A Visual Analysis-Based Defect Identification and Analysis System for Elevator Components

Abstract

This invention discloses a visual analysis-based elevator component defect identification and analysis system, belonging to the field of elevator component defect identification technology. It includes a platform and a device. The platform includes an elevator analysis module and a defect analysis module; the device includes a monitoring module and a display module. The elevator analysis module analyzes the target elevator, determines its monitoring functions, and configures the monitoring accordingly. The defect analysis module analyzes the received elevator monitoring data, obtains the corresponding defect analysis results, and feeds them back to the display module on the device. The monitoring module monitors the target elevator in real time, obtains the corresponding elevator monitoring data, and transmits the elevator monitoring data to the platform's defect analysis module. The display module displays the received defect analysis results to the user.

Description

Technical Field

[0001] This invention belongs to the field of elevator component defect identification technology, specifically an elevator component defect identification and analysis system based on visual analysis. Background Technology

[0002] Against the backdrop of the rapid development of the elevator industry, elevators, as indispensable vertical transportation equipment in modern buildings, are directly related to the safety and reliability of public life and property. However, many elevators currently in use suffer from a lack of intelligent monitoring methods, especially in the identification of defects in key components, which still heavily relies on regular manual inspections and offline testing. The existing technological system and traditional elevator maintenance methods suffer from the following core pain points: Firstly, manual inspections are limited by long inspection cycles, strong subjectivity, and poor visibility at night or in complex environments, making it difficult to promptly detect early signs of hidden defects such as broken wire ropes, uneven brake shoe wear, and guide rail deformation. Especially when abnormalities occur, passengers rarely provide timely feedback; they typically only report to property management when serious problems occur, resulting in low efficiency. Secondly, intelligent retrofitting of existing elevators requires invasive upgrades to the original control system, involving complex engineering such as sensor wiring, control cabinet replacement, and communication protocol adaptation. The cost of retrofitting a single elevator can reach tens of thousands of yuan and requires several days of downtime. This leads property management companies to generally adopt a wait-and-see attitude due to cost sensitivity and the risk of operational interruption, further exacerbating the difficulties in promoting defect identification technology.

[0003] In order to solve the above problems, this invention provides a visual analysis-based elevator component defect identification and analysis system. Summary of the Invention

[0004] To address the problems of the above solutions, this invention provides a visual analysis-based elevator component defect identification and analysis system.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A visual analysis-based elevator component defect identification and analysis system, including platform and equipment ends;

[0007] The platform includes an elevator analysis module and a defect analysis module.

[0008] The elevator analysis module is used to analyze the target elevator, determine the monitoring functions of the target elevator, and the monitoring functions include basic functions and additional functions. The basic functions include image monitoring and sound monitoring, and the additional functions are monitoring functions that are not basic functions added according to the user's monitoring needs; and the corresponding monitoring configuration is performed on the target elevator according to the monitoring functions.

[0009] Further analysis of the target elevator includes:

[0010] A preset elevator information database is used to store elevator information corresponding to various types of elevators, as well as monitoring and recommendation functions.

[0011] Based on the target elevator, the system matches the corresponding monitoring recommendation function from the elevator information and sends the monitoring recommendation function to the user, who then selects the monitoring function.

[0012] Furthermore, the determination of elevator types includes:

[0013] The platform acquires various elevator information, presets classification calibration items, performs feature recognition on the elevator information based on each classification calibration item, obtains the individual features corresponding to each classification calibration item, and integrates the individual features into the classification feature data of the elevator information.

[0014] Analyze the data of each category feature to determine whether the corresponding elevator information belongs to the same category. Elevator information belonging to the same category is merged into one category, marked as elevator type, and corresponding elevator information is set for each elevator type.

[0015] Furthermore, the data for each category feature are analyzed, including:

[0016] Establish a classification and evaluation model. The expression for the classification and evaluation model is as follows:

[0017] ;

[0018] In the formula: (s, f) are the input data, where s and f are the classification feature data of the two elevator information for comparison and analysis, and s=f indicates that the two classification feature data are considered the same; the output data is the classification evaluation value FP(s, f), and the classification evaluation value is 1 or 0;

[0019] The classification features corresponding to each elevator information are combined in pairs to form several sets of input data. The corresponding input data are analyzed through a classification evaluation model to obtain the classification evaluation value between the corresponding elevator information.

[0020] When the classification evaluation value is 1, it is determined that the corresponding elevator information belongs to the same category;

[0021] When the classification evaluation value is 0, it is determined that the corresponding elevator information does not belong to the same category.

[0022] Furthermore, the determination of the monitoring and recommendation function includes:

[0023] Set up basic functions, which include image monitoring and sound monitoring;

[0024] Based on elevator information, various component defects are obtained; based on basic functions, component defects that cannot be monitored are identified, and these component defects are marked as supplementary defects.

[0025] Determine the corresponding defect monitoring method for the supplementary defect, and estimate the defect occurrence probability and defect risk value of the supplementary defect; evaluate whether the supplementary defect meets the recommended requirements based on the defect occurrence probability, defect risk value, and defect monitoring method; generate corresponding recommended monitoring functions based on the defect monitoring methods that meet the recommended requirements.

[0026] Furthermore, supplementary defects are identified based on the basic functions, including:

[0027] Based on elevator information, obtain the defect characteristics of each component. Determine whether the corresponding defect characteristics can be detected based on basic functions. Obtain the identification and judgment results of the corresponding defect characteristics. The identification and judgment results include whether the feature identification is satisfied or not.

[0028] Part defects that do not meet the defect performance characteristics identified by the identification judgment result are marked as supplementary defects.

[0029] Furthermore, based on the basic functional assessment, it can be determined whether the corresponding defect characteristics can be detected, including:

[0030] A defect feature recognition model is established, and the expression of the defect feature recognition model is:

[0031] ;

[0032] In the formula: (U) is the input data, where U represents the defect manifestation characteristics of the corresponding part; the output data is the defect feature identification value QP(U), where the defect feature identification value is 1 or 0;

[0033] The defect feature recognition model is used to analyze the defect manifestation characteristics of each component and obtain the corresponding defect feature recognition value.

[0034] When the defect feature identification value is 1, the identification judgment result is that the feature identification is satisfied;

[0035] When the defect feature identification value is 0, the identification judgment result is that the feature identification is not satisfied.

[0036] Furthermore, the supplementary defects are evaluated to determine whether they meet the recommended requirements based on the defect occurrence probability, defect risk value, and defect monitoring methods, including:

[0037] To estimate the monitoring cost of the defect monitoring method, the probability of defect occurrence, the defect risk value, and the monitoring cost are substituted into a preset defect assessment formula to calculate the corresponding comprehensive assessment value. The defect assessment formula is as follows:

[0038] ;

[0039] Where: PK is the comprehensive evaluation value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; e is the natural constant; β is the probability of defect occurrence; QF is the defect risk value; CB is the monitoring cost.

[0040] When the comprehensive evaluation value is greater than the threshold X1, it meets the recommended requirements when using the corresponding defect monitoring method for evaluating supplementary defects.

[0041] The defect analysis module is used to analyze the received elevator monitoring data to obtain the corresponding defect analysis results. The defect analysis results are the defect probabilities of the elevator being normal or abnormal and the corresponding accessory defects; and the defect analysis results are fed back to the display module at the corresponding device end.

[0042] The device end includes a monitoring module and a display module;

[0043] The monitoring module is used to monitor the target elevator in real time to obtain the corresponding elevator monitoring data; and the elevator monitoring data is transmitted to the defect analysis module at the platform end.

[0044] The display module is used to display the received defect analysis results to the user.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] The application of the elevator accessory defect identification and analysis system based on visual analysis in the present invention has brought significant and multi-dimensional positive impacts to the elevator industry. By introducing advanced visual analysis technology, the system realizes real-time and accurate identification of defects in key elevator accessories, completely changing the traditional maintenance mode that relies on manual inspections. In terms of defect identification efficiency and accuracy, the system can break through the limitations of long manual detection cycles and strong subjectivity. It can monitor the elevator regardless of day or night and complex environments, promptly detect abnormal problems, and prompt the user to dispatch maintenance personnel for repair in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is the principle block diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0050] like Figure 1 As shown, the elevator component defect identification and analysis system based on visual analysis includes a platform and an equipment.

[0051] The platform includes an elevator analysis module, a defect analysis module, and...

[0052] The elevator analysis module is used to analyze the target elevator and determine its monitoring functions. The monitoring functions include basic functions and additional functions. The basic functions include image monitoring and sound monitoring, while the additional functions include various other optional monitoring functions, such as electromagnetic monitoring and tensile monitoring. Based on the monitoring functions, the module configures the target elevator accordingly to achieve the corresponding monitoring functions.

[0053] The target elevator refers to the elevator that needs to be analyzed, which may be an elevator that is intended to be modified.

[0054] In one embodiment, the analysis of the target elevator includes:

[0055] A preset elevator information database is used to store elevator information corresponding to various types of elevators, as well as monitoring and recommendation functions.

[0056] Based on the target elevator, the system matches the corresponding monitoring and recommendation functions from the elevator information and sends the monitoring and recommendation functions to the user. The user then selects the monitoring functions and marks the selected non-basic functions as additional functions.

[0057] In one embodiment, elevator types are set according to brand, model, etc.

[0058] In one embodiment, it can also be set up in various existing ways to improve storage space utilization and subsequent elevator information matching efficiency.

[0059] In one embodiment, determining the type of elevator includes:

[0060] The platform acquires various elevator information and pre-sets classification calibration items, such as drive method (traction elevator, hydraulic elevator, forced drive elevator), usage scenario (commercial elevator, residential elevator, industrial elevator), control method (traditional relay control elevator, PLC control elevator), and manufacturing year. The specific settings are based on the platform's requirements. Based on each classification calibration item, the elevator information is characterized to obtain the individual features corresponding to each classification calibration item, and these individual features are integrated into the classification feature data of the elevator information.

[0061] Analyze the various classification feature data to determine whether the corresponding elevator information belongs to the same category. Merge elevator information belonging to the same category into one category and mark it as elevator type. Set corresponding elevator information for each elevator type. That is, summarize the elevator information corresponding to each elevator type to obtain a representative elevator information. Various methods such as union integration and removal of irrelevant information can be used to determine representative elevator information, because subsequent matching is mainly based on classification feature data.

[0062] In one embodiment, the analysis of various classification feature data can be based on existing technologies for judgment.

[0063] In one embodiment, the analysis of various classification feature data includes:

[0064] Establish a classification and evaluation model. The expression for the classification and evaluation model is as follows:

[0065] ;

[0066] In the formula: (s, f) represents the input data, where s and f are the classification feature data of the two elevator information items being compared and analyzed. s=f indicates that the two classification feature data are considered the same. If all individual features are the same, or if a certain different individual feature is specified, it can be considered the same and is also considered the same. This is set by the platform. The output data is the classification evaluation value FP(s, f), which is 1 or 0. The corresponding training set is pre-labeled by the platform for training.

[0067] The classification features corresponding to each elevator information are combined in pairs to form several sets of input data. The corresponding input data are analyzed through a classification evaluation model to obtain the classification evaluation value between the corresponding elevator information.

[0068] When the classification evaluation value is 1, it is determined that the corresponding elevator information belongs to the same category;

[0069] When the classification evaluation value is 0, it is determined that the corresponding elevator information does not belong to the same category.

[0070] Elevator information with a total evaluation value of 1 will be classified into one category.

[0071] In one embodiment, determining the monitoring recommendation function includes:

[0072] Set up basic functions, including image and sound monitoring. This allows for the rapid installation of video and audio monitoring equipment at a low cost, and further cost reduction can be achieved by integrating with the existing elevator video monitoring system. Mark these basic functions as recommended monitoring features.

[0073] Based on elevator information, various component defects of the elevator are identified. Based on basic functions, monitorable component defects are determined, as many component defects have corresponding manifestations. For example, worn brake shoes or spring failure can cause high-frequency screeching or low-frequency vibration during braking; broken wires or corrosion can change the natural frequency of the wire rope, generating periodic impact noise during operation; rolling bearing failure can trigger impact pulses at specific frequencies; door gap width and debris accumulation on the sill can be identified, and door deformation or derailment can be detected using semantic segmentation models; combining images and sound can identify abnormal situations and predict the probability of corresponding component defects, providing a basis for subsequent manual inspection; unmonitorable component defects are marked as supplementary defects.

[0074] Determine the corresponding defect monitoring method for the supplementary defect, that is, how to monitor the defect of the component according to the existing component monitoring technology. There can be multiple defect monitoring methods. Estimate the probability of occurrence and the defect risk value of the supplementary defect. Evaluate whether the supplementary defect meets the recommended requirements based on the probability of occurrence, the defect risk value and the defect monitoring method.

[0075] Based on the defect monitoring methods that meet the recommended requirements, corresponding recommended monitoring functions are generated.

[0076] In one embodiment, supplementary defects are determined based on basic functions. This can be done using existing methods, such as manually determining them because the number and types of elevators are limited and relatively fixed.

[0077] In one embodiment, determining supplementary defects based on basic functionality includes:

[0078] The system obtains the defect characteristics of each component based on elevator information. It then determines whether the corresponding defect characteristics, such as abnormal noise, can be detected based on basic functions. It is not necessary to be 100% certain that the defect is in a specific component. As long as the abnormality can be detected and it is determined that the elevator has a component abnormality, it is considered that the defect characteristics can be detected. The system obtains the identification and judgment results of the corresponding defect characteristics, which include whether the characteristic identification is satisfied or not.

[0079] Part defects that do not include defect characteristics that meet the identification criteria are marked as supplementary defects; that is, as long as they include detectable defect characteristics, they are not considered part defects.

[0080] In one embodiment, the determination of whether the corresponding defect characteristics can be detected based on the basic functions can be made by simulation based on existing methods or by using relevant historical monitoring data.

[0081] In one embodiment, determining whether corresponding defect characteristics can be detected based on basic functionalities includes:

[0082] A defect feature recognition model is established, and the expression of the defect feature recognition model is:

[0083] ;

[0084] In the formula: (U) is the input data, where U represents the defect manifestation characteristics of the corresponding accessory defect; the output data is the defect feature identification value QP(U), where the defect feature identification value is 1 or 0; the corresponding training set is marked using the corresponding historical data for training, or the judgment can be made by pre-setting the monitoring range corresponding to the basic function;

[0085] The defect feature recognition model is used to analyze the defect manifestation characteristics of each component and obtain the corresponding defect feature recognition value.

[0086] When the defect feature identification value is 1, the identification judgment result is that the feature identification is satisfied;

[0087] When the defect feature identification value is 0, the identification judgment result is that the feature identification is not satisfied.

[0088] In one embodiment, the probability of occurrence and the risk value of the defect are estimated. The probability of occurrence can be determined statistically based on historical component data corresponding to the elevator information. The risk value is set on a percentage basis, which can be done in existing ways, such as summarizing various safety accidents that occur in the elevator, sorting the safety accidents from highest to lowest severity, with the highest score corresponding to 100, and the risk value of a defect with no risk being 0. The corresponding risk value can be set for different safety accident markers using methods such as the difference method. Alternatively, the risk value can be sorted and calculated based on the accident losses. The safety accidents corresponding to the failure of each component defect are analyzed to determine the corresponding risk value. Alternatively, the risk value can be set manually.

[0089] In one embodiment, it is evaluated whether supplementary defects meet the recommendation requirements according to the defect occurrence probability, defect risk value, and defect monitoring method. The recommendation requirements refer to whether there is a definite need for monitoring. For example, if the defect occurrence probability is greater than a preset value, it is considered to meet the recommendation requirements. The monitoring cost is estimated according to the defect monitoring method, and if the cost is lower than the preset value, it is considered to meet the recommendation requirements. The comprehensive evaluation value can also be calculated based on the defect occurrence probability, defect risk value, and monitoring cost, and it is determined whether the recommendation requirements are met according to the comprehensive evaluation value.

[0090] Exemplarily, the monitoring cost of the defect monitoring method is estimated, and the defect occurrence probability, defect risk value, and monitoring cost are substituted into a preset defect evaluation formula to calculate the corresponding comprehensive evaluation value. For dimensionless removal, its numerical value is calculated; the defect evaluation formula is:

[0091] ;

[0092] In the formula: PK is the comprehensive evaluation value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; e is the natural constant; β is the defect occurrence probability; QF is the defect risk value; CB is the monitoring cost;

[0093] When the comprehensive evaluation value is greater than the threshold X1, it is evaluated that the supplementary defects meet the recommendation requirements when adopting the corresponding defect monitoring method;

[0094] Otherwise, it does not meet.

[0095] In one embodiment, the determination of the elevator type can also be directly determined according to whether the recommended monitoring functions corresponding to each elevator information are the same.

[0096] In one embodiment, corresponding monitoring configurations are performed on the target elevator according to the monitoring function. Multiple existing technologies can be used for configuration, such as docking the elevator monitoring system, installing multiple cameras, etc., and specific installation is carried out according to user needs.

[0097] The defect analysis module is used to analyze the received elevator monitoring data to obtain the corresponding defect analysis results. The defect analysis results are the defect probabilities of the elevator being normal or abnormal and the corresponding accessory defects; the defect analysis results are fed back to the display module at the corresponding device end.

[0098] In one embodiment, the received elevator monitoring is analyzed. The platform party pre-establishes a corresponding intelligent analysis model in advance, and the intelligent analysis model analyzes the elevator monitoring data to determine whether there are accessory defects, such as whether the corresponding defect manifestation characteristics are recognized. If not, the elevator is evaluated as normal, otherwise the elevator is evaluated as abnormal. The appropriate accessory defects are determined according to the corresponding defect manifestation characteristics, and the probability of each accessory defect is estimated, that is, the defect probability is determined within the selectable accessory defects.

[0099] The intelligent analysis model is built based on existing technologies, such as machine learning and deep learning algorithms. It can also utilize platform resources to build large models to improve analysis accuracy.

[0100] The device includes a monitoring module and a display module;

[0101] The monitoring module is used to monitor the target elevator in real time and obtain the corresponding elevator monitoring data; the elevator monitoring data is then transmitted to the defect analysis module on the platform.

[0102] The display module is used to display the received defect analysis results to the user. The specific display method and display interface are set according to the user's needs.

[0103] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0104] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A visual analysis-based elevator component defect identification and analysis system, characterized in that, Including both platform and device ends; The platform includes an elevator analysis module and a defect analysis module; the equipment includes a monitoring module and a display module. The elevator analysis module is used to analyze the target elevator, determine the monitoring functions of the target elevator, and the monitoring functions include basic functions and additional functions. The basic functions include image monitoring and sound monitoring, and the additional functions are non-basic monitoring functions added according to the user's monitoring needs; and the monitoring configuration of the target elevator is performed accordingly based on the monitoring functions. The defect analysis module is used to analyze the received elevator monitoring data and obtain the corresponding defect analysis results. The defect analysis results are the elevator being normal or abnormal and the probability of defects in the corresponding parts. The defect analysis results are fed back to the display module on the corresponding device. The monitoring module is used to monitor the target elevator in real time, obtain the corresponding elevator monitoring data, and transmit the elevator monitoring data to the defect analysis module on the platform. The display module is used to display the received defect analysis results to the user; The target elevator was analyzed, including: A preset elevator information database is used to store elevator information corresponding to various types of elevators, as well as monitoring and recommendation functions. Based on the target elevator, the corresponding monitoring recommendation function is matched from the elevator information and sent to the user for the user to select the monitoring function. The determination of the monitoring and recommendation function includes: Configure basic functions, which include image monitoring and sound monitoring; mark the basic functions as recommended monitoring functions. Based on elevator information, various component defects are obtained; based on basic functions, component defects that cannot be monitored are identified, and these component defects are marked as supplementary defects. Determine the corresponding defect monitoring method for the supplementary defect, and estimate the defect occurrence probability and defect risk value of the supplementary defect; evaluate whether the supplementary defect meets the recommended requirements based on the defect occurrence probability, defect risk value, and defect monitoring method; generate corresponding recommended monitoring functions based on the defect monitoring methods that meet the recommended requirements.

2. The elevator component defect identification and analysis system based on visual analysis according to claim 1, characterized in that, The determination of elevator types includes: The platform acquires various elevator information, presets classification calibration items, performs feature recognition on the elevator information based on each classification calibration item, obtains the individual features corresponding to each classification calibration item, and integrates the individual features into the classification feature data of the elevator information. Analyze the data of each category feature to determine whether the corresponding elevator information belongs to the same category. Elevator information belonging to the same category is merged into one category, marked as elevator type, and corresponding elevator information is set for each elevator type.

3. The elevator component defect identification and analysis system based on visual analysis according to claim 2, characterized in that, The data for each category feature is analyzed, including: Establish a classification and evaluation model. The expression for the classification and evaluation model is as follows: ； In the formula: (s, f) are the input data, where s and f are the classification feature data of the two elevator information for comparison and analysis, and s=f indicates that the two classification feature data are considered the same; the output data is the classification evaluation value FP(s, f), and the classification evaluation value is 1 or 0; The classification features corresponding to each elevator information are combined in pairs to form several sets of input data. The corresponding input data are analyzed through a classification evaluation model to obtain the classification evaluation value between the corresponding elevator information. When the classification evaluation value is 1, it is determined that the corresponding elevator information belongs to the same classification; When the classification evaluation value is 0, it is determined that the corresponding elevator information does not belong to the same classification.

4. The elevator component defect identification and analysis system based on visual analysis according to claim 1, characterized in that, Determine supplementary defects according to the basic functions, including: Obtain the defect manifestation characteristics of each component defect based on the elevator information, judge whether the corresponding defect manifestation characteristics can be monitored according to the basic functions, obtain the recognition judgment result of the corresponding defect manifestation characteristics, and the recognition judgment result includes meeting the feature recognition and not meeting the feature recognition; Mark the component defects that do not include the defect manifestation characteristics with the recognition judgment result of meeting the feature recognition as supplementary defects.

5. The elevator component defect identification and analysis system based on visual analysis according to claim 4, characterized in that, Judge whether the corresponding defect manifestation characteristics can be monitored according to the basic functions, including: Establish a defect feature recognition model, and the expression of the defect feature recognition model is: ； In the formula: (U) is the input data, and U represents the defect manifestation characteristics of the corresponding component defect; the output data is the defect feature recognition value QP(U), and the defect feature recognition value is 1 or 0; Analyze the defect manifestation characteristics of each component defect through the defect feature recognition model to obtain the defect feature recognition value of the corresponding defect manifestation characteristics; When the defect feature recognition value is 1, the recognition judgment result is meeting the feature recognition; When the defect feature recognition value is 0, the recognition judgment result is not meeting the feature recognition.

6. The elevator component defect identification and analysis system based on visual analysis according to claim 1, characterized in that, Evaluate whether the supplementary defects meet the recommended requirements according to the defect occurrence probability, defect risk value and defect monitoring method, including: Estimate the monitoring cost of the defect monitoring method, substitute the defect occurrence probability, defect risk value and monitoring cost into the preset defect evaluation formula to calculate the corresponding comprehensive evaluation value, and the defect evaluation formula is: ； In the formula: PK is the comprehensive evaluation value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; e is the natural constant; β is the defect occurrence probability; QF is the defect risk value; CB is the monitoring cost; When the comprehensive evaluation value is greater than the threshold X1, it is evaluated that the supplementary defects meet the recommended requirements when adopting the corresponding defect monitoring method.

Images