A damage-based inspection strategy intelligent generation system and method for pressure-bearing equipment

Abstract

The application discloses a kind of based on damage pressure-bearing equipment inspection strategy intelligent generation system and method, it is related to pressure-bearing detection technical field.The system includes: database module, equipment information acquisition module, damage identification module, pressure-bearing equipment risk assessment module and inspection strategy generation module.Wherein through equipment information acquisition module and database module, equipment preparation data and label data are obtained, then using equipment preparation data in damage identification module successively carries out damage identification, mode screening and damage calculation, obtains screened damage mode and corresponding damage data, and then through risk assessment calculation, the equipment failure possibility grade of damage identification model, equipment failure consequence grade and risk grade are obtained, finally the inspection strategy of pressure-bearing equipment is generated.The application reduces the formulation cost of inspection strategy, improves the inspection efficiency of pressure-bearing equipment.

Description

Technical Field

[0001] This invention relates to the field of pressure testing technology, and in particular to an intelligent generation system and method for inspection strategies of pressure-bearing equipment based on damage. Background Technology

[0002] The long-term safe operation of petrochemical pressure equipment is directly related to the safety of people's lives and property, and also affects the production efficiency and economic benefits of petrochemical enterprises. To ensure the safe operation of in-use pressure equipment, regular inspections are currently implemented for pressure vessels, pressure pipelines, boilers, and other in-use pressure equipment, and corresponding safety technical specifications have been established. However, the traditional inspection model for petrochemical plant pressure equipment still has certain limitations and is somewhat arbitrary. Traditional inspections do not link equipment inspection with risk; statistical studies show that 20% of the equipment in a plant bears 80% of the risk. Therefore, adopting risk-based inspection (RBI) technology can formulate inspection strategies based on equipment damage patterns and risk levels, focusing on the inspection and maintenance of high-risk areas, making inspections more targeted and effective, saving inspection and coordination costs, shortening major overhaul time, and improving inspection efficiency.

[0003] However, current equipment risk calculations and inspection strategy formulation still require assessors to determine and input key assessment parameters such as damage mechanisms, damage rates and susceptibility, and inspection effectiveness based on experience and historical data in order to obtain reasonable and accurate results. Therefore, in the actual operation of calculating a large number of pieces of equipment, this can lead to problems such as incomplete identification of damage mechanisms, inaccurate calculation of damage rates and susceptibility, and unreasonable inspection strategies. Furthermore, manual judgment and calculation require assessors to search through a large amount of data, which increases the cost of developing inspection strategies and affects the efficiency of pressure equipment inspection. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent generation system and method for inspection strategies of pressure equipment based on damage, which can reduce the cost of formulating inspection strategies and improve the efficiency of inspection of pressure equipment.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] In a first aspect, the present invention provides an intelligent generation system for inspection strategies of pressure-bearing equipment based on damage, comprising:

[0007] A database module is used to store relevant data for pressure equipment; the relevant data includes material and medium data, equipment basic data, and label data for the pressure equipment; the material and medium data includes material data and medium data; the equipment basic data includes construction data, process data, and inspection history data; the label data includes device labels, equipment labels, and corrosion circuit labels.

[0008] The equipment information acquisition module, connected to the database module, is used to acquire equipment preparation data and tag data of the target pressure-bearing equipment; the equipment preparation data is the updated basic equipment data of the target pressure-bearing equipment; the data update involves extracting the material medium data of the target pressure-bearing equipment into the basic equipment data of the target pressure-bearing equipment.

[0009] The damage identification module, connected to the equipment information acquisition module, is used to sequentially perform damage identification, pattern filtering, and damage calculation on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment; the damage data includes corrosion rate and sensitivity data; the target data includes equipment preparation data and label data of the target pressure-bearing equipment.

[0010] The pressure equipment risk assessment module is connected to the equipment information acquisition module and the damage identification module, respectively. It is used to perform risk assessment calculations based on the equipment preparation data, damage modes and corresponding damage data to obtain the pressure equipment risk assessment result corresponding to the damage mode. The risk assessment calculation includes failure consequence calculation and failure probability calculation. The pressure equipment risk assessment result includes equipment failure probability level, equipment failure consequence level and risk level.

[0011] The inspection strategy generation module is connected to the equipment information acquisition module, the damage identification module, and the pressure equipment risk assessment module, respectively. It is used to generate an inspection strategy based on the equipment preparation data, the damage mode and the corresponding damage data, and the pressure equipment risk assessment results. The inspection strategy includes inspection methods and corresponding inspection ratios. The inspection methods include macroscopic inspection, wall thickness measurement, surface defect detection, and buried defect detection.

[0012] Optionally, the database module includes:

[0013] A material medium data storage unit, connected to the equipment information acquisition module, is used to store the material medium data of the pressure equipment;

[0014] The equipment basic data storage unit is connected to the equipment information acquisition module and is used to store the basic data of the pressure equipment;

[0015] The tag data storage unit is connected to the device information acquisition module and is used to store the tag data of the pressure equipment.

[0016] Optionally, the device information acquisition module includes:

[0017] The information acquisition unit, connected to the database module, is used to acquire material medium data, equipment basic data, and label data of the target pressure-bearing equipment.

[0018] An information update unit, connected to the information acquisition unit, is used to extract the material data of the target pressure-bearing equipment into the construction data of the target pressure-bearing equipment, and to extract the medium data of the target pressure-bearing equipment into the process data of the target pressure-bearing equipment, so as to obtain equipment preparation data;

[0019] The information transmission unit is connected to the information acquisition unit, the information update unit, the damage identification module, the pressure equipment risk assessment module, and the inspection strategy generation module, respectively, and is used to transmit the target data to the damage identification module, the pressure equipment risk assessment module, and the inspection strategy generation module, respectively.

[0020] Optionally, the damage identification module includes:

[0021] A primary identification unit, connected to the equipment information acquisition module, is used to sequentially perform tag combination and damage identification based on the tag data of the target pressure-bearing equipment to determine the corresponding preliminary damage result; the tag combination includes the combination of different device tags and equipment tags, and the combination of different device tags and corrosion circuit tags; the preliminary damage result includes the damage mode corresponding to the combination of different device tags and equipment tags, and the damage mode corresponding to the combination of different device tags and corrosion circuit tags.

[0022] A secondary identification unit, connected to the primary identification unit and the equipment information acquisition module respectively, is used to perform pattern filtering on the preliminary damage results based on the equipment preparation data of the target pressure-bearing equipment to obtain the filtered damage patterns.

[0023] The third-level identification unit is connected to the second-level identification unit, the equipment information acquisition module, the pressure equipment risk assessment module, and the inspection strategy generation module, respectively. It is used to perform damage calculation on the screened damage modes based on the equipment preparation data of the target pressure equipment to obtain the damage data corresponding to the screened damage modes.

[0024] Optionally, the pressure equipment risk assessment module includes:

[0025] The equipment failure consequence calculation unit is connected to the equipment information acquisition module and the inspection strategy generation module respectively. It is used to calculate the failure consequence based on the equipment preparation data of the target pressure-bearing equipment, obtain the failure consequence area, and classify the failure consequence area to obtain the equipment failure consequence level.

[0026] The equipment failure probability calculation unit is connected to the equipment information acquisition module, the damage identification module and the inspection strategy generation module respectively. It is used to calculate the failure probability based on the equipment preparation data of the target pressure equipment and the damage mode and the corresponding damage data, and to obtain the equipment failure probability level corresponding to the damage mode.

[0027] The risk level calculation unit is connected to the equipment failure probability calculation unit and the inspection strategy generation module, respectively, and is used to determine the risk level based on the equipment failure consequence level and the equipment failure probability level corresponding to the damage mode.

[0028] Optionally, the device failure probability calculation unit includes:

[0029] The inspection validity acquisition subunit is connected to the equipment information acquisition module and is used to calculate the inspection validity based on the inspection history data of the target pressure-bearing equipment to obtain the inspection validity corresponding to the damage mode.

[0030] The damage technology factor value calculation subunit is connected to the equipment information acquisition module, the inspection validity acquisition subunit and the damage identification module respectively. It is used to calculate the damage technology factor based on the equipment preparation data, the inspection validity corresponding to the damage mode, the damage mode and the corresponding damage data, and obtain the technology factor value corresponding to the damage mode.

[0031] The failure probability calculation subunit is connected to the damage technology factor value calculation subunit and the inspection strategy generation module, respectively, and is used to calculate the failure probability of the technology factor value corresponding to the damage mode to obtain the equipment failure probability level corresponding to the damage mode.

[0032] Secondly, a method for intelligently generating inspection strategies for pressure-bearing equipment based on damage, applied to the first aspect, characterized in that the method includes:

[0033] Acquire material medium data, equipment basic data, and label data of the target pressure-bearing equipment, and update the equipment basic data based on the material medium data to obtain equipment preparation data; the material medium data includes material data and medium data; the equipment basic data includes construction data, process data, and inspection history data; the label data includes device labels, equipment labels, and corrosion circuit labels;

[0034] Damage identification, pattern filtering, and damage calculation are performed sequentially on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment; the damage data includes corrosion rate and sensitivity data; the target data includes equipment preparation data and label data of the target pressure-bearing equipment.

[0035] Risk assessment calculations are performed based on the equipment preparation data, damage modes, and corresponding damage data to obtain the risk assessment results for the pressure equipment corresponding to the damage modes. The risk assessment calculations include failure consequence calculations and failure probability calculations. The risk assessment results for the pressure equipment include the equipment failure probability level, the equipment failure consequence level, and the risk level.

[0036] An inspection strategy is generated based on the equipment preparation data, the damage mode and corresponding damage data, and the risk assessment results of the pressure equipment. The inspection strategy includes inspection methods and corresponding inspection ratios. The inspection methods include macroscopic inspection, wall thickness measurement, surface defect detection, and buried defect detection.

[0037] Optionally, the step of sequentially performing damage identification, pattern filtering, and damage calculation on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment specifically includes:

[0038] Based on the tag data of the target pressure-bearing equipment, tag combinations and damage identification are performed sequentially to determine the corresponding preliminary damage results; the tag combinations include combinations of different device tags and equipment tags, and combinations of different device tags and corrosion circuit tags; the preliminary damage results include the damage modes corresponding to the combinations of different device tags and equipment tags, and the damage modes corresponding to the combinations of different device tags and corrosion circuit tags.

[0039] Based on the equipment preparation data of the target pressure-bearing equipment, the preliminary damage results are screened to obtain the screened damage patterns.

[0040] Damage calculations are performed on the screened damage modes based on the equipment preparation data of the target pressure-bearing equipment to obtain the damage data corresponding to the screened damage modes.

[0041] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0042] This invention discloses an intelligent generation system and method for inspection strategies of pressure equipment based on damage, including a database module, an equipment information acquisition module, a damage identification module, a pressure equipment risk assessment module, and an inspection strategy generation module. The equipment information acquisition module acquires material medium data, equipment basic data, and label data from the database module, and updates the equipment basic data using the material medium data to obtain equipment preparation data. Then, using this equipment preparation data, the damage identification module sequentially performs damage identification, pattern filtering, and damage calculation to obtain the filtered damage patterns and corresponding damage data. Finally, the risk assessment calculation yields the equipment failure probability level, equipment failure consequence level, and risk level of the damage identification model, ultimately generating an inspection strategy for the pressure equipment. This invention achieves rapid automatic identification of damage patterns through the damage identification module and generates inspection strategies for pressure equipment through the pressure equipment risk assessment module and the inspection strategy generation module, reducing the prediction cost of inspection strategies and thus improving the inspection efficiency of pressure equipment. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram of the intelligent generation system for damage-based pressure equipment inspection strategy according to the present invention.

[0045] Figure 2 This is a schematic diagram of the results of the pressure equipment risk assessment module in this embodiment;

[0046] Figure 3 This is a flowchart of the intelligent generation method for inspection strategies of pressure-bearing equipment based on damage according to the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] The purpose of this invention is to provide an intelligent generation system and method for inspection strategies of pressure equipment based on damage, which can reduce the cost of formulating inspection strategies and improve the efficiency of inspection of pressure equipment.

[0049] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] like Figure 1 As shown in the figure, an intelligent generation system for inspection strategies of pressure equipment based on damage provided by an embodiment of the present invention includes: a database module, an equipment information acquisition module, a damage identification module, a pressure equipment risk assessment module, and an inspection strategy generation module.

[0051] The database module is used to store relevant data of the pressure equipment; the relevant data includes material medium data, equipment basic data and label data of the pressure equipment; the material medium data includes material data and medium data; the equipment basic data includes construction data, process data and inspection history data; the label data includes device labels, equipment labels and corrosion circuit labels.

[0052] In one preferred embodiment, the database module specifically includes: a material medium data storage unit, a device basic data storage unit, and a tag data storage unit.

[0053] Specifically, the material medium data storage unit is connected to the equipment information acquisition module and is used to store the material medium data of the pressure equipment. The equipment basic data storage unit is connected to the equipment information acquisition module and is used to store the equipment basic data of the pressure equipment. The label data storage unit is connected to the equipment information acquisition module and is used to store the label data of the pressure equipment.

[0054] As a specific embodiment, the database module includes the following:

[0055] The material data includes material standard grades and their corresponding chemical compositions, allowable stresses at different temperatures, material categories, and subcategories. Specifically, it includes over 1000 major domestic and international material standard grades, each with data such as chemical composition, allowable stresses at different temperatures, material grade, and material category / subcategory. This eliminates the need for operators to consult literature, manuals, or input data into the system. For example, if an operator selects the material grade 12Cr2Mo1R steel, the system will automatically identify the material category as low-alloy steel and the material subcategory as 2.25Cr1Mo steel; selecting the material grade S30408 ​​steel will automatically identify the material category as austenitic stainless steel and the material subcategory as 300 stainless steel.

[0056] The media data includes molecular weight, density, boiling point, phase in the environment, and representative media for each medium, covering more than 1,000 typical media in the petrochemical field. Operators no longer need to consult literature, manuals, or input data into the system. For example, if the operator selects gasoline as the medium, the system will automatically determine the phase as liquid based on pressure, with C6-C8 as a representative medium; if the operator selects ethylbenzene, the system will automatically determine the phase as liquid based on pressure, with styrene as a representative medium.

[0057] The equipment construction data includes basic construction data such as the name, number, type, size, material, service life, and whether insulation is required. The material is selected from a material database.

[0058] The equipment's process information data includes design temperature, design pressure, operating temperature, operating pressure, material composition, pH value, and other process information data, with the material composition selected from the media database.

[0059] The equipment's inspection history data includes the time, method, proportion, and results of each inspection. Inspection methods include internal or external inspection, macroscopic inspection, wall thickness measurement, surface defect detection, buried defect detection, and other inspections. Macroscopic inspection includes specific methods such as internal macroscopic inspection, external insulation removal inspection, and external insulation-free inspection. Wall thickness measurement includes specific methods such as ultrasonic scanning, ultrasonic sampling, cross-sectional X-ray, and ultrasonic guided wave. Surface defect detection includes specific methods such as carburizing test (PT), magnetic particle testing (MT), and eddy current testing (ET). Buried defect detection includes specific methods such as ultrasonic testing (UT), X-ray testing (RT), time-of-flight diffraction ultrasonic testing (TOFD), acoustic emission monitoring (AE), and eddy current testing (ET). Other inspections include specific methods such as metallographic analysis, hardness measurement, dimensional measurement, and ferrite content determination, which can be selected by the operator according to the actual situation. For example, when entering the 2020 inspection data of a pressure vessel, the inspection method was internal inspection, the macroscopic inspection was internal macroscopic inspection with a rate of 100%, and no abnormalities were found; the wall thickness was measured by ultrasonic sampling with a minimum wall thickness of 20mm; the surface defect detection was MT with a rate of 20%, and no abnormalities were found; the buried defect detection was UT with a rate of 20%, and no abnormalities were found.

[0060] The setting of device and equipment tags facilitates subsequent automatic damage identification, diagnosis, and statistical analysis. Based on the tags of pressure equipment stored in the tag storage unit, the system pre-sets tag types for typical devices and equipment. Device tags include atmospheric and vacuum distillation units, coking units, and hydrogenation units; equipment tags include atmospheric and vacuum distillation towers, hydrogenation reactors, and coke towers. Due to the large number of tag types, they are not listed here. Corrosion loops are devices with similar materials, media, and processes, exhibiting similar damage patterns. Therefore, setting corrosion loop tags facilitates subsequent automatic damage identification, diagnosis, and statistical analysis. Corrosion loop tags include atmospheric pressure tower top loops and vacuum distillation tower bottom loops. Due to the large number of tag types, they are not listed here.

[0061] The equipment information acquisition module, connected to the database module, is used to acquire equipment preparation data and tag data of the target pressure-bearing equipment; the equipment preparation data is the basic equipment data of the target pressure-bearing equipment after data update; the data update is to extract the material medium data of the target pressure-bearing equipment into the basic equipment data of the target pressure-bearing equipment.

[0062] In a preferred embodiment, the device information acquisition module specifically includes: an information acquisition unit, an information update unit, and an information transmission unit.

[0063] Specifically, the information acquisition unit is connected to the database module and is used to acquire material medium data, equipment basic data, and label data of the target pressure-bearing equipment. The information update unit is connected to the information acquisition unit and is used to extract the material data of the target pressure-bearing equipment into the construction data of the target pressure-bearing equipment, and to extract the medium data of the target pressure-bearing equipment into the process data of the target pressure-bearing equipment, to obtain equipment preparation data. The information transmission unit is connected to the information acquisition unit, the information update unit, the damage identification module, the pressure-bearing equipment risk assessment module, and the inspection strategy generation module, respectively, and is used to transmit the target data to the damage identification module, the pressure-bearing equipment risk assessment module, and the inspection strategy generation module, respectively.

[0064] The damage identification module, connected to the equipment information acquisition module, is used to sequentially perform damage identification, pattern filtering, and damage calculation on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment; the damage data includes corrosion rate and sensitivity data; the target data includes equipment preparation data and label data.

[0065] In a preferred embodiment, the damage identification module specifically includes: a primary identification unit, a secondary identification unit, and a tertiary identification unit.

[0066] Specifically, the primary identification unit is connected to the equipment information acquisition module and is used to sequentially perform tag combination and damage identification based on the tag data of the target pressure-bearing equipment to determine the corresponding preliminary damage results. The tag combination includes combinations of different device tags and equipment tags, and combinations of different device tags and corrosion circuit tags. The preliminary damage results include damage patterns corresponding to the combinations of different device tags and equipment tags, and damage patterns corresponding to the combinations of different device tags and corrosion circuit tags. The secondary identification unit is connected to the primary identification unit and the equipment information acquisition module, respectively, and is used to perform pattern filtering on the preliminary damage results based on the equipment preparation data of the target pressure-bearing equipment to obtain the filtered damage patterns. The tertiary identification unit is connected to the secondary identification unit, the equipment information acquisition module, the pressure-bearing equipment risk assessment module, and the inspection strategy generation module, respectively, and is used to perform damage calculation on the filtered damage patterns based on the equipment preparation data of the target pressure-bearing equipment to obtain the damage data corresponding to the filtered damage patterns.

[0067] As a specific embodiment, the implementation process of the damage identification module is as follows:

[0068] The primary identification unit is used to initially determine the damage mode, first by acquiring the device tag (L) of the equipment. unit ), equipment label (L) equip ) and corrosion circuit label (L loop The system has a built-in tag-based identification and diagnosis rule base (partially shown in Table 1) containing information such as the combination of different device tags and equipment tags, and different combinations of device tags and corrosion circuit tags, covering all possible damage modes. It can be used to combine input tag information and identify and diagnose according to the rules (f1(L)). unit L equip L loop Output all corresponding damage modes ({D) a1 D a2 ... D aN The process proceeds to the secondary identification unit. For example, if the equipment type is selected as a hydrogenation reactor, the damage modes output by the identification and diagnosis will be high-temperature sulfidation corrosion (hydrogen-free environment), high-temperature sulfidation corrosion (hydrogen environment), polythionite stress corrosion cracking, tempering embrittlement, high-temperature hydrogen corrosion, chloride stress corrosion cracking, hydrogen embrittlement, and σ-phase embrittlement. Similarly, if the corrosion circuit is selected as an electro-deionized water circuit, the damage modes output by the identification and diagnosis will be salt water corrosion, hydrochloric acid corrosion, chloride stress corrosion cracking, etc. Due to the numerous judgment logics, they are not all listed here; some identification and diagnosis rules are shown in Table 1.

[0069] Table 1. Partial List of Label-Based First-Level Recognition Rule Base

[0070]

[0071]

[0072] The secondary identification unit is used for detailed damage mode identification. Based on data such as material category (Mat1), material subcategory (Mat2), main medium (Flu), material composition (Comp), temperature (T), pressure (P), and pH value (pH) from the equipment preparation data, as well as the system's built-in parameter-based identification and diagnosis rule base (f2(Mat1, Mat2, Flu, Comp, T, P, pH…), some of which are shown in Table 2), the computer judges all possible damage modes output from the primary identification unit one by one, and outputs damage modes that meet the first preset evaluation range. The first preset evaluation range is finally confirmed by the operator, and the screened damage modes {D} are selected. a1 D a2 ... D aM The values ​​(M≤N) are input to the third-level identification unit. For damage patterns in Table 2 with multiple rules, the computer determines the existence of the damage pattern only if all identification and diagnostic rules are met. For example, in the previous example of hydrochloric acid corrosion in the electrostatic desalination tank, the system checks for the presence of HCl and water in the material and whether the pH value is less than 7.0. If HCl and water are present and the pH is less than 7.0, then the hydrochloric acid corrosion damage pattern is confirmed. Due to the complexity of the judgment logic, it is not listed here; some identification and diagnostic rules can also be found in Table 2.

[0073] Table 2. Parameter-based Secondary Recognition Rule Base (Partial)

[0074]

[0075] The advantage of using two-level identification here is that the identification is more accurate. First, all possible damage patterns are screened, and then the actual damage patterns are determined. Moreover, the first preset evaluation range conforms to the knowledge logic behavior of experts, and will not miss the damage patterns that should exist, nor will it incorrectly identify the damage patterns that should not exist.

[0076] The third-level identification unit is used to perform detailed calculations on the corrosion rate or sensitivity of different damage modes. This unit acquires all the final damage modes {D} output from the second-level identification unit. a1 D a2 ... D aN}, and based on data such as material category (Mat1), material subcategory (Mat2), main medium (Flu), material composition (Comp), temperature (T), pressure (P), and pH value (pH), as well as the diagnostic logic in the system's built-in corrosion rate and sensitivity diagnostic rule base (see Tables 3-5 for part f3), for each damage mode {D a1 D a2... D aM The corresponding corrosion rate or sensitivity {v} Da1 v Da2 ..., v DaM The system performs detailed calculations and outputs the results to the equipment failure probability calculation unit. For example, if the damage mode of a certain equipment is hydrochloric acid corrosion, the material library grade is 20 steel, the medium library is hydrochloric acid, the temperature is 25℃, and the pH value is 5.75, then the system automatically outputs a corrosion rate of 0.1 mm / year. Since there are many other judgment logics, they are not listed here. Some identification and diagnostic logics can also be seen in Tables 3-5. The advantage of three-level identification is that operators do not need to consult literature or manuals to determine the corrosion rate or sensitivity.

[0077] Table 3. Diagnostic Rules for Hydrochloric Acid Corrosion Rate of Carbon Steel

[0078]

[0079] Table 4. Diagnostic Rules for High-Temperature Oxidation Corrosion Rate

[0080]

[0081]

[0082] Table 5. Diagnostic Rules for High-Temperature Sulfur Corrosion Rate

[0083]

[0084]

[0085] The pressure equipment risk assessment module is connected to the equipment information acquisition module and the damage identification module, respectively. It is used to perform risk assessment calculations based on the equipment preparation data, damage mode and corresponding damage data, and obtain the pressure equipment risk assessment result corresponding to the damage mode. The risk assessment calculation includes failure consequence calculation and failure probability calculation. The pressure equipment risk assessment result includes equipment failure probability level, equipment failure consequence level and risk level.

[0086] In a preferred embodiment, the pressure equipment risk assessment module specifically includes: an equipment failure consequence calculation unit, an equipment failure probability calculation unit, and a risk level calculation unit.

[0087] Specifically, the equipment failure consequence calculation unit is connected to both the equipment information acquisition module and the inspection strategy generation module. It calculates the failure consequences based on the equipment preparation data of the target pressure-bearing equipment, obtains the failure consequence area, and classifies the area into levels to obtain the equipment failure consequence level. The equipment failure probability calculation unit is connected to the equipment information acquisition module, the damage identification module, and the inspection strategy generation module. It calculates the failure probability based on the equipment preparation data of the target pressure-bearing equipment, the damage mode, and the corresponding damage data, obtaining the equipment failure probability level corresponding to the damage mode. The risk level calculation unit is connected to both the equipment failure probability calculation unit and the inspection strategy generation module. It determines the risk level based on the equipment failure consequence level and the equipment failure probability level corresponding to the damage mode.

[0088] The further embodiment of the device failure probability calculation unit includes: a validity verification acquisition subunit, a damage technology factor value calculation subunit, and a failure probability calculation subunit.

[0089] Specifically, the inspection validity acquisition subunit is connected to the equipment information acquisition module and is used to calculate the inspection validity based on the inspection history data of the target pressure-bearing equipment to obtain the inspection validity corresponding to the damage mode. The damage technology factor value calculation subunit is connected to the equipment information acquisition module, the inspection validity acquisition subunit, and the damage identification module, respectively, and is used to calculate the damage technology factor based on the equipment preparation data, the inspection validity corresponding to the damage mode, the damage mode, and the corresponding damage data to obtain the technology factor value corresponding to the damage mode. The failure probability calculation subunit is connected to the damage technology factor value calculation subunit and the inspection strategy generation module, respectively, and is used to calculate the failure probability of the technology factor value corresponding to the damage mode to obtain the equipment failure probability level corresponding to the damage mode.

[0090] As a specific embodiment, the implementation process of the pressure equipment risk assessment module is as follows:

[0091] The equipment failure probability calculation unit first obtains the damage mode and corresponding corrosion rate or sensitivity information output from the damage identification module, and then calculates the test validity information {V} corresponding to the damage mode. Da1 V Da2 ... V DaM}, Test count information {Test Da1 Test DaM}, based on the system's built-in damage technology factor calculation rule base (f4(Da, v) Da V Da TestDa )) Calculate the technical factor value {F} corresponding to this damage. Da1 F DaM}

[0092] The validity assessment subunit within the equipment failure probability calculation unit incorporates a built-in rule base for calculating validity (f5(Test)). Method Test prop (See Table 7 for details), and the historical number of equipment inspections can be obtained from the historical inspection data. Da ), Test method Method ) and test ratio (Test) prop ), and calculate the test validity {V} for each damage mode accordingly. Da1 V Da2 ... V DaM The validity of the inspection is categorized into high validity, medium-high validity, medium validity, general validity, and invalid. The discrimination rules are further divided into internal and external inspections. For example, historical inspection data unit 23 records one inspection (in 2020), with internal inspection as the method, internal macroscopic inspection as the method (40%), and no abnormalities found. Wall thickness was measured using ultrasonic sampling, with a minimum wall thickness of 20mm. Surface defect detection was performed using MT (20%), and no abnormalities were found. Buried defect detection was performed using UT (20%), and no abnormalities were found. Based on the built-in corrosion thinning damage mode calculation logic (see Table 6), the computer determines the validity of the hydrochloric acid corrosion inspection to be medium-high validity.

[0093] Table 6 Rules for Judging the Effectiveness of Corrosion Thinning Inspection

[0094]

[0095]

[0096] There are seven main categories of damage technology factors, including thinning sub-factors, stress corrosion cracking sub-factors, high-temperature hydrogen erosion sub-factors, furnace tube damage sub-factors, mechanical fatigue sub-factors, equipment lining failure sub-factors, outer wall damage sub-factors, and brittle fracture sub-factors. The calculation rules for each sub-factor differ within the failure probability calculation sub-unit. For example, the calculation rules for corrosion thinning technology factors are shown in Table 7. Based on the equipment's hydrochloric acid corrosion rate, service life *a*, original wall thickness *t*, inspection validity level, and number of inspections, the computer determines the technology factor for the hydrochloric acid corrosion damage mode to be 70 according to the calculation logic in Table 7. Furthermore, due to the numerous logics involved in determining the inspection validity and technology factors for other damage modes, they are not listed here.

[0097] The method of calculation and automatic identification of test validity here eliminates the tedious process of manual data search and evaluation by traditional operators. Moreover, it provides a computer-automated method for determining the validity of different damage modes according to the number of tests, test methods and test ratios, which is clearer and easier to operate than the traditional descriptive methods in the standard.

[0098] Finally, in the failure probability calculation subunit, based on the technical factor values ​​of each damage mode, the failure probability level (D) of each damage mode's technical factor is divided. Then, according to the standard method of GB / T 26610 "Guidelines for Risk-Based Inspection of Pressure Equipment Systems", the total factor value F of the technical module is calculated. Da and the final equipment failure probability level F(F) Da The failure probability level (D) of the technology factor includes 5 levels, as shown in Table 8. For example, if the corrosion thinning technology factor is 70, the corresponding level is 3.

[0099] The equipment failure consequence calculation unit calculates the impact area level (CA) of failure consequences such as equipment medium inventory, toxicity, and explosion based on information such as equipment type, main medium, material composition, medium phase, operating temperature, and operating pressure, and in accordance with the GB / T 26610 standard method. For each piece of equipment, the failure consequence level is divided into AE level according to the area after failure from low to high, as shown in Table 8.

[0100] Based on the calculated equipment failure probability level and failure consequence level, the equipment risk level is comprehensively determined. The risk level includes low risk, medium risk, medium-high risk, and high risk. See details below. Figure 2 As shown.

[0101] Table 7 Calculation Rules for Corrosion Thinning Technology Factors

[0102]

[0103] Table 8. Classification Standards for Failure Probability Levels and Failure Consequence Levels of Technical Factors

[0104]

[0105]

[0106] The inspection strategy generation module is connected to the equipment information acquisition module, the damage identification module, and the pressure equipment risk assessment module, respectively. It is used to generate an inspection strategy based on the equipment preparation data, the damage mode and the corresponding damage data, and the pressure equipment risk assessment results. The inspection strategy includes inspection methods and corresponding inspection ratios. The inspection methods include macroscopic inspection, wall thickness measurement, surface defect detection, and buried defect detection.

[0107] As a specific embodiment, the implementation process of the inspection strategy generation module is as follows:

[0108] Based on the computer's built-in inspection strategy generation rule base (f6(Da, Risk, D, Mat1, Mat2, t, insulat)), inspection strategies are combined according to basic data such as risk level, equipment material type, wall thickness, and whether insulation is present, to generate the final inspection strategy. This strategy should fall within the second preset assessment range, which is ultimately confirmed by the operator. The inspection methods within the inspection strategy can also be adjusted according to specific implementation needs.

[0109] Finally, the output inspection strategy includes the use of internal or external inspection, macroscopic inspection methods and proportions, wall thickness measurement methods and proportions, surface defect detection methods and proportions, and buried defect detection methods and proportions. For example, for a low-alloy steel pressure vessel with a medium-to-high risk level, its corrosion thinning technology failure probability is level 3, and its environmental cracking technology factor is level 3. Operators select the internal inspection method based on the risk level and site conditions. The system's built-in inspection strategy generation logic is to perform macroscopic internal inspection, wall thickness measurement, and surface defect detection. The wall thickness measurement and surface defect detection methods and proportions are determined according to Table 9 of the system's built-in inspection strategy generation logic, and confirmed by the operator as ultrasonic sampling of wall thickness + MT (wet magnetic particle) testing of surface defects, with a proportion not less than 15%, significantly saving operators' time in manually formulating inspection strategies. Since there are many inspection strategy generation logics, they are not listed here.

[0110] Table 9. Automatic Generation Logic of Testing Strategies (Partial)

[0111]

[0112]

[0113] In summary, based on traditional risk assessment techniques, this invention achieves automatic identification of data such as material type, medium phase, corrosion rate, and inspection validity through technological innovations such as intelligent databases of materials and media, equipment and corrosion circuit labels, graded damage identification and diagnosis, and expert systems for identifying inspection effectiveness and formulating inspection strategies. It also enables intelligent diagnosis of damage modes and intelligent generation of inspection strategies, significantly improving the accuracy and efficiency of risk assessment, realizing intelligent risk assessment, reducing the prediction cost of inspection strategies, and improving the efficiency of pressure equipment inspection.

[0114] This invention also provides a method for intelligently generating inspection strategies for damage-based pressure equipment, applied to the aforementioned intelligent generation system for inspection strategies for damage-based pressure equipment, such as... Figure 3 As shown, the method includes:

[0115] Step 100: Obtain the material medium data, equipment basic data, and label data of the target pressure-bearing equipment, and update the equipment basic data according to the material medium data to obtain equipment preparation data; the material medium data includes material data and medium data; the equipment basic data includes construction data, process data, and inspection history data; the label data includes device labels, equipment labels, and corrosion circuit labels.

[0116] Step 200: Perform damage identification, pattern filtering, and damage calculation on the target data in sequence to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment; the damage data includes corrosion rate and sensitivity data; the target data includes equipment preparation data and label data of the target pressure-bearing equipment.

[0117] Step 300: Perform risk assessment calculations based on the equipment preparation data, damage modes, and corresponding damage data to obtain the risk assessment results for the pressure equipment corresponding to the damage modes; the risk assessment calculations include failure consequence calculations and failure probability calculations; the risk assessment results for the pressure equipment include the equipment failure probability level, the equipment failure consequence level, and the risk level.

[0118] Step 400: Generate an inspection strategy based on the equipment preparation data, the damage mode and corresponding damage data, and the risk assessment results of the pressure equipment; the inspection strategy includes inspection methods and corresponding inspection ratios; the inspection methods include macroscopic inspection, wall thickness measurement, surface defect detection and buried defect detection.

[0119] Step 200 specifically includes:

[0120] Step 201: Based on the tag data of the target pressure equipment, perform tag combination and damage identification in sequence to determine the corresponding preliminary damage results; the tag combination includes the combination of different device tags and equipment tags, and the combination of different device tags and corrosion circuit tags; the preliminary damage results include the damage modes corresponding to the combinations of different device tags and equipment tags, and the damage modes corresponding to the combinations of different device tags and corrosion circuit tags.

[0121] Step 202: Based on the equipment preparation data of the target pressure-bearing equipment, perform pattern screening on the preliminary damage results to obtain the screened damage patterns.

[0122] Step 203: Perform damage calculation on the screened damage modes based on the equipment preparation data of the target pressure-bearing equipment to obtain the damage data corresponding to the screened damage modes.

[0123] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0124] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A damage-based intelligent generation system for inspecting pressure-bearing equipment, characterized in that, include: A database module is used to store relevant data for pressure equipment; the relevant data includes material and medium data, equipment basic data, and label data for the pressure equipment; the material and medium data includes material data and medium data; the equipment basic data includes construction data, process data, and inspection history data; the label data includes device labels, equipment labels, and corrosion circuit labels. The equipment information acquisition module, connected to the database module, is used to acquire equipment preparation data and tag data of the target pressure-bearing equipment; the equipment preparation data is the updated basic equipment data of the target pressure-bearing equipment; the data update involves extracting the material medium data of the target pressure-bearing equipment into the basic equipment data of the target pressure-bearing equipment. The damage identification module, connected to the equipment information acquisition module, is used to sequentially perform damage identification, pattern filtering, and damage calculation on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment; the damage data includes corrosion rate and sensitivity data; the target data includes equipment preparation data and label data of the target pressure-bearing equipment. The damage identification module includes: A primary identification unit, connected to the equipment information acquisition module, is used to sequentially perform tag combination and damage identification based on the tag data of the target pressure-bearing equipment to determine the corresponding preliminary damage result; the tag combination includes the combination of different device tags and equipment tags, and the combination of different device tags and corrosion circuit tags; the preliminary damage result includes the damage mode corresponding to the combination of different device tags and equipment tags, and the damage mode corresponding to the combination of different device tags and corrosion circuit tags. The secondary identification unit, connected to both the primary identification unit and the equipment information acquisition module, is used to perform pattern filtering on the preliminary damage results based on the equipment preparation data of the target pressure-bearing equipment, thereby obtaining the filtered damage patterns. Specifically, the secondary identification unit uses the material category, sub-category, main medium, material composition, temperature, pressure, and pH value data in the equipment preparation data, as well as the system's built-in parameter-based identification and diagnosis rule library, to judge all possible damage patterns output by the primary identification unit one by one, and outputs damage patterns that meet the first preset evaluation range. The first preset evaluation range is finally confirmed by the operator, and the filtered damage patterns are then input into the tertiary identification unit. The third-level identification unit is connected to the second-level identification unit, the equipment information acquisition module, the pressure equipment risk assessment module and the inspection strategy generation module, respectively. It is used to perform damage calculation on the screened damage modes based on the equipment preparation data of the target pressure equipment to obtain the damage data corresponding to the screened damage modes. The pressure equipment risk assessment module is connected to the equipment information acquisition module and the damage identification module, respectively. It is used to perform risk assessment calculations based on the equipment preparation data, damage modes and corresponding damage data to obtain the pressure equipment risk assessment result corresponding to the damage mode. The risk assessment calculation includes failure consequence calculation and failure probability calculation. The pressure equipment risk assessment result includes equipment failure probability level, equipment failure consequence level and risk level. The inspection strategy generation module is connected to the equipment information acquisition module, the damage identification module, and the pressure equipment risk assessment module, respectively. It is used to generate an inspection strategy based on the equipment preparation data, the damage mode and corresponding damage data, and the pressure equipment risk assessment results. The inspection strategy includes inspection methods and corresponding inspection ratios. The inspection methods include macroscopic inspection, wall thickness measurement, surface defect detection, and buried defect detection. Specifically, based on the computer's built-in inspection strategy generation rule library, it combines inspection strategies according to the risk level, the equipment's material type, wall thickness, and whether it has insulation, to generate the final inspection strategy.

2. The intelligent generation system for damage-based pressure equipment inspection strategies according to claim 1, characterized in that, The database module includes: A material medium data storage unit, connected to the equipment information acquisition module, is used to store the material medium data of the pressure equipment; The equipment basic data storage unit is connected to the equipment information acquisition module and is used to store the basic data of the pressure equipment; The tag data storage unit is connected to the device information acquisition module and is used to store the tag data of the pressure equipment.

3. The intelligent generation system for damage-based pressure equipment inspection strategies according to claim 1, characterized in that, The device information acquisition module includes: The information acquisition unit, connected to the database module, is used to acquire material medium data, equipment basic data, and label data of the target pressure-bearing equipment. An information update unit, connected to the information acquisition unit, is used to extract the material data of the target pressure-bearing equipment into the construction data of the target pressure-bearing equipment, and to extract the medium data of the target pressure-bearing equipment into the process data of the target pressure-bearing equipment, so as to obtain equipment preparation data; The information transmission unit is connected to the information acquisition unit, the information update unit, the damage identification module, the pressure equipment risk assessment module, and the inspection strategy generation module, respectively, and is used to transmit the target data to the damage identification module, the pressure equipment risk assessment module, and the inspection strategy generation module, respectively.

4. The intelligent generation system for damage-based pressure equipment inspection strategies according to claim 1, characterized in that, The pressure equipment risk assessment module includes: The equipment failure consequence calculation unit is connected to the equipment information acquisition module and the inspection strategy generation module respectively. It is used to calculate the failure consequence based on the equipment preparation data of the target pressure-bearing equipment, obtain the failure consequence area, and classify the failure consequence area to obtain the equipment failure consequence level. The equipment failure probability calculation unit is connected to the equipment information acquisition module, the damage identification module and the inspection strategy generation module respectively. It is used to calculate the failure probability based on the equipment preparation data of the target pressure equipment and the damage mode and the corresponding damage data, and to obtain the equipment failure probability level corresponding to the damage mode. The risk level calculation unit is connected to the equipment failure probability calculation unit and the inspection strategy generation module, respectively, and is used to determine the risk level based on the equipment failure consequence level and the equipment failure probability level corresponding to the damage mode.

5. The intelligent generation system for damage-based pressure equipment inspection strategies according to claim 4, characterized in that, The device failure probability calculation unit includes: The inspection validity acquisition subunit is connected to the equipment information acquisition module and is used to calculate the inspection validity based on the inspection history data of the target pressure-bearing equipment to obtain the inspection validity corresponding to the damage mode. The damage technology factor value calculation subunit is connected to the equipment information acquisition module, the inspection validity acquisition subunit and the damage identification module respectively. It is used to calculate the damage technology factor based on the equipment preparation data, the inspection validity corresponding to the damage mode, the damage mode and the corresponding damage data, and obtain the technology factor value corresponding to the damage mode. The failure probability calculation subunit is connected to the damage technology factor value calculation subunit and the inspection strategy generation module, respectively, and is used to calculate the failure probability of the technology factor value corresponding to the damage mode to obtain the equipment failure probability level corresponding to the damage mode.

6. A method for intelligently generating inspection strategies for pressure-bearing equipment based on damage, applied to the intelligent generation system for inspection strategies for pressure-bearing equipment based on damage as described in any one of claims 1-5, characterized in that, The method includes: Acquire material medium data, equipment basic data, and label data of the target pressure-bearing equipment, and update the equipment basic data based on the material medium data to obtain equipment preparation data; the material medium data includes material data and medium data; the equipment basic data includes construction data, process data, and inspection history data; the label data includes device labels, equipment labels, and corrosion circuit labels; Damage identification, pattern filtering, and damage calculation are performed sequentially on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment; the damage data includes corrosion rate and sensitivity data; the target data includes equipment preparation data and label data of the target pressure-bearing equipment. Risk assessment calculations are performed based on the equipment preparation data, damage modes, and corresponding damage data to obtain the risk assessment results for the pressure equipment corresponding to the damage modes. The risk assessment calculations include failure consequence calculations and failure probability calculations. The risk assessment results for the pressure equipment include the equipment failure probability level, the equipment failure consequence level, and the risk level. An inspection strategy is generated based on the equipment preparation data, the damage mode and corresponding damage data, and the risk assessment results of the pressure equipment. The inspection strategy includes inspection methods and corresponding inspection ratios. The inspection methods include macroscopic inspection, wall thickness measurement, surface defect detection, and buried defect detection. Specifically, a rule library is generated based on the built-in inspection strategy in the computer. Inspection strategies are combined according to the risk level and the material type, wall thickness, and whether there is insulation of the equipment to generate the final inspection strategy. The process of sequentially performing damage identification, pattern filtering, and damage calculation on the target data to obtain the filtered damage patterns and corresponding damage data of the target pressure-bearing equipment specifically includes: Based on the tag data of the target pressure-bearing equipment, tag combinations and damage identification are performed sequentially to determine the corresponding preliminary damage results; the tag combinations include combinations of different device tags and equipment tags, and combinations of different device tags and corrosion circuit tags; the preliminary damage results include the damage modes corresponding to the combinations of different device tags and equipment tags, and the damage modes corresponding to the combinations of different device tags and corrosion circuit tags. Based on the equipment preparation data of the target pressure equipment, the preliminary damage results are filtered to obtain the filtered damage patterns. Specifically, based on the material category, sub-category, main medium, material composition, temperature, pressure, and pH value data in the equipment preparation data, as well as the system's built-in parameter-based identification and diagnosis rule library, the computer judges all possible damage patterns output by the primary identification unit one by one, and outputs damage patterns that meet the first preset evaluation range. The first preset evaluation range is finally confirmed by the operator. Damage calculations are performed on the screened damage modes based on the equipment preparation data of the target pressure-bearing equipment to obtain the damage data corresponding to the screened damage modes.

Images