A circuit board design layout open and short circuit inspection method and system

Abstract

The invention discloses a circuit board design layout open and short circuit inspection method and system, which relate to the field of virtual test technology and are used to solve the false short circuit phenomenon of different sensitivity line models when simulation parameters are inaccurate. The method comprises collecting line model data to analyze whether the current line is stable, screening the lines according to the current line stability, screening out the lines with low stability, analyzing the reliability of the current line model by fuzzy reasoning, analyzing the accuracy of the simulation model by logical regression calculation results, scoring the line model by comprehensively considering the reliability of the line model and the accuracy of the simulation model, adjusting the simulation parameters of the line model marked as low according to the scoring results and the results of the logical regression calculation, setting the adjustment ratio by the results of the logical regression calculation, adjusting the simulation parameters according to the adjustment ratio to prevent the influence caused by the false short circuit phenomenon of the line model and other sensitivity problems, thereby improving the accuracy of the virtual test.

Description

Technical Field

[0001] The present invention relates to the field of virtual testing technology, and more specifically, to a method and system for checking open and short circuits in a circuit board design layout. Background Art

[0002] Virtual testing technology is a circuit testing method based on simulation models. It simulates real circuits through simulation model construction and test environment construction to help users analyze various circuit conditions. The application of virtual testing technology in circuit board design layout open and short circuit inspection can improve work efficiency and greatly help circuit troubleshooting.

[0003] The prior art has the following deficiencies:

[0004] In the past, when performing virtual testing on circuit board design drawings to check for open and short circuits, it was necessary to set simulation parameters and then perform simulation tests. When the simulation parameters were inaccurate, circuit models with different sensitivities would experience false short circuits and other phenomena, which would cause misjudgment of the design and lead to various chain problems.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above defects of the prior art, an embodiment of the present invention provides a circuit board design layout open and short circuit inspection method and system, which adjusts the circuit simulation parameters by analyzing the difference between the real circuit and the model circuit to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A circuit board design layout open and short circuit inspection system includes a data acquisition module, a circuit screening module, a data processing module and a parameter adjustment module, and the modules are signal connected;

[0009] The data acquisition module is used to collect line model data and send the line model data to the line screening module;

[0010] The line screening module receives the line model data and analyzes whether the line is stable according to the line model data. If the line stability is low, the line screening module marks the line and transmits the line mark to the data acquisition module and sends the calculated stability coefficient to the data processing module. After confirming the line mark, the data acquisition module collects the marked line model component data and sends it to the data processing module.

[0011] The data processing module uses fuzzy reasoning to analyze the reliability of the line model based on the stability coefficient and the component data and collects the system operation data. It uses the logistic regression method to analyze the accuracy of the simulation model based on the stability coefficient and the system operation data. It uses the line model reliability and the simulation model accuracy to score the line model, and sends the scoring results and the logistic regression calculation results to the parameter modulation module.

[0012] The parameter adjustment module is used to receive the scoring results and logistic regression calculation results transmitted by the data processing module, adjust the simulation parameters of the line model marked as low score, set the adjustment ratio through the logistic regression calculation result, and adjust the simulation parameters according to the adjustment ratio.

[0013] In a preferred embodiment, the line model data includes line model sensitivity and pseudo model accuracy, and the specific steps of calculating line model sensitivity are as follows:

[0014] The data acquisition module performs sensitivity tests on the lines by automatically inputting voltage to the lines and detecting the wire inductance. The data acquisition model collects multiple lines as sample lines and inputs the same voltage to each of them to detect the wire inductance. The wire inductance is then normalized using a normalization formula. The result of the normalized wire inductance is used as the line model sensitivity. All line model sensitivities calculated through sample lines are combined into a sensitivity data set.

[0015] In a preferred embodiment, the data acquisition module calculates the accuracy of the pseudo model in the following specific steps:

[0016] When the data acquisition module obtains the virtual test results, the virtual circuit model is powered on, and the output results are recorded and compared with the results of the actual system test. If the results are consistent, they are marked as successful; the ratio of the number of lines marked as successful to the number of sample lines is used as the accuracy of the virtual model.

[0017] In a preferred embodiment, the line screening module determines whether to mark the current line in the following specific steps:

[0018] The difference between the accuracy of the sample line model and the average value of the sensitivity data set is set as the line stability threshold;

[0019] The difference between the line model accuracy and the line model sensitivity is used as the line stability coefficient, and the line stability coefficient is compared with the line stability threshold to determine whether to mark the current line;

[0020] If the line stability coefficient exceeds the stability threshold, the current line stability is judged to be high and it is classified as a low-sensitivity line model; if the line stability coefficient is lower than the stability threshold, the current line stability is judged to be low and it is classified as a high-sensitivity line model and marked.

[0021] In a preferred embodiment, the component data includes the line resistance change rate and the line material insulation strength, and the line screening module uses fuzzy reasoning to analyze the reliability of the line model to define the line resistance change rate and the line material insulation strength as input variables, and divides them into different fuzzy sets respectively;

[0022] The line model reliability is defined as the output variable and divided into fuzzy sets;

[0023] Formulate fuzzy rules based on the line resistance change rate, line material insulation strength, and line model reliability;

[0024] Fuzzy reasoning is performed based on fuzzy rules to determine the reliability of the line model.

[0025] In a preferred embodiment, when obtaining the model result deviation, the data processing module connects the virtual line model and the actual line to the same voltage, detects the virtual line model and the actual line electric power respectively, and takes the absolute value of the difference as the result deviation. The data processing module automatically sets multiple groups of different voltages to calculate the result deviation respectively, takes the average value as the model result deviation, normalizes the model result deviation and marks it, establishes a logistic regression formula based on the received line stability coefficient, and analyzes the accuracy of the simulation model according to the logistic regression calculation results.

[0026] In a preferred embodiment, the data processing module analyzes the accuracy of the simulation model and scores the line model in the following specific steps:

[0027] When the logistic regression calculation result exceeds the preset logistic regression threshold, the simulation model is judged to have high accuracy, otherwise, the simulation model is judged to have low accuracy;

[0028] If the reliability of the current line model is high and the simulation model is accurate, the current line model score is marked as high, otherwise the current line model is marked as low.

[0029] In a preferred implementation, the specific process of the parameter adjustment module adjusting the current line simulation parameters is as follows:

[0030] The parameter adjustment module receives the current line model scoring results and logistic regression calculation results transmitted by the data processing module for preliminary judgment. If the current line model is marked as a high score, no simulation parameter adjustment is required. If the current line model is marked as a low score, the difference between 1 and the logistic regression calculation result is set as the adjustment ratio, and the simulation parameters are adjusted according to the adjustment ratio.

[0031] A circuit board design layout open and short circuit inspection method, used to implement the above-mentioned circuit board design layout open and short circuit inspection system, characterized in that it includes the following steps:

[0032] Step S1, collecting line model data;

[0033] Step S2, calculating the stability coefficient according to the line model data and analyzing whether the line is stable. If the line stability is low, collecting component data and system operation data;

[0034] Step S3, analyzing the reliability of the current line model using fuzzy reasoning according to the component data, analyzing the accuracy of the simulation model using a logistic regression method according to the line model data and the system operation data, and scoring and marking the line model based on the line model reliability and the simulation model accuracy;

[0035] Step S4, adjusting simulation parameters of the line model marked as low score, setting an adjustment ratio using the calculation result obtained by the logistic regression method, and adjusting the simulation parameters according to the adjustment ratio.

[0036] The technical effects and advantages of the circuit board design layout open and short circuit inspection method and system of the present invention are as follows:

[0037] The present invention collects line model data, analyzes the line model sensitivity according to the line model data and classifies them, takes the high-sensitivity line model as the marked line model, collects the marked line model component data and system operation data, analyzes the marked line model reliability according to the component data, analyzes the simulation parameter accuracy using the system operation data, scores the marked line model based on the line model reliability and the simulation parameter accuracy, and if the marked line model score is low, adjusts the simulation parameters according to the system operation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram of the structure of a circuit board design layout open and short circuit inspection system of the present invention.

[0039] Figure 2 The present invention is a flow chart of a circuit board design layout open and short circuit inspection method. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] The present invention collects line model data, analyzes the line model sensitivity according to the line model data and classifies them, takes the high-sensitivity line model as the marked line model, collects the marked line model component data and system operation data, analyzes the marked line model reliability according to the component data, analyzes the simulation parameter accuracy using the system operation data, scores the marked line model based on the line model reliability and the simulation parameter accuracy, and if the marked line model score is low, adjusts the simulation parameters according to the system operation data.

[0042] Embodiment 1, a circuit board design layout open and short circuit inspection system, such as Figure 1 As shown, it includes: a data acquisition module, a line screening module, a data processing module and a parameter adjustment module, and the modules are connected by signals.

[0043] The functions of each module are as follows:

[0044] The data acquisition module is used to collect line model data and component data. The line model data includes line model sensitivity and pseudo-model accuracy. The data acquisition module detects the line model sensitivity by performing sensitivity tests on the line, and calculates the pseudo-model accuracy using multiple virtual test results and actual system test results, and sends the detected line model sensitivity and model accuracy to the line screening module. The line screening module selects and marks the line and transmits it back to the data acquisition module. The data acquisition module collects the marked line model component data after confirming the line mark. The component data includes the line resistance change rate and the line material insulation strength. The data acquisition module detects the circuit resistance change by controlling the line power-on time, calculates the current line resistance change rate using the resistance at different power-on time points and adjacent time points and records it, visits the line material manufacturer's official website to obtain the current line material insulation strength and sends the collected component data to the data processing module.

[0045] The line screening module receives the line model sensitivity and the pseudo-model accuracy to calculate the line stability coefficient and the line stability threshold, and calculates the current line stability coefficient through the current line model sensitivity and the current pseudo-model accuracy to compare with the line stability threshold to analyze whether the current line is stable. If the current line stability is low, the line screening module marks the current line and transmits the line mark to the data acquisition module and sends the calculated stability coefficient to the data processing module.

[0046] The data processing module is used to obtain system operation data and score the line model, wherein the system operation data is the line stability coefficient and the model result deviation. The data processing module receives component data and uses fuzzy reasoning to analyze the reliability of the current line model based on the current line resistance change rate and the current line material insulation strength. In addition, the data processing module automatically calculates the model result deviation based on the virtual test results and the actual system test results. The data processing module uses the logistic regression method to calculate the line stability coefficient and the model result deviation, analyzes the accuracy of the simulation model through the logistic regression calculation results, scores the line model based on the line model reliability and the simulation model accuracy, and sends the scoring results and the logistic regression calculation results to the parameter adjustment module.

[0047] The parameter adjustment module is used to receive the scoring results and logistic regression calculation results transmitted by the data processing module, adjust the simulation parameters of the line model marked as low score, set the adjustment ratio according to the logistic regression calculation results, and adjust the simulation parameters according to the adjustment ratio to reduce the line analysis errors caused by the sensitivity of the simulation parameters.

[0048] It should be noted that the model sensitivity is the degree of influence of a small change in the input parameters of the virtual model on the model output. The lower the sensitivity of the line model, the higher its stability. The accuracy of the pseudo-model is to compare whether the output results of the virtual model are consistent with the actual model. The higher the accuracy of the pseudo-model, the higher its stability. The line resistance change rate is the speed of change of the line resistance under the influence of temperature. The higher the line resistance change rate, that is, the longer the passing time, the higher the degree of resistance suppression current, and the lower the reliability of the line model. The insulation strength of the line material affects the power loss when the line is energized. The lower the insulation strength of the line material, the more power loss when the line is energized, and the lower the reliability of the line model. The line stability coefficient reflects the stability of the line. The higher the line stability and the smaller the deviation of the model results, the higher the accuracy of the simulation model.

[0049] The specific steps for sensitivity testing and obtaining the accuracy of the pseudo-model in the data acquisition module are as follows:

[0050] When the data acquisition module performs sensitivity testing on the line, it automatically inputs voltage to the line and detects the inductance of the wire. It should be explained that the inductance of the wire is the magnetic field generated by the current flowing through the wire. This magnetic field will generate an induced voltage inside the wire to limit the short-circuit current. The higher the line wire inductance under different voltages, the higher the line sensitivity. The data acquisition model collects enough lines as sample lines and inputs the same voltage to detect the wire inductance. The wire inductance is normalized through the normalization formula, and the result of the normalized wire inductance is used as the line model sensitivity. The normalization formula can be formula: ,in is the wire inductance, is the normalized result of the corresponding wire inductance, is the minimum value of the wire inductance in the sample circuit, is the maximum value of the wire inductance in the sample line. All line model sensitivities calculated through the sample line are combined into a sensitivity data set.

[0051] When the data acquisition module obtains the virtual test results, it energizes the virtual line model, records the output results and compares them with the results of the actual system test. If the results are consistent, it is marked as successful. It should be explained that the actual system test is to energize the actual line, and the output result can be short circuit or non-short circuit. When the output result of the virtual line model is energized and the result of the actual line is energized is the same, the result is marked as successful. The accuracy of the sample line pseudo model can be calculated by the formula: ,in is the accuracy of the pseudo model, r is the number of lines marked as successful, and n is the number of sample lines.

[0052] It should be noted that when the data acquisition module collects data for the current line, the sensitivity of the current line model is calculated in the same way. The accuracy of the current line pseudo-model can be calculated by setting multiple different voltages for the current line to energize the virtual line model and the actual line, and using the same formula to calculate the accuracy of the pseudo-model , where r is the number of times marked as successful and n is the total number of setup power-ups.

[0053] After receiving the sensitivity data set and the accuracy of the pseudo model, the line screening module performs weighted summation to calculate the line stability coefficient and the line stability threshold. The line stability threshold can be obtained by weighted summation of the average value of the calculated sensitivity data set and the accuracy of the pseudo model of the sample line. The formula can be: , where b is the line stability threshold, is the average value of the sensitivity data set, is the accuracy of the simulated model for the sample line.

[0054] The line stability coefficient can be calculated by weighted summing the sensitivity of the current line model and the accuracy of the current line pseudo model. The formula is: ,in is the line stability coefficient, m is the sensitivity of the current line model, is the accuracy of the current line model.

[0055] The line screening module determines whether to mark the current line by comparing the line stability coefficient and the line stability threshold. , that is, the line stability coefficient exceeds the stability threshold, and the current line stability is judged to be high, and it is classified as a low-sensitivity line model; if , that is, the line stability coefficient is lower than the stability threshold, and the current line stability is judged to be low. It is classified as a highly sensitive line model and marked. The line screening module sends the marking result to the data acquisition module and sends the sensitivity of the current line model to the data processing module.

[0056] It should be noted that the formula and method for calculating the line stability coefficient and the line stability threshold are not unique. The above formulas can be adjusted according to actual conditions and will not be elaborated here.

[0057] After receiving the marking results, the data acquisition module collects the circuit model component data in the following specific steps:

[0058] The data acquisition module automatically selects a period of time to energize the current line, selects multiple time points with the same time interval under the same voltage to detect the line resistance, subtracts the line resistance at adjacent time points to obtain multiple resistance changes, and takes the average value of the resistance change and divides it by the adjacent time interval to obtain the resistance change rate.

[0059] The data acquisition module sets different time intervals and uses the same voltage to repeat the operation, obtains multiple resistance change rates and takes the average value as the current line resistance change rate. After accessing the official website of the line material manufacturer to obtain the insulation strength of the current line material, the component data is sent to the data processing module.

[0060] It should be noted that the official website of the circuit material manufacturer is a website that provides various circuit materials. Data and information on various circuit materials can be obtained from the official website of the circuit material manufacturer, including the insulation strength of various circuit materials.

[0061] The data processing module uses fuzzy reasoning to analyze the reliability of the current line model. The specific steps are as follows:

[0062] The data processing module receives the component data and defines the current line resistance change rate and the current line material insulation strength as input variables, and divides them into different fuzzy sets respectively.

[0063] For example, "Fast", "Slow" for the current line resistance change rate, "High", "Low" for the current line material insulation strength.

[0064] Define the reliability of the current line model as the output variable and divide it into fuzzy sets such as "Yes" and "No" for the reliability of the current line model.

[0065] Formulate a set of fuzzy rules to determine the relationship between different input variables and output variables. The formulation of fuzzy rules can be based on professional knowledge or a large amount of experimental data. For example:

[0066] The current line resistance change rate is marked as R, the current line material insulation strength is marked as I, and the current line model reliability is marked as K.

[0067] Rule 1: IF (R is Slow) AND (I is High) THEN (K is Yes)

[0068] Rule 2: IF (R is Fast) AND (I is Low) THEN (K is No) ...

[0070] When the output result is "Yes", it is judged that the reliability of the current line model is high; when the output result is "No", it is judged that the reliability of the current line model is low.

[0071] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, this example uses two fuzzy sets as an example, but in fact it can also be divided into two or more sets, so as to better evaluate the reliability of the line model according to different situations. In addition, for the judgment of the current line resistance change rate and the current line material insulation strength, the threshold can be set according to the actual situation. For example, if the current line resistance change rate exceeds , it is marked as "Fast", if the insulation strength of the current line material exceeds , marked as "High" etc., and no analysis is done here.

[0072] The data processing module calculates the deviation of the model results, uses the logistic regression method to analyze the accuracy of the simulation model, and scores the line model based on logical reasoning. The specific steps are as follows:

[0073] When obtaining the model result deviation, the data processing module will automatically connect the virtual line model and the actual line to the same voltage to detect the virtual line model and the actual line power respectively and take the absolute value as the result deviation. The data processing module automatically sets multiple groups of different voltages to calculate the result deviation respectively and takes the average value as the model result deviation. The normalization formula normalizes it and marks it as , the comprehensive received line stability coefficient Build the logistic regression formula: , where q is the result of logistic regression calculation used to classify the accuracy of the simulation model, is the natural base, and y is the intermediate variable, which can be represented by the following companies: , where y is affected by the model result deviation and the line stability coefficient a. When the model result deviation is smaller or the line stability coefficient is larger, y is larger and the logistic regression calculation result is The bigger, the When the preset logistic regression threshold is exceeded, the simulation model is judged to have high accuracy, otherwise, it is judged to have low accuracy.

[0074] If the reliability of the current line model is high and the simulation model is accurate, the current line model score is marked as high, otherwise the current line model is marked as low. Sent to the parameter adjustment module.

[0075] It should be noted that the logistic regression threshold involved in the above steps can be set according to the actual situation. For example, the logistic regression threshold is set to 0.2. When it exceeds 0.2, the simulation model is judged to be highly accurate. There is no unique method for analyzing the accuracy of the simulation model and the scoring logical reasoning method. This example only provides one method for implementation.

[0076] The specific process of the parameter adjustment module adjusting the current line simulation parameters is as follows:

[0077] The parameter adjustment module receives the current line model scoring results and the logistic regression calculation results transmitted by the data processing module for preliminary judgment. If the current line model is marked as high, no simulation parameter adjustment is required. If the current line model is marked as low, the adjustment ratio is set according to the logistic regression calculation results. The adjustment ratio formula can be ,in To adjust the ratio, the simulation parameters are adjusted using the adjustment ratio. The simulation parameters here may be the simulation time step, the fault duration, etc. For example, the simulation time step may be adjusted by the formula: ,in is the adjusted simulation time step, if 50ns, is 0.1, then It is 45ns.

[0078] It should be noted that the simulation time step is the discrete time point in circuit simulation that determines the circuit changes during the simulation process, that is, the time directly from the circuit state changing from one time point to the next time point. The smaller the simulation time step, the more accurate the simulation result, but the simulation time will be longer as the amount of calculation increases. By setting the adjustment ratio according to the results of the logistic regression calculation, reasonably reducing the simulation time step, and adjusting the simulation parameters, the error can be reduced to the greatest extent.

[0079] Embodiment 2, a circuit board design layout open short circuit inspection method, such as Figure 2 As shown, the following steps are included:

[0080] Step S1, collecting line model data.

[0081] Step S2, calculate the stability coefficient according to the line model data and analyze whether the line is stable. If the line stability is low, collect component data and system operation data.

[0082] Step S3, using fuzzy reasoning to analyze the reliability of the current line model according to the component data, using the logistic regression method to analyze the accuracy of the simulation model according to the line model data and the system operation data, and scoring and marking the line model based on the reliability of the line model and the accuracy of the simulation model.

[0083] Step S4, adjusting simulation parameters of the line model marked as low score, setting an adjustment ratio using the calculation result obtained by the logistic regression method, and adjusting the simulation parameters according to the adjustment ratio.

[0084] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0085] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0086] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0087] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0088] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A circuit board design layout open and short circuit inspection system, including a data acquisition module, a circuit screening module, a data processing module and a parameter adjustment module, and the signal connections between the modules; The data acquisition module is used to collect line model data and send the line model data to the line screening module; The line screening module receives the line model data and analyzes whether the line is stable according to the line model data. If the line stability is low, the line screening module marks the line and transmits the line mark to the data acquisition module and sends the calculated stability coefficient to the data processing module. After confirming the line mark, the data acquisition module collects the marked line model component data and sends it to the data processing module. The data processing module uses fuzzy reasoning to analyze the reliability of the line model based on the stability coefficient and the component data and collects the system operation data. It uses the logistic regression method to analyze the accuracy of the simulation model based on the stability coefficient and the system operation data. It uses the line model reliability and the simulation model accuracy to score the line model, and sends the scoring results and the logistic regression calculation results to the parameter modulation module. The parameter adjustment module is used to receive the scoring results and logistic regression calculation results transmitted by the data processing module, adjust the simulation parameters of the line model marked as low score, set the adjustment ratio according to the logistic regression calculation result, and adjust the simulation parameters according to the adjustment ratio; The system operation data include the line stability coefficient and the model result deviation.

2. A circuit board design layout open and short circuit inspection system according to claim 1, characterized in that: The line model data includes line model sensitivity and pseudo-model accuracy. The specific steps for calculating line model sensitivity are as follows: The data acquisition module performs sensitivity tests on the lines by automatically inputting voltage to the lines and detecting the wire inductance. The data acquisition model collects multiple lines as sample lines and inputs the same voltage to each of them to detect the wire inductance. The wire inductance is then normalized using a normalization formula. The result of the normalized wire inductance is used as the line model sensitivity. All line model sensitivities calculated through sample lines are combined into a sensitivity data set.

3. A circuit board design layout open and short circuit inspection system according to claim 2, characterized in that: The specific steps for the data acquisition module to calculate the accuracy of the pseudo model are as follows: When the data acquisition module obtains the virtual test results, the virtual circuit model is powered on, and the output results are recorded and compared with the results of the actual system test. If the results are consistent, they are marked as successful; the ratio of the number of lines marked as successful to the number of sample lines is used as the accuracy of the virtual model.

4. A circuit board design layout open and short circuit inspection system according to claim 1, characterized in that: The specific steps for the line screening module to determine whether to mark the current line are as follows: The difference between the accuracy of the sample line model and the average value of the sensitivity data set is set as the line stability threshold; The difference between the line model accuracy and the line model sensitivity is used as the line stability coefficient, and the line stability coefficient is compared with the line stability threshold to determine whether to mark the current line; If the line stability coefficient exceeds the stability threshold, the current line stability is judged to be high and it is classified as a low-sensitivity line model; if the line stability coefficient is lower than the stability threshold, the current line stability is judged to be low and it is classified as a high-sensitivity line model and marked.

5. A circuit board design layout open and short circuit inspection system according to claim 1, characterized in that: The component data includes the line resistance change rate and the line material insulation strength. The line screening module uses fuzzy reasoning to analyze the reliability of the line model and defines the line resistance change rate and the line material insulation strength as input variables, dividing them into different fuzzy sets respectively. The line model reliability is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules based on the line resistance change rate, line material insulation strength, and line model reliability; Fuzzy reasoning is performed based on fuzzy rules to determine the reliability of the line model.

6. A circuit board design layout open and short circuit inspection system according to claim 1, characterized in that: When obtaining the model result deviation, the data processing module connects the virtual line model and the actual line to the same voltage to detect the virtual line model and the actual line electric power respectively, and takes the absolute value of the difference as the result deviation. The data processing module automatically sets multiple groups of different voltages to calculate the result deviation respectively, takes the average value as the model result deviation, normalizes the model result deviation and marks it, establishes a logistic regression formula based on the received line stability coefficient, and analyzes the accuracy of the simulation model according to the logistic regression calculation results.

7. A circuit board design layout open and short circuit inspection system according to claim 6, characterized in that: The data processing module analyzes the accuracy of the simulation model and scores the line model in the following specific steps: When the logistic regression calculation result exceeds the preset logistic regression threshold, the simulation model is judged to have high accuracy, otherwise, the simulation model is judged to have low accuracy; If the reliability of the current line model is high and the simulation model is accurate, the current line model score is marked as high, otherwise the current line model is marked as low.

8. A circuit board design layout open and short circuit inspection system according to claim 7, characterized in that: The specific process of the parameter adjustment module adjusting the current line simulation parameters is as follows: The parameter adjustment module receives the current line model scoring results and logistic regression calculation results transmitted by the data processing module for preliminary judgment. If the current line model is marked as a high score, no simulation parameter adjustment is required. If the current line model is marked as a low score, the difference between 1 and the logistic regression calculation result is set as the adjustment ratio, and the simulation parameters are adjusted according to the adjustment ratio.

9. A circuit board design layout open and short circuit inspection method, based on a circuit board design layout open and short circuit inspection system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step S1, collecting line model data; Step S2, calculating the stability coefficient according to the line model data and analyzing whether the line is stable. If the line stability is low, collecting component data and system operation data; Step S3, analyzing the reliability of the current line model using fuzzy reasoning according to the component data, analyzing the accuracy of the simulation model using a logistic regression method according to the line model data and the system operation data, and scoring and marking the line model based on the line model reliability and the simulation model accuracy; Step S4, adjusting simulation parameters of the line model marked as low score, setting an adjustment ratio using the calculation result obtained by the logistic regression method, and adjusting the simulation parameters according to the adjustment ratio.

Images