Detection method of MI process in PCB production, control system and computer equipment

Abstract

The invention relates to the technical field of PCB production, in particular to a detection method and control system for an MI process in PCB production and computer equipment. According to the method, PCB key performance indexes are obtained through material characteristic data, then a performance attenuation curve is obtained, the service life of the PCB is predicted in advance, the problem of time hysteresis of finished product inspection is solved, then process parameter compliance values and process defect information are obtained according to processing process data, and the former is used for quantitative evaluation in the process evaluation stage; the method comprises the following steps: providing data for comprehensive evaluation, mining potential defect risks of a machining process, dynamically coupling and analyzing an amplification effect of environmental stress on process defects by combining process defect information and application environment parameters, calculating a reliability index value of a PCB, and finally calculating a comprehensive evaluation value through a process parameter compliance value and the reliability index value. And the reliability of the MI process is judged by comparing the preset threshold, so that the detection accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of PCB production, and particularly relates to a detection method, a control system and a computer device for the MI process in PCB production. Background Art

[0002] In the field of printed circuit board (PCB) manufacturing, Manufacturing Instructions (MI) refers to the normative documents that specifically guide production operations, and the MI process refers to the whole-process engineering management system with the MI document as the output target, covering manufacturing preparation activities such as technical analysis, process design, and collaborative review. For the quality control link of the MI process - "MI process detection", it refers to the systematic work of comprehensively verifying the accuracy, executability, and implementation compliance of the manufacturing instruction documents. The existing MI process detection methods are to conduct full-process coverage detection on the MI compilation, process review, production execution, final inspection stages, etc. through diversified means such as manual review and digital-assisted detection, which is the key defense line for ensuring the quality of PCB production and can effectively control the quality risks of each link from design to finished product.

[0003] However, the current MI process detection mechanism has significant drawbacks. The existing detection methods only independently verify around local goals (such as the integrity of design documents, compliance of single-process parameters, inspection of operation compliance, and quality determination of finished products) at different stages (such as compilation, process review, production execution, final inspection), without starting from the overall perspective of the entire PCB manufacturing process to discover the linkage effects of risks in each link, thus missing systematic problems that affect the long-term reliability of the PCB and resulting in inaccurate detection results. Summary of the Invention

[0004] The main object of the present invention is to provide a detection method, a control system and a computer device for the MI process in PCB production, aiming to solve the technical problems in the prior art.

[0005] The present invention proposes a detection method for the MI process in PCB production, including: Obtaining the design requirement information, material property data, and processing technology data of the PCB according to the MI document, and obtaining the application environment parameters according to the design requirement information; Obtaining the key performance indicators of the PCB according to the material property data, and obtaining the performance decay curve of the PCB according to the key performance indicators; Obtaining the process parameter compliance values and process defect information according to the processing technology data, wherein the process defect information includes first process defect information and second process defect information; Obtaining the process risk coefficient according to the first process defect information, the second process defect information, and the application environment parameters; Obtain the reliability index value of the PCB according to the process risk coefficient and the performance degradation curve; Obtain the comprehensive evaluation value of the MI process according to the reliability index value and the process parameter compliance value; Judge whether the comprehensive evaluation value is greater than a preset threshold: If the comprehensive evaluation value is greater than the preset threshold, it is determined that the overall MI process is reliable; If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the overall MI process is unreliable.

[0006] Preferably, the step of obtaining the key performance indicators of the PCB according to the material characteristic data includes: Obtain multiple performance indicators and performance parameter fluctuation ranges of the PCB according to the material characteristic data, wherein the performance indicators include glass transition temperature, thermal expansion coefficient, dielectric constant and water absorption rate, and the performance parameter fluctuation ranges include glass transition temperature range, thermal expansion coefficient range, dielectric constant fluctuation range and water absorption rate fluctuation range; Arrange and combine the multiple performance indicators to obtain a performance indicator coupling group; Obtain the performance life correlation data set of the PCB, and obtain the corresponding life prediction correlation group according to the performance life correlation data set and the performance indicator coupling group; Use Monte Carlo simulation to obtain the failure probability distribution range according to the performance parameter fluctuation range and the corresponding life prediction correlation group, and screen the performance indicators according to the multiple failure probability distribution ranges to obtain the key performance indicators.

[0007] Preferably, the step of obtaining the performance degradation curve of the PCB according to the key performance indicators includes: Obtain the performance sensitivity factor according to the key performance indicators, and obtain the performance sensitive parameters of the performance sensitivity factor according to the application environment parameters; Obtain the performance factor correlation data set, and perform correlation analysis on the performance sensitivity factor and the key performance indicators according to the performance factor correlation data set to obtain the influence factor sensitive data; Obtain the comprehensive sensitivity coefficient according to the influence factor sensitive data and the performance sensitive parameters; Obtain the initial performance degradation curve according to the life prediction correlation group corresponding to the key performance indicators, and correct the initial performance degradation curve according to the comprehensive sensitivity coefficient to obtain the performance degradation curve.

[0008] Preferably, the step of obtaining the process parameter compliance value and the process defect information according to the processing technology data includes: Obtain multiple processing technology parameters according to the described processing technology data; Obtain the production process limit parameter set; Obtain the customized requirement parameter set according to the described design requirement information, and obtain the processing parameter constraint set according to the customized requirement parameter set and the production process limit parameter set; Screen the processing technology parameters according to the processing parameter constraint set to obtain compliant process parameters and non-compliant process parameters, and obtain the process parameter compliance value according to the compliant process parameters and non-compliant process parameters; Obtain the first process defect information according to the non-compliant process parameters; Obtain the process defect history database, and obtain the second process defect information according to the process defect history database and the compliant process parameters.

[0009] Preferably, the step of obtaining the process risk coefficient according to the first process defect information, the second process defect information and the application environment parameters includes: Obtain multiple PCB defect types and defect type incidence rates according to the first process defect information and the second process defect information; Obtain multiple environmental impact factors and impact factor parameters according to the application environment parameters; Match multiple PCB defect types and the environmental impact factors to obtain a defect type - environmental factor association table, and obtain the environmental stress action list according to the defect type - environmental factor association table and the impact factor parameters; Obtain the potential deterioration mode of the PCB defect according to the environmental stress action list, and obtain the defect deterioration index of the PCB defect according to the potential deterioration mode; Obtain the process risk coefficient according to multiple defect deterioration indexes and the defect type incidence rate.

[0010] Preferably, the step of obtaining the reliability index value of the PCB according to the process risk coefficient and the performance decay curve includes: Obtain the actual predicted life of the PCB according to the performance decay curve, and obtain the curve slope sequence according to the performance decay curve; Obtain the slope fluctuation characteristic according to the curve slope sequence, and obtain the decay stability score value according to the slope fluctuation characteristic; Obtain the target life of the PCB according to the design requirement information, and obtain the reliability index value according to the target life, the actual predicted life, the decay stability score value and the process risk coefficient.

[0011] This application also provides a control system for the MI process in PCB production, including: The first acquisition module is used to acquire the design requirement information, material characteristic data, and processing technology data of the PCB according to the MI file, and acquire the application environment parameters according to the design requirement information; The second acquisition module is used to acquire the key performance indicators of the PCB according to the material characteristic data, and acquire the performance decay curve of the PCB according to the key performance indicators; The third acquisition module is used to acquire the process parameter compliance values and process defect information according to the processing technology data, wherein the process defect information includes first process defect information and second process defect information; The fourth acquisition module is used to acquire the process risk coefficient according to the first process defect information, the second process defect information, and the application environment parameters; The fifth acquisition module is used to acquire the reliability index value of the PCB according to the process risk coefficient and the performance decay curve; The sixth acquisition module is used to acquire the comprehensive evaluation value of the MI process according to the reliability index value and the process parameter compliance values; The judgment module is used to judge whether the comprehensive evaluation value is greater than a preset threshold: If the comprehensive evaluation value is greater than the preset threshold, it is determined that the MI process is overall reliable; If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the MI process is overall unreliable.

[0012] Preferably, the third acquisition module includes: The first acquisition unit is used to acquire a plurality of processing technology parameters according to the processing technology data; The second acquisition unit is used to acquire the production process limit parameter set; The third acquisition unit is used to acquire the customized requirement parameter set according to the design requirement information, and acquire the processing parameter constraint set according to the customized requirement parameter set and the production process limit parameter set; The screening unit is used to screen the processing technology parameters according to the processing parameter constraint set to obtain the compliant process parameters and non-compliant process parameters, and acquire the process parameter compliance values according to the compliant process parameters and non-compliant process parameters; The fourth acquisition unit is used to acquire the first process defect information according to the non-compliant process parameters; The fifth acquisition unit is used to acquire the process defect historical database, and acquire the second process defect information according to the process defect historical database and the compliant process parameters.

[0013] The present invention also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned detection method for the MI process in PCB production are implemented.

[0014] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned detection method for the MI process in PCB production are implemented.

[0015] The beneficial effects of the present invention are as follows: Through mandatory requirement extraction and verification, the integrity of the MI file is verified to avoid omission of key parameters. At the same time, application environment factors are incorporated into the PCB quality risk assessment to identify the amplification effect of the environment on process defects. Then, key performance indicators of the PCB are obtained using material characteristic data, and a performance decay curve is obtained to predict the PCB life in advance, solving the problem of "time lag" in finished product inspection. Then, compliance values of process parameters and process defect information are obtained based on processing technology data. The former is used for quantitative evaluation in the process review stage to provide data for comprehensive evaluation, and the latter mines the potential defect risks of the processing technology. Combining the process defect information with application environment parameters, the amplification effect of environmental stress on process defects is analyzed through dynamic coupling, and a process risk coefficient is calculated to quantify the risk of product failure due to process defects. Since the process risk coefficient reflects the probability of hidden defects and the performance decay curve reflects the durability of the PCB, the two form a closed loop, and based on this, the reliability index value of the PCB is calculated to achieve scientific evaluation and prediction of its reliability. Finally, according to the characteristics of the MI process, weights are assigned to the compliance values of process parameters that reflect the standardization of process execution and the reliability index values that reflect the reliability of process output to obtain a comprehensive evaluation value, which is compared with a preset threshold to determine whether the MI process is reliable. If the MI process is reliable, it can guide the batch production of PCBs; otherwise, production is suspended and traced for improvement. This method can identify the systematic risk of "qualified individually but failed in combination", making the MI process detection more proactive and scientific, and effectively improving the accuracy of MI process detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present invention.

[0017] Figure 2 It is a schematic structural diagram of the system according to an embodiment of the present invention.

[0018] Figure 3 It is a schematic internal structural diagram of a computer device according to an embodiment of the present application.

[0019] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] Such as Figure 1As shown, the present application provides a detection method for the MI process in PCB production, including: S1. Obtain the design requirement information, material property data, and processing technology data of the PCB according to the MI file, and obtain the application environment parameters according to the design requirement information; S2. Obtain the key performance indicators of the PCB according to the material property data, and obtain the performance decay curve of the PCB according to the key performance indicators; S3. Obtain the process parameter compliance values and process defect information according to the processing technology data, wherein the process defect information includes first process defect information and second process defect information; S4. Obtain the process risk coefficient according to the first process defect information, the second process defect information, and the application environment parameters; S5. Obtain the reliability index value of the PCB according to the process risk coefficient and the performance decay curve; S6. Obtain the comprehensive evaluation value of the MI process according to the reliability index value and the process parameter compliance values; S7. Determine whether the comprehensive evaluation value is greater than a preset threshold: If the comprehensive evaluation value is greater than the preset threshold, it is determined that the overall MI process is reliable; If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the overall MI process is unreliable.

[0022] As described in the above steps S1 - S7, the present invention obtains the design requirement information, material property data, and processing technology data of the PCB according to the MI file. Through forced requirement extraction and verification, it can verify whether the MI file is complete and avoid missing key parameters. If data is found to be missing, the problem in the MI compilation stage can be directly located. Among them, the design requirement information refers to the core design elements related to the specific technical requirements, functional indicators, and application scenarios of the PCB provided by the customer. The material property data refers to the physical, chemical, and electrical performance parameters of the raw materials used in PCB production (such as substrate materials, copper foils, etc.), including the coefficient of thermal expansion, dielectric constant, mechanical strength, etc. The processing technology data refers to the process parameters and operation specifications of each link in PCB production, including drilling parameters (hole diameter, rotation speed), electroplating thickness, etching accuracy, etc. The detection in the process review stage of the existing MI process usually targets whether the processing parameters of each processing procedure meet the standards. However, even if the processing parameters meet the standards, processing defects may still occur. During the actual use of the PCB, such defects will be further amplified due to the influence of the application environment, ultimately leading to the failure of the PCB performance. Therefore, further obtain the application environment parameters according to the design requirement information. Among them, the application environment parameters refer to the environmental conditions expected to be used for the PCB finished product, including temperature, humidity, vibration frequency, electromagnetic interference, etc. Incorporating the application environment factors into the MI full - process quality risk assessment system is beneficial to identifying the potential amplification effect of the environment on process defects. Then, obtain the key performance indicators of the PCB through the material property data. Among them, the key performance indicators refer to the performance indicators selected from multiple performance indicators through the above - mentioned analysis process and having the greatest impact on the service life of the PCB. And obtain the performance decay curve of the PCB through the key performance indicators. Among them, the performance decay curve refers to a curve used to reflect the dynamic decay process of the key performance of the PCB over time. Through the performance decay curve, the life performance of the PCB can be predicted in advance, rather than relying only on the post - verification in the finished product inspection stage of the MI process, which is beneficial to exposing the life defects of the PCB in the initial stage of the MI process detection, thus solving the "time lag" problem of the current detection. Immediately afterwards, obtain the process parameter compliance value and process defect information according to the processing technology data. Among them, the process parameter compliance value refers to a value used to quantify the degree of compliance between the process parameters of the processing procedure and the design specifications. The process defect information refers to the relevant information on the defects occurring in the PCB caused by the deviation of the process parameters. By obtaining the process parameter compliance value, a quantitative assessment of the process review stage in the MI process detection can be achieved, and basic data support for the comprehensive assessment of the subsequent MI process can be provided. By obtaining the process defect information, the potential defect risks hidden under the surface of the processing technology can be excavated. The process defect information includes the first process defect information and the second process defect information. Among them, the first process defect information refers to the potential defect information directly caused by non - compliant parameters, and the second process defect information refers to the hidden defect information that may be caused by the combination of compliant parameters under specific conditions.Then, by combining the first process defect information, the second process defect information, and the application environment parameters, through dynamic coupling analysis of process defects and environmental stresses, the potential amplification effect of application environment parameters on process defects is quantified, so as to scientifically evaluate the risk index of PCB processing process defects in the actual use scenario and obtain the process risk coefficient. The process risk coefficient refers to a quantitative value that comprehensively reflects the overall risk level of product failure that may be caused by process defects in the PCB manufacturing process considering the influence of environmental factors. Since the process risk coefficient reflects the probability of latent defects introduced in the PCB production process and determines the potential risk of early PCB failures, while the performance decay curve depicts the law of the PCB's performance decline over time in actual use and reflects its durability under environmental stresses, there is a causal closed-loop of "defect-driven degradation and degradation amplifying risk" between the two, that is, PCB process defects will accelerate the performance decay of the PCB, and the performance decline of the PCB will further expose the potential defects of the PCB. Therefore, the reliability index value of the PCB is obtained by combining the process risk coefficient and the performance decay curve. The reliability index value refers to the value calculated to quantify the performance reliability of the PCB. Through the reliability index value, the reliable degree of the PCB's full-life cycle performance can be reflected, so as to achieve scientific evaluation and accurate prediction of the PCB's reliability. Finally, since the compliance value of process parameters reflects the execution normality of the MI process itself, and the reliability index value reflects the reliability of the MI process output, different weights are assigned to the compliance value of process parameters and the reliability index value according to the characteristics of the MI process. For example, for mature processes, more emphasis is placed on the result (higher weight for the reliability index) because the process has been verified through history. For new processes, more emphasis is placed on the process (higher weight for process parameters) because there is insufficient result data and it is necessary to ensure the execution normality first. The comprehensive evaluation value is calculated based on the differential weight allocation method according to the characteristics of the MI process. The comprehensive evaluation value refers to the value used to evaluate the overall reliability of the MI process. Finally, the comprehensive evaluation value is compared with the preset threshold. If the comprehensive evaluation value is greater than the preset threshold, it is determined that the MI process is overall reliable and mass production of the PCB can be guided through the MI. If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the MI process is overall unreliable, indicating that there are systematic risks in the MI process (such as unreasonable setting of processing parameters, etc.), and production needs to be suspended and traced for improvement. By identifying such systematic risks of "qualified individually but failed in combination", the detection of the MI process can be made more pre-emptive and scientific, thus improving the accuracy of the MI process detection.,

[0023] In one embodiment, step S21 of obtaining the key performance indicators of the PCB according to the material property data includes: S211. Obtain multiple performance indicators and performance parameter fluctuation ranges of the PCB according to the material property data, where the performance indicators include glass transition temperature, coefficient of thermal expansion, dielectric constant, and water absorption rate, and the performance parameter fluctuation ranges include glass transition temperature range, coefficient of thermal expansion range, dielectric constant fluctuation range, and water absorption rate fluctuation range; S212. Arrange and combine the multiple performance indicators to obtain a performance indicator coupling group; S213. Obtain a performance life correlation data set of the PCB, and obtain a corresponding life prediction correlation group according to the performance life correlation data set and the performance indicator coupling group; S214. Use Monte Carlo simulation to obtain a failure probability distribution range according to the performance parameter fluctuation range and the corresponding life prediction correlation group, and screen the performance indicators according to the multiple failure probability distribution ranges to obtain key performance indicators.

[0024] As described in the above steps S211 - S214, the present invention extracts performance indicators that directly affect the PCB life from the material property data. Here, the performance indicators refer to the index names for characterizing the core performance of the PCB material, which are the key dimensions for measuring the PCB performance, such as glass transition temperature, coefficient of thermal expansion, dielectric constant, and water absorption rate. And the fluctuation range of the performance parameters corresponding to each performance indicator is obtained. Here, the fluctuation range of the performance parameters refers to the fluctuation range of the parameter values corresponding to each performance indicator, such as the glass transition temperature range, the coefficient of thermal expansion range, the dielectric constant fluctuation range, and the water absorption rate fluctuation range. The natural fluctuation of the material properties can be reflected by the fluctuation range of the performance parameters. Then, multiple single performance indicators are arranged and combined to obtain a performance indicator coupling group. Here, the performance indicator coupling group refers to the combined unit formed by arranging and combining multiple performance indicators, which is used to simulate the influence of the interaction of multiple performance indicators on the PCB life. For example, the glass transition temperature determines the mechanical strength and thermal fatigue resistance of the PCB at high temperatures. The mismatch of the coefficient of thermal expansion will cause thermal cycling stress, resulting in delamination or via copper fracture. Therefore, the coupling group composed of the glass transition temperature and the coefficient of thermal expansion can be used to evaluate the thermal fatigue life of the PCB; the water absorption rate affects the electrochemical migration rate in the humid and hot environment, and the dielectric constant affects the impedance characteristics. Therefore, the coupling group composed of the water absorption rate and the dielectric constant can be used to evaluate the electrochemical migration life of the PCB. Subsequently, a performance - life correlation data set is obtained. Here, the performance - life correlation data set refers to the data set recording the corresponding relationship between the performance indicator data and the service life data of the PCB material, which is used to analyze the influence law of the change of performance indicators on the life. And based on the performance - life correlation data set, a mathematical mapping between the performance indicator coupling group and life prediction is established to obtain a life prediction correlation group. Here, the life prediction correlation group refers to the life prediction model established for each performance indicator coupling group based on the performance - life correlation data set, which is used to quantify the life change trend under the interaction of multiple indicators. For example, the thermal fatigue life prediction model constructed for the glass transition temperature and the coefficient of thermal expansion, the electrochemical migration life prediction model constructed for the water absorption rate and the dielectric constant, etc. Immediately afterwards, the Monte Carlo simulation technique is used to simulate the random combination of performance parameters within their fluctuation ranges, and the failure probability distribution range is calculated. Here, the failure probability distribution range refers to the numerical distribution range of the failure probability of the PCB under specific working conditions obtained by calculation. For example, taking the parameters of the glass transition temperature and the coefficient of thermal expansion within their respective fluctuation ranges as input parameters and substituting them into the thermal fatigue life prediction model, the failure probability distribution range of the thermal fatigue life can be obtained as follows: within 500 - 800 hours of use, the failure probability is 10% - 25%;Within 1000 - 1500 hours of use, the failure probability increases to 40% - 60%. Taking the parameters of water absorption rate and dielectric constant within the fluctuation range as input values and substituting them into the electrochemical migration life prediction model, the failure probability distribution range of electrochemical migration can be obtained as follows: within 300 - 600 hours of use, the probability of short - circuit caused by electrochemical migration is 5% - 15%; within 800 - 1200 hours of use, the failure probability increases to 20% - 35%. Through this dynamic simulation method, the limitation of the traditional "fixed - value inspection" is broken through, and the dynamic prediction of the PCB life is realized. Then, the performance indicators are screened according to multiple failure probability distribution ranges to obtain the key performance indicators. When processing multiple failure probability distribution ranges, first judge whether the failure times of different failure modes are concentrated in the key stages of the product design life. Assuming the PCB design life is 5000h, then: for pre - electrochemical migration failure (1000h - 3000h), it mainly occurs in the early stage; for thermal fatigue failure (2000h - 4000h), it partially overlaps with the middle and early stages of the design life; for mechanical failure (3000h - 6000h), it overlaps with the end stage of the design life. Then it can be concluded that if within the design life (such as before 5000h), the overlapping degree of the time intervals of thermal fatigue failure and mechanical failure is the highest, then these two types of failure modes need to be preferentially investigated. Then determine which failure mode has the highest probability of occurrence within the same time period and determine it as the dominant failure mode. For example, if thermal fatigue failure is the dominant failure mode, then the glass transition temperature and thermal expansion coefficient corresponding to thermal fatigue failure are the key performance indicators. This method realizes the transformation of the PCB life prediction from the traditional "post - detection" mode to the "pre - prediction" mode, can identify the combination of highly sensitive performance indicators that may cause failure risks at the initial stage of the MI process detection. Based on this, the material selection plan can be optimized in advance to effectively avoid potential problems in the production manufacturing and product application processes.

[0025] In one embodiment, step S22 of obtaining the performance decay curve of the PCB according to the key performance indicators includes: S221. Obtain a performance sensitivity factor according to the key performance indicators, and obtain a performance sensitivity parameter of the performance sensitivity factor according to the application environment parameters; S222. Obtain a performance factor association data set, and perform a correlation analysis on the performance sensitivity factor and the key performance indicators according to the performance factor association data set to obtain influence factor sensitive data; S223. Obtain a comprehensive sensitivity coefficient according to the influence factor sensitive data and the performance sensitivity parameter; S224. Obtain an initial performance decay curve according to the life prediction association group corresponding to the key performance indicators, and correct the initial performance decay curve according to the comprehensive sensitivity coefficient to obtain a performance decay curve.

[0026] As described in the above steps S221 - S224, the present invention can construct a multi - stress coupling analysis framework by obtaining performance - sensitive factors that have a significant impact on key performance indicators. Among them, the performance - sensitive factor refers to external environmental factors that have a significant impact on the key performance indicators of the PCB, such as temperature, humidity, vibration, etc. Then, according to the application environment parameters, the performance - sensitive parameters of the performance - sensitive factors are obtained, so as to quantify the action intensity of the performance - sensitive factors. Among them, the performance - sensitive parameter refers to the specific quantification value of the environmental factor, such as temperature value, humidity percentage, vibration frequency, etc. In this way, it is possible to break through the traditional single - environmental - stress analysis mode, dynamically associate multiple performance - sensitive factors through key performance indicators, identify composite stress effects, such as the synergistic effect of high temperature and high humidity. Subsequently, a performance - factor association data set is obtained. Among them, the performance - factor association data set refers to the structured data recording the degradation relationship between environmental stress and performance indicators. And according to the performance - factor association data set, using a correlation analysis method, such as Pearson correlation analysis, taking the performance - sensitive factor and the key performance indicator as the analysis objects, calculating the correlation coefficient between them, judging their correlation, and obtaining the influence - factor sensitive data according to the correlation analysis result. Among them, the influence - factor sensitive data refers to the quantified weight of the performance - sensitive factor in different environments on the key performance. Then, the influence - factor parameters are normalized, and combined with the influence - factor sensitive data, a comprehensive sensitive coefficient is obtained by using the weighted aggregation method. Among them, the comprehensive sensitive coefficient refers to the correction coefficient reflecting the combined action of multi - stresses in the actual environment. In this way, by synthesizing the environmental - factor sensitivity and the actual parameter values, a unified correction coefficient is generated, which can dynamically quantify the acceleration effect of environmental stress on the PCB performance, providing a scientific basis for the subsequent attenuation - curve correction. Finally, a life - prediction model matching the key performance indicator is extracted from the life - prediction association group as the initial performance - degradation curve. Among them, the initial performance - degradation curve refers to the theoretical performance - degradation trajectory of the PCB in an ideal environment. And according to the comprehensive sensitive coefficient, the initial performance - degradation curve is corrected to obtain the performance - attenuation curve. Through the correction curve, the full - process interaction of materials and environment can be reflected, solving the problem of "local verification and ignoring linkage" of traditional methods, and fundamentally solving the defect of "ignoring systematic problems" in traditional MI detection, realizing the leap from "passive compliance inspection" to "active reliability regulation".

[0027] In one embodiment, step S3 of obtaining the process - parameter compliance value and process - defect information according to the processing - technology data includes: S31. Obtain a plurality of processing - technology parameters according to the processing - technology data; S32. Obtain a set of production - process limit parameters; S33. Obtain a customized requirement parameter set according to the design requirement information, and obtain a processing parameter constraint set according to the customized requirement parameter set and the production process limit parameter set; S34. Screen the processing process parameters according to the processing parameter constraint set to obtain compliant process parameters and non-compliant process parameters, and obtain a process parameter compliance value according to the compliant process parameters and the non-compliant process parameters; S35. Obtain first process defect information according to the non-compliant process parameters; S36. Obtain a process defect history database, and obtain second process defect information according to the process defect history database and the compliant process parameters.

[0028] As described in the above steps S31-S36, the present invention can extract the core control parameters of each process in the PCB production process by acquiring multiple processing parameters, provide a data basis for subsequent compliance analysis, and then obtain a production process limit parameter set, wherein the production process limit parameter set refers to the parameter extreme value set of the actual production capacity of the factory and the standard requirements. The obtained production process limit parameter set can define the process capability boundary of the factory equipment and materials, and serve as a compliance criterion, and then obtain a customized demand parameter set according to the design requirement information, wherein the customized demand parameter set refers to the additional constraints on the process parameters imposed by the customer or design specification, and obtain a processing parameter constraint set in combination with the customized demand parameter set and the production process limit parameter set, wherein the processing parameter constraint set refers to a set of composite conditions that must be met in actual production. In this way, the problem of the disconnection between design requirements and production capacity in traditional methods can be solved, and then the processing parameter constraint set and the processing process parameters are compared item by item, and the processing process parameters that fully meet the requirements of the processing parameter constraint set are taken as compliant process parameters, and the processing process parameters that do not meet the requirements of the processing parameter constraint set are taken as non-compliant process parameters, and the number of compliant process parameters and non-compliant process parameters are determined according to the number of compliant process parameters and the number of non-compliant process parameters. The compliance value of the process parameters is obtained by the ratio of the number of process parameters. The compliance value of the process parameters can replace the traditional binary judgment of "qualified / unqualified", and the compliance level of the overall processing technology can be quantified by percentage. At the same time, when the compliance value of the process parameters is lower than the threshold (such as 90%), a high-risk warning is automatically triggered, which can directly locate the problem in the MI process review stage, and then the first process defect information is directly obtained from the non-compliant parameters. Production defects can be predicted in the MI stage without waiting for physical verification, and then the process defect history database is obtained. Among them, the process defect history database refers to a knowledge base that records actual defect cases of compliant parameter combinations, and the second process defect information is obtained based on the process defect history database and compliant process parameters. This method can effectively identify "compliant but high-risk" scenarios that are difficult to detect with traditional detection methods by deeply mining historical data, thereby revealing the hidden defect risks hidden under compliant parameters. Compared with the traditional method that only focuses on the explicit defects caused by non-compliant parameters, this method can innovatively realize the dual monitoring of defects caused by compliant and non-compliant parameters, significantly improving the accuracy and reliability of defect detection, and achieving full coverage of explicit and implicit defect risks.

[0029] In one embodiment, the step S4 of acquiring the process risk coefficient according to the first process defect information, the second process defect information and the application environment parameter includes: S41, acquiring multiple PCB defect types and defect type occurrence rates according to the first process defect information and the second process defect information; S42, obtaining a plurality of environmental influencing factors and influencing factor parameters according to the application environment parameters; S43. Match multiple PCB defect types with the environmental impact factors to obtain a defect type - environmental factor association table, and obtain an environmental stress action list according to the defect type - environmental factor association table and the impact factor parameters; S44. Obtain the potential deterioration mode of the PCB defect according to the environmental stress action list, and obtain the defect deterioration index of the PCB defect according to the potential deterioration mode; S45. Obtain the process risk coefficient according to multiple defect deterioration indices and the defect type incidence rate.

[0030] As described in the above steps S41 - S45, the present invention obtains the PCB defect types and the occurrence rates of the defect types by integrating the process defects of different processing technologies in the PCB processing flow. Among them, the PCB defect type refers to the category divided according to the cause and caused by the process defect. For example, if the process defect is the uneven thickness of the copper layer on the PCB hole wall, then the corresponding PCB defect type is hole copper crack; if the process defect is the deviation between the solder mask opening and the pad position, then the corresponding PCB defect type is solder mask deviation. The occurrence rate of the defect type refers to the frequency of occurrence of a certain defect type. Obtaining this information can identify the high - frequency defect types to optimize the process parameters preferentially. Subsequently, the environmental impact factors and the impact factor parameters are obtained. Among them, the environmental impact factor refers to the physical and chemical driving factors in the environmental parameters that directly act on the PCB defects, and the impact factor parameter refers to the quantitative value describing the action intensity of the environmental impact factor, so as to convert the static environmental data into dynamic stress indicators. Matching multiple PCB defect types and environmental impact factors, a defect type - environmental factor association table is obtained. Among them, the defect type - environmental factor association table is a corresponding relationship table describing which environmental factors play a dominant role in a specific defect type. For example, "electrochemical migration defect" corresponds to "humidity factor" and "bias factor". And according to the defect type - environmental factor association table and the impact factor parameters, an environmental stress action list is obtained, thereby establishing a mapping relationship between PCB defects and environmental factors. Among them, the environmental stress action list is a list recording the types of environmental stress and their parameter combinations endured by each defect type. By this method, a defect - environment coupling model can be introduced in the MI detection to identify long - term latent risks (such as slow dendrite growth in a humid and hot environment) ignored by traditional detection methods. Then, according to the environmental stress action list, the potential deterioration mode of the PCB defects is obtained. Among them, the potential deterioration mode refers to the possible development form of the PCB defects under the action of environmental stress. For example, "solder mask deviation → moisture absorption of the dielectric layer → decrease in insulation resistance → arc breakdown". Subsequently, based on a physical model (such as LSTM predicting the crack propagation rate), the deterioration process of the PCB defects is simulated to obtain the defect deterioration index of the PCB defects. Among them, the defect deterioration index is used to quantify the potential risk degree of the PCB defects evolving into functional failures under specific environmental stress. Finally, through the method of weighted aggregation, the process risk coefficient is obtained according to the defect deterioration index and the occurrence rate of the defect type. Through the process risk coefficient, the overall risk level of the full - process processing technology can be quantified, thus solving the problem of "seeing only the trees but not the forest" in traditional MI detection. For example, even if the defect rate of a single process meets the standard, if the multi - process defects cause synergistic deterioration in the environment (such as drilling burrs + insufficient electroplating jointly accelerating the fracture of the hole wall), then the PCB performance will still be at high risk. And this method converts the scattered local detection results into an overall reliability prediction, which is conducive to rising the local detection to the reliability prediction of the entire MI process.

[0031] In one embodiment, step S5 of obtaining the reliability index value of the PCB according to the process risk coefficient and the performance degradation curve includes: S51. Obtain the actual predicted life of the PCB according to the performance degradation curve, and obtain the curve slope sequence according to the performance degradation curve; S52. Obtain the slope fluctuation characteristics according to the curve slope sequence, and obtain the attenuation stability score value according to the slope fluctuation characteristics; S53. Obtain the target life of the PCB according to the design requirement information, and obtain the reliability index value according to the target life, the actual predicted life, the attenuation stability score value, and the process risk coefficient.

[0032] As described in steps S51 - S53 above, the performance degradation curve in the present invention can reflect the dynamic degradation process of the key performance of the PCB, and obtain the performance critical value of the PCB from the product design requirements. When the key performance parameter exceeds the performance critical value, it is determined that the PCB fails. That is to say, mark the horizontal line corresponding to the performance critical value in the performance degradation curve, and the abscissa (time) corresponding to the intersection of the performance degradation curve and the performance critical value is the actual predicted life. And obtain the curve slope sequence according to the performance degradation curve. The curve slope sequence refers to the sequence of the attenuation rates of the performance parameters at different time nodes. The core purpose of obtaining the curve slope sequence is to dynamically track the change trend of the performance degradation speed, such as identifying slope fluctuation characteristics such as slow degradation in the early stage, accelerated degradation in the middle stage, or sudden failure before, etc. The slope fluctuation characteristics refer to the statistical indicators representing the stability of the attenuation rate, such as standard deviation, kurtosis, coefficient of variation, etc. In this way, performance mutation points can be captured in time through the fluctuation characteristics, breaking through the limitation of traditional static life prediction that only depends on the average degradation rate. Subsequently, quantify the attenuation stability through the formula "attenuation stability score value = 1 - (slope standard deviation / maximum slope standard deviation)", the closer this score value is to 1, the more stable the performance attenuation is, and the stronger the reliability robustness of the PCB in a complex environment. Finally, calculate the reliability index value through the formula: "reliability index value = (actual predicted life / target life) * (1 - process risk coefficient * attenuation stability score value)", this index value positively evaluates the achievement degree of the design goal through the life ratio, and at the same time inversely restricts the influence of defects and fluctuations by the product of the process risk and the stability score, realizing a systematic evaluation of the reliability of the entire life cycle of the PCB, reflecting the dynamic balance between "life reaching standard ability" and "risk resistance ability", and breaking through the limitation of traditional single - dimension detection.

[0033] As Figure 2 shown, the present application also provides a control system for the MI process in PCB production, including: The first acquisition module is used to acquire the design requirement information, material property data, and processing technology data of the PCB according to the MI file, and acquire the application environment parameters according to the design requirement information; The second acquisition module is used to acquire the key performance indicators of the PCB according to the material property data, and acquire the performance attenuation curve of the PCB according to the key performance indicators; The third acquisition module is used to acquire the process parameter compliance values and process defect information according to the processing technology data, wherein the process defect information includes first process defect information and second process defect information; The fourth acquisition module is used to acquire the process risk coefficient according to the first process defect information, second process defect information, and application environment parameters; The fifth acquisition module is used to acquire the reliability index value of the PCB according to the process risk coefficient and the performance attenuation curve; The sixth acquisition module is used to acquire the comprehensive evaluation value of the MI process according to the reliability index value and the process parameter compliance value; The judgment module is used to judge whether the comprehensive evaluation value is greater than a preset threshold: If the comprehensive evaluation value is greater than the preset threshold, it is determined that the MI process is overall reliable; If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the MI process is overall unreliable.

[0034] In one embodiment, the third acquisition module includes: The first acquisition unit is used to acquire a plurality of processing technology parameters according to the processing technology data; The second acquisition unit is used to acquire the production process limit parameter set; The third acquisition unit is used to acquire the customized requirement parameter set according to the design requirement information, and acquire the processing parameter constraint set according to the customized requirement parameter set and the production process limit parameter set; The screening unit is used to screen the processing technology parameters according to the processing parameter constraint set to obtain the compliant process parameters and non-compliant process parameters, and acquire the process parameter compliance value according to the compliant process parameters and non-compliant process parameters; The fourth acquisition unit is used to acquire the first process defect information according to the non-compliant process parameters; The fifth acquisition unit is used to acquire the process defect history database, and acquire the second process defect information according to the process defect history database and the compliant process parameters.

[0035] Such as Figure 3As shown, the present invention also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned detection method for the MI process in PCB production are implemented.

[0036] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned detection method for the MI process in PCB production are implemented.

[0037] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. Among them, any reference to a memory, storage, database, or other medium provided in the present application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be obtained in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0038] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such a process, device, article or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, device, article or method including that element.

[0039] The above are only the preferred embodiments of the present invention, and do not thereby limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall similarly be included within the patent protection scope of the present invention.

Claims

1. A detection method for the MI process in PCB production, characterized in that, Including: Obtain the design requirement information, material property data, and processing technology data of the PCB according to the MI file, and obtain the application environment parameters according to the design requirement information; Obtain the key performance indicators of the PCB according to the material property data, and obtain the performance decay curve of the PCB according to the key performance indicators; Obtain the process parameter compliance values and process defect information according to the processing technology data, where the process defect information includes first process defect information and second process defect information; Obtain the process risk coefficient according to the first process defect information, second process defect information, and application environment parameters; Obtain the reliability index value of the PCB according to the process risk coefficient and the performance decay curve; Obtain the comprehensive evaluation value of the MI process according to the reliability index value and the process parameter compliance values; Judge whether the comprehensive evaluation value is greater than a preset threshold: If the comprehensive evaluation value is greater than the preset threshold, it is determined that the overall MI process is reliable; If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the overall MI process is unreliable.

2. The detection method for the MI process in PCB production according to claim 1, wherein The step of obtaining the key performance indicators of the PCB according to the material property data includes: Obtain multiple performance indicators and performance parameter fluctuation ranges of the PCB according to the material property data, where the performance indicators include glass transition temperature, coefficient of thermal expansion, dielectric constant, and water absorption rate, and the performance parameter fluctuation ranges include glass transition temperature range, coefficient of thermal expansion range, dielectric constant fluctuation range, and water absorption rate fluctuation range; Arrange and combine multiple performance indicators to obtain a performance indicator coupling group; Obtain the performance life correlation data set of the PCB, and obtain the corresponding life prediction correlation group according to the performance life correlation data set and the performance indicator coupling group; Obtain the failure probability distribution range by using Monte Carlo simulation according to the performance parameter fluctuation range and the corresponding life prediction correlation group, and screen the performance indicators according to multiple failure probability distribution ranges to obtain the key performance indicators.

3. The detection method for the MI process in PCB production according to claim 2, wherein The step of obtaining the performance decay curve of the PCB according to the key performance indicators includes: Obtain the performance sensitivity factor according to the key performance indicators, and obtain the performance sensitive parameters of the performance sensitivity factor according to the application environment parameters; Obtain the performance factor correlation data set, and perform a correlation analysis on the performance sensitivity factor and the key performance indicators according to the performance factor correlation data set to obtain the influence factor sensitive data; Obtain the comprehensive sensitivity coefficient according to the influence factor sensitive data and the performance sensitive parameters; Obtain the initial performance decline curve according to the life prediction correlation group corresponding to the key performance indicators, and correct the initial performance decline curve according to the comprehensive sensitivity coefficient to obtain the performance decay curve.

4. The detection method for the MI process in PCB production according to claim 1, wherein The step of obtaining the process parameter compliance values and process defect information according to the processing technology data includes: Obtain multiple processing technology parameters according to the processing technology data; Obtain the production process limit parameter set; Obtain the customized requirement parameter set according to the design requirement information, and obtain the processing parameter constraint set according to the customized requirement parameter set and the production process limit parameter set; Screen the processing parameters according to the set of processing parameter constraints to obtain compliant process parameters and non-compliant process parameters, and obtain a process parameter compliance value according to the compliant process parameters and non-compliant process parameters; Obtain first process defect information according to the non-compliant process parameters; Obtain a process defect history database, and obtain second process defect information according to the process defect history database and the compliant process parameters.

5. The detection method for the MI process in PCB production according to claim 1, characterized in that, The step of obtaining the process risk coefficient according to the first process defect information, the second process defect information, and the application environment parameters includes: Obtain multiple PCB defect types and defect type incidence rates according to the first process defect information and the second process defect information; Obtain multiple environmental impact factors and impact factor parameters according to the application environment parameters; Match the multiple PCB defect types with the environmental impact factors to obtain a defect type - environmental factor association table, and obtain a list of environmental stress actions according to the defect type - environmental factor association table and the impact factor parameters; Obtain the potential deterioration mode of the PCB defect according to the list of environmental stress actions, and obtain a defect deterioration index of the PCB defect according to the potential deterioration mode; Obtain the process risk coefficient according to the multiple defect deterioration indices and the defect type incidence rates.

6. The detection method for the MI process in PCB production according to claim 1, characterized in that, The step of obtaining the reliability index value of the PCB according to the process risk coefficient and the performance decay curve includes: Obtain the actual predicted life of the PCB according to the performance decay curve, and obtain a curve slope sequence according to the performance decay curve; Obtain a slope fluctuation characteristic according to the curve slope sequence, and obtain a decay stability score value according to the slope fluctuation characteristic; Obtain the target life of the PCB according to the design requirement information, and obtain the reliability index value according to the target life, the actual predicted life, the decay stability score value, and the process risk coefficient.

7. A control system for the MI process in PCB production, characterized in that, Includes: A first acquisition module, configured to obtain the design requirement information, material characteristic data, and processing technology data of the PCB according to the MI file, and obtain application environment parameters according to the design requirement information; A second acquisition module, configured to obtain the key performance indicators of the PCB according to the material characteristic data, and obtain the performance decay curve of the PCB according to the key performance indicators; A third acquisition module, configured to obtain a process parameter compliance value and process defect information according to the processing technology data, where the process defect information includes first process defect information and second process defect information; A fourth acquisition module, configured to obtain a process risk coefficient according to the first process defect information, the second process defect information, and the application environment parameters; A fifth acquisition module, configured to obtain the reliability index value of the PCB according to the process risk coefficient and the performance decay curve; A sixth acquisition module, configured to obtain a comprehensive evaluation value of the MI process according to the reliability index value and the process parameter compliance value; A judgment module, configured to judge whether the comprehensive evaluation value is greater than a preset threshold: If the comprehensive evaluation value is greater than the preset threshold, it is determined that the MI process is overall reliable; If the comprehensive evaluation value is not greater than the preset threshold, it is determined that the MI process is overall unreliable.

8. The control system for the MI process in PCB production according to claim 7, wherein, The third acquisition module includes: A first acquisition unit, configured to acquire a plurality of processing parameter sets according to the processing technology data; A second acquisition unit, configured to acquire a set of production process limit parameters; A third acquisition unit, configured to acquire a set of customized requirement parameters according to the design requirement information, and acquire a set of processing parameter constraints according to the set of customized requirement parameters and the set of production process limit parameters; A screening unit, configured to screen the processing parameter sets according to the set of processing parameter constraints to obtain compliant process parameters and non-compliant process parameters, and acquire a process parameter compliance value according to the compliant process parameters and the non-compliant process parameters; A fourth acquisition unit, configured to acquire first process defect information according to the non-compliant process parameters; A fifth acquisition unit, configured to acquire a process defect history database, and acquire second process defect information according to the process defect history database and the compliant process parameters.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images