Intelligent early warning method and system for pressure of liquid storage tank

Abstract

The invention relates to the technical field of pressure early warning, in particular to an intelligent early warning method and system for the pressure of a liquid storage tank, and the method comprises the steps: 1, carrying out the real-time collection of the early warning data of the liquid storage tank, and obtaining the monitoring parameters of the intelligent early warning of the pressure, 2, analyzing the monitoring parameters of the step 1, and obtaining the influence indexes of the pressure early warning of the liquid storage tank, 3, evaluating the liquid storage tank pressure fused with the influence index obtained through analysis in the step 2 to obtain a pressure fluctuation parameter, and 4, comparing the results obtained in the step 2 and the step 3 with a pressure threshold value and a pressure fluctuation threshold value respectively to obtain the liquid storage tank pressure fused with the influence index. And step 5, carrying out man-machine interaction on the intelligent early warning information of the pressure of the liquid storage tank obtained in the step 4. Through the big data technology and the sensor technology, real-time monitoring and early warning of the pressure of the liquid storage tank can be achieved, and the production safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure early warning, and in particular to an intelligent early warning method and system for liquid storage tank pressure. Background Art

[0002] With the continuous development of industrial production, liquid storage tanks, as important equipment for storing various liquid media, have been widely used in many fields such as petroleum, chemical industry, and gas. However, the safety issues of liquid storage tanks have become increasingly prominent, especially the pressure changes inside the liquid storage tanks. The stability of its internal pressure is crucial for safe production and storage. With the development of artificial intelligence technology, technical support is provided for intelligent early warning of storage tank pressure.

[0003] Traditional tank pressure monitoring methods rely mainly on manual inspections and simple sensor alarms to achieve early warning purposes. Inspectors will regularly check tanks, including checking the pressure readings on the pressure indicator or display to confirm whether the pressure in the tank is within a safe range; traditional sensor alarm systems send out alarm signals after monitoring the pressure reaching a preset threshold. When the sensor triggers an alarm, inspectors can respond quickly and go to the site for confirmation and processing.

[0004] However, there are still some shortcomings in its actual use. For example, manual inspections require a lot of manpower and time, and it is difficult to detect and deal with abnormal situations in a timely manner; traditional sensor alarm systems usually only send out alarm signals after the pressure reaches the preset threshold, and cannot achieve real-time monitoring and early warning of pressure changes in the storage tank; traditional monitoring systems often lack advanced data processing and analysis capabilities, and are unable to conduct in-depth mining and effective use of the collected pressure data, resulting in problems such as untimely and inaccurate early warnings, which in turn lead to potential safety risks and economic losses. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a liquid storage tank pressure intelligent early warning method and system to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a liquid storage tank pressure intelligent early warning method, comprising:

[0007] Step 1: Use big data technology to collect the early warning data of the liquid storage tank in real time, and obtain and analyze the monitoring parameters of the pressure intelligent early warning;

[0008] Step 2: Analyze the monitoring parameters in step 1 through big data analysis technology to obtain various influencing indexes of the liquid storage tank pressure warning, and then fuse the monitored pressure data with the influencing index to obtain the liquid storage tank pressure of the fused influencing index;

[0009] Step 3: Evaluate the tank pressure of the fusion impact index obtained by the analysis in step 2 to obtain the pressure fluctuation parameter;

[0010] Step 4: Based on the fusion impact index of the liquid storage tank pressure obtained in step 2 and the abnormal index of the liquid storage tank pressure fluctuation obtained in step 3, the pressure threshold and the pressure fluctuation threshold are compared respectively, and a warning is issued for the comparison results that do not meet the warning threshold;

[0011] Step 5: Perform human-computer interaction on the intelligent warning information of the liquid storage tank pressure obtained in step 4.

[0012] Preferably, the monitoring parameters in step 1 include target area information of the liquid storage tank, identity authentication information of the management personnel, pressure parameters, temperature parameters, liquid level parameters and gas component concentration parameters.

[0013] Preferably, the model of the temperature-pressure influence index in each influence index in step 2 is: Where ρ_TP represents the temperature influence index on pressure, n represents the number of sampling points, T(i) represents the temperature value of the i-th sampling point, P(i) represents the pressure value corresponding to the i-th sampling point, T_m represents the average temperature of all sampling points, P_m represents the average pressure of all sampling points, max[P(i)] and min[P(i)] represent the pressure value at high temperature max[T(i)] and low temperature min[T(i)], and ΔTP represents the pressure change rate under the standard temperature gradient.

[0014] Preferably, the model of the liquid level influence index on pressure in each influence index in step 2 is: Where ρ_HP represents the influence index of liquid level on pressure, P_m represents the average pressure of all sampling points corresponding to the current liquid level, Pref represents the reference pressure value, H represents the liquid level height, Href represents the reference liquid level height, and ΔHP represents the pressure change rate under the standard liquid level gradient.

[0015] Preferably, the model of the gas component influence index on pressure in each influence index in step 2 is: Wherein ρ_GP represents the influence index of gas component on pressure, P(aft) represents the pressure value after the gas component changes, P(bef) represents the pressure value before the gas component changes, ΔC_G represents the rate of change of gas component during the regular monitoring time, ΔC_G=(Cc-Rc) / Rc, Cc represents the current gas component concentration, Rc represents the reference gas component concentration, and P_m represents the average value of the liquid storage tank pressure during the regular monitoring time of the gas component.

[0016] Preferably, the tank pressure model of the fusion impact index in step 2 is: Where n represents the number of sampling points, pk represents the pressure value of the liquid storage tank at the kth sampling point, and a1, a2 and a3 represent the weights of each influencing index respectively.

[0017] Preferably, the pressure fluctuation parameter in step 3 comprises the following steps:

[0018] Step 3.1: Through the timestamp technology and sensor technology, record the maximum value P(max), minimum value P(min) and average value P(avg) of the pressure of the liquid storage tank within the monitoring time t, and obtain the liquid storage tank pressure fluctuation index PFI.

[0019] Step 3.2: Through the time stamp technology and sensor technology, record the change ΔP of the pressure of the liquid storage tank within the same monitoring time t, that is, the difference between the maximum pressure P(max) and the minimum pressure P(min), and obtain the pressure change rate stability index PSI. Where ΔP(N) and ΔP(N-1) represent the changes in the pressure of the liquid storage tank during the Nth and N-1th monitoring time t, and ΔP(avg) represents the average value of the pressure changes during the N monitoring time t;

[0020] Step 3.3: Based on the tank pressure fluctuation index PFI in step 3.1 and the pressure change rate stability index PSI in step 3.2, the tank pressure fluctuation anomaly index PAI is obtained, PAI = PFI × (1-PSI), where b1 and b2 represent the corresponding weights respectively.

[0021] Preferably, the warning rules in step 4 include the following steps:

[0022] Step 4.1: Through big data analysis technology, when the tank pressure P_F of the fusion impact index exceeds or falls below the pressure warning threshold P_F(0) in the normal pressure mode of the tank, that is, the tank pressure deviation index DDI, If the DDI is within the deviation range, it means that the pressure of the liquid storage tank is normal; otherwise, it is judged to be an abnormal pressure mode, and the early warning mechanism is triggered;

[0023] Step 4.2: Through big data analysis technology, when the abnormal pressure fluctuation index PAI of the liquid storage tank exceeds the pressure fluctuation warning threshold PAI(0) in the normal pressure change mode, that is, the abnormal deviation degree index VDI of the liquid storage tank pressure fluctuation, If VDI is within the deviation range, it means that the pressure fluctuation of the liquid storage tank is normal; otherwise, it is judged as an abnormal pressure mode, and the early warning mechanism is triggered;

[0024] Step 4.3: Based on the liquid storage tank pressure deviation degree index DDI in step 4.1 and the liquid storage tank pressure fluctuation abnormal deviation degree index VDI in step 4.2, obtain the liquid storage tank pressure intelligent warning level rule:

[0025] Step 4.3.1: General warning: If the DDI is within the deviation range and the VDI is beyond the deviation range or the DDI is beyond the deviation range and the VDI is within the deviation range, it is judged as a slight deviation under the abnormal pressure mode and the general warning mechanism is triggered;

[0026] Step 4.3.2: Severe warning: If the DDI exceeds the deviation range and the VDI exceeds the deviation range, it is judged as a severe deviation under the abnormal pressure mode, triggering the severe warning mechanism.

[0027] Preferably, a liquid storage tank pressure intelligent early warning system comprises:

[0028] Liquid storage tank early warning data acquisition module: used to collect liquid storage tank early warning data, obtain and analyze various monitoring parameters of intelligent early warning, and transmit them to the liquid storage tank early warning data analysis module;

[0029] Liquid storage tank early warning data analysis module: used to analyze the various monitoring parameters of the data acquisition module, obtain the various influencing indexes of the liquid storage tank pressure early warning, then fuse the monitored pressure data with the influencing index, and transmit the fused pressure parameters to the liquid storage tank pressure data evaluation module;

[0030] Liquid storage tank pressure data evaluation module: used to evaluate the fused pressure parameters obtained by the data analysis module, obtain pressure fluctuation parameters, and transmit them to the liquid storage tank pressure intelligent early warning module;

[0031] Liquid storage tank pressure intelligent early warning module: used to compare the fusion pressure parameter obtained by the data analysis module and the pressure fluctuation parameter obtained by the data evaluation module with the threshold value respectively, issue an early warning for the comparison result that does not meet the early warning threshold value, and transmit the early warning signal to the liquid storage tank pressure intelligent early warning human-computer interaction module;

[0032] Liquid storage tank pressure intelligent warning human-computer interaction module: used to output the warning signal transmitted by the intelligent warning module to the management personnel information terminal.

[0033] Technical effects and advantages of the present invention:

[0034] 1. The present invention uses big data technology and sensor technology to achieve real-time monitoring and early warning of parameters such as pressure, temperature, liquid level, and gas composition of liquid storage tanks, timely discover and handle abnormal situations, provide reliable technical support for the safe operation of liquid storage tanks, reduce risks in the production and storage process, and improve production safety;

[0035] 2. The present invention uses big data analysis technology and advanced data processing and analysis algorithms to deeply mine and utilize the collected liquid storage tank warning data, providing scientific technical support for the safe operation of the liquid storage tank and data support for the management of administrators, reducing the risks in the production and storage process and improving the accuracy and reliability of intelligent warning of liquid storage tank pressure;

[0036] 3. The present invention provides a variety of warning rules through the liquid storage tank pressure intelligent warning module, which is divided into general warning and severe warning abnormal pressure modes, and ensures that relevant personnel can receive warning information in time. It has good scalability and upgradeability, and can take corresponding emergency measures according to actual needs to effectively prevent safety accidents caused by abnormal pressure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the overall process of the present invention.

[0038] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] See also Figure 1 As shown, the present invention provides a liquid storage tank pressure intelligent warning system, including: a liquid storage tank warning data acquisition module, a liquid storage tank warning data analysis module, a liquid storage tank pressure data evaluation module, a liquid storage tank pressure intelligent warning module and a liquid storage tank pressure intelligent warning human-computer interaction module.

[0041] What needs to be specifically explained in this embodiment is that the present invention adopts machine learning algorithms, such as support vector machines, random forests, etc., and establishes recognition models for normal pressure change patterns and abnormal pressure patterns by learning a large amount of historical pressure data. The system integrates advanced sensor technology to monitor key parameters such as pressure, temperature, and liquid level of the liquid storage tank in real time. It also has a powerful intelligent liquid storage tank early warning data analysis module that can analyze data. When parameters such as the pressure of the liquid storage tank are abnormal, early warning information is intelligently issued.

[0042] The liquid storage tank warning data acquisition module is connected to the liquid storage tank warning data analysis module, the liquid storage tank pressure data evaluation module is respectively connected to the liquid storage tank pressure intelligent warning module and the liquid storage tank warning data analysis module, and the liquid storage tank pressure intelligent warning human-computer interaction module is respectively connected to the liquid storage tank pressure intelligent warning module and the liquid storage tank warning data analysis module.

[0043] Liquid storage tank early warning data acquisition module: used to collect liquid storage tank early warning data, obtain and analyze various monitoring parameters of intelligent early warning, and transmit them to the liquid storage tank early warning data analysis module;

[0044] Liquid storage tank early warning data analysis module: used to analyze the various monitoring parameters of the data acquisition module, obtain the various influencing indexes of the liquid storage tank pressure early warning, then fuse the monitored pressure data with the influencing index, and transmit the fused pressure parameters to the liquid storage tank pressure data evaluation module;

[0045] Liquid storage tank pressure data evaluation module: used to evaluate the fused pressure parameters obtained by the data analysis module, obtain pressure fluctuation parameters, and transmit them to the liquid storage tank pressure intelligent early warning module;

[0046] Liquid storage tank pressure intelligent early warning module: used to compare the fusion pressure parameter obtained by the data analysis module and the pressure fluctuation parameter obtained by the data evaluation module with the threshold value respectively, issue an early warning for the comparison result that does not meet the early warning threshold value, and transmit the early warning signal to the liquid storage tank pressure intelligent early warning human-computer interaction module;

[0047] Liquid storage tank pressure intelligent warning human-computer interaction module: used to output the warning signal transmitted by the intelligent warning module to the management personnel information terminal.

[0048] See also Figure 2 As shown, a liquid storage tank pressure intelligent early warning method includes the following steps: Step 1: Using big data technology, real-time collection of liquid storage tank early warning data is performed to obtain various monitoring parameters for analyzing pressure intelligent early warning; Step 2: Using big data analysis technology, various monitoring parameters of step 1 are analyzed to obtain various influence indexes of liquid storage tank pressure early warning, and then the monitored pressure data is fused with the influence index to obtain the liquid storage tank pressure of the fused influence index; Step 3: The liquid storage tank pressure of the fused influence index obtained by step 2 is evaluated to obtain a pressure fluctuation parameter; Step 4: Based on the liquid storage tank pressure of the fused influence index obtained in step 2 and the liquid storage tank pressure fluctuation abnormality index obtained in step 3, they are compared with the pressure threshold and the pressure fluctuation threshold respectively, and an early warning is issued for the comparison result that does not meet the early warning threshold; Step 5: Human-computer interaction is performed on the liquid storage tank pressure intelligent early warning information obtained in step 4.

[0049] Step 1: Through big data technology, the early warning data of the liquid storage tank is collected in real time to obtain and analyze various monitoring parameters of the pressure intelligent early warning, including the target area information of the liquid storage tank, the identity authentication information of the management personnel, the pressure parameters, the temperature parameters, the liquid level parameters and the gas component concentration parameters;

[0050] Step 2: Analyze the monitoring parameters of step 1 through big data analysis technology to obtain various influencing indexes of liquid storage tank pressure warning, and then fuse the monitored pressure data with the influencing index to obtain the liquid storage tank pressure with the fused influencing index, including a temperature and pressure analysis unit, a liquid level and pressure analysis unit, and a gas component and pressure analysis unit, wherein the temperature and pressure analysis unit is used to calculate the temperature and pressure parameters, the liquid level and pressure analysis unit is used to calculate the liquid level and pressure parameters, and the gas component and pressure analysis unit is used to calculate the gas component and pressure parameters, and its parameter analysis includes the following steps;

[0051] Step 2.1: By analyzing the temperature and pressure parameters, the influence of temperature changes on the pressure of the liquid storage tank can be measured. By combining the real-time monitoring data of temperature and pressure, the intelligent early warning system can automatically adjust the early warning threshold to adapt to the pressure changes at different temperatures. Through sensor technology, the temperature and pressure data of multiple sampling points in the liquid storage tank are recorded simultaneously. Therefore, the model for obtaining the temperature-pressure influence index in the temperature and pressure analysis unit is: Where ρ_TP represents the temperature influence index on pressure, n represents the number of sampling points, T(i) represents the temperature value of the i-th sampling point, P(i) represents the pressure value corresponding to the i-th sampling point, T_m represents the average temperature of all sampling points, P_m represents the average pressure of all sampling points, max[P(i)] and min[P(i)] represent the pressure value at high temperature max[T(i)] and the pressure value at low temperature min[T(i)], and ΔTP represents the pressure change rate under the standard temperature gradient;

[0052] What needs to be specifically explained in this embodiment is that temperature is one of the important factors affecting the pressure in the liquid storage tank. When the temperature rises, the movement speed of the gas molecules accelerates and the collision force increases, thereby causing the pressure to rise; conversely, when the temperature drops, the movement speed of the gas molecules slows down, the collision force decreases, and the pressure will also drop accordingly.

[0053] Step 2.2: By analyzing the liquid level and pressure parameters, the influence of the liquid level change on the pressure of the liquid storage tank can be measured. By combining the real-time monitoring data of the liquid level and pressure, the intelligent early warning system can more accurately judge the operating status of the liquid storage tank and reduce false alarms and missed alarms. Through sensor technology, the pressure data and liquid level height of multiple sampling points in the liquid storage tank are recorded simultaneously. Therefore, the model for obtaining the liquid level on pressure influence index in the liquid level and pressure analysis unit is: Where ρ_HP represents the liquid level influence index on pressure, P_m represents the average pressure of all sampling points corresponding to the current liquid level, Pref represents the reference pressure value, H represents the liquid level height, Href represents the reference liquid level height, and ΔHP represents the pressure change rate under the standard liquid level gradient;

[0054] It should be specifically noted in this embodiment that the height of the liquid level will affect the equilibrium state of the gas phase and the liquid phase inside the storage tank, thereby affecting the pressure inside the tank. When the liquid level is high, the volume of liquid nitrogen occupies a larger volume, the gas phase space is reduced, and the space for accommodating gas is relatively small, resulting in an increase in the pressure inside the tank; conversely, when the liquid level is low, the volume of liquid nitrogen is small, the gas phase space is larger, and the gas is more likely to diffuse and escape, resulting in a decrease in the pressure inside the tank.

[0055] Step 2.3: By analyzing the gas composition and pressure parameters, the influence of the gas composition change on the pressure of the liquid storage tank can be measured. By monitoring the changes in the gas composition in real time and the changes in the corresponding pressure data, the pressure in the storage tank can be judged more accurately, and an early warning instruction can be issued if an abnormality is found; through sensor technology, the changes in gas composition and the pressure data of multiple sampling points are monitored in real time. Therefore, the model for obtaining the gas composition influence index on pressure in the gas composition and pressure analysis unit is: Where ρ_GP represents the gas component influence index on pressure, P(aft) represents the pressure value after the gas component changes, P(bef) represents the pressure value before the gas component changes, ΔC_G represents the rate of change of the gas component within the regular monitoring time (such as 1 hour), ΔC_G=(Cc-Rc) / Rc, Cc represents the current gas component concentration, Rc represents the reference gas component concentration, and P_m represents the average value of the liquid storage tank pressure within the regular monitoring time of the gas component;

[0056] It should be specifically noted in this embodiment that changes in gas composition in the liquid storage tank will also affect changes in pressure. Interactions, chemical reactions or dissolution phenomena between different gases may affect the calculation of gas partial pressures, thereby affecting the total pressure. For example, in some cases, changes in gas composition may cause instability or abnormal increase in pressure inside the storage tank.

[0057] Step 2.4: Based on step 2.1, step 2.2 and step 2.3, the monitored pressure data and the influence index are fused to obtain the tank pressure model integrating the influence index: Where n represents the number of sampling points, p k represents the pressure value of the liquid storage tank at the kth sampling point, a1, a2 and a3 represent the weights of each influencing index, for example, a1 = 0.4, a2 = 0.3 and a3 = 0.3;

[0058] Step 3: evaluating the reservoir pressure of the fusion impact index obtained by the analysis in step 2 to obtain a pressure fluctuation parameter, including the following steps;

[0059] Step 3.1: Through the timestamp technology and sensor technology, record the maximum value P(max), minimum value P(min) and average value P(avg) of the pressure of the liquid storage tank within the monitoring time t, and obtain the liquid storage tank pressure fluctuation index PFI.

[0060] Step 3.2: Using timestamp technology and sensor technology, record the pressure change ΔP of N (e.g., 3, 5) tanks in the same monitoring time t, that is, the difference between the maximum pressure value P(max) and the minimum pressure value P(min), and obtain the pressure change rate stability index PSI. Where ΔP(N) and ΔP(N-1) represent the changes in the pressure of the liquid storage tank during the Nth and N-1th monitoring time t, and ΔP(avg) represents the average value of the pressure changes during the N monitoring time t;

[0061] Step 3.3: Based on the tank pressure fluctuation index PFI in step 3.1 and the pressure change rate stability index PSI in step 3.2, the tank pressure fluctuation abnormality index PAI is obtained, PAI = PFI × (1-PSI), where b1 and b2 represent corresponding weights, for example, b1 = 0.6 and b2 = 0.4;

[0062] Step 4: Based on the tank pressure of the fusion influence index obtained in step 2 and the tank pressure fluctuation abnormality index obtained in step 3, the pressure threshold and the pressure fluctuation threshold are compared respectively, and a warning is issued for the comparison result that does not meet the warning threshold. The warning rules include the following steps:

[0063] Step 4.1: Through big data analysis technology, when the tank pressure P_F of the fusion impact index exceeds or falls below the pressure warning threshold P_F(0) in the normal pressure mode of the tank, that is, the tank pressure deviation index DDI, If the DDI is within the deviation range, it means that the pressure of the liquid storage tank is normal; otherwise, it is judged to be an abnormal pressure mode, and the early warning mechanism is triggered;

[0064] Step 4.2: Through big data analysis technology, when the abnormal pressure fluctuation index PAI of the liquid storage tank exceeds the pressure fluctuation warning threshold PAI(0) in the normal pressure change mode, that is, the abnormal deviation degree index VDI of the liquid storage tank pressure fluctuation, If VDI is within the deviation range, it means that the pressure fluctuation of the liquid storage tank is normal; otherwise, it is judged as an abnormal pressure mode, and the early warning mechanism is triggered;

[0065] Step 4.3: Based on the liquid storage tank pressure deviation degree index DDI in step 4.1 and the liquid storage tank pressure fluctuation abnormal deviation degree index VDI in step 4.2, obtain the liquid storage tank pressure intelligent warning level rule:

[0066] Step 4.3.1: General warning: If the DDI is within the deviation range and the VDI is beyond the deviation range or the DDI is beyond the deviation range and the VDI is within the deviation range, it is judged as a slight deviation under the abnormal pressure mode and the general warning mechanism is triggered;

[0067] Step 4.3.2: Severe warning: If the DDI exceeds the deviation range and the VDI exceeds the deviation range, it is judged as a severe deviation under the abnormal pressure mode, triggering the severe warning mechanism;

[0068] Step 5: Perform human-computer interaction on the intelligent warning information of the liquid storage tank pressure obtained in step 4. If a general warning is received, the management personnel will be prompted to take timely measures, such as adjusting the pressure, stopping the liquid inlet, adjusting the temperature, etc., to ensure the safe operation of the liquid storage tank; if a serious warning is received, the management personnel will be prompted to immediately initiate an emergency response plan, and according to the target area information, comprehensively check the safety valve or special pressure relief device of the liquid storage tank, set up a warning area around the liquid storage tank to prevent people from approaching and ensure their safety.

[0069] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0070] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent early warning method for liquid storage tank pressure, characterized in that: include: Step 1: Use big data technology to collect the early warning data of the liquid storage tank in real time, and obtain and analyze the monitoring parameters of the pressure intelligent early warning; Step 2: Analyze the monitoring parameters in step 1 through big data analysis technology to obtain various influencing indexes of the liquid storage tank pressure warning, and then fuse the monitored pressure data with the influencing index to obtain the liquid storage tank pressure of the fused influencing index; Step 3: Evaluate the tank pressure of the fusion impact index obtained by the analysis in step 2 to obtain the pressure fluctuation parameter; Step 4: Based on the fusion impact index of the liquid storage tank pressure obtained in step 2 and the abnormal index of the liquid storage tank pressure fluctuation obtained in step 3, the pressure threshold and the pressure fluctuation threshold are compared respectively, and a warning is issued for the comparison results that do not meet the warning threshold; Step 5: Perform human-computer interaction on the intelligent warning information of the liquid storage tank pressure obtained in step 4.

2. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized in that: The monitoring parameters in step 1 include target area information of the liquid storage tank, identity authentication information of the management personnel, pressure parameters, temperature parameters, liquid level parameters and gas component concentration parameters.

3. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized in that: The model of the temperature-pressure influence index in each influence index in step 2 is: Where ρ_TP represents the temperature influence index on pressure, n represents the number of sampling points, T(i) represents the temperature value of the i-th sampling point, P(i) represents the pressure value corresponding to the i-th sampling point, T_m represents the average temperature of all sampling points, P_m represents the average pressure of all sampling points, max[P(i)] and min[P(i)] represent the pressure value at high temperature max[T(i)] and low temperature min[T(i)], and ΔTP represents the pressure change rate under the standard temperature gradient.

4. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized in that: The model of the liquid level influence index on pressure in each influence index in step 2 is: Where ρ_HP represents the influence index of liquid level on pressure, P_m represents the average pressure of all sampling points corresponding to the current liquid level, Pref represents the reference pressure value, H represents the liquid level height, Href represents the reference liquid level height, and ΔHP represents the pressure change rate under the standard liquid level gradient.

5. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized in that: The model of the gas component influence index on pressure in each influence index in step 2 is: Wherein ρ_GP represents the influence index of gas component on pressure, P(aft) represents the pressure value after the gas component changes, P(bef) represents the pressure value before the gas component changes, ΔC_G represents the rate of change of gas component during the regular monitoring time, ΔC_G=(Cc-Rc) / Rc, Cc represents the current gas component concentration, Rc represents the reference gas component concentration, and P_m represents the average value of the liquid storage tank pressure during the regular monitoring time of the gas component.

6. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized by: The tank pressure model of the fusion impact index in step 2 is: Where n represents the number of sampling points, p k represents the pressure value of the liquid storage tank at the kth sampling point, and a1, a2 and a3 represent the weights of each influencing index respectively.

7. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized by: The pressure fluctuation parameter in step 3 comprises the following steps: Step 3.1: Through the timestamp technology and sensor technology, record the maximum value P(max), minimum value P(min) and average value P(avg) of the pressure of the liquid storage tank within the monitoring time t, and obtain the liquid storage tank pressure fluctuation index PFI. Step 3.2: Through the time stamp technology and sensor technology, record the change ΔP of the pressure of the liquid storage tank within the same monitoring time t, that is, the difference between the maximum pressure P(max) and the minimum pressure P(min), and obtain the pressure change rate stability index PSI. Where ΔP(N) and ΔP(N-1) represent the changes in the pressure of the liquid storage tank during the Nth and N-1th monitoring time t, and ΔP(avg) represents the average value of the pressure changes during the N monitoring time t; Step 3.3: Based on the tank pressure fluctuation index PFI in step 3.1 and the pressure change rate stability index PSI in step 3.2, the tank pressure fluctuation anomaly index PAI is obtained, PAI = PFI × (1-PSI), where b1 and b2 represent the corresponding weights respectively.

8. The intelligent early warning method for liquid storage tank pressure according to claim 1 is characterized by: The warning rules in step 4 include the following steps: Step 4.1: Through big data analysis technology, when the tank pressure P_F of the fusion impact index exceeds or falls below the pressure warning threshold P_F(0) in the normal pressure mode of the tank, that is, the tank pressure deviation index DDI, If the DDI is within the deviation range, it means that the pressure of the liquid storage tank is normal; otherwise, it is judged to be an abnormal pressure mode, and the early warning mechanism is triggered; Step 4.2: Through big data analysis technology, when the abnormal pressure fluctuation index PAI of the liquid storage tank exceeds the pressure fluctuation warning threshold PAI(0) in the normal pressure change mode, that is, the abnormal deviation degree index VDI of the liquid storage tank pressure fluctuation, If VDI is within the deviation range, it means that the pressure fluctuation of the liquid storage tank is normal; otherwise, it is judged as an abnormal pressure mode, and the early warning mechanism is triggered; Step 4.3: Based on the liquid storage tank pressure deviation degree index DDI in step 4.1 and the liquid storage tank pressure fluctuation abnormal deviation degree index VDI in step 4.2, obtain the liquid storage tank pressure intelligent warning level rule: Step 4.3.1: General warning: If the DDI is within the deviation range and the VDI is beyond the deviation range or the DDI is beyond the deviation range and the VDI is within the deviation range, it is judged as a slight deviation under the abnormal pressure mode and the general warning mechanism is triggered; Step 4.3.2: Severe warning: If the DDI exceeds the deviation range and the VDI exceeds the deviation range, it is judged as a severe deviation under the abnormal pressure mode, triggering the severe warning mechanism.

9. A liquid storage tank pressure intelligent early warning system, used to use the liquid storage tank pressure intelligent early warning method according to any one of claims 1 to 8, comprising: Liquid storage tank early warning data acquisition module: used to collect liquid storage tank early warning data, obtain and analyze various monitoring parameters of intelligent early warning, and transmit them to the liquid storage tank early warning data analysis module; Liquid storage tank early warning data analysis module: used to analyze the various monitoring parameters of the data acquisition module, obtain the various influencing indexes of the liquid storage tank pressure early warning, then fuse the monitored pressure data with the influencing index, and transmit the fused pressure parameters to the liquid storage tank pressure data evaluation module; Liquid storage tank pressure data evaluation module: used to evaluate the fused pressure parameters obtained by the data analysis module, obtain pressure fluctuation parameters, and transmit them to the liquid storage tank pressure intelligent early warning module; Liquid storage tank pressure intelligent early warning module: used to compare the fusion pressure parameter obtained by the data analysis module and the pressure fluctuation parameter obtained by the data evaluation module with the threshold value respectively, issue an early warning for the comparison result that does not meet the early warning threshold value, and transmit the early warning signal to the liquid storage tank pressure intelligent early warning human-computer interaction module; Liquid storage tank pressure intelligent warning human-computer interaction module: used to output the warning signal transmitted by the intelligent warning module to the management personnel information terminal.

Images