Pressure vessel defect safety evaluation method and system based on industrial cloud computing

Abstract

The present invention discloses a pressure vessel defect safety evaluation method and system based on industrial cloud computing, which belongs to the technical field of pressure vessel safety evaluation. The system includes a data initialization module, a test batch data analysis module, a superiority index analysis module, a mapping table generation module, an inspection batch data analysis module, a comprehensive safety evaluation module and a result visualization output module, and provides a corresponding evaluation method. The present invention processes pressure vessels in batches and comprehensively detects pressure vessels by parts, that is, determines the detection method corresponding to each part from the test batch of pressure vessels, and generates a method-part mapping table, selects the corresponding detection method for the verification batch of pressure vessels according to the method-part mapping table to detect the corresponding part, and performs a comprehensive safety evaluation, so as to obtain a more comprehensive and detailed detection result of the pressure vessel, and solves the problem of incomplete and detailed pressure vessel detection in the prior art.

Description

Technical Field

[0001] The present invention belongs to the technical field of pressure vessel safety evaluation, and in particular, relates to a pressure vessel defect safety evaluation method and system based on industrial cloud computing. Background Art

[0002] Pressure vessels are indispensable closed equipment in chemical production. They carry gas or liquid and withstand a certain amount of pressure. These devices are widely used in industries such as petrochemicals, electricity, and metallurgy, and play a key role in improving industrial automation and production efficiency. However, during use, pressure vessels may develop defects such as cracks and pits due to manufacturing defects, improper operation, material aging, or environmental factors. If these defects are not detected and repaired in time, they may cause serious safety accidents.

[0003] At present, the metal magnetic memory detection method is a common technology for detecting surface defects of pressure vessels. This method is based on the magnetization characteristics of the material in the stress concentration area, and identifies defects by detecting the abnormal magnetic field on the surface of the material. For example, CN108629094B proposed a method for characterizing the safety margin of crack defects in pressure vessels based on velocity product. This method determines the safe attenuation path of crack defects through an assessment process and calculates the safety margin of each point. In addition, CN117056686B proposed an alarm method for detecting surface defects of pressure vessels. This method uses three-dimensional modeling and simulation models, combined with the classification of defect coordinate sets and the diffusion prediction network layer, to predict the spread of defects and assess risks.

[0004] However, existing technologies have some limitations in pressure vessel inspection. The metal magnetic memory inspection method is mainly applicable to ferromagnetic materials, has limited detection capabilities for deep defects, and requires professional analysis of the inspection results, which may lead to deviations between the inspection results and the actual situation. In addition, the amount of data generated during the inspection process is large, which increases the complexity of data processing. Therefore, the current pressure vessel inspection technology is not comprehensive and detailed enough, and further improvements and innovations are needed to improve the accuracy and efficiency of inspection. Summary of the invention

[0005] In view of the above deficiencies in the prior art, the purpose of the present invention is to provide a pressure vessel defect safety evaluation method and system based on industrial cloud computing, which solves the problem of incomplete and detailed pressure vessel detection in the prior art and achieves more comprehensive and detailed pressure vessel detection results.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is a pressure vessel defect safety evaluation method based on industrial cloud computing, comprising the following steps:

[0007] Divide the pressure vessels of specified models into test batches and inspection batches, and divide the inspection parts of each pressure vessel;

[0008] Obtain different detection method data from the associated database through the industrial cloud computing platform, and obtain the test batch defect detection information of different parts of each pressure vessel in the test batch according to the different detection method data;

[0009] The superiority index of different detection methods when detecting different parts is judged according to the defect detection information. The superiority index is used to describe the detection effect of the detection method on different parts of the pressure vessel;

[0010] The superiority indexes of different parts of the pressure vessel are ranked high and low, the optimal detection methods corresponding to different parts are obtained, and a method-part mapping table between the detection method data and the part data is generated;

[0011] Obtain designated inspection method data from the associated database according to the method-part mapping table, inspect corresponding parts of the pressure vessels in the inspection batch according to the designated inspection method data, and obtain defect inspection information of the inspection batch;

[0012] Conduct comprehensive safety evaluation on the defect detection information of inspection batches of different parts of each pressure vessel to obtain an overall safety score, which is used to determine the overall safety level of the pressure vessel.

[0013] The inspection batch defect detection information and overall safety score are visualized and displayed to users through the industrial cloud computing platform.

[0014] As a preferred embodiment of the present invention, the detection parts are divided into surface parts, internal parts, welding parts and joint parts;

[0015] Surface part: including the outer surface and inner surface of the pressure vessel;

[0016] Internal parts: including pipes and cavities inside the pressure vessel;

[0017] Welding area: including all welding joints and weld areas;

[0018] Joint parts: including connection points and interfaces of various parts of the pressure vessel.

[0019] As a preferred solution of the present invention, the detection method data refers to the step data corresponding to each detection method stored in the device, including:

[0020] Detection steps: describe the operation steps and parameter settings of each detection method;

[0021] Testing conditions: including environmental conditions, equipment parameters and operating specification information;

[0022] Equipment performance: including equipment performance indicators.

[0023] As a preferred solution of the present invention, the superiority index is obtained in the following manner:

[0024] Obtain the test batch defect detection information, and analyze the sensitivity, penetration depth, time cost and expense of the detection method based on the test batch defect detection information;

[0025] The sensitivity, penetration depth, time cost and expense of the detection method are standardized, and the superiority index is analyzed based on the standardized results.

[0026] As a preferred embodiment of the present invention, the calculation formula of the superiority index is:

[0027] ;

[0028] In the formula, is the superiority index of the i-th detection method for the j-th part, is the sensitivity of the i-th detection method to the j-th part, is the penetration depth of the i-th detection method to the j-th part, is the time cost of the i-th detection method for the j-th part, is the cost of the i-th detection method for the j-th part.

[0029] As a preferred embodiment of the present invention, the sensitivity of the detection method refers to the minimum detectable size;

[0030] The penetration depth of a detection method refers to the depth range of detection;

[0031] The time cost of a test method refers to the length of time required to record and complete the test;

[0032] The cost of the test method is the cost of performing the test.

[0033] As a preferred solution of the present invention, the overall safety score is obtained as follows:

[0034] Number the pressure vessels and number the corresponding part types of the pressure vessels;

[0035] Obtain inspection batch defect detection information of various parts of pressure vessels;

[0036] Obtain the defect detection information of the test batch, and filter out the defect detection information corresponding to the part according to the method-part mapping table;

[0037] Count the defect detection information of the same part of multiple pressure vessels and take the average value as the defect expectation value of the part;

[0038] Analyze the defect deviation value by comparing the defect detection information of the inspection batch with the defect expected value;

[0039] Obtain the weight setting value of the part type, and calculate the overall safety score based on the weight setting value and the defect deviation value.

[0040] As a preferred embodiment of the present invention, the calculation formula of the overall safety score is:

[0041] ;

[0042] ;

[0043] In the formula, is the overall safety score of the kth pressure vessel, k is the number of the pressure vessel, is the defect deviation value of the jth part in the kth pressure vessel, j is the number of the inspection part in the pressure vessel, j=1,2,...,J, J is the total number of inspection parts in the pressure vessel, is the weight value of the jth part, is the inspection batch defect detection information of the jth part in the kth pressure vessel, is the expected value of defects at the jth location in the kth pressure vessel.

[0044] As a preferred embodiment of the present invention, the visual display comprises the following steps:

[0045] Use the industrial cloud computing platform to generate charts and reports, and update and dynamically display inspection batch defect detection information and overall safety scores in real time;

[0046] Through the user interaction interface, users can view the effect comparison of different detection methods, defect data of each part and the overall safety score.

[0047] The pressure vessel defect safety evaluation system based on industrial cloud computing is used to implement the above-mentioned pressure vessel defect safety evaluation method based on industrial cloud computing, including a data initialization module, a test batch data analysis module, a superiority index analysis module, a mapping table generation module, an inspection batch data analysis module, a comprehensive safety evaluation module and a result visualization output module;

[0048] Among them, the data initialization module is used to divide the pressure vessels of the specified model into test batches and inspection batches, and divide the inspection parts for each pressure vessel;

[0049] The test batch data analysis module is used to obtain different detection method data from the associated database through the industrial cloud computing platform, and obtain the test batch defect detection information of different parts of each pressure vessel in the test batch according to the different detection method data;

[0050] The superiority index analysis module is used to judge the superiority index of different detection methods when detecting different parts based on defect detection information. The superiority index is used to describe the detection effect of the detection method on different parts of the pressure vessel;

[0051] A mapping table generation module is used to sort the superiority indexes of different parts of the pressure vessel, obtain the optimal detection methods corresponding to different parts, and generate a method-part mapping table between the detection method data and the part data;

[0052] The inspection batch data analysis module is used to obtain the specified inspection method data from the associated database according to the method and part mapping table, detect the corresponding parts of the pressure vessels in the inspection batch according to the specified inspection method data, and obtain the inspection batch defect detection information;

[0053] The comprehensive safety evaluation module is used to conduct comprehensive safety evaluation on the inspection batch defect detection information of different parts of each pressure vessel to obtain an overall safety score. The overall safety score is used to determine the overall safety level of the pressure vessel.

[0054] The result visualization output module is used to visualize the inspection batch defect detection information and overall safety score to users through the industrial cloud computing platform.

[0055] The present invention has the following technical effects or advantages:

[0056] The present invention comprehensively detects the pressure vessel by parts and comprehensively calculates the data of each part of the pressure vessel, thereby obtaining an overall comprehensive analysis result of the pressure vessel, thereby achieving more comprehensive and detailed detection results of the pressure vessel, and effectively solving the problem of incomplete and detailed pressure vessel detection in the prior art.

[0057] The present invention sets four key parameters based on sensitivity, penetration depth, time cost and expense. By standardizing these parameters, the performance of each detection method in different parts is quantitatively compared, the superiority index is standardized and the method-part mapping table is generated, thereby ensuring the optimal selection of the detection method, and then realizing automatic selection of the optimal detection method, reducing the time of manual judgment and selection, improving detection efficiency and accuracy, and minimizing the detection cost.

[0058] The present invention uses a visualization function to update and dynamically display detection information and safety scores in real time through an industrial cloud computing platform, so that users can intuitively view the detection results and safety scores, thereby effectively improving the safety management level of pressure vessels. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of the method of the present invention;

[0060] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0061] The above technical solution is described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0062] Example 1

[0063] like Figure 1 As shown, a pressure vessel defect safety evaluation method based on industrial cloud computing is applied to a pressure vessel defect safety evaluation system based on industrial cloud computing, and includes the following steps: dividing the pressure vessels of a specified model into test batches and inspection batches, and dividing the inspection parts for each pressure vessel;

[0064] Obtain different detection method data from the associated database through the industrial cloud computing platform, and obtain the test batch defect detection information of different parts of each pressure vessel in the test batch according to the different detection method data;

[0065] The superiority index of different detection methods when detecting different parts is judged according to the defect detection information. The superiority index is used to describe the detection effect of the detection method on different parts of the pressure vessel;

[0066] The superiority indexes of different parts of the pressure vessel are ranked high and low, the optimal detection methods corresponding to different parts are obtained, and a method-part mapping table between the detection method data and the part data is generated;

[0067] Obtain designated inspection method data from the associated database according to the method-part mapping table, inspect corresponding parts of the pressure vessels in the inspection batch according to the designated inspection method data, and obtain defect inspection information of the inspection batch;

[0068] Conduct comprehensive safety evaluation on the defect detection information of inspection batches of different parts of each pressure vessel to obtain an overall safety score, which is used to determine the overall safety level of the pressure vessel.

[0069] The inspection batch defect detection information and overall safety score are visualized and displayed to users through the industrial cloud computing platform.

[0070] Furthermore, the division of inspection parts includes surface parts, internal parts, welding parts and joint parts; surface parts: including the outer surface and inner surface of the pressure vessel; internal parts: including the pipes and cavities inside the pressure vessel; welding parts: including all welding joints and weld areas; joint parts: including the connection points and interfaces of various parts of the pressure vessel.

[0071] In this embodiment, the pressure vessel can also be divided into various parts, such as: top, bottom, side wall, weld, support structure, etc. Top and bottom: metal magnetic memory detection (MMM) and eddy current detection (ET) are used to mainly detect surface cracks and corrosion. Side wall: ultrasonic detection (UT) and metal magnetic memory detection (MMM) are used to mainly detect internal cracks and surface defects. Weld: radiographic detection (RT) and ultrasonic detection (UT) are used to mainly detect welding quality, internal pores and inclusions. Support structure: eddy current detection (ET) and acoustic emission detection (AE) are used to mainly detect surface corrosion and monitor defect development in real time.

[0072] Furthermore, the detection method data refers to the step data corresponding to each detection method stored in the device, including:

[0073] Test steps: describe the operating steps and parameter settings for each test method; Test conditions: include environmental conditions, equipment parameters, and operating specification information; Equipment performance: includes equipment performance indicators.

[0074] In this embodiment, the detection methods include metal magnetic memory testing (MMM), ultrasonic testing (UT), radiographic testing (RT), eddy current testing (ET) and acoustic emission testing (AE).

[0075] Furthermore, the superiority index is obtained by: obtaining the defect detection information of the test batch, and analyzing the sensitivity, penetration depth, time cost and expense of the detection method based on the defect detection information of the test batch; standardizing the sensitivity, penetration depth, time cost and expense of the detection method, and analyzing the superiority index based on the standardized results.

[0076] In this embodiment, the sensitivity, penetration depth, time cost and cost of the detection method are standardized, and the standardized formula is as follows: , , , ,in, , , , They are the standardized sensitivity, penetration depth, time cost and expense; , , , They are sensitivity, penetration depth, time cost and expense before standardization.

[0077] Furthermore, the calculation formula of the superiority index is:

[0078] ;

[0079] In the formula, is the superiority index of the i-th detection method for the j-th part, is the sensitivity of the i-th detection method to the j-th part, is the penetration depth of the i-th detection method to the j-th part, is the time cost of the i-th detection method for the j-th part, is the cost of the i-th detection method for the j-th part.

[0080] In a specific embodiment, the parameters of the i-th detection method for the j-th part are: sensitivity , penetration depth , time cost ,cost The superiority index is The higher the superiority index, the better the detection effect.

[0081] In this embodiment, the sensitivity of the i-th detection method to the j-th part is , is the minimum defect size of the jth part for the i-th detection method, For example, if a certain detection method can identify defects as small as 0.2mm, and the reference standard size is 1mm, then the sensitivity is: .

[0082] Furthermore, the sensitivity of a detection method refers to the minimum detectable size; the penetration depth of a detection method refers to the depth range of detection; the time cost of a detection method refers to the length of time required to record the completion of the detection; and the cost of a detection method refers to the cost of conducting the detection.

[0083] In this embodiment, the sensitivity is obtained by measuring the responsiveness of the detection method to small defects through standard test materials, and using a standard test block with a known defect size to measure the minimum detectable defect size. This minimum defect size usually refers to the diameter or length of the defect, such as the minimum detectable length of a crack or the minimum detectable diameter of a hole. The commonly used unit in industrial detection is millimeter (mm); micrometer (µm) is commonly used in precision detection for very small defects, such as surface cracks or tiny holes. Among them, the minimum defect size of magnetic memory detection can be the minimum detectable length of a crack, such as 0.5 mm. The minimum defect size of ultrasonic detection can be the minimum detectable diameter of a crack or a hole, such as 1 mm. The minimum defect size of X-ray detection can be the minimum diameter of the defect, such as 2 mm, based on the clarity and resolution of the image.

[0084] The penetration depth is obtained by measuring the penetration ability of the detection method in standard test blocks of different thicknesses, referring to standard test specifications (such as ASTM E114-20 Standard Practice for Ultrasonic Pulse Echo Straight Beam Contact Tests), and recording the depth range of the test. The penetration depth is in millimeters (mm).

[0085] Time cost is obtained by recording the time required to complete the test, which is determined through actual operation records or experimental measurements. The time cost is measured in hours (h) or minutes (min).

[0086] How to obtain the cost of the test method: Calculate the cost of conducting the test, including equipment usage and labor costs. Cost data can also be obtained through financial records or cost analysis. The cost is in monetary units (such as yuan or US dollars).

[0087] Furthermore, the overall safety score is obtained by: numbering the pressure vessels and numbering the corresponding part types of the pressure vessels; obtaining the inspection batch defect detection information of each part of the pressure vessel; obtaining the test batch defect detection information, and filtering out the defect detection information corresponding to the part according to the method-part mapping table; counting the defect detection information of the same part of multiple pressure vessels, and taking the average value as the defect expected value of the part; analyzing the defect deviation value by comparing the inspection batch defect detection information with the defect expected value; obtaining the weight setting value of the part type, and deriving the overall safety score according to the weight setting value and the defect deviation value.

[0088] In this embodiment, the sum of the weights of various types of parts is 1. The weight setting value is extracted from a mapping table between parts and weights obtained from a database.

[0089] Furthermore, the calculation formula for the overall safety score is:

[0090] ;

[0091] ;

[0092] In the formula, is the overall safety score of the kth pressure vessel, k is the number of the pressure vessel, is the defect deviation value of the jth part in the kth pressure vessel, j is the number of the inspection part in the pressure vessel, j=1,2,...,J, J is the total number of inspection parts in the pressure vessel, is the weight value of the jth part, is the inspection batch defect detection information of the jth part in the kth pressure vessel, is the expected value of defects at the jth location in the kth pressure vessel.

[0093] In this embodiment, the inspection batch defect detection information of the jth part in the kth pressure vessel These are the test values ​​obtained by testing the corresponding parts using different methods. The methods corresponding to different parts may be different, so the units of the test values ​​obtained may also be different. Therefore, the deviation can be calculated using the defect deviation value calculation formula while eliminating the unit.

[0094] Furthermore, the visual display includes the following steps: using the industrial cloud computing platform to generate charts and reports, and updating and dynamically displaying the inspection batch defect detection information and the overall safety score in real time; through the user interaction interface, allowing users to view the effect comparison of different detection methods, the defect data of each part and the overall safety score.

[0095] In this embodiment, the visual display content is updated in real time through the industrial cloud computing platform to ensure the real-time and accuracy of the displayed data. Based on the industrial cloud computing platform, through data analysis and calculation of multiple detection methods, efficient and accurate detection of defects in different parts of the pressure vessel can be achieved. The standardized calculation of the superiority index and the generation of the method-part mapping table ensure the optimal selection of the detection method and improve the detection efficiency and accuracy. The calculation steps of the comprehensive safety evaluation can comprehensively evaluate the overall safety status of the pressure vessel and provide a reliable safety score. At the same time, through the visual display function of the industrial cloud computing platform, users can intuitively view the test results and safety scores, which is convenient for decision-making and maintenance. Overall, the method of the present invention has high reliability, simple operation, and objective and true evaluation results, which can effectively improve the safety management level of pressure vessels.

[0096] Example 2

[0097] like Figure 2 As shown, the pressure vessel defect safety evaluation system based on industrial cloud computing is used to implement the pressure vessel defect safety evaluation method based on industrial cloud computing of Example 1, including: a data initialization module, a test batch data analysis module, a superiority index analysis module, a mapping table generation module, an inspection batch data analysis module, a comprehensive safety evaluation module and a result visualization output module;

[0098] Among them, the data initialization module is used to divide the pressure vessels of the specified model into test batches and inspection batches, and divide the inspection parts for each pressure vessel;

[0099] The test batch data analysis module is used to obtain different detection method data from the associated database through the industrial cloud computing platform, and obtain the test batch defect detection information of different parts of each pressure vessel in the test batch according to the different detection method data;

[0100] The superiority index analysis module is used to judge the superiority index of different detection methods when detecting different parts based on defect detection information. The superiority index is used to describe the detection effect of the detection method on different parts of the pressure vessel;

[0101] A mapping table generation module is used to sort the superiority indexes of different parts of the pressure vessel, obtain the optimal detection methods corresponding to different parts, and generate a method-part mapping table between the detection method data and the part data;

[0102] The inspection batch data analysis module is used to obtain the specified inspection method data from the associated database according to the method and part mapping table, detect the corresponding parts of the pressure vessels in the inspection batch according to the specified inspection method data, and obtain the inspection batch defect detection information;

[0103] The comprehensive safety evaluation module is used to conduct comprehensive safety evaluation on the inspection batch defect detection information of different parts of each pressure vessel to obtain an overall safety score. The overall safety score is used to determine the overall safety level of the pressure vessel.

[0104] The result visualization output module is used to visualize the inspection batch defect detection information and overall safety score to users through the industrial cloud computing platform.

[0105] In summary, the embodiments of the present application process the pressure vessels in batches and comprehensively inspect the pressure vessels by parts, that is, determine the inspection method corresponding to each part from the pressure vessels in the test batch, and generate a method-part mapping table. For the inspection batch pressure vessels, the corresponding inspection method is selected according to the method-part mapping table to inspect the corresponding parts, and a comprehensive safety evaluation is performed, so that the inspection results of the pressure vessels can be obtained in a more comprehensive and detailed manner.

[0106] The algorithms and modules involved in the present invention can be executed by electronic devices. The electronic devices include a memory, a processor, and a computer program stored in the memory and executable on the processor. The above-mentioned algorithm calculations and module functions are implemented by executing software through the processor.

Claims

1. A pressure vessel defect safety assessment method based on industrial cloud computing, characterized by The following steps are involved: Divide the pressure vessels of specified models into test batches and inspection batches, and divide the inspection parts of each pressure vessel; Obtain different detection method data from the associated database through the industrial cloud computing platform, and obtain the test batch defect detection information of different parts of each pressure vessel in the test batch according to the different detection method data; The superiority index of different detection methods when detecting different parts is judged according to the defect detection information. The superiority index is used to describe the detection effect of the detection method on different parts of the pressure vessel; The superiority indexes of different parts of the pressure vessel are ranked high and low, the optimal detection methods corresponding to different parts are obtained, and a method-part mapping table between the detection method data and the part data is generated; Obtain designated inspection method data from the associated database according to the method-part mapping table, inspect corresponding parts of the pressure vessels in the inspection batch according to the designated inspection method data, and obtain defect inspection information of the inspection batch; Conduct comprehensive safety evaluation on the defect detection information of inspection batches of different parts of each pressure vessel to obtain an overall safety score, which is used to determine the overall safety level of the pressure vessel. The inspection batch defect detection information and overall safety score are visualized and displayed to users through the industrial cloud computing platform; The superiority index is obtained as follows: Obtain the test batch defect detection information, and analyze the sensitivity, penetration depth, time cost and expense of the detection method based on the test batch defect detection information; Standardize the sensitivity, penetration depth, time cost and expense of the detection method, and analyze the superiority index based on the standardized results; The calculation formula of the superiority index is: ； In the formula, is the superiority index of the i-th detection method for the j-th part, is the sensitivity of the i-th detection method to the j-th part, is the penetration depth of the i-th detection method to the j-th part, is the time cost of the i-th detection method for the j-th part, is the cost of the i-th detection method for the j-th part; The overall safety score is obtained as follows: Number the pressure vessels and number the corresponding part types of the pressure vessels; Obtain inspection batch defect detection information of various parts of pressure vessels; Obtain the defect detection information of the test batch, and filter out the defect detection information corresponding to the part according to the method-part mapping table; Count the defect detection information of the same part of multiple pressure vessels and take the average value as the defect expectation value of the part; Analyze the defect deviation value by comparing the defect detection information of the inspection batch with the defect expected value; Obtain the weight setting value of the part type, and calculate the overall safety score based on the weight setting value and the defect deviation value; The calculation formula for the overall safety score is: ； ； In the formula, is the overall safety score of the kth pressure vessel, k is the number of the pressure vessel, is the defect deviation value of the jth part in the kth pressure vessel, j is the number of the inspection part in the pressure vessel, j=1,2,...,J, J is the total number of inspection parts in the pressure vessel, is the weight value of the jth part, is the inspection batch defect detection information of the jth part in the kth pressure vessel, is the expected value of defects at the jth location in the kth pressure vessel.

2. The pressure vessel defect safety assessment method based on industrial cloud computing according to claim 1, characterized in that: The division of the inspection parts includes surface parts, internal parts, welding parts and joint parts; Surface part: including the outer surface and inner surface of the pressure vessel; Internal parts: including pipes and cavities inside the pressure vessel; Welding area: including all welding joints and weld areas; Joint parts: including connection points and interfaces of various parts of the pressure vessel.

3. The pressure vessel defect safety assessment method based on industrial cloud computing according to claim 1, characterized in that: The detection method data refers to the step data corresponding to each detection method stored in the device, including: Detection steps: describe the operation steps and parameter settings of each detection method; Testing conditions: including environmental conditions, equipment parameters and operating specification information; Equipment performance: including equipment performance indicators.

4. The pressure vessel defect safety assessment method based on industrial cloud computing according to claim 1, characterized in that: The sensitivity of the detection method refers to the smallest detectable size; The penetration depth of a detection method refers to the depth range of detection; The time cost of a test method refers to the length of time required to record and complete the test; The cost of the test method is the cost of performing the test.

5. The pressure vessel defect safety assessment method based on industrial cloud computing according to claim 1, characterized in that: The visual display comprises the following steps: Use the industrial cloud computing platform to generate charts and reports, and update and dynamically display inspection batch defect detection information and overall safety scores in real time; Through the user interaction interface, users can view the effect comparison of different detection methods, defect data of each part and the overall safety score.

6. A pressure vessel defect safety assessment system based on industrial cloud computing, used to implement the pressure vessel defect safety assessment method based on industrial cloud computing according to any one of claims 1 to 5, characterized in that: It includes data initialization module, test batch data analysis module, superiority index analysis module, mapping table generation module, inspection batch data analysis module, comprehensive safety evaluation module and result visualization output module; Among them, the data initialization module is used to divide the pressure vessels of the specified model into test batches and inspection batches, and divide the inspection parts for each pressure vessel; The test batch data analysis module is used to obtain different detection method data from the associated database through the industrial cloud computing platform, and obtain the test batch defect detection information of different parts of each pressure vessel in the test batch according to the different detection method data; The superiority index analysis module is used to judge the superiority index of different detection methods when detecting different parts based on defect detection information. The superiority index is used to describe the detection effect of the detection method on different parts of the pressure vessel; A mapping table generation module is used to sort the superiority indexes of different parts of the pressure vessel, obtain the optimal detection methods corresponding to different parts, and generate a method-part mapping table between the detection method data and the part data; The inspection batch data analysis module is used to obtain the specified inspection method data from the associated database according to the method and part mapping table, detect the corresponding parts of the pressure vessels in the inspection batch according to the specified inspection method data, and obtain the inspection batch defect detection information; The comprehensive safety evaluation module is used to conduct comprehensive safety evaluation on the inspection batch defect detection information of different parts of each pressure vessel to obtain an overall safety score. The overall safety score is used to determine the overall safety level of the pressure vessel. The result visualization output module is used to visualize the inspection batch defect detection information and overall safety score to users through the industrial cloud computing platform.

Images