynamic analysis module and the circuit transient analysis module.
The implementation process of the method provided by the embodiment of the present application may refer to the system embodiment described above, and thus, details are not described herein.
The PCB automatic wiring method provided by the embodiment of the application can realize a high-efficiency automatic wiring process through the combined action of the schematic diagram module, the multiplexing processing module, the automatic rule module and the AI wiring module in the system. The schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information; the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module; the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the automatic rule module comprises a rule generation model obtained by deep learning of wiring rules of a plurality of circuit board diagrams; the AI wiring module comprises a wiring model obtained after deep learning of a plurality of functional modules and wiring rules, and the automatic rule module and the AI wiring module comprise the model obtained after deep learning, so that the accuracy of automatic wiring and the wiring efficiency can be improved.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. An automatic routing system for a PCB, the system comprising: the device comprises a schematic diagram module, a multiplexing processing module, an automatic rule module and an AI wiring module;
the schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information;
the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module;
the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning of wiring rules of a plurality of circuit board diagrams;
the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules.
2. The system of claim 1, wherein the automatic rule module is further configured to extract rule information from the netlist, and input the rule information and the user preset rule into the rule generation model, so that the rule generation model outputs a routing rule corresponding to each functional module.
3. The system of claim 1, wherein the AI routing module comprises: the system comprises a wiring model generation module, a wiring module and a post-processing module;
the AI wiring module is further configured to perform layout matching on the module information corresponding to each function module and perform rule matching on the wiring rules corresponding to each function module through the wiring model generation module to generate target wiring models corresponding to each function module, call the wiring module corresponding to each target wiring model to perform wiring operation, and output a wiring result through the post-processing module.
4. The system of claim 3, further comprising: an evaluation module; the evaluation module comprises an evaluation model generated by deep learning of a plurality of circuit wiring rules and layout information;
the AI wiring module is also used for sending the current wiring information to the evaluation module in real time through the post-processing module;
and the evaluation module is used for evaluating the current wiring information through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
5. The system of claim 4, further comprising: a simulation module;
the multiplexing processing module is further configured to extract a simulation model and a simulation parameter corresponding to each functional module from the netlist, and send the simulation model and the simulation parameter corresponding to each functional module to the simulation module;
the AI wiring module is also used for sending wiring information to the simulation module after the automatic wiring is finished; the wiring information includes: line width, line length, position, via hole;
and the simulation module is used for simulating the PCB after wiring is finished based on the simulation model and the simulation parameters corresponding to each functional module and the wiring information to obtain a simulation result.
6. The system of claim 5,
the AI wiring module is also used for sending the current wiring information to the evaluation module;
the automatic rule module is also used for sending the wiring rule to the evaluation module;
the simulation module is also used for sending a simulation result to the evaluation module;
the evaluation module is further configured to evaluate the current wiring information, the wiring rule, and the simulation result through the evaluation model, and return evaluation information to the AI wiring module, so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets a preset evaluation requirement.
7. The system of claim 5, wherein the simulation module comprises: the circuit comprises an information processing module, a circuit analysis module and a display module;
the information processing module is used for carrying out comprehensive processing according to the simulation model, the simulation parameters and the wiring result to generate a global model of the PCB and sending the global model to the circuit analysis module;
the circuit analysis module is used for carrying out circuit analysis on the global model and sending a circuit analysis result to the display module;
and the display module is used for displaying the circuit analysis result and outputting a simulation result.
8. The system of claim 7, wherein the circuit analysis module comprises: the circuit dynamic analysis module and the circuit transient analysis module.
9. A PCB automatic wiring method is characterized in that the method is applied to a PCB automatic wiring system, and the PCB automatic wiring system comprises: the device comprises a schematic diagram module, a multiplexing processing module, an automatic rule module and an AI wiring module; the method comprises the following steps:
the schematic diagram module is used for generating a netlist corresponding to the circuit schematic diagram; the netlist includes: device parameters, electrical connection relationships, layout and rule information;
the multiplexing processing module is used for extracting module information corresponding to each functional module in the circuit schematic diagram from the netlist; the module information includes: layout information, routing information and device parameters of the module;
the automatic rule module is used for generating a wiring rule corresponding to each functional module according to the netlist and a user preset rule; the automatic rule module comprises a rule generation model obtained by deep learning of wiring rules of a plurality of circuit board diagrams;
the AI wiring module is used for automatically wiring according to the module information and the wiring rule corresponding to each functional module; the AI wiring module comprises a wiring model obtained by deep learning of a plurality of functional modules and wiring rules.
10. The method of claim 9, wherein the PCB automated routing system further comprises: an evaluation module; the evaluation module comprises an evaluation model generated by deep learning of a plurality of circuit wiring rules and layout information; the method further comprises the following steps:
the AI wiring module is also used for sending the current wiring information to the evaluation module in real time;
and the evaluation module is used for evaluating the current wiring information through the evaluation model and returning the evaluation information to the AI wiring module so that the AI wiring module modifies the wiring model based on the evaluation information and performs wiring operation again until the evaluation information meets the preset evaluation requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910892545.0A CN110610052B (en) | 2019-09-20 | 2019-09-20 | PCB automatic wiring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910892545.0A CN110610052B (en) | 2019-09-20 | 2019-09-20 | PCB automatic wiring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110610052A true CN110610052A (en) | 2019-12-24 |
| CN110610052B CN110610052B (en) | 2021-04-30 |
Family
ID=68891626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910892545.0A Active CN110610052B (en) | 2019-09-20 | 2019-09-20 | PCB automatic wiring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610052B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233115A (en) * | 2020-12-11 | 2021-01-15 | 西安国微半导体有限公司 | Deep learning-based wiring violation prediction method after placement and readable storage medium |
| CN112270158A (en) * | 2020-09-15 | 2021-01-26 | 海宁利伊电子科技有限公司 | Method for optimizing perforation distribution of through holes in packaging ground based on deep reinforcement learning |
| CN112464611A (en) * | 2020-12-11 | 2021-03-09 | 电子科技大学 | Automatic PCB wiring system based on cloud-end collaborative intelligent processing |
| CN112528591A (en) * | 2020-12-11 | 2021-03-19 | 电子科技大学 | Automatic PCB wiring method based on joint Monte Carlo tree search |
| CN113177385A (en) * | 2021-04-20 | 2021-07-27 | 深圳市一博科技股份有限公司 | PCB design method for automatically generating MeshLine |
| CN113705143A (en) * | 2020-05-22 | 2021-11-26 | 华为技术有限公司 | Automatic simulation system and automatic simulation method |
| CN114218887A (en) * | 2022-02-14 | 2022-03-22 | 西安芯瞳半导体技术有限公司 | Chip configuration design method, device and medium based on deep learning |
| CN114417717A (en) * | 2022-01-17 | 2022-04-29 | 上海季丰电子股份有限公司 | Simulation method and device of printed circuit board |
| CN114972576A (en) * | 2022-05-25 | 2022-08-30 | 大陆汽车研发（重庆）有限公司 | Method, apparatus and storage medium for generating LTT schematic diagram |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7124387B2 (en) * | 2004-07-29 | 2006-10-17 | International Business Machines Corporation | Integrated circuit macro placing system and method |
| CN101089858A (en) * | 2006-06-12 | 2007-12-19 | 英业达股份有限公司 | System and method for auxiliary layout snake wire |
| CN201185461Y (en) * | 2008-02-22 | 2009-01-21 | 中国科学院软件研究所 | Wireless sensor network node equipment for image acquisition and transmission |
| CN201698495U (en) * | 2010-05-11 | 2011-01-05 | 中国科学院软件研究所 | Automatic high-resolution image generating system |
| WO2011019496A1 (en) * | 2009-08-10 | 2011-02-17 | Apple Inc. | Mechanisms for detecting tampering of an electronic device |
| CN103593527A (en) * | 2013-11-15 | 2014-02-19 | 浪潮电子信息产业股份有限公司 | Design method for one-click setting of different types of routing rule BGAs in PCB |
| CN106021684A (en) * | 2016-05-16 | 2016-10-12 | 北京航天发射技术研究所 | Module power supply standard design system, and design method and application thereof |
| CN106777723A (en) * | 2016-12-25 | 2017-05-31 | 张帆 | A kind of method of automatic drawing principle figure |
| CN206813938U (en) * | 2017-03-20 | 2017-12-29 | 江西景旺精密电路有限公司 | A kind of PCB upper plates automate Wiring device |
| CN109241594A (en) * | 2018-08-23 | 2019-01-18 | 郑州云海信息技术有限公司 | T-type topological structure wire length inspection method, device, equipment and readable storage medium storing program for executing |
| CN109284578A (en) * | 2018-02-27 | 2019-01-29 | 上海安路信息科技有限公司 | Logic circuit layout wiring method, graphic software platform method and its system |
| CN109858098A (en) * | 2018-12-29 | 2019-06-07 | 遵义市水世界科技有限公司 | Method, apparatus, computer equipment and the storage medium of PCB layout |
-
2019
- 2019-09-20 CN CN201910892545.0A patent/CN110610052B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7124387B2 (en) * | 2004-07-29 | 2006-10-17 | International Business Machines Corporation | Integrated circuit macro placing system and method |
| CN101089858A (en) * | 2006-06-12 | 2007-12-19 | 英业达股份有限公司 | System and method for auxiliary layout snake wire |
| CN201185461Y (en) * | 2008-02-22 | 2009-01-21 | 中国科学院软件研究所 | Wireless sensor network node equipment for image acquisition and transmission |
| WO2011019496A1 (en) * | 2009-08-10 | 2011-02-17 | Apple Inc. | Mechanisms for detecting tampering of an electronic device |
| CN201698495U (en) * | 2010-05-11 | 2011-01-05 | 中国科学院软件研究所 | Automatic high-resolution image generating system |
| CN103593527A (en) * | 2013-11-15 | 2014-02-19 | 浪潮电子信息产业股份有限公司 | Design method for one-click setting of different types of routing rule BGAs in PCB |
| CN106021684A (en) * | 2016-05-16 | 2016-10-12 | 北京航天发射技术研究所 | Module power supply standard design system, and design method and application thereof |
| CN106777723A (en) * | 2016-12-25 | 2017-05-31 | 张帆 | A kind of method of automatic drawing principle figure |
| CN206813938U (en) * | 2017-03-20 | 2017-12-29 | 江西景旺精密电路有限公司 | A kind of PCB upper plates automate Wiring device |
| CN109284578A (en) * | 2018-02-27 | 2019-01-29 | 上海安路信息科技有限公司 | Logic circuit layout wiring method, graphic software platform method and its system |
| CN109241594A (en) * | 2018-08-23 | 2019-01-18 | 郑州云海信息技术有限公司 | T-type topological structure wire length inspection method, device, equipment and readable storage medium storing program for executing |
| CN109858098A (en) * | 2018-12-29 | 2019-06-07 | 遵义市水世界科技有限公司 | Method, apparatus, computer equipment and the storage medium of PCB layout |
Non-Patent Citations (2)
| Title |
|---|
| JIN LIN ET AL: ""EDA technology and its implementation in modern electronic technology"", 《IEEE》 * |
| 张哲: ""辊磨机和定向仪控制系统设计及峰形评估方法研究"", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113705143A (en) * | 2020-05-22 | 2021-11-26 | 华为技术有限公司 | Automatic simulation system and automatic simulation method |
| CN113705143B (en) * | 2020-05-22 | 2024-03-26 | 华为技术有限公司 | Automatic simulation system and automatic simulation method |
| CN112270158A (en) * | 2020-09-15 | 2021-01-26 | 海宁利伊电子科技有限公司 | Method for optimizing perforation distribution of through holes in packaging ground based on deep reinforcement learning |
| CN112270158B (en) * | 2020-09-15 | 2022-11-18 | 海宁利伊电子科技有限公司 | Method for optimizing perforation distribution of through holes in packaging ground based on deep reinforcement learning |
| CN112464611B (en) * | 2020-12-11 | 2022-09-20 | 电子科技大学 | Automatic PCB wiring system based on cloud-end collaborative intelligent processing |
| CN112233115A (en) * | 2020-12-11 | 2021-01-15 | 西安国微半导体有限公司 | Deep learning-based wiring violation prediction method after placement and readable storage medium |
| CN112528591A (en) * | 2020-12-11 | 2021-03-19 | 电子科技大学 | Automatic PCB wiring method based on joint Monte Carlo tree search |
| CN112464611A (en) * | 2020-12-11 | 2021-03-09 | 电子科技大学 | Automatic PCB wiring system based on cloud-end collaborative intelligent processing |
| CN113177385A (en) * | 2021-04-20 | 2021-07-27 | 深圳市一博科技股份有限公司 | PCB design method for automatically generating MeshLine |
| CN113177385B (en) * | 2021-04-20 | 2024-02-02 | 深圳市一博科技股份有限公司 | PCB design method for automatically generating Meshline |
| CN114417717A (en) * | 2022-01-17 | 2022-04-29 | 上海季丰电子股份有限公司 | Simulation method and device of printed circuit board |
| CN114417717B (en) * | 2022-01-17 | 2022-12-09 | 上海季丰电子股份有限公司 | Simulation method and device of printed circuit board |
| CN114218887A (en) * | 2022-02-14 | 2022-03-22 | 西安芯瞳半导体技术有限公司 | Chip configuration design method, device and medium based on deep learning |
| CN114972576A (en) * | 2022-05-25 | 2022-08-30 | 大陆汽车研发（重庆）有限公司 | Method, apparatus and storage medium for generating LTT schematic diagram |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110610052B (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610052B (en) | PCB automatic wiring system and method | |
| US8364449B2 (en) | Process for automatic creation of wiring simulation | |
| US20030028630A1 (en) | Method and system for processing topology data and geometry data of networks | |
| CN108629103A (en) | The manufacture of SMT patches and SMT screen plate production method and system | |
| CN111125052B (en) | Big data intelligent modeling system and method based on dynamic metadata | |
| US6795950B2 (en) | Printed circuit board design system | |
| CN105701289A (en) | Integrated solution method for full-automatic harness processing device | |
| US8301422B2 (en) | Process for creating a library of algorithmic representations of electronic equipment | |
| CN113705143B (en) | Automatic simulation system and automatic simulation method | |
| US9317638B1 (en) | Polymorphic circuit simulation system | |
| US6230115B1 (en) | Simulator, simulation method, and medium having simulation program recorded, taking account of timing in electronic component and signal transmission through transmission line on printed-circuit board | |
| CN109993387A (en) | A kind of automatic scoring method and device based on NLP, examination system | |
| CN109815635B (en) | Boiler MFT automatic design system and method | |
| CN115270674B (en) | LIB extraction method and device with timing margin based on automation | |
| CN110021215A (en) | A kind of power equipment auxiliary training terminal equipment | |
| CN113792422B (en) | Digital twinning-based TPM equipment management virtual verification method and system | |
| Korolev et al. | The Implementation of the Cross-Cutting Design Technique of Electronic Communication Modules Using National Instruments Technologies | |
| US6912473B2 (en) | Method for verifying cross-sections | |
| CN112799900A (en) | Modelica-based model fault injection method and system | |
| JP4355930B2 (en) | Semiconductor integrated circuit power supply model creation method, program, and information processing apparatus | |
| CN113221504B (en) | Efficient Via simulation data acquisition method, system and medium | |
| CN112632883B (en) | Method, device, equipment and medium for testing simulation result of device model | |
| US6961887B1 (en) | Streamlined LASAR-to-L200 post-processing for CASS | |
| KR100475014B1 (en) | How to calculate delay time of interconnect | |
| Chawda et al. | A novel methodology for electronic design exchange |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |