Intelligent auxiliary system and method for regular inspection of pressure vessel

Abstract

The invention discloses an intelligent auxiliary system and method for regular inspection of a pressure vessel, and aims to improve the intelligence, efficiency and accuracy of inspection of the pressure vessel. The system comprises a data acquisition module, a data processing module, a risk assessment module, an inspection plan generation module, a report generation module, a remote monitoring module and a historical data management module. Operation parameters of the pressure vessel are collected in real time through the sensor, the data processing module carries out elimination and trend analysis on abnormal data, and the risk assessment module assesses the operation state of the pressure vessel through machine learning and a fuzzy logic algorithm. The system dynamically generates an inspection plan according to an evaluation result and adjusts an inspection period through Bayesian updating, and a generated inspection report has a digital signature to ensure safety. The historical data management module stores and analyzes long-term data and supports trend prediction of equipment health conditions, and the remote monitoring module provides real-time state checking and early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure vessel detection, and in particular to an intelligent auxiliary system and method for periodic inspection of pressure vessels. Background Art

[0002] Pressure vessels are widely used in various industrial fields such as chemical, petroleum, pharmaceutical, and energy to store or react flammable, explosive, toxic, or high-temperature and high-pressure media. Since they are subjected to very harsh working conditions, once a failure occurs, it is very easy to cause a major safety accident. Therefore, the safety of pressure vessels is of vital importance. In order to ensure the safe operation of pressure vessels, the state and the industry have clear legal and technical requirements for the regular inspection of pressure vessels. Regular inspection is a key means to ensure the long-term safe use of pressure vessels.

[0003] 1. Limitations of traditional inspection methods

[0004] Traditional periodic inspections of pressure vessels mainly rely on manual operations, including manual inspections of equipment surface corrosion, cracks, weld quality, and measurement of operating parameters such as pressure and temperature. Common inspection methods include visual inspection, ultrasonic testing, radiographic testing, and magnetic particle testing. Although these methods have been widely used in the past, they have the following significant problems in the current technical environment:

[0005] Large manual errors: Manual inspection relies on the experience of inspectors and is easily affected by subjective factors. In large-scale equipment inspection, it is easy to have problems such as missed inspections and false inspections. Especially in harsh industrial environments, it is more difficult to guarantee the energy and accuracy of inspectors.

[0006] Low efficiency: The traditional inspection process is cumbersome and involves many inspection contents. The inspection of a single device may take a lot of time and human resources, especially for large or high-voltage equipment, which requires a lot of professional equipment and personnel, increasing the difficulty and cost of inspection.

[0007] Difficulty in data management: Inspection data generated by traditional methods are often recorded in the form of paper reports or simple spreadsheets, which makes it difficult to effectively manage and analyze large-scale data. There is a lack of comprehensive data utilization capabilities, and historical data is difficult to trace and mine.

[0008] Unable to monitor in real time: Traditional inspections are mostly conducted periodically, usually every 6 months or 1 year, and cannot reflect changes in the status of the equipment in real time. In extreme cases, equipment failure may occur during the inspection interval, leading to safety accidents.

[0009] 2. Current technology trends and challenges

[0010] With the rapid development of technologies such as the Internet of Things (IoT), big data, artificial intelligence (AI) and cloud computing, intelligent management of industrial equipment has become a trend, especially in the field of equipment safety. The inspection efficiency and safety of pressure vessels can be significantly improved through real-time monitoring of equipment status, automated data analysis, dynamic risk prediction and automatic generation of inspection plans using advanced intelligent technologies.

[0011] At present, there are some preliminary intelligent monitoring and detection systems on the market, but these systems still have the following problems:

[0012] Low degree of intelligence: Most systems only realize data collection and basic parameter monitoring, lack the function of in-depth assessment of equipment health status and fault prediction under complex working conditions, and cannot fully replace traditional manual inspection methods.

[0013] Lack of data analysis depth: Although some systems can perform preliminary analysis of equipment operation data, most of these analyses remain at the data display level and are unable to achieve equipment health prediction and long-term trend analysis through data mining and deep learning.

[0014] Insufficient dynamic adjustment capabilities: Existing systems mostly set inspection plans on a regular basis, and are unable to flexibly adjust the inspection frequency and content based on the actual operating conditions and risk levels of the equipment, making it impossible to achieve true dynamic risk management.

[0015] Therefore, in view of the defects in the above-mentioned prior art, an intelligent auxiliary system and method for periodic inspection of pressure vessels based on real-time data collection, intelligent analysis, and dynamic inspection plan generation is proposed, which has important technical significance and application value. The system can improve inspection efficiency, reduce manual errors, realize long-term storage and trend analysis of data, automatically generate inspection plans, and greatly improve the safety and reliability of pressure vessels through remote monitoring and real-time early warning.

[0016] To this end, we designed an underwater robotic arm dragging control method and a robotic arm system to solve the above problems. Summary of the invention

[0017] The purpose of the present invention is to provide an underwater robotic arm dragging control method and a robotic arm system to address the deficiencies of the prior art, so as to solve the problems raised in the background technology.

[0018] To achieve the above object, the present invention provides the following technical solution: an intelligent auxiliary system for periodic inspection of pressure vessels, the system comprising:

[0019] A data acquisition module, used to collect operating parameters of the pressure vessel in real time through sensors, wherein the sensors include temperature sensors, pressure sensors, strain gauges and corrosion detectors, and the collected operating parameters include temperature, pressure, stress and corrosion conditions of the pressure vessel;

[0020] The data processing module is used to process the collected operating parameter data. The processing process includes the elimination of abnormal data, data trend analysis, and the judgment and prediction of the operating status;

[0021] The risk assessment module is used to assess the safety risk of the pressure vessel based on the data processed by the data processing module, by combining the historical operation data and real-time data of the pressure vessel, and adopting the linear regression model f(x)=W·X+b based on machine learning, wherein f(x) is the predicted safety risk value, W is the weight matrix, X is the input pressure vessel parameter matrix, and b is the bias term of the model;

[0022] An inspection plan generation module is used to automatically generate an inspection plan for the pressure vessel according to the risk assessment results obtained by the risk assessment module, wherein the inspection plan includes inspection time, inspection content, inspection standards and required inspection tools;

[0023] The report generation module is used to automatically generate an inspection report based on various data obtained during the inspection process. The report includes the analysis of the inspection data, the evaluation of the equipment's operating status and the final inspection conclusion. The report is digitally signed to ensure its security and non-tamperability.

[0024] Remote monitoring module, used to connect to the remote terminal via the Internet, so that users can monitor the operating status of the pressure vessel in real time, check the inspection status, and receive early warning information in real time when the equipment is abnormal;

[0025] The historical data management module is used to store and manage the historical inspection data of pressure vessels, and use big data analysis technology to archive, classify and analyze long-term trends of historical data.

[0026] As a preferred technical solution of the present invention, the data processing module removes abnormalities from the collected data based on the following formula:

[0027]

[0028] Among them, D i is the filtered data, x i is a single data point collected, μ is the mean of the collected data, σ is the standard deviation, and when the data point x i When the difference from the mean μ exceeds three times the standard deviation σ, the system regards the data point as an anomaly and removes it.

[0029] As a preferred technical solution of the present invention, the risk assessment module calculates the risk coefficient R of the pressure vessel by the following formula:

[0030]

[0031] Among them, R is the risk factor, which indicates the probability of failure of the pressure vessel, N is the number of historical data samples, and y i is the actual detection value, f(x i ) is the value predicted by the machine learning model, α is the adjustment coefficient, and the system evaluates the health status of the pressure vessel based on the risk factor R and gives a risk warning.

[0032] As a preferred technical solution of the present invention, the inspection plan generation module dynamically adjusts the time of the next inspection using the following formula according to the operating parameters of the pressure vessel and the risk assessment results:

[0033] T next =T current +β·(1-R)

[0034] Among them, T next is the time of the next inspection, T current is the time of the current inspection cycle, R is the risk factor, and β is the adjustment parameter related to the inspection cycle. When the risk factor is high, the system automatically shortens the inspection cycle to strengthen equipment monitoring.

[0035] As a preferred technical solution of the present invention, the report generation module uses the RSA algorithm for digital signature and encryption to ensure that the generated inspection report is unique, complete and tamper-proof. The core formula of the RSA algorithm is:

[0036] c=m e mod n

[0037] Among them, c is the encrypted ciphertext, m is the original data, e is the encrypted public key exponent, and n is the modulus, which ensures the secure transmission of the inspection report in the system.

[0038] As a preferred technical solution of the present invention, the remote monitoring module transmits the collected data to the cloud server via a wireless network, supporting users to access the operating status data of the pressure vessel anytime and anywhere through mobile terminal devices, and if an abnormal situation occurs during the operation of the equipment, the system will send real-time warning information to the user through the remote push function.

[0039] As a preferred technical solution of the present invention, the historical data management module performs linear regression analysis on the historical data based on the following formula to predict the long-term operation trend of the pressure vessel:

[0040] H(t)=γ·t+δ

[0041] Among them, H(t) is the predicted health status value of the pressure vessel, t is the time variable, γ is the regression coefficient, and δ is the constant term. By analyzing long-term historical data, the future health status of the pressure vessel can be predicted, thereby assisting the formulation of the inspection plan.

[0042] The present invention also provides an intelligent auxiliary method for periodic inspection of pressure vessels, the method comprising the following steps:

[0043] (1) collecting operating parameters of the pressure vessel in real time through a data acquisition module, wherein the operating parameters include pressure, temperature, stress and corrosion conditions;

[0044] (2) The data processing module pre-processes the collected parameter data, removes abnormal data, and performs trend analysis and risk assessment on the data;

[0045] (3) calculating the risk factor of the pressure vessel based on the processed data through the risk assessment module, and performing safety risk assessment based on the risk factor;

[0046] (4) Based on the risk assessment results, the inspection plan generation module automatically generates an inspection plan for the pressure vessel, which includes the inspection time, inspection content and inspection standards;

[0047] (5) After the inspection is completed, the report generation module automatically generates an inspection report based on the inspection process data and digitally signs and archives it;

[0048] (6) The historical data management module is used to store and manage the historical data of pressure vessels, and to perform long-term trend analysis on the data to assist in subsequent risk assessment and inspection plan generation.

[0049] As a preferred technical solution of the present invention, the risk assessment step also includes risk assessment based on a fuzzy logic algorithm, which performs a comprehensive assessment through the following formula:

[0050] R final =max(R1, R2, ..., R n )

[0051] Among them, R final is the final risk assessment value, R1, R2, ..., R n They are sub-risk assessment values ​​obtained based on different detection parameters (such as temperature, pressure, corrosion, etc.). The system combines various parameters according to fuzzy logic rules and obtains the final risk value.

[0052] As a preferred technical solution of the present invention, the inspection plan generation step further uses the Bayesian update formula to adjust the inspection period according to the operating conditions and environmental conditions of the pressure vessel:

[0053]

[0054] Among them, P(H|D) is the posterior probability of equipment failure H under given operating data D, P(D|H) is the possibility of observing data under fault conditions, P(H) is the initial failure probability of the equipment, and P(D) is the total probability of data occurrence. This formula is used to dynamically adjust the inspection cycle and frequency to ensure that the inspection interval is shortened in high-risk scenarios and extended in low-risk scenarios, thereby optimizing the efficiency and resource allocation of the inspection plan.

[0055] Compared with the prior art, the present invention has the following beneficial effects: Improved inspection efficiency and accuracy: The present invention uses intelligent data acquisition and processing modules to achieve real-time monitoring of pressure vessel operating parameters and automatic elimination of abnormal data, avoiding errors and missed inspections in traditional manual inspections. Machine learning and fuzzy logic algorithms are used to analyze and assess risks in the data, improving the accuracy and automation of the inspection process and significantly reducing manual intervention and time costs.

[0056] Realize dynamic inspection plan generation and optimization: The system can dynamically adjust the inspection cycle of pressure vessels based on real-time monitoring data and risk assessment results. By optimizing the inspection plan through algorithms such as Bayesian updating, the system can flexibly adjust the inspection frequency according to actual working conditions, shorten the cycle when the risk is high, and extend the cycle when the risk is low, ensuring the reasonable allocation and safety of inspection resources.

[0057] Enhanced data management and safety early warning capabilities: The system has historical data management and long-term trend analysis functions, supports big data mining and fault prediction, and helps users understand the operating trends of pressure vessels. At the same time, through the remote monitoring module, users can check the equipment status at any time and receive early warning information in time when there is a risk of failure, which greatly improves the initiative and reliability of equipment safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a system block diagram of an intelligent auxiliary system for periodic inspection of pressure vessels proposed by the present invention;

[0059] Figure 2 This is a method flow chart of an intelligent auxiliary method for periodic inspection of pressure vessels proposed by the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] The following is combined with Figure 1 and Figure 2 With reference to the accompanying drawings and a number of embodiments, specific embodiments of the present invention are described in detail.

[0062] Example 1: Pressure vessel operation data collection and processing

[0063] This embodiment describes how to monitor and analyze the operating status of a pressure vessel in real time through a data acquisition module and a data processing module.

[0064] First, at industrial sites, a variety of sensors are installed on pressure vessels, including temperature sensors, pressure sensors, strain gauges, and corrosion detectors. These sensors are used to collect various parameters related to the operating status of pressure vessels, such as temperature, pressure, stress, and corrosion. The sensors are connected to the data acquisition module wirelessly or wired, and the system can obtain these operating parameters in real time.

[0065] The data received by the system will be processed by the data processing module. The processing steps include:

[0066] Abnormal data elimination: Use the triple standard deviation elimination method to eliminate abnormal data that are obviously deviated from the normal range. The formula is:

[0067]

[0068] Among them, D i is the filtered data, x i is a single data point collected in real time, μ is the mean of this type of data, and σ is the standard deviation.

[0069] When the data point x i When the difference from the mean exceeds three standard deviations, the system removes the data point.

[0070] Data trend analysis: After removing abnormal data, the system performs trend analysis on the remaining data, analyzing the changes in pressure vessel parameters over time to determine whether there is a gradually deteriorating operating trend.

[0071] This embodiment ensures the accuracy and timeliness of the pressure vessel operation data and provides a reliable data basis for subsequent risk assessment.

[0072] Example 2: Risk assessment based on machine learning

[0073] In this embodiment, it is described how to use the risk assessment module to perform intelligent risk prediction on the operating status of the pressure vessel. The system performs risk assessment on the processed operating parameters (temperature, pressure, stress, corrosion, etc.) and uses a machine learning model to predict the health status of the equipment.

[0074] Based on historical data and real-time data, the system constructs a linear regression model with the following formula:

[0075] f(x)=W·X+b

[0076] Where: f(x) is the predicted safety risk value of the pressure vessel, W is the weight matrix of the model, which is used to represent the weights of different parameters (such as temperature and pressure), X is the input parameter matrix, which contains data such as pressure, temperature, stress and corrosion, and b is the bias term of the model, which is used to correct the predicted value.

[0077] Based on the risk value calculated by the machine learning model, the system can evaluate the current health status of the pressure vessel and determine whether there is a potential risk of failure. For example, if the model prediction value exceeds a certain preset threshold, the system will immediately issue a risk warning and prompt the operator to take appropriate maintenance measures.

[0078] Example 3: Comprehensive risk assessment based on fuzzy logic

[0079] This embodiment introduces how to combine fuzzy logic algorithm in risk assessment to perform comprehensive risk assessment.

[0080] The operating parameters of pressure vessels are not only affected by a single factor, but also involve multiple interrelated parameters. In order to more accurately predict equipment risks, this system uses fuzzy logic algorithms to comprehensively evaluate the risks of various detection parameters.

[0081] Specifically, the system calculates sub-risk assessment values ​​R1, R2, ..., R according to each detection parameter (temperature, pressure, stress, corrosion, etc.). n , and then the final comprehensive risk value is obtained by the following formula:

[0082] R final =max(R1, R2, ..., R n )

[0083] Among them, R final The final risk assessment result.

[0084] The formula shows that the final risk value of the pressure vessel depends on the one with the greatest risk among all the detection parameters, which ensures that the system can issue an early warning even if a certain parameter is abnormal.

[0085] Through the application of fuzzy logic, the system can handle a variety of complex parameter relationships and improve the accuracy of risk assessment.

[0086] Example 4: Dynamic Generation and Optimization of Inspection Plans

[0087] This embodiment describes how to dynamically adjust the inspection cycle of a pressure vessel through the inspection plan generation module of the system.

[0088] According to the risk assessment results, the system will automatically generate the next inspection plan. If the system assesses that the risk factor R of the pressure vessel is high, the inspection cycle will be automatically shortened, otherwise the inspection cycle will be extended. The inspection plan is generated using the following formula:

[0089] T next =T current +β·(1-R)

[0090] in:

[0091] T next is the time of the next inspection, T current is the time of the current inspection cycle, R is the current risk coefficient, and β is the adjustment parameter.

[0092] For example, if the risk factor of a pressure vessel is R = 0.7, and the current inspection cycle is 6 months, the time for the next inspection is:

[0093] T next =6+β·(1-0.7)

[0094] The system automatically adjusts β according to the specific operating conditions of the equipment, thereby optimizing the inspection cycle and improving the safety and inspection efficiency of the equipment.

[0095] Example 5: Inspection cycle optimization based on Bayesian updating

[0096] In order to further optimize the inspection plan under different operating environments and working conditions, this embodiment introduces the application of Bayesian updating in the inspection cycle adjustment.

[0097] The system dynamically adjusts the inspection cycle based on the operating data and historical experience of the pressure vessel using the Bayesian update formula:

[0098]

[0099] Where: P(H|D) represents the posterior probability of device failure under given data D, P(D|H) is the possibility of observing the data under failure conditions, P(H) is the initial probability of device failure, and P(D) is the total probability of data occurrence.

[0100] Through this formula, the system can dynamically update the failure probability based on real-time data, and then automatically adjust the inspection cycle. For example, when the equipment has abnormal operating data, the posterior probability P(H|D) increases, and the system will automatically shorten the inspection cycle to increase the inspection frequency.

[0101] This approach enables the system to respond flexibly in complex and changing industrial environments and ensures the safe operation of pressure vessels.

[0102] Example 6: Remote monitoring and real-time warning

[0103] This embodiment describes how to improve the operating safety of a pressure vessel through a remote monitoring module and a real-time early warning function.

[0104] The system uploads the collected pressure vessel operation data to the cloud server via wireless network. Users can access the system through PC, mobile phone and other terminal devices to view the operation status and historical data of the pressure vessel in real time. At the same time, if the system detects that a parameter exceeds the normal range, or the risk assessment module calculates a high probability of failure, the system will send an alarm message to relevant personnel through mobile devices to remind them to take timely measures.

[0105] For example, if the temperature of a pressure vessel rises sharply in a short period of time, the system will automatically identify this anomaly and immediately send an alarm to the manager's mobile phone, ensuring that relevant personnel can respond quickly and avoid potential equipment failures and accidents.

[0106] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent auxiliary system for periodic inspection of pressure vessels, characterized in that: The system includes: Data acquisition module: used to collect the operating parameters of the pressure vessel in real time through sensors, the sensors include temperature sensors, pressure sensors, strain gauges and corrosion detectors, and the collected operating parameters include temperature, pressure, stress and corrosion conditions of the pressure vessel; Data processing module: used to process the collected operating parameter data. The processing process includes the elimination of abnormal data, data trend analysis, and the judgment and prediction of operating status; Risk assessment module: It is used to assess the safety risk of pressure vessels based on the data processed by the data processing module, by combining the historical operation data and real-time data of the pressure vessels, and adopting the linear regression model f(x)=W·X+b based on machine learning, where f(x) is the predicted safety risk value, W is the weight matrix, X is the input pressure vessel parameter matrix, and b is the bias term of the model; Inspection plan generation module: used to automatically generate an inspection plan for pressure vessels based on the risk assessment results obtained by the risk assessment module. The inspection plan includes inspection time, inspection content, inspection standards and required inspection tools; Report generation module: used to automatically generate inspection reports based on various data obtained during the inspection process. The reports include analysis of inspection data, evaluation of equipment operation status and final inspection conclusions, and digitally sign the reports. Remote monitoring module: used to connect to the remote terminal through the Internet, so that users can monitor the operating status of the pressure vessel in real time, check the inspection status, and receive real-time warning information when the equipment is abnormal; Historical data management module: used to store and manage historical inspection data of pressure vessels, and use big data analysis technology to archive, classify and analyze long-term trends of historical data.

2. The intelligent auxiliary system for periodic inspection of pressure vessels according to claim 1, characterized in that: The data processing module removes abnormalities from the collected data based on the following formula: Among them, D i is the filtered data, x i is a single data point collected, μ is the mean of the collected data, σ is the standard deviation, and when the data point x i When the difference from the mean μ exceeds three times the standard deviation σ, the system regards the data point as an anomaly and removes it.

3. The intelligent auxiliary system for periodic inspection of pressure vessels according to claim 1, characterized in that: The risk assessment module calculates the risk factor R of the pressure vessel by the following formula: Among them, R is the risk factor, which indicates the probability of failure of the pressure vessel, N is the number of historical data samples, and y i is the actual detection value, f(x i ) is the value predicted by the machine learning model, α is the adjustment coefficient, and the system evaluates the health status of the pressure vessel based on the risk factor R and gives a risk warning.

4. The intelligent auxiliary system for periodic inspection of pressure vessels according to claim 1, characterized in that: The inspection plan generation module dynamically adjusts the time of the next inspection based on the operating parameters of the pressure vessel and the risk assessment results using the following formula: T next =T current +β·(1-R) Among them, T next is the time of the next inspection, T current is the time of the current inspection cycle, R is the risk coefficient, and β is the adjustment parameter related to the inspection cycle. When the risk coefficient is high, the system automatically shortens the inspection cycle.

5. The intelligent auxiliary system for periodic inspection of pressure vessels according to claim 1, characterized in that: The report generation module uses the RSA algorithm for digital signature and encryption. The core formula of the RSA algorithm is: c=m e mod n Among them, c is the encrypted ciphertext, m is the original data, e is the encrypted public key exponent, and n is the modulus.

6. The intelligent auxiliary system for periodic inspection of pressure vessels according to claim 1, characterized in that: The remote monitoring module transmits the collected data to the cloud server via a wireless network, and supports users to access the operating status data of the pressure vessel anytime and anywhere through mobile terminal devices. If an abnormal situation occurs during the operation of the equipment, the system will send real-time warning information to the user through the remote push function.

7. The intelligent auxiliary system for periodic inspection of pressure vessels according to claim 1, characterized in that: The historical data management module performs linear regression analysis on the historical data based on the following formula to predict the long-term operating trend of the pressure vessel: H(t)=γ·t+δ Among them, H(t) is the predicted health status value of the pressure vessel, t is the time variable, γ is the regression coefficient, and δ is the constant term.

8. An intelligent auxiliary method for periodic inspection of pressure vessels, characterized in that: The method comprises the following steps: (1) collecting operating parameters of the pressure vessel in real time through a data acquisition module, wherein the operating parameters include pressure, temperature, stress and corrosion conditions; (2) The data processing module pre-processes the collected parameter data, removes abnormal data, and performs trend analysis and risk assessment on the data; (3) calculating the risk factor of the pressure vessel based on the processed data through the risk assessment module, and performing safety risk assessment based on the risk factor; (4) Based on the risk assessment results, the inspection plan generation module automatically generates an inspection plan for the pressure vessel, which includes the inspection time, inspection content and inspection standards; (5) After the inspection is completed, the report generation module automatically generates an inspection report based on the inspection process data and digitally signs and archives it; (6) The historical data management module is used to store and manage the historical data of pressure vessels, and to perform long-term trend analysis on the data to assist in subsequent risk assessment and inspection plan generation.

9. The intelligent auxiliary method for periodic inspection of pressure vessels according to claim 8, characterized in that: The risk assessment step also includes a risk assessment based on a fuzzy logic algorithm, which performs a comprehensive assessment using the following formula: R final =max(R1,R2,…,R n ) Among them, R final is the final risk assessment value, R1, R2,…, R n They are sub-risk assessment values ​​obtained based on different detection parameters (such as temperature, pressure, corrosion, etc.). The system combines various parameters according to fuzzy logic rules and obtains the final risk value.

10. The intelligent auxiliary method for periodic inspection of pressure vessels according to claim 8, characterized in that: The inspection plan generation step further uses the Bayesian update formula to adjust the inspection period according to the operating conditions and environmental conditions of the pressure vessel: Where P(H|D) is the posterior probability of equipment failure H under given operating data D, P(D|H) is the possibility of observing data under fault conditions, P(H) is the initial failure probability of the equipment, and P(D) is the total probability of data occurrence.

Images