1. A PCB insertion loss impedance test analysis method is characterized by comprising the following steps:

quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-target function by combining the variables, and setting constraint conditions of the multi-target function according to the requirements of the evaluation targets;

training a multi-target function by using a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster which accords with constraint conditions;

screening an activity variable scheme from the advantage variable scheme cluster according to the crowding distance, and carrying out proportional cloning on the screened activity variable scheme to obtain an alternative scheme;

and selecting a target scheme from the alternatives according to the requirement on the evaluation target.

2. The method of claim 1, wherein quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-objective function in combination with the variables, and setting constraints of the multi-objective function according to requirements of the evaluation targets comprises:

quantifying the laminated structure, the copper foil material, the temperature, the humidity and the manufacturer process;

selecting impedance, insertion loss, production period and cost as evaluation targets;

constructing an impedance subfunction, an insertion loss subfunction, a production period subfunction and a cost subfunction according to the influence relation between the variables and the evaluation target, wherein the impedance subfunction, the insertion loss subfunction, the production period subfunction and the cost subfunction form a multi-target function;

and setting the constraint value of the evaluation target according to the requirement of the evaluation target.

3. The method of claim 1, wherein training a multi-objective function by using a non-dominated neighborhood immune algorithm to obtain a dominance variable scheme cluster meeting a constraint condition comprises:

randomly arranging the values of all variables to generate a variable scheme to form an initialization population;

substituting test data of the insertion loss impedance test into the initial population for calculation to obtain a multi-target function value corresponding to the initial population;

and selecting the initialized population with the multi-objective function values conforming to the constraint conditions as the dominant variable schemes, and storing all the dominant variable schemes as the dominant variable scheme clusters.

4. The method of claim 1, wherein screening the population of activity variable plans for activity variable plans according to crowding distance and performing proportional cloning on the screened activity variable plans results in alternatives comprising:

calculating the crowdedness distance of the dominant variable schemes in the dominant variable scheme cluster, and sequencing the dominant variable schemes from large to small according to the crowdedness distance to obtain a dominant variable scheme sequence;

selecting an advantage variable scheme with the largest crowding degree distance from the advantage variable scheme sequence as an activity variable scheme according to a preset proportional cloning parameter;

copying the active variable scheme, randomly adjusting the variable value of the active variable scheme within the crowdedness distance range, and combining the adjusted variables to serve as an alternative scheme;

and taking the alternative schemes and the dominant variable schemes as initial scheme clusters, and carrying out iterative screening on the initial scheme clusters by using a non-dominated neighborhood immune algorithm.

5. The method of claim 1, wherein selecting a target solution from the alternatives based on a need for an assessment target comprises:

selecting a corresponding target scheme according to the expected value of the evaluation target;

designing and trial-producing the PCB according to the target scheme, and testing the trial-produced PCB to obtain an actual evaluation target value;

and comparing the consistency of the actual evaluation target value and the expected value, and if the actual evaluation target value and the expected value are inconsistent, correcting the non-dominated neighborhood immune algorithm iterative model of the multi-target function.

6. A PCB insertion loss impedance test analysis system is characterized by comprising:

the function building unit is used for quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, building a multi-target function by combining the variables, and setting constraint conditions of the multi-target function according to the requirements of the evaluation targets;

the function training unit is used for training a multi-target function by utilizing a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster which accords with constraint conditions;

the scheme cloning unit is used for screening the activity variable schemes from the advantage variable scheme clusters according to the crowding distance and carrying out proportional cloning on the screened activity variable schemes to obtain alternative schemes;

and the target selecting unit is used for selecting a target scheme from the alternative schemes according to the requirement on the evaluation target.

7. The system of claim 6, wherein the function building unit comprises:

the variable quantization module is used for quantizing the laminated structure, the copper foil material, the temperature, the humidity and the manufacturer process;

the target selection module is used for selecting impedance, insertion loss, production period and cost as evaluation targets;

the function building module is used for building an impedance sub-function, an insertion loss sub-function, a production period sub-function and a cost sub-function according to the influence relation between the variables and the evaluation target, and the impedance sub-function, the insertion loss sub-function, the production period sub-function and the cost sub-function form a multi-target function;

and the constraint setting module is used for setting a constraint value of the evaluation target according to the requirement of the evaluation target.

8. The system of claim 6, wherein the function training unit comprises:

the random value taking module is used for randomly arranging the values of all the variables and forming an initialization population by the generated variable scheme;

the function calculation module is used for substituting the test data of the insertion loss impedance test into the initial population to calculate to obtain a multi-target function value corresponding to the initial population;

and the advantage screening module is used for selecting the initialized population with the multi-objective function values meeting the constraint conditions as an advantage variable scheme and storing all the advantage variable schemes as an advantage variable scheme cluster.

9. A terminal, comprising:

a processor;

a memory for storing instructions for execution by the processor;

wherein the processor is configured to perform the method of any one of claims 1-5.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.

Background

A Printed Circuit Board (PCB) is an important electronic component, is a support for an electronic component, and is a carrier for electrical connection of the electronic component. It is called a "printed" circuit board because it is made using electronic printing. With the development of high-speed transmission technology, the signal rate on the PCB is higher and higher, and the requirement for a transmission line for carrying signals is higher and higher, in order to ensure the transmission quality of high-speed signals, impedance and insertion loss tests are required to be performed on a high-speed PCB board, and the board card for testing is a coupon strip reserved when the PCB board card is processed. There are various impedances, such as 50 ohms, 85 ohms, and 100 ohms, which are common, and the insertion loss (insertion loss) is another key parameter for measuring the signal loss of the PCB, which is the load power loss caused by the insertion of a component in a certain position of the transmission system, and is expressed as the ratio of the power received by the load before the component is inserted to the power received by the same load after the component is inserted in decibels. Empirical data shows that factors affecting impedance and insertion loss are various, including a laminated structure, a copper foil material, temperature, humidity, a process and the like, and the impedance and insertion loss values are changed by changing a plurality of conditions, so that the problem is a multi-objective optimization problem to some extent. The existing analysis and evaluation method is to fix part of parameters, change other parameters, obtain impedance and insertion loss data by software simulation or other modes, modify parameters by iteration and measure, and finally find a group of data which accords with design indexes.

The method is slow in speed, particularly, when the impedance and the insertion loss data cannot be obtained through software simulation, a small amount of trial production is needed, and then the impedance and the insertion loss data are obtained through measuring the coupon, so that the number of required iterations in the initial design stage is large, the consumed time is very long, and the cost is very high. The method is characterized in that other parameters are modified by adopting fixed part parameters for a multi-objective optimization problem, and target data which is similar to the target data found by means of parameter dimension reduction and even simplification into a single-objective optimization problem with constraint conditions meets design indexes but is not optimal data. The method can still cope with the situation of adopting a mature technology, but materials and processes are rapidly developed, if a great deal of attempts are made to apply a new technology to the design of the circuit board and find new data meeting design indexes, the perception efficiency of the new technology is low, and a great deal of time is consumed when the new technology is applied to the design of the circuit board and new data meeting the design indexes are found.

Disclosure of Invention

In view of the above-mentioned deficiencies of the prior art, the present invention provides a PCB insertion loss impedance test analysis method, system, terminal and storage medium, so as to solve the above-mentioned technical problems.

In a first aspect, the present invention provides a PCB insertion loss impedance test analysis method, including:

quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-target function by combining the variables, and setting constraint conditions of the multi-target function according to the requirements of the evaluation targets;

training a multi-target function by using a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster which accords with constraint conditions;

screening an activity variable scheme from the advantage variable scheme cluster according to the crowding distance, and carrying out proportional cloning on the screened activity variable scheme to obtain an alternative scheme;

and selecting a target scheme from the alternatives according to the requirement on the evaluation target.

Furthermore, quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-objective function by combining the variables, and setting constraint conditions of the multi-objective function according to the requirements of the evaluation targets, wherein the constraint conditions comprise:

quantifying the laminated structure, the copper foil material, the temperature, the humidity and the manufacturer process;

selecting impedance, insertion loss, production period and cost as evaluation targets;

constructing an impedance subfunction, an insertion loss subfunction, a production period subfunction and a cost subfunction according to the influence relation between the variables and the evaluation target, wherein the impedance subfunction, the insertion loss subfunction, the production period subfunction and the cost subfunction form a multi-target function;

and setting the constraint value of the evaluation target according to the requirement of the evaluation target.

Further, training a multi-objective function by using a non-dominated neighborhood immune algorithm to obtain a dominant variable scheme cluster meeting constraint conditions, wherein the method comprises the following steps:

randomly arranging the values of all variables to generate a variable scheme to form an initialization population;

substituting test data of the insertion loss impedance test into the initial population for calculation to obtain a multi-target function value corresponding to the initial population;

and selecting the initialized population with the multi-objective function values conforming to the constraint conditions as the dominant variable schemes, and storing all the dominant variable schemes as the dominant variable scheme clusters.

Further, screening an activity variable scheme from the advantage variable scheme cluster according to the crowding distance, and carrying out proportional cloning on the screened activity variable scheme to obtain an alternative scheme, wherein the alternative scheme comprises the following steps:

calculating the crowdedness distance of the dominant variable schemes in the dominant variable scheme cluster, and sequencing the dominant variable schemes from large to small according to the crowdedness distance to obtain a dominant variable scheme sequence;

selecting an advantage variable scheme with the largest crowding degree distance from the advantage variable scheme sequence as an activity variable scheme according to a preset proportional cloning parameter;

copying the active variable scheme, randomly adjusting the variable value of the active variable scheme within the crowdedness distance range, and combining the adjusted variables to serve as an alternative scheme;

and taking the alternative schemes and the dominant variable schemes as initial scheme clusters, and carrying out iterative screening on the initial scheme clusters by using a non-dominated neighborhood immune algorithm.

Further, selecting a target scheme from the alternatives according to the requirement on the evaluation target, comprising:

selecting a corresponding target scheme according to the expected value of the evaluation target;

designing and trial-producing the PCB according to the target scheme, and testing the trial-produced PCB to obtain an actual evaluation target value;

and comparing the consistency of the actual evaluation target value and the expected value, and if the actual evaluation target value and the expected value are inconsistent, correcting the non-dominated neighborhood immune algorithm iterative model of the multi-target function.

In a second aspect, the present invention provides a PCB insertion loss impedance test analysis system, including:

the function building unit is used for quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, building a multi-target function by combining the variables, and setting constraint conditions of the multi-target function according to the requirements of the evaluation targets;

the function training unit is used for training a multi-target function by utilizing a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster which accords with constraint conditions;

the scheme cloning unit is used for screening the activity variable schemes from the advantage variable scheme clusters according to the crowding distance and carrying out proportional cloning on the screened activity variable schemes to obtain alternative schemes;

and the target selecting unit is used for selecting a target scheme from the alternative schemes according to the requirement on the evaluation target.

Further, the function building unit includes:

the variable quantization module is used for quantizing the laminated structure, the copper foil material, the temperature, the humidity and the manufacturer process;

the target selection module is used for selecting impedance, insertion loss, production period and cost as evaluation targets;

the function building module is used for building an impedance sub-function, an insertion loss sub-function, a production period sub-function and a cost sub-function according to the influence relation between the variables and the evaluation target, and the impedance sub-function, the insertion loss sub-function, the production period sub-function and the cost sub-function form a multi-target function;

and the constraint setting module is used for setting a constraint value of the evaluation target according to the requirement of the evaluation target.

Further, the function training unit includes:

the random value taking module is used for randomly arranging the values of all the variables and forming an initialization population by the generated variable scheme;

the function calculation module is used for substituting the test data of the insertion loss impedance test into the initial population to calculate to obtain a multi-target function value corresponding to the initial population;

and the advantage screening module is used for selecting the initialized population with the multi-objective function values meeting the constraint conditions as an advantage variable scheme and storing all the advantage variable schemes as an advantage variable scheme cluster.

Further, the scheme cloning unit comprises:

the scheme sorting module is used for calculating the crowding degree distance of the dominant variable schemes in the dominant variable scheme cluster, and sorting the dominant variable schemes from large to small according to the crowding degree distance to obtain a dominant variable scheme sequence;

the acquisition screening module is used for selecting an advantage variable scheme with the largest crowding degree distance from the advantage variable scheme sequence as an activity variable scheme according to a preset proportional cloning parameter;

the scheme replication module is used for replicating the active variable scheme, randomly adjusting the variable value of the active variable scheme within the crowdedness distance range, and combining the adjusted variables to serve as an alternative scheme;

and the iterative screening module is used for taking the alternative schemes and the dominant variable schemes as initial scheme clusters and carrying out iterative screening on the initial scheme clusters by using a non-dominated neighborhood immune algorithm.

In a third aspect, a terminal is provided, including:

a processor, a memory, wherein,

the memory is used for storing a computer program which,

the processor is used for calling and running the computer program from the memory so as to make the terminal execute the method of the terminal.

In a fourth aspect, a computer storage medium is provided having stored therein instructions that, when executed on a computer, cause the computer to perform the method of the above aspects.

The beneficial effect of the invention is that,

according to the PCB insertion loss impedance test analysis method, a multi-objective optimization model is introduced, a classical non-dominated neighborhood immune algorithm (NNIA) is adopted and existing test data are combined, and the optimization model which takes a quantized laminated structure, a copper foil material, temperature, humidity and a manufacturer process as multi-dimensional variables and takes impedance, insertion loss, a production period and cost as multi-dimensional objectives and constraint conditions is constructed. By utilizing the advantages of multi-objective algorithm search, through the multi-dimensional variable adjustment, various parameters are comprehensively set, multiple groups of optimal data meeting conditions are quickly obtained, the times of software simulation and trial production are greatly reduced through artificial preliminary screening, and the analysis and evaluation efficiency is improved. Meanwhile, the new technology quantization parameters can be applied to the existing model to obtain the target scheme, the feasibility of the new technology is preliminarily evaluated, the existing model can be modified aiming at the new technology, and the perception efficiency of the new technology is improved.

According to the PCB insertion loss impedance test analysis system, a multi-objective optimization model is introduced, a classical non-dominated neighborhood immune algorithm (NNIA) is adopted and existing test data are combined, and the optimization model which takes a quantized laminated structure, a copper foil material, temperature, humidity and a manufacturer process as multi-dimensional variables and takes impedance, insertion loss, a production period and cost as multi-dimensional objectives and constraint conditions is constructed. By utilizing the advantages of multi-objective algorithm search, through the multi-dimensional variable adjustment, various parameters are comprehensively set, multiple groups of optimal data meeting conditions are quickly obtained, the times of software simulation and trial production are greatly reduced through artificial preliminary screening, and the analysis and evaluation efficiency is improved. Meanwhile, the new technology quantization parameters can be applied to the existing model to obtain the target scheme, the feasibility of the new technology is preliminarily evaluated, the existing model can be modified aiming at the new technology, and the perception efficiency of the new technology is improved.

The terminal provided by the invention can execute a PCB insertion loss impedance test analysis method, and an optimization model which takes a quantized laminated structure, a copper foil material, temperature, humidity and manufacturer process as multidimensional variables and takes impedance, insertion loss, production period and cost as multidimensional targets and constraint conditions is constructed by introducing a multi-objective optimization model, adopting a classical non-dominated neighborhood immune algorithm (NNIA) and combining existing test data. By utilizing the advantages of multi-objective algorithm search, through the multi-dimensional variable adjustment, various parameters are comprehensively set, multiple groups of optimal data meeting conditions are quickly obtained, the times of software simulation and trial production are greatly reduced through artificial preliminary screening, and the analysis and evaluation efficiency is improved. Meanwhile, the new technology quantization parameters can be applied to the existing model to obtain the target scheme, the feasibility of the new technology is preliminarily evaluated, the existing model can be modified aiming at the new technology, and the perception efficiency of the new technology is improved.

The storage medium provided by the invention stores a program for executing the PCB insertion loss impedance test analysis method, and constructs an optimization model which takes a quantized laminated structure, a copper foil material, temperature, humidity and manufacturer process as multidimensional variables and takes impedance, insertion loss, production period and cost as multidimensional targets and constraint conditions by introducing a multi-objective optimization model, adopting a classical non-dominated neighborhood immune algorithm (NNIA) and combining existing test data. By utilizing the advantages of multi-objective algorithm search, through the multi-dimensional variable adjustment, various parameters are comprehensively set, multiple groups of optimal data meeting conditions are quickly obtained, the times of software simulation and trial production are greatly reduced through artificial preliminary screening, and the analysis and evaluation efficiency is improved. Meanwhile, the new technology quantization parameters can be applied to the existing model to obtain the target scheme, the feasibility of the new technology is preliminarily evaluated, the existing model can be modified aiming at the new technology, and the perception efficiency of the new technology is improved.

In addition, the invention has reliable design principle, simple structure and very wide application prospect.

Drawings

In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.

FIG. 1 is a schematic flow diagram of a method of one embodiment of the invention.

FIG. 2 is another schematic flow diagram of a method of one embodiment of the invention.

Fig. 3 is a schematic flow diagram of a generation alternative of the method of one embodiment of the invention.

FIG. 4 is a schematic block diagram of a system of one embodiment of the present invention.

Fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. 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 invention.

The following explains key terms appearing in the present invention.

An insertion loss impedance strip Coupon;

multi-objective optimization problem MOP;

the non-dominant neighborhood Immune Algorithm Multi-object Immune Algorithm with non-dominated Neighbor-based Selection (NNIA).

FIG. 1 is a schematic flow diagram of a method of one embodiment of the invention. The execution main body in fig. 1 may be a PCB insertion loss impedance test analysis system.

As shown in fig. 1, the method includes:

110, quantifying variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-objective function by combining the variables, and setting constraint conditions of the multi-objective function according to the requirements of the evaluation targets;

step 120, training a multi-objective function by using a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster meeting constraint conditions;

step 130, screening an activity variable scheme from the advantage variable scheme cluster according to the crowding distance, and carrying out proportional cloning on the screened activity variable scheme to obtain an alternative scheme;

and step 140, selecting a target scheme from the alternatives according to the requirement on the evaluation target.

In order to facilitate understanding of the present invention, the PCB insertion loss impedance test analysis method provided by the present invention is further described below with reference to the principle of the PCB insertion loss impedance test analysis method of the present invention and the process of analyzing the PCB insertion loss impedance test in the embodiments.

The method is based on a multi-objective optimization model, adopts a classical non-dominated neighborhood immune algorithm (NNIA) and combines the existing test data to construct an optimization model which takes a quantized laminated structure, a copper foil material, temperature, humidity and a manufacturer process as multi-dimensional variables and takes impedance, insertion loss, a production period and cost as multi-dimensional targets and constraint conditions. By utilizing the advantages of multi-objective algorithm search, through the multi-dimensional variable adjustment, various parameters are comprehensively set, multiple groups of optimal data meeting conditions are quickly obtained, and then through artificial preliminary screening, the times of software simulation and trial production test are greatly reduced, and finally the analysis and evaluation efficiency is improved. Meanwhile, the new technology can be quantized into parameters and applied to the existing model to obtain target data, the feasibility of the new technology can be preliminarily evaluated, the existing model can be modified aiming at the new technology, and the perception efficiency of the new technology is improved.

Specifically, referring to fig. 2, the PCB insertion loss impedance test analysis method includes:

s1, quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-target function by combining the variables, and setting constraint conditions of the multi-target function according to the requirements of the evaluation targets.

First, the dependent variable is quantized. The multi-dimensional variables set by the invention comprise a laminated structure ss, a copper foil material ct, a temperature t, a humidity h and a manufacturer process vt, the laminated structure, the copper foil material and the manufacturer process need to be quantized, and the quantization aims to obtain a target value through a mathematical calculation mode when a certain variable value is adjusted or selected, so that the influence degree of the change of the variables on the target is reflected. For example, the different lamination structures are quantized to 1, 2 and 3, the different copper foil materials used are quantized to 1, 2 and 3, and the like, and the quantization forms and magnitudes depend on the built model and the relationship abstracted from the existing test data.

Four evaluation targets are selected in the embodiment, namely impedance imp, insertion loss il, production period pp and cost. Since high loss may cause signal attenuation, eye closure and jitter in the channel, and low loss may cause signal overshoot and signal reflection, constraints are set on insertion loss, and corresponding constraints are set on production cycle and cost according to project requirements, for example, every 1000 production cycles do not exceed 1 week, and every cost does not exceed 2000 yuan, etc.

A large amount of test data can be accumulated in production test, the data are coupon corresponding to PCBs designed and produced by adopting different laminated structures ss, copper foil materials ct, temperature t, humidity h, manufacturer process vt and the like, impedance imp, insertion loss value il, capacity pp and cost of PCBs produced by manufacturers are obtained through test, and multi-dimensional variable to multi-target functions constructed by combining the quantization conditions are respectively recorded as

S2, training a multi-objective function by using a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster meeting constraint conditions;

the non-dominated neighborhood immune algorithm model requires population initialization. Specifically, values of the variables are randomly arranged, and the generated variable scheme constitutes an initialization population.

The initial population setting is generated by adopting a random permutation and combination mode, each individual in the population corresponds to a group of variable data, namely the laminated structure, the copper foil material, the temperature, the humidity and the manufacturer process, the size and the individual difference of the population are related to the test data mastered by the current company or unit, for example, the laminated structure is different from 1 to 20, the temperature is different from 10 to 20, the cooperative manufacturer process has more than 10 kinds, and the size of the population is 30. The population evolution termination algebra is set to be 30, the upper limit of the number of target schemes is 5, the proportional cloning scale is 10, and the active population scale is 10. The initial population was written as Bt t t ═ 0.

Updating the dominant individual population. For each individual in the population Bt, the individual here refers to a variable scheme, a corresponding objective function value is calculated, the optimal individual with the highest upper limit scheme number is selected for all the individuals meeting the constraint condition to enter the dominant individual group Dt, and the parameter corresponding to each individual represents a design scheme.

S3, screening the activity variable schemes from the advantage variable scheme clusters according to the crowding distance, and carrying out proportional cloning on the screened activity variable schemes to obtain alternative schemes.

Referring to fig. 3, a current active population is generated. Calculating the crowding degree distance of individuals in the current dominant individual population Dt, calculating the crowding degree by adopting a mode provided by NNIA algorithm, then arranging the crowding degree distances in a descending order, and preferentially selecting the individuals with large crowding degree distances to form the current active antibody population At according to the set proportional cloning parameters

A new population of alternatives is generated. Carrying out proportional cloning operation, namely 1:1 duplication, on individuals in the current active antibody population At, randomly approaching the quantized laminated structure, copper foil material, temperature, humidity and manufacturer process corresponding to each individual within the crowding distance range to generate a new numerical value, and obtaining the population Ct of the alternative design scheme

Updating the dominant individual population. And (3) forming a new generation population Bt +1 by the alternative design scheme population Ct and the dominant individual population Dt, and then carrying out iterative optimization on the new population by using a non-dominated neighborhood immune algorithm model.

And (5) terminating the judgment. The termination condition refers to the evolution algebra, if the algebra is satisfied, the algorithm is terminated, and the corresponding optimization scheme is output, otherwise, the next step is continued.

And S4, selecting a target scheme from the alternatives according to the requirement on the evaluation target.

According to the alternative scheme obtained by the multi-target model, through artificial preliminary screening, the impedance and insertion loss numerical values are obtained through software simulation or a small amount of trial production is carried out on a designed PCB, then the impedance and insertion loss numerical values are obtained through testing coupon, the impedance insertion loss numerical values are compared with the theoretical impedance and insertion loss numerical values calculated by the multi-target model, and if the impedance and insertion loss numerical values have deviation, the model is corrected in time. In addition, for a new technology and a new process, the new technology and the new process can be put into an existing multi-target model after quantization, the actual impedance and insertion loss values are tested by using the obtained design scheme, and the multi-target model is corrected in time, so that the new technology and the new process are applied to production design in time, and the sensing efficiency of the new technology and the new process is improved. Multiple alternative design schemes can be obtained through multi-objective optimization, each scheme is a compromise of a target value, the target values set in the embodiment are impedance, insertion loss, production cycle and cost, designers can flexibly select the design schemes according to actual needs, for example, the design schemes with the target values being smaller costs can be selected with emphasis on cost indexes, and the design schemes with the target values being shorter production cycles can be selected with emphasis on production.

As shown in fig. 4, the system 400 includes:

the function construction unit 410 is used for quantifying the variables of the insertion loss impedance test, selecting a plurality of evaluation targets, constructing a multi-target function by combining the variables, and setting constraint conditions of the multi-target function according to the requirements of the evaluation targets;

the function training unit 420 is used for training a multi-target function by using a non-dominated neighborhood immune algorithm to obtain an advantage variable scheme cluster meeting constraint conditions;

the scheme cloning unit 430 is used for screening the activity variable schemes from the advantage variable scheme clusters according to the crowding distance, and carrying out proportional cloning on the screened activity variable schemes to obtain alternative schemes;

and the target selecting unit 440 is used for selecting the target scheme from the alternative schemes according to the requirement on the evaluation target.

Optionally, as an embodiment of the present invention, the function constructing unit includes:

the variable quantization module is used for quantizing the laminated structure, the copper foil material, the temperature, the humidity and the manufacturer process;

the target selection module is used for selecting impedance, insertion loss, production period and cost as evaluation targets;

the function building module is used for building an impedance sub-function, an insertion loss sub-function, a production period sub-function and a cost sub-function according to the influence relation between the variables and the evaluation target, and the impedance sub-function, the insertion loss sub-function, the production period sub-function and the cost sub-function form a multi-target function;

and the constraint setting module is used for setting a constraint value of the evaluation target according to the requirement of the evaluation target.

Optionally, as an embodiment of the present invention, the function training unit includes:

the random value taking module is used for randomly arranging the values of all the variables and forming an initialization population by the generated variable scheme;

the function calculation module is used for substituting the test data of the insertion loss impedance test into the initial population to calculate to obtain a multi-target function value corresponding to the initial population;

and the advantage screening module is used for selecting the initialized population with the multi-objective function values meeting the constraint conditions as an advantage variable scheme and storing all the advantage variable schemes as an advantage variable scheme cluster.

Fig. 5 is a schematic structural diagram of a terminal 500 according to an embodiment of the present invention, where the terminal 500 may be used to perform a PCB insertion loss impedance test analysis method according to the embodiment of the present invention.

Among them, the terminal 500 may include: a processor 510, a memory 520, and a communication unit 530. The components communicate via one or more buses, and those skilled in the art will appreciate that the architecture of the servers shown in the figures is not intended to be limiting, and may be a bus architecture, a star architecture, or may include more or less components than those shown, or some variation of components, or a different arrangement of components.

The memory 520 may be used for storing instructions executed by the processor 510, and the memory 520 may be implemented by any type of volatile or non-volatile storage terminal or a variant thereof, such as a Static Random Access Memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk. The executable instructions in memory 520, when executed by processor 510, enable terminal 500 to perform some or all of the steps in the method embodiments described below.

The processor 510 is a control center of the storage terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by operating or executing software programs and/or modules stored in the memory 520 and calling data stored in the memory. The processor may be composed of an Integrated Circuit (IC), for example, a single packaged IC, or a plurality of packaged ICs connected with the same or different functions. For example, processor 510 may include only a Central Processing Unit (CPU). In the embodiment of the present invention, the CPU may be a single operation core, or may include multiple operation cores.

A communication unit 530 for establishing a communication channel so that the storage terminal can communicate with other terminals. And receiving user data sent by other terminals or sending the user data to other terminals.

The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and the program may include some or all of the steps in the embodiments provided by the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).

Therefore, the invention constructs an optimization model which takes a quantized laminated structure, a copper foil material, temperature, humidity and manufacturer process as multidimensional variables and takes impedance, insertion loss, production period and cost as multidimensional targets and constraint conditions by introducing a multi-objective optimization model, adopting a classical non-dominated neighborhood immune algorithm (NNIA) and combining existing test data. By utilizing the advantages of multi-objective algorithm search, through the multi-dimensional variable adjustment, various parameters are comprehensively set, multiple groups of optimal data meeting conditions are quickly obtained, the times of software simulation and trial production are greatly reduced through artificial preliminary screening, and the analysis and evaluation efficiency is improved. Meanwhile, the new technology quantization parameters can be applied to the existing model to obtain the target scheme, the feasibility of the new technology can be preliminarily evaluated, the existing model can be modified aiming at the new technology, the perception efficiency of the new technology can be improved, the technical effect which can be achieved by the embodiment can be referred to the description above, and the details are not repeated here.

Those skilled in the art will readily appreciate that the techniques of the embodiments of the present invention may be implemented as software plus a required general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be embodied in the form of a software product, where the computer software product is stored in a storage medium, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like, and the storage medium can store program codes, and includes instructions for enabling a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, and the like) to perform all or part of the steps of the method in the embodiments of the present invention.

The same and similar parts in the various embodiments in this specification may be referred to each other. Especially, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant points can be referred to the description in the method embodiment.

In the embodiments provided in the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, systems or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

Although the present invention has been described in detail by referring to the drawings in connection with the preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made on the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and these modifications or substitutions are within the scope of the present invention/any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.