LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data

Abstract

The invention discloses an LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data, and belongs to the technical field of liquefied natural gas. The LNG intelligent control valve operation diagnosis and optimization decision-making system comprises a multi-dimensional data acquisition module and a data preprocessing module, and the output end of the multi-dimensional data acquisition module is connected with the input end of the data preprocessing module; the output end of the data preprocessing module is connected with the input end of the data mining analysis module; according to the system, a fault prevention and control decision model is constructed by utilizing association rule mining and a decision tree algorithm, and intelligent diagnosis and maintenance decision of operation of the special valve are realized. The system response time is shortened to be smaller than or equal to 0.5 second, the intelligent comprehensive level reaches 27 minutes or above, the operation efficiency and the fault prevention capacity of the LNG control valve are remarkably improved, the fault response speed of the system and the accuracy of maintenance decision making can be greatly improved, and therefore the overall operation efficiency and the safety level of equipment are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of liquefied natural gas, and in particular relates to an LNG intelligent control valve operation diagnosis and optimization decision system based on big data. Background Art

[0002] As an important component of clean energy, liquefied natural gas (LNG) requires high-precision control valves to ensure the safety and stability of the system during transportation and storage. However, existing valve control systems generally lack intelligent fault warning and maintenance decision-making capabilities, resulting in the equipment being unable to respond in time after a fault occurs, and even causing serious safety hazards. In order to monitor the status of the control valve, maintenance and detection methods need to be applied.

[0003] Today's fault detection methods are usually based on manual or simple automated detection, with long response time, low efficiency, and the detection accuracy cannot be guaranteed. In order to solve this problem, an LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data is urgently needed. Summary of the invention

[0004] The purpose of the present invention is to propose an LNG intelligent control valve operation diagnosis and optimization decision system based on big data in order to solve the problem that the current fault detection methods are usually based on manual or simple automated detection, with long response time, low efficiency, and the detection accuracy cannot be guaranteed.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data, including a multidimensional data acquisition module and a data preprocessing module, the output end of the multidimensional data acquisition module is connected to the input end of the data preprocessing module, the output end of the data preprocessing module is connected to the input end of the data mining and analysis module, the output end of the data mining and analysis module is connected to the input end of the fault diagnosis and decision-making module, and the output end of the fault diagnosis and decision-making module is connected to the input end of the intelligent comprehensive evaluation module.

[0006] As a further description of the above technical solution: The multidimensional data acquisition module includes a temperature data acquisition module, a vibration data acquisition module, a pressure data acquisition module and a flow data acquisition module, and the output ends of the temperature data acquisition module, the vibration data acquisition module, the pressure data acquisition module and the flow data acquisition module are all connected to the input of the data concentration module.

[0007] As a further description of the above technical solution: The data preprocessing module includes a data concentration module, the output end of the data concentration module is connected to the input end of the edge computing module, and the output end of the edge computing module is connected to the input end of the data cleaning module.

[0008] As a further description of the above technical solution: The output end of the data cleaning module is connected to the input end of the abnormal data marking module, the output end of the abnormal data marking module is connected to the input end of the abnormal data deletion module, and the output end of the abnormal data deletion module is connected to the input end of the deleted data re-filling module.

[0009] As a further description of the above technical solution: The data mining and analysis module includes a historical operation data extraction module and an association rule mining algorithm module, the output end of the historical operation data extraction module is connected to the input end of the association rule mining algorithm module, the output end of the association rule mining algorithm module is connected to the input end of the valve fault identification module, and the output end of the valve fault identification module is connected to the input end of the decision tree algorithm import module.

[0010] As a further description of the above technical solution: The output end of the decision tree algorithm import module is connected to the input end of the fault diagnosis and decision model training module, and the output end of the fault diagnosis and decision model training module is connected to the input end of the model automatic learning and updating module.

[0011] As a further description of the above technical solution: The fault diagnosis and decision-making module includes a fault prevention and control decision model import module and a system anomaly detection module. The output end of the fault prevention and control decision model import module is connected to the input end of the system anomaly detection module, and the output end of the system anomaly detection module is connected to the input end of the fault diagnosis module.

[0012] As a further description of the above technical solution: The output end of the fault diagnosis module is connected to the input end of the maintenance suggestion automatic generation module, and the output end of the maintenance suggestion automatic generation module is connected to the input end of the control strategy optimization module.

[0013] The present invention also discloses an LNG intelligent control valve operation diagnosis and optimization decision method based on big data, comprising the following steps: S1. Use multi-dimensional sensors installed on the LNG control valve to collect the operating status of the valve in real time; S2, transfer valid data to the cloud database; S3. In the data center, historical operation data is analyzed through association rule mining algorithms to identify potential correlation factors of valve failures; S4. When the system detects an abnormal situation, the diagnosis module will quickly analyze the real-time data, use the built fault prevention and control decision model to make accurate fault diagnosis, and automatically give maintenance suggestions; S5. Conduct intelligent evaluation on the overall system operation data and fault diagnosis results.

[0014] As a further description of the above technical solution: In S1, a multi-dimensional sensor installed on the LNG control valve is used to collect the operating status of the valve in real time. The collected data is preliminarily processed by the edge computing device to filter out invalid or redundant data. The multi-dimensional sensors include temperature, pressure, flow and vibration sensors. In S3, in the data center, the historical operating data is analyzed by the association rule mining algorithm to identify the potential associated factors of valve failure. The decision tree algorithm is based on these data to train a fault diagnosis and decision model suitable for special valves. In S4, when the system detects an abnormal situation, the diagnosis module will quickly analyze the real-time data, use the constructed fault prevention and control decision model, make accurate fault diagnosis within ≤0.5 seconds, and automatically give maintenance suggestions. The system will also optimize the control strategy based on the current environment and working conditions to ensure the safety and stability of valve operation. In S5, through the intelligent evaluation of the overall operating data and fault diagnosis effect of the system, the system will comprehensively score to ensure that the intelligence level of the system reaches or exceeds 27 points.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: In the present invention, the system uses association rule mining and decision tree algorithms to build a fault prevention and control decision model, realizing intelligent diagnosis and maintenance decision-making for special valve operation. The system response time is shortened to ≤0.5 seconds, and the comprehensive intelligence level reaches more than 27 points, which significantly improves the operating efficiency and fault prevention ability of the LNG control valve. The system can greatly improve the system's response speed to faults and the accuracy of maintenance decisions, thereby improving the overall operating efficiency and safety level of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of the module structure of the LNG intelligent control valve operation diagnosis and optimization decision system based on big data.

[0017] Figure 2 This is a schematic diagram of the sub-module structure of the multi-dimensional data acquisition module in the LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data.

[0018] Figure 3This is a schematic diagram of the sub-module structure of the data preprocessing module in the LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data.

[0019] Figure 4 This is a schematic diagram of the sub-module structure of the data mining analysis module in the LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data.

[0020] Figure 5 This is a schematic diagram of the sub-module structure of the fault diagnosis and decision-making module in the LNG intelligent control valve operation diagnosis and optimization decision-making system based on big data.

[0021] Figure 6 This is a flow chart of the LNG intelligent control valve operation diagnosis and optimization decision-making method based on big data.

[0022] Legend: 1. Multi-dimensional data acquisition module; 2. Data preprocessing module; 3. Data mining and analysis module; 4. Fault diagnosis and decision-making module. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example 1 See also Figure 1-5 The present invention provides a technical solution: an LNG intelligent control valve operation diagnosis and optimization decision system based on big data, comprising a multidimensional data acquisition module 1 and a data preprocessing module 2, wherein the output end of the multidimensional data acquisition module 1 is connected to the input end of the data preprocessing module 2, the output end of the data preprocessing module 2 is connected to the input end of the data mining and analysis module 3, the output end of the data mining and analysis module 3 is connected to the input end of the fault diagnosis and decision module 4, and the output end of the fault diagnosis and decision module 4 is connected to the input end of the intelligent comprehensive evaluation module.

[0025] The multi-dimensional data acquisition module 1 includes a temperature data acquisition module, a vibration data acquisition module, a pressure data acquisition module and a flow data acquisition module, and the output ends of the temperature data acquisition module, the vibration data acquisition module, the pressure data acquisition module and the flow data acquisition module are all connected to the input of the data concentration module.

[0026] The data preprocessing module 2 includes a data concentration module, the output end of the data concentration module is connected to the input end of the edge computing module, the output end of the edge computing module is connected to the input end of the data cleaning module, the output end of the data cleaning module is connected to the input end of the abnormal data marking module, the output end of the abnormal data marking module is connected to the input end of the abnormal data deletion module, and the output end of the abnormal data deletion module is connected to the input end of the deleted data re-filling module.

[0027] The data mining and analysis module 3 includes a historical operation data extraction module and an association rule mining algorithm module, the output end of the historical operation data extraction module is connected to the input end of the association rule mining algorithm module, the output end of the association rule mining algorithm module is connected to the input end of the valve fault identification module, the output end of the valve fault identification module is connected to the input end of the decision tree algorithm import module, the output end of the decision tree algorithm import module is connected to the input end of the fault diagnosis and decision model training module, and the output end of the fault diagnosis and decision model training module is connected to the input end of the model automatic learning and updating module.

[0028] The fault diagnosis and decision module 4 includes a fault prevention and control decision model import module and a system anomaly detection module, the output end of the fault prevention and control decision model import module is connected to the input end of the system anomaly detection module, the output end of the system anomaly detection module is connected to the input end of the fault diagnosis module, the output end of the fault diagnosis module is connected to the input end of the maintenance suggestion automatic generation module, and the output end of the maintenance suggestion automatic generation module is connected to the input end of the control strategy optimization module.

[0029] In this embodiment, the intelligent control decision-making function based on the above system can be widely used in LNG production and storage and transportation equipment. In practical applications, the system can combine a large amount of historical data with real-time operating data, quickly respond to sudden failures, and make corresponding maintenance decisions. For example, when an abnormal pressure in the pipeline is detected, the system will determine the possible fault type through the decision model and automatically trigger the maintenance procedure to prevent further damage to the equipment.

[0030] Example 2 See also Figure 1-5The present invention provides a technical solution: an LNG intelligent control valve operation diagnosis and optimization decision system based on big data, comprising a multidimensional data acquisition module 1 and a data preprocessing module 2, wherein the output end of the multidimensional data acquisition module 1 is connected to the input end of the data preprocessing module 2, the output end of the data preprocessing module 2 is connected to the input end of the data mining and analysis module 3, the output end of the data mining and analysis module 3 is connected to the input end of the fault diagnosis and decision module 4, and the output end of the fault diagnosis and decision module 4 is connected to the input end of the intelligent comprehensive evaluation module.

[0031] The multi-dimensional data acquisition module 1 includes a temperature data acquisition module, a vibration data acquisition module, a pressure data acquisition module and a flow data acquisition module, and the output ends of the temperature data acquisition module, the vibration data acquisition module, the pressure data acquisition module and the flow data acquisition module are all connected to the input of the data concentration module.

[0032] The data preprocessing module 2 includes a data concentration module, the output end of the data concentration module is connected to the input end of the edge computing module, the output end of the edge computing module is connected to the input end of the data cleaning module, the output end of the data cleaning module is connected to the input end of the abnormal data marking module, the output end of the abnormal data marking module is connected to the input end of the abnormal data deletion module, and the output end of the abnormal data deletion module is connected to the input end of the deleted data re-filling module.

[0033] The data mining and analysis module 3 includes a historical operation data extraction module and an association rule mining algorithm module, the output end of the historical operation data extraction module is connected to the input end of the association rule mining algorithm module, the output end of the association rule mining algorithm module is connected to the input end of the valve fault identification module, the output end of the valve fault identification module is connected to the input end of the decision tree algorithm import module, the output end of the decision tree algorithm import module is connected to the input end of the fault diagnosis and decision model training module, and the output end of the fault diagnosis and decision model training module is connected to the input end of the model automatic learning and updating module.

[0034] The fault diagnosis and decision module 4 includes a fault prevention and control decision model import module and a system anomaly detection module, the output end of the fault prevention and control decision model import module is connected to the input end of the system anomaly detection module, the output end of the system anomaly detection module is connected to the input end of the fault diagnosis module, the output end of the fault diagnosis module is connected to the input end of the maintenance suggestion automatic generation module, and the output end of the maintenance suggestion automatic generation module is connected to the input end of the control strategy optimization module.

[0035] See also Figure 6The present invention also discloses an LNG intelligent control valve operation diagnosis and optimization decision method based on big data, comprising the following steps: S1. Use multi-dimensional sensors installed on the LNG control valve to collect the operating status of the valve in real time. The collected data is preliminarily processed by the edge computing device to filter out invalid or redundant data. The multi-dimensional sensors include temperature, pressure, flow and vibration sensors; S2, transfer valid data to the cloud database; S3. In the data center, historical operation data is analyzed through association rule mining algorithms to identify potential related factors of valve failure. Based on these data, the decision tree algorithm trains a fault diagnosis and decision model suitable for special valves; S4. When the system detects an abnormal situation, the diagnostic module will quickly analyze the real-time data and use the built fault prevention and control decision model to make accurate fault diagnosis within ≤0.5 seconds and automatically give maintenance suggestions. The system will also optimize the control strategy based on the current environment and working conditions to ensure the safety and stability of valve operation; S5. Through intelligent evaluation of the overall system operation data and fault diagnosis results, the system will give a comprehensive score to ensure that the system's intelligence level exceeds 27 points.

[0036] In this embodiment, the system uses association rule mining and decision tree algorithms to build a fault prevention and control decision model, realizing intelligent diagnosis and maintenance decision-making for special valve operation. The system response time is shortened to ≤0.5 seconds, and the comprehensive intelligence level reaches more than 27 points, which significantly improves the operating efficiency and fault prevention capabilities of the LNG control valve. The system can greatly improve the system's response speed to faults and the accuracy of maintenance decisions, thereby improving the overall operating efficiency and safety level of the equipment.

[0037] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An LNG intelligent control valve operation diagnosis and optimization decision system based on big data, comprising a multi-dimensional data acquisition module (1) and a data preprocessing module (2), characterized in that: The output end of the multidimensional data acquisition module (1) is connected to the input end of the data preprocessing module (2), the output end of the data preprocessing module (2) is connected to the input end of the data mining and analysis module (3), the output end of the data mining and analysis module (3) is connected to the input end of the fault diagnosis and decision module (4), and the output end of the fault diagnosis and decision module (4) is connected to the input end of the intelligent comprehensive evaluation module.

2. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 1 is characterized in that: The multi-dimensional data acquisition module (1) comprises a temperature data acquisition module, a vibration data acquisition module, a pressure data acquisition module and a flow data acquisition module, and the output ends of the temperature data acquisition module, the vibration data acquisition module, the pressure data acquisition module and the flow data acquisition module are all connected to the input of the data concentration module.

3. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 2 is characterized in that: The data preprocessing module (2) comprises a data concentration module, the output end of the data concentration module is connected to the input end of the edge computing module, and the output end of the edge computing module is connected to the input end of the data cleaning module.

4. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 3 is characterized in that: The output end of the data cleaning module is connected to the input end of the abnormal data marking module, the output end of the abnormal data marking module is connected to the input end of the abnormal data deletion module, and the output end of the abnormal data deletion module is connected to the input end of the deleted data re-filling module.

5. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 1 is characterized in that: The data mining analysis module (3) comprises a historical operation data extraction module and an association rule mining algorithm module, wherein the output end of the historical operation data extraction module is connected to the input end of the association rule mining algorithm module, the output end of the association rule mining algorithm module is connected to the input end of the valve fault identification module, and the output end of the valve fault identification module is connected to the input end of the decision tree algorithm import module.

6. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 5 is characterized in that: The output end of the decision tree algorithm import module is connected to the input end of the fault diagnosis and decision model training module, and the output end of the fault diagnosis and decision model training module is connected to the input end of the model automatic learning and updating module.

7. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 1 is characterized in that: The fault diagnosis and decision module (4) comprises a fault prevention and control decision model import module and a system anomaly detection module, wherein the output end of the fault prevention and control decision model import module is connected to the input end of the system anomaly detection module, and the output end of the system anomaly detection module is connected to the input end of the fault diagnosis module.

8. The LNG intelligent control valve operation diagnosis and optimization decision system based on big data according to claim 7 is characterized in that: The output end of the fault diagnosis module is connected to the input end of the maintenance suggestion automatic generation module, and the output end of the maintenance suggestion automatic generation module is connected to the input end of the control strategy optimization module.

9. The LNG intelligent control valve operation diagnosis and optimization decision-making method based on big data is characterized by: The steps include: S1. Use multi-dimensional sensors installed on the LNG control valve to collect the operating status of the valve in real time; S2, transfer valid data to the cloud database; S3. In the data center, historical operation data is analyzed through association rule mining algorithms to identify potential correlation factors of valve failures; S4. When the system detects an abnormal situation, the diagnosis module will quickly analyze the real-time data, use the built fault prevention and control decision model to make accurate fault diagnosis, and automatically give maintenance suggestions; S5. Conduct intelligent evaluation on the overall system operation data and fault diagnosis results.

10. The LNG intelligent control valve operation diagnosis and optimization decision method based on big data according to claim 9 is characterized in that: In S1, a multidimensional sensor installed on the LNG control valve is used to collect the operating status of the valve in real time. The collected data is preliminarily processed by an edge computing device to filter out invalid or redundant data. The multidimensional sensors include temperature, pressure, flow and vibration sensors. In S3, in the data center, historical operating data is analyzed by an association rule mining algorithm to identify potential related factors of valve failure. The decision tree algorithm is based on these data to train a fault diagnosis and decision model suitable for special valves. In S4, when the system detects an abnormal situation, the diagnosis module will quickly analyze the real-time data and use the constructed fault prevention and control decision model to make an accurate fault diagnosis within ≤0.5 seconds and automatically give maintenance suggestions. The system will also optimize the control strategy based on the current environment and working conditions to ensure the safety and stability of valve operation. In S5, the system will make a comprehensive score by intelligently evaluating the overall operating data and fault diagnosis effect of the system to ensure that the intelligence level of the system reaches or exceeds 27 points.

Images