Multifunctional fuel gas storage tank state monitoring method, device and equipment and storage medium

Abstract

The invention relates to the technical field of gas engineering safety, in particular to a multifunctional gas storage tank state monitoring method which comprises the steps of collecting rated parameters and historical parameters of a storage tank, and generating a historical deviation data set. Then, combining the use data to construct a use-deviation data set, and analyzing and generating an aging prediction factor by using an aging analysis model and a machine self-learning algorithm; based on the factors, the aging prediction model predicts the performance change of the storage tank and formulates an inflation strategy; and comparing the real-time monitoring data with the prediction parameters, generating actual difference data, judging the aging condition through a preset difference threshold value, and generating an aging judgment report. The fuel gas storage tank has the effect of improving the use safety of the fuel gas storage tank.

Description

Technical Field

[0001] The present invention relates to the technical field of gas engineering safety, and in particular to a multifunctional gas storage tank state monitoring method, device, equipment and storage medium. Background Art

[0002] Gas storage tanks are widely used in civil and industrial fields to store and supply gas to meet production and living needs.

[0003] Existing gas storage tanks may have safety hazards such as leakage and corrosion during use, and require regular inspection and maintenance to ensure safe use. The existing gas storage tank monitoring system only monitors valve parameters and compares them with pre-set basic parameters, and uses valve comparison data to monitor whether there are abnormalities in the gas storage tank. However, the abnormal conditions of gas storage tanks are relatively diverse, and the existing monitoring methods are relatively single, which reduces the accuracy of gas storage tank status monitoring, thereby reducing the safety of gas storage tank use, so it needs to be improved. Summary of the invention

[0004] In order to improve the safety of the use of gas storage tanks, the present application provides a multifunctional gas storage tank status monitoring method.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: A multifunctional gas storage tank status monitoring method, the method comprising the steps of: Acquire rated parameter data of the gas storage tank, wherein the rated parameter data includes valve rated pressure parameters, valve rated pressure loss parameters, tank rated gas pressure parameters, and tank rated capacity parameters; Acquire historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct a historical deviation parameter data set based on a preset common time axis; Acquire usage data of the gas storage tank, and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; The preset aging analysis model analyzes the usage-bias dataset based on a machine self-learning algorithm to generate an aging prediction factor; The preset aging prediction model performs aging prediction on the gas storage tank based on the aging prediction factor to generate prediction parameter data of the gas storage tank; generating a gas storage tank charging strategy based on the predicted parameter data; Acquire real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether the tank body is aged based on the preset difference threshold data, and generate a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold; In the step of judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the following steps are included: If the actual difference data exceeds the normal difference threshold but does not reach the re-test difference threshold, the result is judged as normal loss; If the actual difference data exceeds the re-inspection difference threshold but does not reach the aging difference threshold, it is determined that the gas storage tank may be aged and needs to be re-inspected; If the actual difference data exceeds the aging difference threshold, it is determined that the gas storage tank has aged and the aged tank needs to be replaced.

[0006] By adopting the above-mentioned technical scheme, the rated parameters and historical parameter data of the gas storage tank are collected, and accurate historical deviation data is generated to provide a basis for subsequent analysis. The usage data and real-time data obtained in real time ensure the timeliness of monitoring, and can capture any state changes in time. By utilizing the aging analysis model and aging prediction model of the machine self-learning algorithm, this method can automatically analyze a large amount of data, identify performance change trends, and realize forward-looking maintenance and replacement guidance. This intelligent analysis not only improves the efficiency of monitoring, but also reduces manual intervention and improves the level of intelligence. In addition, this method integrates multiple functions, such as inflation strategy generation and aging judgment report production, which clearly guides staff to monitor gas storage tanks, ensuring the convenience of operation and the intuitiveness of monitoring. Compared with the existing technology, this application has comprehensive and in-depth monitoring capabilities, and has real-time, predictive, economical, and adaptable multifunctional intelligent monitoring, which improves the safety and economy of gas storage tank use.

[0007] In a preferred example, the present application can be further configured as follows: after judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the following steps are included: Marking the actual difference data according to the aging judgment report, marking the data with a judgment result of normal wear and tear as normal, and marking the data with a judgment result of the possibility of aging and aging as abnormal; Associating the historical parameter data and the historical usage data of the storage tank marked as abnormal according to the common time axis one by one and constructing a usage habit parameter change data set; The preset usage habit analysis model analyzes the habit parameter change data set based on a machine self-learning algorithm to generate an aging correction factor, and the aging correction factor is used to correct and predict the aging differences corresponding to different usage habits.

[0008] By adopting the above technical solution, the specific impact of different usage habits on the aging of storage tanks can be identified through the habit analysis model analysis, and an aging correction factor can be generated. For example, if it is found that frequent filling and discharging operations will cause the aging of the storage tank to accelerate, the algorithm will generate a corresponding correction factor and correct the aging prediction based on the usage habits to improve the accuracy of the prediction.

[0009] In a preferred example, the present application may be further configured as follows: after marking the actual difference data according to the aging judgment report, marking the data with a judgment result of normal loss as normal, and marking the data with a judgment result of the possibility of aging and aging as abnormal, the following steps are further included: Acquire historical environmental data of the gas storage tank, associate the historical environmental data with the historical parameter data one by one according to the common time axis, and construct an environmental parameter change data set; The preset environmental impact analysis model analyzes the environmental parameter change data set based on a machine self-learning algorithm to generate an environmental correction factor, and the environmental correction factor is used to correct and predict the aging differences corresponding to different environments.

[0010] By adopting the above technical solution, the application of environmental correction factors can adjust the aging prediction model, consider the impact of environmental factors on storage tank performance, and improve the accuracy and reliability of the prediction.

[0011] In a preferred example, the present application can be further configured as follows: after judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the following steps are also included: Acquire historical transportation data of the gas storage tank, associate the historical transportation data with the historical parameter data one by one according to the common time axis, and construct a transportation impact data set; The preset transportation impact analysis model analyzes the transportation impact data set based on a machine self-learning algorithm to generate a transportation impact factor, and the transportation impact factor is used to make a correct prediction of the aging differences corresponding to different transportation conditions.

[0012] By adopting the above technical solutions, the generation of transportation influencing factors helps to make personalized predictions on the aging process of storage tanks under different transportation conditions, improves the accuracy and reliability of the predictions, and by identifying the key influencing factors in the transportation process, optimizes the transportation plan, reduces adverse effects on storage tanks, and extends the service life of storage tanks.

[0013] In a preferred example, the present application can be further configured as follows: the transport impact data set is analyzed in a preset transport impact analysis model based on a machine self-learning algorithm to generate a transport impact factor, and the transport impact factor is used in the step of making a correct prediction of the aging differences corresponding to different transport conditions. The transport impact factor includes a transport route impact sub-factor, a transport duration impact sub-factor and a transport environment impact sub-factor.

[0014] In a preferred example, the present application can be further configured as follows: in the step of acquiring real-time data of the gas storage tank and comparing it with the real-time prediction parameter data to generate actual difference data, judging whether there is tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the aging judgment report includes: a detailed description of the aging state, the detailed description including the comparison result of the actual difference data and the difference threshold data; When the result is judged to be normal wear and tear, provide suggestions for maintenance and care; When the judgment result shows that there is a possibility of aging, provide a re-inspection schedule and a list of re-inspection items; When it is determined that the equipment is already aged, a specific plan and timetable for replacement or repair will be provided.

[0015] By adopting the above technical solution, not only the aging status of the gas storage tank is evaluated, but also customized maintenance, re-inspection or replacement plans are provided based on the evaluation results, and specific response measures are provided according to the degree of aging, which significantly improves the management efficiency and safety of the gas storage system.

[0016] In a preferred example, the present application can be further configured as follows: the machine self-learning algorithm includes a support vector machine, a random forest and a deep neural network.

[0017] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions: A multifunctional gas storage tank state monitoring device, the device comprising: a rated parameter data acquisition module, used to acquire rated parameter data of the gas storage tank, wherein the rated parameter data includes valve rated pressure parameters, valve rated pressure loss parameters, tank rated gas pressure parameters, and tank rated capacity parameters; A historical deviation parameter data set construction module, used for acquiring historical parameter data of the gas storage tank, comparing the historical parameter data with the rated parameter data to generate historical deviation data, and constructing the historical deviation parameter data set based on a preset common time axis; A usage-deviation data set construction module, used for acquiring usage data of the gas storage tank, and associating the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; an aging prediction factor generation module, which is pre-set with an aging analysis model to analyze the usage-bias data set based on a machine self-learning algorithm to generate an aging prediction factor; A prediction parameter data generating module, which is pre-set with an aging prediction model to perform aging prediction on the gas storage tank based on the aging prediction factor, and generates prediction parameter data for the gas storage tank; A gas storage tank filling strategy generation module, used to generate a gas storage tank filling strategy based on the predicted parameter data; The gas storage tank aging judgment report generation module is used to obtain real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether the tank body is aged based on the preset difference threshold data, and generate a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold.

[0018] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the multifunctional gas storage tank status monitoring method when executing the computer program.

[0019] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the multifunctional gas storage tank status monitoring method.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. Collect the rated parameters and historical parameter data of the gas storage tank, generate accurate historical deviation data, and provide a basis for subsequent analysis. The real-time usage data and real-time data ensure the timeliness of monitoring, and can capture any state changes in time. By using the aging analysis model and aging prediction model of the machine self-learning algorithm, this method can automatically analyze a large amount of data, identify performance change trends, and achieve forward-looking maintenance and replacement guidance. This intelligent analysis not only improves the efficiency of monitoring, but also reduces manual intervention and improves the level of intelligence. In addition, this method integrates multiple functions, such as inflation strategy generation and aging judgment report production, clearly guides staff to monitor gas storage tanks, and ensures the convenience of operation and the intuitiveness of monitoring. Compared with the existing technology, this application has real-time, predictive, economical, and adaptable multifunctional intelligent monitoring through its comprehensive and in-depth monitoring capabilities, which improves the safety and economy of gas storage tanks. 2. Through the habit analysis model, the specific impact of different usage habits on the aging of the storage tank is identified, and an aging correction factor is generated. For example, if it is found that frequent filling and discharging operations will lead to accelerated aging of the storage tank, the algorithm will generate a corresponding correction factor and correct the aging prediction based on the usage habits to improve the accuracy of the prediction; 3. The generation of transportation influencing factors helps to make personalized predictions on the aging process of storage tanks under different transportation conditions, which improves the accuracy and reliability of the predictions. By identifying the key influencing factors in the transportation process, the transportation plan can be optimized, the adverse effects on the storage tanks can be reduced, and the service life of the storage tanks can be extended; 4. The aging status of the gas storage tanks was evaluated, and customized maintenance, re-inspection or replacement plans were provided based on the evaluation results. Specific response measures were provided according to the degree of aging, which significantly improved the management efficiency and safety of the gas storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic diagram of the steps of a multifunctional gas storage tank status monitoring method in one embodiment of the present application; Figure 2 This is a principle block diagram of a multifunctional gas storage tank status monitoring system in one embodiment of the present application; Figure 3 It is a schematic diagram of an electronic device in an embodiment of the present application.

[0022] Figure Number: 1. Rated parameter data acquisition module; 2. Historical deviation parameter data set construction module; 3. Use-deviation data set construction module; 4. Aging prediction factor generation module; 5. Prediction parameter data generation module; 6. Gas storage tank filling strategy generation module; 7. Gas storage tank aging judgment report generation module. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a multifunctional gas storage tank status monitoring method, which specifically includes the following steps: S10: Acquire rated parameter data of the gas storage tank, wherein the rated parameter data includes valve rated pressure parameters, valve rated pressure loss parameters, tank rated gas pressure parameters, and tank rated capacity parameters; Specifically, through the factory parameter table and design documents of the gas storage tank, the valve rated pressure, pressure loss, tank gas pressure and capacity and other parameters are manually input or automatically imported into the monitoring system database to provide a benchmark for subsequent monitoring. In the embodiment of the present application, barcode or RFID technology is used to achieve fast and accurate acquisition of parameter data.

[0025] S20: Acquire historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct a historical deviation parameter data set based on a preset common time axis; Specifically, historical operating data is collected from sensors of storage tanks on a regular basis and compared with rated parameters, deviations are automatically calculated, and stored in a database based on a common time axis to construct a historical deviation parameter data set. In this embodiment of the application, the unit interval of the common time axis is (days).

[0026] S30: Acquire usage data of the gas storage tank, and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; Specifically, usage data includes usage frequency, usage environment, etc. The usage frequency, usage environment and other data are combined with historical deviation data to construct a comprehensive usage-deviation data set to reflect the performance changes of gas storage tanks under actual usage conditions and provide multi-dimensional data for in-depth analysis.

[0027] S40: The preset aging analysis model analyzes the usage-bias data set based on a machine self-learning algorithm to generate an aging prediction factor; Specifically, a machine self-learning algorithm is used to analyze the usage-bias data set. The purpose of the aging analysis model is to learn the performance change patterns of the gas storage tanks from historical data and identify factors that may lead to performance degradation. In an embodiment of the present application, the deep learning framework Keras and the random forest algorithm are used to analyze the usage-bias data set, extract aging features, and generate aging prediction factors. The aging prediction factors can quantify the degree of performance degradation of the storage tanks and provide a scientific basis for prediction and maintenance.

[0028] In an embodiment of the present application, the aging prediction factor is used to predict the pressure change rate of the gas storage tank, the capacity change rate of the storage tank, and the pressure loss change rate of the valve.

[0029] S50: The preset aging prediction model performs aging prediction on the gas storage tank based on the aging prediction factor, and generates prediction parameter data of the gas storage tank; Specifically, the aging prediction model predicts the future state of the gas storage tank based on the aging prediction factor generated in step S40. The aging prediction model can use a variety of machine self-learning technologies. In the embodiment of the present application, the machine self-learning algorithm includes support vector machine (SVM), random forest and deep neural network. For example, multiple linear discriminant analysis classifiers are combined together using an integration method to reduce the noise of transcriptome data. This method can be applied to improve prediction accuracy.

[0030] The predicted parameter data include: the predicted change trend of the valve rated pressure parameters over time; the predicted degradation of the tank rated air pressure parameters over time; and the predicted performance of the tank rated capacity parameters in the future service life.

[0031] In this application, an example is given: suppose that after a gas storage tank has been used for five years, historical data shows that the valve pressure loss parameter has a tendency to increase year by year. The aging analysis model uses this tendency as one of the aging prediction factors. In step S50, the aging prediction model will use this factor, combined with other relevant factors, to predict the range of changes in the valve pressure loss parameter of the storage tank in the next five years, as well as possible maintenance or replacement requirements.

[0032] Through these steps S40 and S50, we can not only have a deep understanding of the performance changes of the gas storage tank, but also predict and plan corresponding maintenance measures in advance, thereby extending the service life of the storage tank and improving safety and economy.

[0033] S60: generating a gas storage tank charging strategy based on the predicted parameter data; Specifically, based on the predicted parameter data, the intelligent optimization algorithm automatically generates a gas storage tank inflation strategy. The gas storage tank inflation strategy includes inflation speed and pressure to extend the service life of the storage tank. The customized inflation strategy helps to maintain the optimal operating state of the storage tank and improve safety and efficiency.

[0034] S70: acquiring real-time data of the gas storage tank and comparing it with the real-time prediction parameter data to generate actual difference data, and judging whether the tank is aged based on preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold; Specifically, the real-time monitoring system collects real-time data of the storage tank and compares it with the predicted parameter data to generate actual difference data. The actual difference data is evaluated through a preset difference threshold to determine the aging status of the storage tank and generate an aging judgment report. The comparison of real-time data and aging judgment improves the response speed and accuracy of storage tank management, ensures storage safety, and further improves the safety of gas storage tanks.

[0035] It should be noted that the aging judgment report includes: a detailed description of the aging state, the detailed description including the comparison result between the actual difference data and the difference threshold data; When the result is judged to be normal wear and tear, provide suggestions for maintenance and care; When the judgment result shows that there is a possibility of aging, provide a re-inspection schedule and a list of re-inspection items; When it is determined that the equipment is already aged, a specific plan and timetable for replacement or repair will be provided.

[0036] Specifically, the aging judgment report first includes a detailed description of the aging status of the gas storage tank. For example, by comparing the actual difference data (such as pressure drop, capacity reduction) with the preset difference threshold, the report details the degree of deviation in the performance of the storage tank. The detailed description provides a clear understanding of the aging status, helping users to quickly grasp the current status and potential risks of the storage tank. If the judgment result is normal loss, the report will provide maintenance and care suggestions. For example, if the pressure of the storage tank drops slightly but is within the normal loss range, it is recommended to conduct regular inspections and cleaning to maintain its performance. For situations where aging is possible, the report will provide a re-inspection schedule and a list of re-inspection items. For example, if certain performance indicators of the storage tank are close to the re-inspection difference threshold, it is recommended to re-inspect within three months and list the specific items that need to be inspected, such as sealing, material integrity, etc.; a clear re-inspection schedule and project list ensure timely monitoring and evaluation, which helps to take action before aging develops further; when the judgment result is aging, the report will provide a specific plan and schedule for replacement or repair. For example, if the key performance indicators of the storage tank seriously exceed the aging difference threshold, the report recommends immediate cessation of use and provides a detailed plan for replacing a new storage tank or repairing key components.

[0037] To summarize, this solution generates accurate historical deviation data by collecting rated parameters and historical parameter data of gas storage tanks, providing a basis for subsequent analysis. The usage data and real-time data obtained in real time ensure the timeliness of monitoring, and can capture any state changes in a timely manner. By utilizing the aging analysis model and aging prediction model of the machine self-learning algorithm, this method can automatically analyze a large amount of data, identify performance change trends, and achieve forward-looking maintenance and replacement guidance. This intelligent analysis not only improves the efficiency of monitoring, but also reduces manual intervention and improves the level of intelligence. In addition, this method integrates multiple functions, such as inflation strategy generation and aging judgment report production, which clearly guides staff to monitor gas storage tanks, ensuring the convenience of operation and the intuitiveness of monitoring. Compared with the existing technology, this application has comprehensive and in-depth monitoring capabilities, and has real-time, predictive, economical, and adaptable multifunctional intelligent monitoring, which improves the safety and economy of gas storage tank use.

[0038] Specifically, in the step of judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the steps include the following: If the actual difference data exceeds the normal difference threshold but does not reach the re-test difference threshold, the result is judged as normal loss; If the actual difference data exceeds the re-inspection difference threshold but does not reach the aging difference threshold, it is determined that the gas storage tank may be aged and needs to be re-inspected; If the actual difference data exceeds the aging difference threshold, it is determined that the gas storage tank has aged and the aged tank needs to be replaced; Specifically, the difference threshold data is set according to the design requirements of the gas storage tank. In the embodiment of the present application, the difference threshold data is set as follows: Normal difference threshold: A baseline is set to represent the parameter fluctuation of the storage tank under normal use conditions. For example, if the pressure reading is within ±5% of the rated pressure and the temperature change is within ±2°C, the storage tank is considered to be in a normal state.

[0039] Recheck difference threshold: When the actual difference data exceeds the normal threshold but does not reach a specific risk level, such as the pressure reading is within ±10% of the rated pressure, a recheck alert is set. This provides a buffer to schedule further inspections if no immediate action is taken.

[0040] Aging difference threshold: If the actual difference data exceeds the higher threshold of the rated parameter, such as the pressure reading exceeds ±15% of the rated pressure, it indicates that the storage tank may have aged and needs to be replaced or repaired immediately.

[0041] By setting the difference threshold, potential aging problems can be identified in advance, so that maintenance can be arranged before the problem occurs, reducing the risk of emergency repairs and unexpected downtime to achieve preventive maintenance. Clear difference thresholds help to quickly determine the safety status of storage tanks and ensure the safety of storage and transportation processes. By reasonably arranging re-inspection and replacement plans, resource allocation can be optimized to reduce unnecessary maintenance costs. The setting of difference thresholds is based on historical data and real-time monitoring data, providing data-driven decision support and increasing the objectivity and accuracy of decision-making. Regulatory compliance: The setting of difference thresholds takes into account industry standards and regulatory requirements, ensuring that the use and management of storage tanks comply with relevant regulations and reducing compliance risks.

[0042] At S70: judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, after this step, the following steps are included: S701: Mark the actual difference data according to the aging judgment report, mark the data with a judgment result of normal wear and tear as normal, and mark the data with a judgment result of the possibility of aging and aging as abnormal; Specifically, an aging judgment report is obtained, which judges the aging of the actual difference data based on the difference threshold data. The data judged as normal loss in the report is marked as normal (no change), and the data judged to have the possibility of aging and has been aged is marked as abnormal. For example, if the pressure reading of a gas storage tank exceeds the re-inspection difference threshold, it is marked as abnormal.

[0043] S702: Associating the historical parameter data and the historical usage data of the storage tank marked as abnormal according to the common time axis one by one and constructing a usage habit parameter change data set; Specifically, for storage tanks marked as abnormal, their historical parameter data and usage data, such as historical pressure, temperature, filling frequency, number of fillings, etc., are collected, and these historical data are associated with usage habits one by one using a common timeline to build a detailed usage habit parameter change data set. For example, this provides a data basis for subsequent analysis of the relationship between the pressure change and filling frequency of a storage tank in the past two years.

[0044] S703: The preset usage habit analysis model analyzes the habit parameter change data set based on a machine self-learning algorithm to generate an aging correction factor, wherein the aging correction factor is used to correct and predict aging differences corresponding to different usage habits; Specifically, the usage habit analysis model adopts a machine self-learning algorithm, which includes random forest and gradient boosting tree, to analyze the usage habit parameter change data set.

[0045] The habit analysis model is used to identify the specific impact of different usage habits on the aging of storage tanks and generate aging correction factors. For example, if it is found that frequent filling and discharging operations will lead to accelerated aging of storage tanks, the algorithm will generate corresponding correction factors (filling correction factor, discharging operation correction factor).

[0046] S704: Acquire historical environmental data of the gas storage tank, associate the historical environmental data with the historical parameter data one by one according to the common time axis, and construct an environmental parameter change data set; Specifically, we collect environmental parameters of gas storage tanks at different time points, such as temperature, humidity, and air pressure. These parameters may affect the performance and aging rate of the storage tanks. Using a common timeline, we associate these historical environmental data with previously collected historical parameter data (such as pressure and capacity) one by one to construct a comprehensive environmental parameter change data set.

[0047] By correlating environmental parameters with historical parameters, changes in storage tank performance under different environmental conditions can be analyzed, providing data support for subsequent environmental impact analysis.

[0048] S705: The preset environmental impact analysis model analyzes the environmental parameter change data set based on a machine self-learning algorithm to generate an environmental correction factor, wherein the environmental correction factor is used to correct and predict aging differences corresponding to different environments; Specifically, an environmental impact analysis model is designed, which uses support vector machine (SVM) and deep neural network (DNN) machine self-learning algorithms to conduct in-depth analysis of environmental parameter change data sets.

[0049] The algorithm analyzes and identifies the specific impact of environmental factors on the performance of the storage tank and generates an environmental correction factor. For example, if the data analysis shows that the aging rate of the storage tank increases by 15% for every 10°C increase in temperature, the corresponding environmental correction factor will reflect this relationship.

[0050] The application of environmental correction factors can adjust the aging prediction model, consider the impact of environmental factors on storage tank performance, and improve the accuracy and reliability of the prediction.

[0051] S706: Acquire historical transportation data of the gas storage tank, and associate the historical transportation data with the historical parameter data one by one according to the common time axis, and construct a transportation impact data set; Specifically, the historical transportation data of gas storage tanks are collected, including transportation routes, transportation duration, and environmental conditions during transportation (such as temperature and humidity). These transportation data are then associated one-to-one with the historical parameter data of the storage tanks (such as pressure, capacity, and material properties) using a common timeline. Through data fusion technology, a comprehensive transportation impact data set is constructed that can reflect the impact of transportation conditions on the performance of storage tanks.

[0052] S707: The preset transportation impact analysis model analyzes the transportation impact data set based on a machine self-learning algorithm to generate a transportation impact factor, wherein the transportation impact factor is used to make a correction prediction on the aging difference corresponding to different transportation conditions, wherein the transportation impact factor includes a transportation route impact sub-factor, a transportation time impact sub-factor, and a transportation environment impact sub-factor; A transportation impact analysis model is designed, which uses a machine self-learning algorithm to analyze the transportation impact data set, extract factors such as transportation routes, transportation time and transportation environment from the data set, and generate corresponding transportation impact sub-factors.

[0053] For example, if data analysis shows that a particular transport route has a higher level of turbulence, resulting in an increased vibration frequency in the storage tanks, the algorithm will generate a transport route impact sub-factor to quantify this impact.

[0054] The generation of transportation influencing factors helps to make personalized predictions on the aging process of storage tanks under different transportation conditions, improves the accuracy and reliability of the predictions, and by identifying the key influencing factors in the transportation process, can optimize the transportation plan, reduce the adverse effects on storage tanks, and extend the service life of storage tanks.

[0055] Through this method, the present invention can provide more accurate and personalized predictions for the status monitoring of the gas storage tank, thereby providing strong support for the safe management and maintenance of the storage tank.

[0056] In addition, this solution also helps to reduce the damage that may be caused to the storage tank during transportation, reduce maintenance costs, and improve the economy and safety of the gas storage system.

[0057] To summarize, the present application can evaluate the aging of gas storage tanks from the aspects of usage habits, environmental impacts and transportation, and more comprehensively evaluate the status of gas storage tanks. It not only considers the performance changes of the storage tanks themselves, but also considers the impact of environmental factors on the aging of storage tanks. It helps to improve the safety management level of storage tanks, optimize maintenance and replacement plans, reduce accidental risks, and improve the economy and safety of gas storage systems.

[0058] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0059] In one embodiment, a multifunctional gas storage tank status monitoring device is provided, and the multifunctional gas storage tank status monitoring device corresponds one-to-one to the multifunctional gas storage tank status monitoring method in the above embodiment. Figure 2 As shown, the multifunctional gas storage tank state monitoring device includes a rated parameter data acquisition module 1, which is used to obtain the rated parameter data of the gas storage tank, wherein the rated parameter data includes valve rated pressure parameters, valve rated pressure loss parameters, tank rated gas pressure parameters, and tank rated capacity parameters; A historical deviation parameter data set construction module 2 is used to obtain historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct the historical deviation parameter data set based on a preset common time axis; A usage-deviation data set construction module 3 is used to obtain usage data of the gas storage tank, and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; An aging prediction factor generation module 4 is configured to be pre-set with an aging analysis model to analyze the usage-bias data set based on a machine self-learning algorithm to generate an aging prediction factor; A prediction parameter data generating module 5, which is used to pre-set an aging prediction model to perform aging prediction on the gas storage tank based on the aging prediction factor, and generate prediction parameter data of the gas storage tank; A gas storage tank filling strategy generating module 6, used for generating a gas storage tank filling strategy based on the predicted parameter data; The gas storage tank aging judgment report generation module 7 is used to obtain real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether there is tank aging based on the preset difference threshold data on the actual difference data, and generate a gas storage tank aging judgment report based on the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold.

[0060] The specific definition of the multifunctional gas storage tank status monitoring device can be found in the definition of the multifunctional gas storage tank status monitoring method above, which will not be repeated here. Each module in the above-mentioned multifunctional gas storage tank status monitoring device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0061] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a database. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multifunctional gas storage tank status monitoring method is implemented.

[0062] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Acquire rated parameter data of the gas storage tank, wherein the rated parameter data includes valve rated pressure parameters, valve rated pressure loss parameters, tank rated gas pressure parameters, and tank rated capacity parameters; Acquire historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct a historical deviation parameter data set based on a preset common time axis; Acquire usage data of the gas storage tank, and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; The preset aging analysis model analyzes the usage-bias dataset based on a machine self-learning algorithm to generate an aging prediction factor; The preset aging prediction model performs aging prediction on the gas storage tank based on the aging prediction factor to generate prediction parameter data of the gas storage tank; generating a gas storage tank charging strategy based on the predicted parameter data; Acquire real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether the tank body is aged based on the preset difference threshold data, and generate a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold; In the step of judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the following steps are included: If the actual difference data exceeds the normal difference threshold but does not reach the re-test difference threshold, the result is judged as normal loss; If the actual difference data exceeds the re-inspection difference threshold but does not reach the aging difference threshold, it is determined that the gas storage tank may be aged and needs to be re-inspected; If the actual difference data exceeds the aging difference threshold, it is determined that the gas storage tank has aged and the aged tank needs to be replaced.

[0063] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire rated parameter data of the gas storage tank, wherein the rated parameter data includes valve rated pressure parameters, valve rated pressure loss parameters, tank rated gas pressure parameters, and tank rated capacity parameters; Acquire historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct a historical deviation parameter data set based on a preset common time axis; Acquire usage data of the gas storage tank, and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; The preset aging analysis model analyzes the usage-bias dataset based on a machine self-learning algorithm to generate an aging prediction factor; The preset aging prediction model performs aging prediction on the gas storage tank based on the aging prediction factor to generate prediction parameter data of the gas storage tank; generating a gas storage tank filling strategy based on the predicted parameter data; Acquire real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether the tank body is aged based on the preset difference threshold data, and generate a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold; In the step of judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the following steps are included: If the actual difference data exceeds the normal difference threshold but does not reach the re-test difference threshold, the result is judged as normal loss; If the actual difference data exceeds the re-inspection difference threshold but does not reach the aging difference threshold, it is determined that the gas storage tank may be aged and needs to be re-inspected; If the actual difference data exceeds the aging difference threshold, it is determined that the gas storage tank has aged and the aged tank needs to be replaced.

[0064] 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 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may 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).

[0065] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0066] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A multifunctional gas storage tank status monitoring method, It is characterized in that The method comprises the steps of: obtaining rated parameter data of a gas storage tank, wherein the rated parameter data comprises a valve rated pressure parameter, a valve rated pressure loss parameter, a tank rated gas pressure parameter, and a tank rated capacity parameter; Acquire historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct a historical deviation parameter data set based on a preset common time axis; Acquire usage data of the gas storage tank, and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; The preset aging analysis model analyzes the usage-bias dataset based on a machine self-learning algorithm to generate an aging prediction factor; The preset aging prediction model performs aging prediction on the gas storage tank based on the aging prediction factor to generate prediction parameter data of the gas storage tank; generating a gas storage tank charging strategy based on the predicted parameter data; Acquire real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether the tank body is aged based on the preset difference threshold data, and generate a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold; The step of judging whether the actual difference data has tank aging based on the preset difference threshold data and generating a gas storage tank aging judgment report according to the judgment result includes the following steps: If the actual difference data exceeds the normal difference threshold but does not reach the re-test difference threshold, the result is judged as normal loss; If the actual difference data exceeds the re-inspection difference threshold but does not reach the aging difference threshold, it is determined that the gas storage tank may be aged and needs to be re-inspected; If the actual difference data exceeds the aging difference threshold, it is determined that the gas storage tank has aged and the aged tank needs to be replaced.

2. A multifunctional gas storage tank status monitoring method according to claim 1, It is characterized in that After judging whether the actual difference data has tank aging based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the following steps are included: Marking the actual difference data according to the aging judgment report, marking the data with a judgment result of normal wear and tear as normal, and marking the data with a judgment result of the possibility of aging and aging as abnormal; Associating the historical parameter data and the historical usage data of the storage tank marked as abnormal according to the common time axis one by one and constructing a usage habit parameter change data set; The preset usage habit analysis model analyzes the habit parameter change data set based on a machine self-learning algorithm to generate an aging correction factor, and the aging correction factor is used to correct and predict the aging differences corresponding to different usage habits.

3. A multifunctional gas storage tank status monitoring method according to claim 1, It is characterized in that After marking the actual difference data according to the aging judgment report, marking the data with a judgment result of normal wear as normal, and marking the data with a judgment result of the possibility of aging and aging as abnormal, the following steps are also included: Acquire historical environmental data of the gas storage tank, associate the historical environmental data with the historical parameter data one by one according to the common time axis, and construct an environmental parameter change data set; The preset environmental impact analysis model analyzes the environmental parameter change data set based on a machine self-learning algorithm to generate an environmental correction factor, and the environmental correction factor is used to correct and predict the aging differences corresponding to different environments.

4. A multifunctional gas storage tank status monitoring method according to claim 1, It is characterized in that After judging whether the actual difference data has tank aging based on the preset difference threshold data and generating a gas storage tank aging judgment report according to the judgment result, the following steps are also included: Acquire historical transportation data of the gas storage tank, associate the historical transportation data with the historical parameter data one by one according to the common time axis, and construct a transportation impact data set; The preset transportation impact analysis model analyzes the transportation impact data set based on a machine self-learning algorithm to generate a transportation impact factor, and the transportation impact factor is used to make a correct prediction of the aging differences corresponding to different transportation conditions.

5. A multifunctional gas storage tank status monitoring method according to claim 4, It is characterized in that In the preset transportation impact analysis model, the transportation impact data set is analyzed based on the machine self-learning algorithm to generate transportation impact factors. The transportation impact factors are used to correct the prediction of aging differences corresponding to different transportation conditions. In this step, the transportation impact factors include transportation route impact sub-factors, transportation time impact sub-factors and transportation environment impact sub-factors.

6. A multifunctional gas storage tank status monitoring method according to claim 5, It is characterized in that In the step of acquiring the real-time data of the gas storage tank and comparing it with the real-time prediction parameter data to generate actual difference data, judging whether the tank body is aged based on the preset difference threshold data, and generating a gas storage tank aging judgment report according to the judgment result, the aging judgment report includes: a detailed description of the aging state, the detailed description including the comparison result of the actual difference data and the difference threshold data; When the result is judged to be normal wear and tear, provide suggestions for maintenance and care; When the judgment result shows that there is a possibility of aging, provide a re-inspection schedule and a list of re-inspection items; When it is determined that the equipment is already aged, a specific plan and timetable for replacement or repair will be provided.

7. A multifunctional gas storage tank status monitoring method according to claim 1, It is characterized in that The machine self-learning algorithms include support vector machines, random forests and deep neural networks.

8. A multifunctional gas storage tank status monitoring device, applied to a multifunctional gas storage tank status monitoring method according to any one of claims 1 to 7, It is characterized in that The device comprises: a rated parameter data acquisition module (1) for acquiring rated parameter data of a gas storage tank, wherein the rated parameter data comprises a valve rated pressure parameter, a valve rated pressure loss parameter, a tank rated gas pressure parameter, and a tank rated capacity parameter; A historical deviation parameter data set construction module (2) is used to obtain historical parameter data of the gas storage tank, compare the historical parameter data with the rated parameter data to generate historical deviation data, and construct the historical deviation parameter data set based on a preset common time axis; A usage-deviation data set construction module (3) is used to obtain usage data of the gas storage tank and associate the deviation data with the usage data based on the common time axis to construct a usage-deviation data set; An aging prediction factor generation module (4) is configured to be pre-set with an aging analysis model to analyze the usage-bias data set based on a machine self-learning algorithm to generate an aging prediction factor; A prediction parameter data generating module (5) is used to pre-set an aging prediction model to perform aging prediction on the gas storage tank based on the aging prediction factor, and generate prediction parameter data of the gas storage tank; A gas storage tank filling strategy generating module (6), used for generating a gas storage tank filling strategy based on the predicted parameter data; A gas storage tank aging judgment report generating module (7) is used to obtain real-time data of the gas storage tank and compare it with the real-time prediction parameter data to generate actual difference data, and judge whether the actual difference data has tank aging based on preset difference threshold data, and generate a gas storage tank aging judgment report according to the judgment result, wherein the difference threshold data includes a normal difference threshold, a re-inspection difference threshold and an aging difference threshold.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the multifunctional gas storage tank status monitoring method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of a multifunctional gas storage tank status monitoring method as described in any one of claims 1 to 7 are implemented.

Images