Intelligent monitoring and life prediction method and device for LNG (Liquefied Natural Gas) low-temperature safety valve and medium

Abstract

The invention provides an intelligent monitoring and life prediction method, device, equipment and medium for an LNG low-temperature safety valve, and the method comprises the steps: obtaining geometric structure parameters of the LNG low-temperature safety valve, building a three-dimensional model, and importing physical and material characteristics; operating data of the LNG low-temperature safety valve are collected in real time, the operating data are dynamically bound with the digital twinborn model, and the digital twinborn model is established; inputting the operation data into the digital twin model in real time to intelligently monitor the LNG low-temperature safety valve; and training a machine learning model through historical operation data, combining the machine learning model with the operation data, and predicting the residual life of the LNG low-temperature safety valve, so as to solve the problem that real-time monitoring and life prediction of the LNG low-temperature safety valve are difficult.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a method, device, equipment and medium for intelligent monitoring and life prediction of an LNG cryogenic safety valve. Background Art

[0002] In the process of liquefied natural gas (LNG) transportation and storage, LNG cryogenic safety valve is one of the key components, and its main function is to prevent equipment damage caused by excessive pressure. Existing LNG cryogenic safety valves are usually designed with a mechanical spring. When the pressure exceeds the set value, the spring force fails, the safety valve automatically opens, and the excess gas is released to reduce the pressure. Usually these valves rely on regular manual inspection and maintenance, and there is no support from real-time data monitoring systems. Although this traditional technology can protect equipment to some extent, it cannot provide real-time feedback and has high maintenance costs.

[0003] The existing technical solution is to use a traditional mechanical pressure safety valve, whose working principle is based on the balance between spring force and pressure. When the pressure in the tank exceeds the spring setting value, the spring contracts, the valve opens and releases gas, and then the valve closes when the pressure drops back to a safe range. In the existing technology, the safety valve relies on the physical action of mechanical components and is usually designed as a non-intelligent system without connecting sensors or data analysis systems, so the valve status cannot be remotely monitored.

[0004] The existing solutions have the following main disadvantages:

[0005] Real-time monitoring is not possible: Existing LNG cryogenic safety valves do not have an integrated sensor network and rely on regular manual inspections, making it difficult to capture abnormal conditions in a timely manner during equipment operation.

[0006] Lack of predictive capabilities: Existing mechanical safety valves cannot predict their working status and remaining life, and can only be estimated through usage time or regular maintenance, which may lead to premature or late maintenance, increasing operating costs and risks.

[0007] Slow response speed: Since there is no sensor-based intelligent system in the existing technology, when the pressure exceeds the safety value, the valve opening response time is slow, and it is difficult to respond quickly to instantaneous pressure fluctuations, which may lead to safety hazards.

[0008] High maintenance costs: Traditional safety valves require regular maintenance and replacement of components, and the equipment usually needs to be stopped during maintenance, resulting in increased downtime and maintenance costs.

[0009] Therefore, it is urgent to propose an intelligent monitoring and life prediction method for LNG cryogenic safety valves to solve the technical problem that it is difficult to monitor and predict the life in real time in the existing technology. Summary of the invention

[0010] In order to overcome the problems existing in the related art, the present disclosure provides a method, device and medium for intelligent monitoring and life prediction of LNG cryogenic safety valve, so as to solve the technical problem that it is difficult to monitor and predict the life in real time in the related art.

[0011] One or more embodiments of this specification provide a method for intelligent monitoring and life prediction of an LNG cryogenic safety valve, comprising the following steps:

[0012] Obtain the geometric structural parameters of the LNG cryogenic safety valve to establish a three-dimensional model, and import the physical and material properties;

[0013] By collecting the operating data of the LNG cryogenic safety valve in real time, the operating data is dynamically bound to the digital twin model to establish the digital twin model;

[0014] Inputting the operation data into the digital twin model in real time to perform intelligent monitoring on the LNG cryogenic safety valve;

[0015] The machine learning model is trained by using historical operating data, and the machine learning model is combined with the operating data to predict the remaining life of the LNG cryogenic safety valve.

[0016] Preferably, the method further comprises the following steps:

[0017] Environmental and load conditions are simulated in the digital twin model to evaluate the working performance and response behavior of the LNG cryogenic safety valve.

[0018] Preferably, the method of training a machine learning model through historical operation data and combining the machine learning model with the operation data to predict the remaining life of the LNG cryogenic safety valve specifically includes the following steps:

[0019] Using supervised learning algorithms to train machine learning models using historical operating data, the supervised learning algorithms include linear regression algorithms and support vector machine algorithms;

[0020] The machine learning model is combined with the operating data to predict the remaining life of the LNG cryogenic safety valve, wherein the life prediction formula is:

[0021]

[0022] Among them, T fsilure Represents the period when the equipment is expected to fail, T cuirent Represents the current operation cycle, and n represents the operating frequency of the device.

[0023] Preferably, the method further comprises the following steps:

[0024] The real-time data and historical data of the digital twin model are collected for analysis, and the parameters of the digital twin model are adjusted and optimized according to the analysis results.

[0025] Preferably, the method further comprises the following steps:

[0026] According to the analysis results and the predicted remaining life of the LNG cryogenic safety valve, a personalized maintenance plan is provided for the LNG cryogenic safety valve.

[0027] One or more embodiments of this specification provide an intelligent monitoring and life prediction device for an LNG cryogenic safety valve, including a three-dimensional model building module, a digital twin model building module, a monitoring module, and a prediction module;

[0028] The three-dimensional model building module is used to obtain the geometric structure parameters of the LNG cryogenic safety valve to build a three-dimensional model and import physical and material properties;

[0029] The digital twin model establishment module is used to collect the operating data of the LNG cryogenic safety valve in real time, dynamically bind the operating data with the digital twin model, and establish the digital twin model;

[0030] The monitoring module is used to input the operating data into the digital twin model in real time to perform intelligent monitoring on the LNG cryogenic safety valve;

[0031] The prediction module is used to train a machine learning model through historical operation data, combine the machine learning model with the operation data, and predict the remaining life of the LNG cryogenic safety valve.

[0032] Preferably, an evaluation module is also included, which is used to simulate environmental and load conditions in the digital twin model and evaluate the working performance and response behavior of the LNG cryogenic safety valve.

[0033] Preferably, an evaluation module is also included, which is used to simulate environmental and load conditions in the digital twin model and evaluate the working performance and response behavior of the LNG cryogenic safety valve.

[0034] One or more embodiments of the present specification provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the intelligent monitoring and life prediction method for the LNG cryogenic safety valve as described above is implemented.

[0035] One or more embodiments of the present specification provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned intelligent monitoring and life prediction method for LNG cryogenic safety valves.

[0036] The present disclosure provides a method, device, equipment and medium for intelligent monitoring and life prediction of LNG cryogenic safety valves, which has the advantages that by acquiring the geometric structure parameters of the LNG cryogenic safety valve to establish a three-dimensional model and importing the physical and material properties, the actual form and intrinsic properties of the LNG cryogenic safety valve can be highly restored in a virtual environment; by real-time collection of the operation data of the LNG cryogenic safety valve, the operation data is dynamically bound to the digital twin model to establish a digital twin model, and the real-time and accurate monitoring of the working state of the LNG cryogenic safety valve is realized; the operation data is input into the digital twin model in real time to perform intelligent monitoring of the LNG cryogenic safety valve, and the real-time and accurate monitoring of the working state of the LNG cryogenic safety valve is realized; the machine learning model is trained by historical operation data, and the machine learning model is combined with the operation data to predict the remaining life of the LNG cryogenic safety valve, which can provide real-time feedback on the current state of the valve, and can also predict its future state in combination with the machine learning model trained by historical operation data. Not only does it improve the real-time monitoring and fault prediction capabilities of the LNG cryogenic safety valve, but it also greatly optimizes the maintenance and management process of the equipment through an intelligent analysis and feedback system. These technical advantages greatly improve the operational safety, economy and reliability of the equipment, and fill in many deficiencies in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 A flow chart of an intelligent monitoring and life prediction method for an LNG cryogenic safety valve provided in one or more embodiments of this specification;

[0039] Figure 2 A flowchart of the digital twin technology implementation provided for one or more embodiments of this specification;

[0040] Figure 3 A schematic diagram of the structure of an intelligent monitoring and life prediction device for an LNG cryogenic safety valve provided in one or more embodiments of this specification;

[0041] Figure 4 A schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the protection scope of the present invention.

[0043] The present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings.

[0044] Method Embodiment

[0045] According to an embodiment of the present invention, a method for intelligent monitoring and life prediction of an LNG cryogenic safety valve is provided. Figure 1 As shown, it is a flow chart of the intelligent monitoring and life prediction method of the LNG cryogenic safety valve provided in this embodiment. The intelligent monitoring and life prediction method of the LNG cryogenic safety valve according to the embodiment of the present invention comprises the following steps:

[0046] S110. By accurately measuring the geometric structure of the LNG cryogenic safety valve, the geometric structure parameters of the LNG cryogenic safety valve, including valve body size, valve core structure, sealing material, etc., are obtained, and a three-dimensional model based on CAD design is established to ensure that the virtual model corresponds to the physical equipment one by one, and physical and material properties are imported, including the material's stress-strain properties, fatigue limit, elastic modulus, and low-temperature resistance. These parameters are crucial for simulating the valve's response under different environments and operating conditions.

[0047] S120. By integrating multiple sensors (such as pressure, temperature, strain, flow, vibration, etc.), the operating data of the LNG cryogenic safety valve is collected in real time, and the operating data is transmitted to the central processing system through the Internet of Things. The central processing system (cloud platform) is used for data processing and the establishment and maintenance of the digital twin model. The operating data is dynamically bound to the digital twin model to establish a digital twin model so that the digital twin model can reflect the actual working status of the equipment in real time. After the sensor data is input, the model can be updated in real time to ensure that the digital twin model is synchronized with the actual physical equipment.

[0048] S130, input the operation data into the digital twin model in real time, and the digital twin model can dynamically simulate the operation of the LNG cryogenic safety valve. For example, when the pressure sensor detects that the inlet and outlet pressures of the valve change, the valve state (such as the degree of opening / closing) in the model will be updated accordingly. Thus, the LNG cryogenic safety valve is intelligently monitored.

[0049] S140. Train a machine learning model using historical operating data, combine the machine learning model with the operating data, and predict the remaining life of the LNG cryogenic safety valve.

[0050] The method provided in this embodiment can highly restore the actual form and intrinsic properties of the LNG cryogenic safety valve in a virtual environment by acquiring the geometric structure parameters of the LNG cryogenic safety valve, and importing the physical and material properties; by collecting the operation data of the LNG cryogenic safety valve in real time, dynamically binding the operation data with the digital twin model, and establishing the digital twin model, the real-time and accurate monitoring of the working state of the LNG cryogenic safety valve is realized; the operation data is input into the digital twin model in real time to intelligently monitor the LNG cryogenic safety valve, and the real-time and accurate monitoring of the working state of the LNG cryogenic safety valve is realized; the machine learning model is trained by historical operation data, and the machine learning model is combined with the operation data to predict the remaining life of the LNG cryogenic safety valve, which can provide real-time feedback on the current state of the valve, and can also predict its future state in combination with the machine learning model trained by historical operation data. Not only does it improve the real-time monitoring and fault prediction capabilities of the LNG cryogenic safety valve, but it also greatly optimizes the maintenance and management process of the equipment through an intelligent analysis and feedback system. These technical advantages greatly improve the operational safety, economy and reliability of the equipment, and fill in many deficiencies in the existing technology.

[0051] In one embodiment, the following steps are also included:

[0052] The environmental and load conditions are simulated in the digital twin model to evaluate the working performance and response behavior of the LNG cryogenic safety valve. Through virtual environment simulation, the performance of the valve under different temperature, pressure and flow conditions is evaluated. By applying different load conditions, the model can predict the response behavior of the valve under extreme conditions.

[0053] The method provided in this embodiment can effectively evaluate the working performance and response behavior of the LNG cryogenic safety valve by simulating the environment and load conditions in the digital twin model, providing a strong basis for optimizing valve design, predicting potential risks in advance, and rationally formulating operation and maintenance strategies, thereby improving the reliability and safety of valve operation.

[0054] In one embodiment, the method of training a machine learning model through historical operation data and combining the machine learning model with the operation data to predict the remaining life of the LNG cryogenic safety valve specifically includes the following steps:

[0055] In life prediction, a supervised learning algorithm is used to train a machine learning model through historical operation data. The supervised learning algorithm includes a linear regression algorithm and a support vector machine algorithm. Linear regression is used to predict simple parameter change trends, such as the impact of pressure and temperature on service life, and support vector machine (SVM) is used to classify complex abnormal operation modes, such as failure modes of equipment under different working conditions.

[0056] Through labeled fault records and sensor data, the model can identify fault modes under different working conditions. The following algorithms can be used for model training:

[0057]

[0058] in, is the prediction result, θ0,θ1,…,θ n are model parameters, x1,x2,…,x n Enter data for the sensor.

[0059] The machine learning model is combined with the operating data provided by the sensor to predict the remaining life of the LNG cryogenic safety valve. The life prediction formula is based on the fatigue state of the equipment, where the life prediction formula is:

[0060]

[0061] Among them, T fsilure Represents the period when the equipment is expected to fail, T cuirent Represents the current operation cycle, and n represents the operating frequency of the device.

[0062] The method provided in this embodiment analyzes current data through a machine learning model to perform fault prediction and life estimation: based on sensor data and historical data, the machine learning model analyzes current operating conditions, predicts potential faults, and estimates the remaining service life of the LNG cryogenic safety valve.

[0063] In one embodiment, the following steps are also included:

[0064] The real-time data and historical data of the digital twin model are collected for analysis, and the parameters of the digital twin model are adjusted and optimized according to the analysis results, so that the prediction accuracy can be improved in the process of continuous updating and learning. For example, the fatigue calculation parameters of the model can be corrected using past operation data, thereby improving the accuracy of future fault prediction.

[0065] In one embodiment, the following steps are also included:

[0066] Based on the analysis results and the predicted remaining life of the LNG cryogenic safety valve, a personalized maintenance plan is provided for the LNG cryogenic safety valve. For example, the system will prompt when the valve needs to be overhauled, the seals replaced, or other preventive maintenance performed.

[0067] Through life prediction, the system can accurately plan maintenance cycles to avoid increased costs and equipment downtime due to insufficient or excessive maintenance.

[0068] After maintenance is completed, all operation records will be entered into the system as part of subsequent machine learning model training to further improve the system's prediction accuracy.

[0069] The data feedback system can evaluate the effectiveness of maintenance operations and optimize future maintenance recommendations accordingly. For example, if a maintenance operation extends the service life of the equipment, the system will adjust the corresponding life prediction model to make it more consistent with the actual situation of the equipment.

[0070] like Figure 2 As shown in FIG. 1 , a flowchart of the implementation of the digital twin technology provided in this embodiment is shown. The entire process described above can be divided into seven main steps:

[0071] (1) Sensor data acquisition: The sensors installed on the LNG cryogenic safety valve (including pressure, temperature, strain, vibration, flow, etc.) collect data in real time. These data reflect the working status, environmental conditions and physical changes of the valve, providing basic information for subsequent analysis.

[0072] (2) Data is transmitted to the central processing system through the Internet of Things: The collected sensor data is transmitted to the central processing system through Internet of Things technology (such as 4G, 5G, satellite communication or Wi-Fi) to ensure that the data can be delivered to the processing platform in a timely and accurate manner.

[0073] (3) Data preprocessing and cleaning: In the central processing system, the transmitted data is preprocessed and cleaned. This step includes removing noise, processing missing data, filtering outliers, etc. to ensure the integrity and validity of the data and make it suitable for further analysis and modeling.

[0074] (4) Data input into the digital twin model for dynamic simulation: The cleaned data is input into the digital twin model of the LNG cryogenic safety valve in real time. This virtual model is a digital copy of the valve and can be dynamically updated based on sensor data to simulate the valve's operating performance under different operating conditions and predict future states.

[0075] (5) Machine learning model analyzes current data to predict faults and estimate life: Based on sensor data and historical data, the machine learning model analyzes current operating conditions, predicts potential faults, and estimates the remaining useful life (RUL) of the LNG cryogenic safety valve. Through machine learning algorithms, the system is able to detect abnormal operating modes and provide accurate predictions.

[0076] (6) Provide real-time warnings and maintenance suggestions based on the results: When the machine learning model identifies an abnormal state, the system will issue a real-time warning to remind the operator to perform maintenance or inspection. At the same time, based on the prediction results, the system will provide specific maintenance suggestions to optimize the equipment operation cycle and reduce the risk of failure.

[0077] (7) Data feedback for model optimization: Sensor data and maintenance records will be fed back to the system to optimize the digital twin model and machine learning algorithm. Through continuous learning and adjustment, the accuracy of the model will gradually improve, further improving the accuracy of fault prediction and life estimation.

[0078] This process ensures intelligent monitoring and efficient maintenance of the LNG cryogenic safety valve. It not only provides real-time feedback on the valve status, but also detects potential problems in advance through predictive technology, thereby reducing equipment downtime and improving safety.

[0079] Device Embodiment

[0080] According to an embodiment of the present invention, an intelligent monitoring and life prediction device for an LNG cryogenic safety valve is provided. Figure 3 As shown, it is a structural schematic diagram of the intelligent monitoring and life prediction of the LNG cryogenic safety valve provided in this embodiment. The intelligent monitoring and life prediction device of the LNG cryogenic safety valve according to the embodiment of the present invention includes a three-dimensional model establishment module 31, a digital twin model establishment module 32, a monitoring module 33 and a prediction module 34.

[0081] The three-dimensional model building module 31 is used to obtain the geometric structure parameters of the LNG cryogenic safety valve to build a three-dimensional model and import physical and material properties.

[0082] The digital twin model establishment module 32 is used to collect the operating data of the LNG cryogenic safety valve in real time, dynamically bind the operating data with the digital twin model, and establish the digital twin model.

[0083] The monitoring module 33 is used to input the operating data into the digital twin model in real time to perform intelligent monitoring on the LNG cryogenic safety valve.

[0084] The prediction module 34 is used to train a machine learning model through historical operation data, combine the machine learning model with the operation data, and predict the remaining life of the LNG cryogenic safety valve.

[0085] In the device provided in this embodiment, the three-dimensional model building module 31 obtains the geometric structure parameters of the LNG cryogenic safety valve to establish a three-dimensional model, and imports the physical and material properties, which can highly restore the actual form and intrinsic properties of the LNG cryogenic safety valve in a virtual environment; the digital twin model building module 32 collects the operation data of the LNG cryogenic safety valve in real time, dynamically binds the operation data with the digital twin model, and establishes a digital twin model, thereby realizing real-time and accurate monitoring of the working state of the LNG cryogenic safety valve; the monitoring module 33 inputs the operation data into the digital twin model in real time to intelligently monitor the LNG cryogenic safety valve, thereby realizing real-time and accurate monitoring of the working state of the LNG cryogenic safety valve; the prediction module 34 trains the machine learning model through historical operation data, combines the machine learning model with the operation data, predicts the remaining life of the LNG cryogenic safety valve, can provide real-time feedback on the current state of the valve, and can also predict its future state in combination with the machine learning model trained by historical operation data. Not only does it improve the real-time monitoring and fault prediction capabilities of the LNG cryogenic safety valve, but it also greatly optimizes the maintenance and management process of the equipment through an intelligent analysis and feedback system. These technical advantages greatly improve the operational safety, economy and reliability of the equipment, and fill in many deficiencies in the existing technology.

[0086] In one embodiment, an evaluation module 35 is further included, which is used to simulate environmental and load conditions in the digital twin model and evaluate the working performance and response behavior of the LNG cryogenic safety valve.

[0087] The device provided in this embodiment can effectively evaluate the working performance and response behavior of the LNG cryogenic safety valve by simulating the environment and load conditions in the digital twin model, providing a strong basis for optimizing valve design, predicting potential risks in advance, and rationally formulating operation and maintenance strategies, thereby improving the reliability and safety of valve operation.

[0088] In one embodiment, the prediction module 34 includes a training unit 341 and a prediction unit 342;

[0089] The training unit 341 is used to train the machine learning model through historical operation data using a supervised learning algorithm, and the supervised learning algorithm includes a linear regression algorithm and a support vector machine algorithm.

[0090] The prediction unit 342 is used to combine the machine learning model with the operation data to predict the remaining life of the LNG cryogenic safety valve, wherein the life prediction formula is:

[0091]

[0092] Among them, T failureRepresents the period when the equipment is expected to fail, T curtent Represents the current operation cycle, and n represents the operating frequency of the device.

[0093] The device provided in this embodiment analyzes current data through a machine learning model to perform fault prediction and life estimation: based on sensor data and historical data, the machine learning model analyzes current operating conditions, predicts potential faults, and estimates the remaining service life of the LNG cryogenic safety valve.

[0094] The embodiment of the present invention is an apparatus embodiment corresponding to the above-mentioned method embodiment. The specific operations of the processing steps of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0095] like Figure 4 As shown, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the intelligent monitoring and life prediction method in the above-mentioned embodiment when the computer program is executed by a processor, or implements the intelligent monitoring and life prediction method of the LNG cryogenic safety valve in the above-mentioned embodiment when the computer program is executed by a processor.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0097] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. An intelligent monitoring and life prediction method for LNG cryogenic safety valves, characterized in that: The following steps are involved: Obtain the geometric structural parameters of the LNG cryogenic safety valve to establish a three-dimensional model, and import the physical and material properties; By collecting the operating data of the LNG cryogenic safety valve in real time, the operating data is dynamically bound to the digital twin model to establish the digital twin model; Inputting the operation data into the digital twin model in real time to perform intelligent monitoring on the LNG cryogenic safety valve; The machine learning model is trained by using historical operating data, and the machine learning model is combined with the operating data to predict the remaining life of the LNG cryogenic safety valve.

2. The intelligent monitoring and life prediction method according to claim 1, characterized in that: The following steps are also included: Environmental and load conditions are simulated in the digital twin model to evaluate the working performance and response behavior of the LNG cryogenic safety valve.

3. The intelligent monitoring and life prediction method according to claim 1, characterized in that: The method of training a machine learning model through historical operation data and combining the machine learning model with the operation data to predict the remaining life of the LNG cryogenic safety valve specifically includes the following steps: Using supervised learning algorithms to train machine learning models using historical operating data, the supervised learning algorithms include linear regression algorithms and support vector machine algorithms; The machine learning model is combined with the operating data to predict the remaining life of the LNG cryogenic safety valve, wherein the life prediction formula is: Among them, T failure Represents the period when the equipment is expected to fail, T current Represents the current operation cycle, and n represents the operating frequency of the device.

4. The intelligent monitoring and life prediction method according to claim 1, characterized in that: The following steps are also included: The real-time data and historical data of the digital twin model are collected for analysis, and the parameters of the digital twin model are adjusted and optimized according to the analysis results.

5. The intelligent monitoring and life prediction method according to claim 4, characterized in that: The following steps are also included: According to the analysis results and the predicted remaining life of the LNG cryogenic safety valve, a personalized maintenance plan is provided for the LNG cryogenic safety valve.

6. An intelligent monitoring and life prediction device for LNG cryogenic safety valve, characterized in that: It includes three-dimensional model building module, digital twin model building module, monitoring module and prediction module; The three-dimensional model building module is used to obtain the geometric structure parameters of the LNG cryogenic safety valve to build a three-dimensional model and import physical and material properties; The digital twin model establishment module is used to collect the operating data of the LNG cryogenic safety valve in real time, dynamically bind the operating data with the digital twin model, and establish the digital twin model; The monitoring module is used to input the operating data into the digital twin model in real time to perform intelligent monitoring on the LNG cryogenic safety valve; The prediction module is used to train a machine learning model through historical operation data, combine the machine learning model with the operation data, and predict the remaining life of the LNG cryogenic safety valve.

7. The intelligent monitoring and life prediction device according to claim 6, characterized in that: It also includes an evaluation module for simulating environmental and load conditions in the digital twin model to evaluate the working performance and response behavior of the LNG cryogenic safety valve.

8. The intelligent monitoring and life prediction device according to claim 6, characterized in that: The prediction module includes a training unit and a prediction unit; The training unit is used to train the machine learning model through historical operation data using a supervised learning algorithm, wherein the supervised learning algorithm includes a linear regression algorithm and a support vector machine algorithm; The prediction unit is used to combine the machine learning model with the operation data to predict the remaining life of the LNG cryogenic safety valve, wherein the life prediction formula is: Among them, T failure Represents the period when the equipment is expected to fail, T current Represents the current operation cycle, and n represents the operating frequency of the device.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the intelligent monitoring and life prediction method of the LNG cryogenic safety valve as described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent monitoring and life prediction method of the LNG cryogenic safety valve as claimed in any one of claims 1 to 5 are implemented.

Images