A method, system and equipment for boosting control of an LNG storage tank

Abstract

This application relates to the technical field of LNG storage tanks, and specifically relates to a method, system, and device for controlling the pressurization of an LNG storage tank. The method includes: before the injection moment, by analyzing the correlation degree between the pressure data and temperature data at all moments, determining the optimal time delay, and combining the differences in pressure data and the change trend of the differences in temperature data between all adjacent moments, determining the temperature influence coefficient of the storage tank; by analyzing the differences in the change trends of the pressure data between the storage tank and the supercharger, and combining the temperature influence coefficient, determining the temperature weight and pressurization weight of the storage tank, and analyzing the growth rate of the internal pressure data of the storage tank, determining the pressure fluctuation index of the storage tank; based on the pressure fluctuation index, temperature weight, and pressurization weight, controlling the pressurization of the LNG storage tank. The purpose of this application is to improve the control accuracy of the pressurization of the storage tank, reduce energy consumption and pollutant emissions.

Description

Technical Field

[0001] This application relates to the technical field of LNG storage tanks, and specifically relates to a method, system, and equipment for controlling the pressurization of an LNG storage tank. Background Art

[0002] Liquefied natural gas (LNG), as an efficient and clean form of energy, is becoming increasingly important in the international energy market. LNG needs to be stored at extremely low temperatures (around -162.5°C), and for ease of transportation and use, it is usually stored in specially designed cryogenic storage tanks. When the LNG storage tank supplies gas to the pipe network, the pressure inside the tank gradually decreases. When the pressure inside the tank drops to a certain pressure value, it will affect the gas supply speed and capacity. At this time, it is necessary to pressurize the LNG storage tank through a booster to maintain normal gas supply. The prior art generally uses a two-position control method to control the pressure of the LNG storage tank, that is, setting the upper and lower limits of the tank pressure. When the tank pressure is less than the set lower limit, the booster is turned on for pressurization. When the tank pressure is greater than the set upper limit, the booster is turned off, and the pressure relief valve is opened to leak some gas, so that the tank pressure is within the set upper and lower limit range, thereby realizing the control of the tank pressure. However, since the LNG storage tank cannot achieve absolute heat insulation, the external temperature will also have a certain impact on the LNG storage tank, causing the tank pressure to rise.

[0003] In the process of pressurization control of the LNG storage tank in the prior art, because the hysteresis effect of temperature on the tank pressure is not considered, there is a problem that the pressurization stop time is inappropriate. If the pressurization stop time is too late, it will cause too much vaporized LNG, which will not only cause energy waste, but also harm the air quality. If the pressurization stop time is too early, it will cause insufficient tank pressure, and during the period of large gas supply demand, frequent pressurization is required, resulting in equipment wear. Therefore, due to the lack of consideration of the hysteresis effect of temperature on the tank pressure in the prior art, the control accuracy of the pressurization of the LNG storage tank is reduced, resulting in increased energy consumption and increased pollutant emissions. Summary of the Invention

[0004] In a first aspect, an embodiment of the present application provides a method for controlling the pressurization of an LNG storage tank, the method including the following steps:

[0005] Collect data when liquefied natural gas (LNG) starts to flow out of the storage tank, and collect in real time the pressure, liquid level data inside the storage tank, temperature data outside the storage tank, and pressure data inside the booster;

[0006] Extract the mutation points of the pressure data at all times inside the storage tank, and use the time corresponding to the last mutation point in time series as the injection time;

[0007] Before the injection time, the correlation between the partial pressure and temperature data is used to determine the optimal time lag, and the temperature influence coefficient of the storage tank is determined by combining the change trend of the pressure data difference and the temperature data difference between all adjacent moments;

[0008] After the injection time, the pressure data in the tank within the preset period is combined into an internal pressure growth sequence, and characteristic temperature data is extracted from all temperature data in combination with the optimal time lag and the injection time;

[0009] Compare the differences between the distribution of each characteristic temperature data and all temperature data before the injection moment, correct all elements in the internal pressure growth sequence, and form an internal pressure correction sequence;

[0010] Based on the changing trend of the differences between all adjacent elements in the internal pressure correction sequence, and the differences between the pressure data of the supercharger and all elements in the internal pressure correction sequence, combined with the temperature influence coefficient, the temperature weight and the boost weight of the storage tank are determined;

[0011] Based on the changing trend of the pressure data difference between all adjacent moments in the tank after the injection moment, the pressure fluctuation index of the tank is determined;

[0012] Based on the pressure fluctuation index, temperature weight and boost weight, the boost pressure control of the LNG storage tank is carried out.

[0013] Preferably, the method for determining the optimal time lag is:

[0014] Before the injection time, the median of the pressure data at all times inside the tank is taken as the upper limit of the range of the time lag k, denoted as a. , the value of k is All integers in ;

[0015] Before the injection time, the temperature data at all times are sequentially shifted backward in time sequence according to the time lag k, and the correlation coefficient between the result after the shift and the temporal intersection of the pressure data at all times is calculated, which is recorded as the correlation value under the time lag k;

[0016] Among the correlation values ​​under all time lags, the time lag corresponding to the largest correlation value is taken as the optimal time lag.

[0017] Preferably, the method for determining the temperature influence coefficient of the storage tank is:

[0018] The first-order difference sequence of the pressure data and the first-order difference sequence of the temperature data at all times inside the storage tank before the injection time are respectively obtained, and a preset number of elements are removed from the first-order difference sequence of the pressure data and the first-order difference sequence of the temperature data, and the remaining elements respectively constitute the internal pressure change sequence and the temperature change sequence;

[0019] Calculate the ratio between all elements in the internal pressure change sequence and all elements in the temperature change sequence, and take the mean value of all the said ratios as the temperature-pressure proportionality index of the storage tank;

[0020] The temperature influence coefficient of the storage tank is expressed as: ; where, represents the temperature-pressure proportionality index of the storage tank; represents the correlation coefficient between the pressure change sequence and the temperature change sequence; represents the optimal time lag.

[0021] Preferably, the process of obtaining the characteristic temperature data is as follows:

[0022] Take the moment corresponding to the last element in the internal pressure growth sequence as the reference moment, and extract the temperature data at the moment located from all the temperature data as the characteristic temperature data, where w represents the reference moment, z represents the injection moment, represents the optimal time lag.

[0023] Preferably, the process of correcting all elements in the internal pressure growth sequence is as follows:

[0024] If there is characteristic temperature data at the moment corresponding to element i in the internal pressure growth sequence, then the correction value of element i is expressed as: ; where, represents the value of element i in the internal pressure growth sequence; represents the characteristic temperature data at the moment corresponding to element i in the internal pressure growth sequence; represents the mean value of the temperature data at all moments before the injection moment; represents the temperature-pressure proportionality index of the storage tank; norm( ) represents the normalization function;

[0025] If there is no characteristic temperature data at the moment corresponding to element i in the internal pressure growth sequence, then the correction value of element i is expressed as: .

[0026] Preferably, the method for determining the temperature weight and the pressure boost weight of the storage tank is as follows:

[0027] Obtain the first-order difference sequence of all elements in the internal pressure correction sequence, and take the variance of all elements in this first-order difference sequence as the contribution difference degree of the storage tank;

[0028] Calculate the difference between the pressure data at all moments inside the supercharger and all elements in the internal pressure correction sequence as the pressure difference of the storage tank;

[0029] Take the ratio of the contribution difference degree of the storage tank and the pressure difference as the pressure boosting influence coefficient of the storage tank;

[0030] Calculate the sum value of the pressure boosting influence coefficient and the temperature influence coefficient of the storage tank, and respectively record the ratio of the temperature influence coefficient to the sum value, and the ratio of the pressure boosting influence coefficient to the sum value as the temperature weight and the pressure boosting weight.

[0031] Preferably, the method for determining the pressure fluctuation index of the storage tank is:

[0032] Obtain the first-order difference sequence of the pressure data at all moments inside the storage tank after the injection moment, and take the variance of all elements in the first-order difference sequence as the pressure fluctuation index of the storage tank.

[0033] Preferably, the pressure boosting control of the LNG storage tank includes:

[0034] Starting from when the liquefied natural gas (LNG) flows out of the storage tank, compose the internal pressure cut-off sequence, the liquid level cut-off sequence, the temperature cut-off sequence and the pressure cut-off sequence respectively with the pressure data, the liquid level data, the temperature data inside the storage tank and the pressure data inside the booster at all moments before the t-th moment;

[0035] Take the internal pressure cut-off sequence, the liquid level cut-off sequence, the temperature cut-off sequence and the pressure cut-off sequence, as well as the temperature weight, the pressure boosting weight and the pressure fluctuation index of the storage tank as the input of the neural network, and output the pressure data as the predicted pressure data at the corresponding moment when translating backward by the moment t from the injection moment;

[0036] Record the deviation between the predicted pressure data at the j-th moment after the injection moment and the preset upper limit of the storage tank pressure as the upper limit difference. If the upper limit difference is less than the preset threshold, stop inputting liquefied natural gas (LNG) into the booster at the j-th moment, otherwise, continue to input liquefied natural gas (LNG) into the booster.

[0037] In a second aspect, an embodiment of the present application provides an LNG storage tank pressure boosting control system, and the system includes:

[0038] A storage tank data acquisition module, configured to perform data acquisition when the liquefied natural gas (LNG) starts to flow out of the storage tank, and collect the pressure, liquid level data inside the storage tank, the temperature data outside the storage tank, and the pressure data inside the booster in real time;

[0039] A storage tank weight acquisition module, configured to extract the mutation points in the pressure data at all moments inside the storage tank, and use the moment corresponding to the last mutation point in time series as the injection moment;

[0040] Before the injection moment, the optimal time delay is determined by analyzing the correlation between pressure and temperature data, and the temperature influence coefficient of the storage tank is determined by combining the pressure data differences and the changing trends of temperature data differences between all adjacent moments.

[0041] After the injection moment, the pressure data in the storage tank within a preset time period are formed into an internal pressure growth sequence, and the characteristic temperature data are extracted from all temperature data by combining the optimal time delay and the injection moment.

[0042] Compare the differences between the distributions of each characteristic temperature data and all temperature data before the injection moment, correct all elements in the internal pressure growth sequence, and form an internal pressure correction sequence.

[0043] Based on the changing trend of the differences between all adjacent elements in the internal pressure correction sequence, the differences between the pressure data of the supercharger and all elements in the internal pressure correction sequence, and in combination with the temperature influence coefficient, determine the temperature weight and the supercharging weight of the storage tank.

[0044] Based on the changing trend of the pressure data differences between all adjacent moments in the storage tank after the injection moment, determine the pressure fluctuation index of the storage tank.

[0045] The storage tank supercharging control module is used to perform supercharging control on the LNG storage tank based on the pressure fluctuation index, the temperature weight, and the supercharging weight.

[0046] In a third aspect, an LNG storage tank supercharging control device provided by an embodiment of the present application includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned LNG storage tank supercharging control methods are implemented.

[0047] As can be seen from the above embodiments, an LNG storage tank supercharging control method provided by an embodiment of the present application has at least the following beneficial effects:

[0048] By analyzing the consistency between temperature and the change of the storage tank pressure, and quantifying the degree of temperature change on the storage tank pressure, the present application constructs a temperature influence coefficient, which can deeply evaluate the influence degree of temperature on the storage tank pressure; further, by analyzing the influence of the gasification of liquefied natural gas (LNG) on the storage tank pressure, a supercharger influence coefficient is constructed, which can deeply evaluate the influence of the gasification effect of the supercharger on the storage tank pressure on the premise of eliminating the influence of temperature lag; further, according to the data characteristics of the pressure rise during the supercharging of the storage tank, the present application constructs a pressure fluctuation index, so as to be able to evaluate whether the pressure rise rate of the storage tank is consistent. By deeply analyzing the influence of temperature and the gasification effect of the supercharger on the storage tank pressure, and combining the fluctuation characteristics of the storage tank pressure rise rate, the present application improves the control accuracy of the storage tank supercharging, and further reduces energy consumption and pollutant emissions. Brief Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 It is a flowchart of the steps of a method for controlling the pressurization of an LNG storage tank provided in an embodiment of the present application;

[0051] Figure 2 It is a schematic diagram of the process for extracting the temperature weight and the pressurization weight provided in an embodiment of the present application;

[0052] Figure 3 It is a block diagram of a system for controlling the pressurization of an LNG storage tank provided in an embodiment of the present application. Detailed Embodiments

[0053] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following will, in conjunction with the drawings and preferred embodiments, detail the specific embodiments, structures, features and effects of a method, system and equipment for controlling the pressurization of an LNG storage tank proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0055] The following will specifically describe the specific solutions of a method, system and equipment for controlling the pressurization of an LNG storage tank provided by the present application in conjunction with the drawings.

[0056] Please refer to Figure 1 , which shows a flowchart of the steps of a method for controlling the pressurization of an LNG storage tank provided in an embodiment of the present application. The method includes the following steps:

[0057] S1: When the liquefied natural gas (LNG) starts to flow out of the storage tank, data is collected, including the pressure data inside the storage tank, the liquid level data, the temperature data outside the storage tank, and the pressure data inside the booster in real time.

[0058] Since LNG storage tanks are usually equipped with pressure sensors and level sensors, in this embodiment, the pressure and level sensors are respectively used to collect the pressure and level data inside the LNG storage tank. At the same time, the ambient temperature data is collected by the temperature sensor outside the LNG storage tank, and the pressure data inside the booster is collected by the pressure sensor.

[0059] Data collection is carried out when the liquefied natural gas (LNG) starts to flow out of the storage tank. The pressure data, level data inside the storage tank, ambient temperature data outside the storage tank, and pressure data inside the booster are collected in real time. The collection frequency is f. When the pressure inside the storage tank reaches the upper limit, the data collection stops.

[0060] It should be noted that the value of the collection frequency f is set manually. In this embodiment, the value of the collection frequency f is 1 Hz. Implementers can also set it according to specific situations by themselves. This embodiment does not make special restrictions.

[0061] To eliminate the influence of the dimension between data, all the collected data is normalized to obtain the processed real-time pressure data, level data, and ambient temperature data.

[0062] It should be noted that there are many common normalization methods. In this embodiment, the maximum-minimum normalization method is used to normalize the data. In the actual application process, as other implementation methods, implementers can also use the z-score standardization method to normalize the data. Regarding the selection of the normalization method, this embodiment does not make special restrictions.

[0063] Among them, the maximum-minimum normalization method is a well-known technology, and the process of normalizing the data will not be elaborated here.

[0064] S2: Extract the mutation points in the pressure data at all times inside the storage tank, and use the time corresponding to the last mutation point in the time series as the injection time. Before the injection time, by analyzing the correlation degree between the pressure data and temperature data at all times, determine the optimal time delay, and combine the differences between the pressure data and the change trend of the differences between the temperature data at all adjacent times to determine the temperature influence coefficient of the storage tank.

[0065] Although the LNG storage tank has a strong heat insulation effect, due to the extremely low temperature of the LNG inside the storage tank and the fact that the storage tank cannot achieve complete heat insulation, it will still be affected by the external ambient temperature. The higher the external ambient temperature, the faster the pressure inside the storage tank rises.

[0066] When liquefied natural gas (LNG) is vaporized in a booster and reinjected into the storage tank, the pressure inside the storage tank will rise rapidly and continuously at this time. Before the injection of gaseous natural gas, the influence of ambient temperature on the storage tank pressure is the most significant. Therefore, by analyzing the change of the storage tank pressure before the injection of gaseous natural gas, the influence of ambient temperature on the pressure inside the storage tank can be analyzed.

[0067] Since the influence of ambient temperature on the storage tank pressure is far less significant than that of the injection of gaseous natural gas, there are significant stage changes in the internal pressure of the storage tank before and after the injection of gaseous natural gas. And when gaseous natural gas is injected into the storage tank, the pressure inside the storage tank will continue to rise and there will no longer be significant mutations.

[0068] Therefore, when the liquefied natural gas (LNG) starts to flow out of the storage tank, a mutation point detection algorithm is used to obtain the mutation points in the pressure data at all times inside the storage tank, and the time corresponding to the last mutation point in the time series is used as the injection time.

[0069] The influence of ambient temperature on the storage tank pressure can be obtained by analyzing the fluctuation of the pressure data inside the storage tank before the injection time. At the same time, the injection time also reflects that from the start of the liquefied natural gas (LNG) flowing out of the storage tank until the injection time, the internal pressure of the storage tank begins to enter the pressurization process.

[0070] It should be noted that there are many common mutation point detection algorithms. In this embodiment, the PELT algorithm is used to obtain the mutation points in the pressure data. In the actual application process, as other implementation methods, the implementer can also use the BG algorithm for non-stationary time series mutation detection. Regarding the selection of the mutation point detection algorithm, this embodiment does not make special restrictions.

[0071] Among them, the PELT algorithm is a well-known technology, and the specific process of detecting mutation points in the data will not be elaborated here.

[0072] Furthermore, considering that although ambient temperature will affect the storage tank pressure, due to the hysteresis of the temperature influence, when the ambient temperature changes, the storage tank pressure will not change immediately but there is a certain time delay. Therefore, it is necessary to first analyze the time delay degree of the influence of ambient temperature change on the storage tank pressure, and then accurately quantify the influence of ambient temperature on the storage tank pressure. The specific analysis process of the time delay degree of the influence of ambient temperature change on the storage tank pressure is as follows:

[0073] Before the injection time, the order corresponding to the median of the pressure data at all times inside the storage tank is used as the upper limit of the value range of the time delay k, denoted as a, and the time delay , k takes the value of All integers in

[0074] Before the injection moment, shift the temperature data at all moments backward in chronological order by a time lag k, and calculate the correlation coefficient between the result after the shift and the intersection part of the pressure data at all moments in time, which is denoted as the correlation value at the time lag k.

[0075] Among the correlation values at all time lags, take the time lag corresponding to the maximum correlation value as the optimal time lag. The optimal time lag reflects the degree of delay in time of the influence of temperature change on the storage tank pressure. The smaller the optimal time lag, the more direct the influence of temperature on the storage tank pressure and the greater the degree of influence.

[0076] It should be noted that there are many methods for calculating the correlation coefficient. In this embodiment, the cross-correlation coefficient between the result after the shift and the intersection part of the pressure data at all moments in time is used as the correlation coefficient between the result after the shift and the intersection part of the pressure data at all moments in time. In actual application processes, as other implementation methods, implementers can also adopt other calculation methods for the correlation coefficient. Regarding the selection of the correlation coefficient calculation method, this embodiment does not make special restrictions.

[0077] Among them, the calculation method of the cross-correlation coefficient is a well-known technology, and its specific calculation process will not be elaborated here.

[0078] Furthermore, in order to eliminate the time-delay influence of environmental temperature change on the storage tank pressure, respectively obtain the first-order difference sequences of the pressure data and the temperature data at all moments inside the storage tank before the injection moment, and remove the first preset number of elements from the first-order difference sequences of the pressure data and the temperature data respectively. The remaining elements respectively form the internal pressure change sequence and the temperature change sequence.

[0079] It should be noted that in this embodiment, the value of the preset number is numerically the same as the value of the optimal time lag.

[0080] Among them, the process of obtaining the first-order difference sequence is a well-known technology, and its specific obtaining steps will not be elaborated here.

[0081] Furthermore, calculate the ratio between all elements in the internal pressure change sequence and all elements in the temperature change sequence, and take the mean value of all the ratios as the temperature-pressure ratio index of the storage tank.

[0082] The temperature influence coefficient of the storage tank The expression is: ; In the formula, represents the temperature-pressure ratio index of the storage tank; represents the correlation coefficient between the pressure change sequence and the temperature change sequence; represents the optimal time lag.

[0083] It should be noted that there are many methods to measure the correlation degree between sequences. In this embodiment, the absolute value of the Pearson correlation coefficient between the pressure change sequence and the temperature change sequence is used as the correlation coefficient between the pressure change sequence and the temperature change sequence. In the actual application process, as other implementation manners, the implementer can also use the Spearman correlation coefficient or the Kendall rank correlation coefficient. Regarding the selection of the method for measuring the correlation degree between sequences, no special limitation is made in this embodiment.

[0084] Among them, the calculation method of the Pearson correlation coefficient is a well-known technology, and its specific calculation process will not be elaborated here.

[0085] According to the temperature influence coefficient of the storage tank, it can be understood that if the temperature-pressure ratio index is larger, the correlation coefficient between the pressure change sequence and the temperature change sequence is smaller, and the obtained temperature influence coefficient is larger, indicating that as the temperature changes, the degree of change of the storage tank pressure is larger, and the response of the storage tank pressure is faster; conversely, if the temperature-pressure ratio index is smaller, the correlation coefficient between the pressure change sequence and the temperature change sequence is larger, and the obtained temperature influence coefficient is smaller, indicating that as the temperature changes, the degree of change of the storage tank pressure is smaller, and the response of the storage tank pressure is slower.

[0086] S3: Analyze the differences in the change trends of the pressure data between the storage tank and the supercharger, and the growth rate of the internal pressure data of the storage tank, and respectively determine the temperature weight, the supercharging weight, and the pressure fluctuation index of the storage tank.

[0087] Since the supercharging process of the storage tank is to flow liquefied natural gas (LNG) into the supercharger, and then gasify it into gaseous natural gas and inject it into the storage tank to achieve supercharging, which has a direct impact on the storage tank pressure. Therefore, it is also necessary to analyze the influence degree of the gasification effect of the supercharger on the storage tank pressure, so as to realize the subsequent accurate supercharging control of the storage tank. The specific process is as follows:

[0088] S301: After the injection moment, form the internal pressure growth sequence with all the pressure data inside the storage tank within the preset time period, and extract the characteristic temperature data from all the temperature data in combination with the optimal time lag and the injection moment.

[0089] After the injection moment, form the internal pressure growth sequence with all the pressure data inside the storage tank within the preset time period.

[0090] It should be noted that the time length between the moment when the liquefied natural gas (LNG) starts to flow out of the storage tank and the injection moment is statistically counted, and this time length is used as the value of the preset time period length.

[0091] It should be understood that when the pressure in the storage tank drops to the lower pressure limit and then starts to increase, due to the large size of the storage tank, the time required for pressure increase is very long. Therefore, the number of data collected after the injection time is very large. The time between the start of LNG output and the injection time is relatively short compared to the overall pressure increase time. Therefore, the data collection duration after the injection time is longer than the time length between the moment when LNG starts to flow out of the storage tank and the injection time.

[0092] Take the moment corresponding to the last element in the internal pressure increase sequence as the reference time, and extract the temperature data at the moment located from the temperature data at all times as the characteristic temperature data, where w represents the reference time, z represents the injection time, represents the optimal time delay.

[0093] S302: Compare the differences between each characteristic temperature data and the average distribution of all temperature data before the injection time, and correct all elements in the internal pressure increase sequence. The correction results form the internal pressure correction sequence.

[0094] If there is characteristic temperature data at the moment corresponding to element i in the internal pressure increase sequence, the correction value of element i is expressed as: ; in the formula, represents the value of element i in the internal pressure increase sequence; represents the characteristic temperature data at the moment corresponding to element i in the internal pressure increase sequence; represents the average value of the temperature data at all times before the injection time; represents the temperature-pressure ratio index of the storage tank; norm( ) represents the normalization function;

[0095] If there is no characteristic temperature data at the moment corresponding to element i in the internal pressure increase sequence, the correction value of element i is expressed as: .

[0096] It can be understood from the correction values of each element in the internal pressure increase sequence that if the difference between the characteristic temperature data and the average value of the temperature data before the injection time is larger and the temperature-pressure ratio index is larger, it indicates that the temperature difference has a greater impact on the change of the storage tank pressure. Therefore, the storage tank pressure is corrected by the temperature difference; conversely, if the difference between the characteristic temperature data and the average value of the temperature data before the injection time is smaller and the temperature-pressure ratio index is smaller, it indicates that the temperature difference has a smaller impact on the change of the storage tank pressure.

[0097] By calculating the difference in the average temperature between the characteristic temperature data and the average of the temperature data at all times before the injection moment, the change in the storage tank pressure corresponding to the temperature difference is obtained, and the existing storage tank pressure is subtracted by the degree of change caused by the temperature change, so as to remove the change in the storage tank pressure caused by the temperature change.

[0098] S303: Based on the change trend of the differences between all adjacent elements in the internal pressure correction sequence, the differences between the pressure data of the supercharger at all times and all elements in the internal pressure correction sequence, and combined with the temperature influence coefficient, determine the temperature weight and supercharging weight of the storage tank.

[0099] Since the flow rate of LNG flowing out of the storage tank is uniform, the volume of LNG entering the supercharger at each moment is also the same. Therefore, if the gasification rate of the supercharger for LNG is consistent, the degree of increase in the storage tank pressure caused by the volume of LNG flowing out at each moment should also be the same.

[0100] Obtain the first-order difference sequence of all elements in the internal pressure correction sequence, and take the variance of all elements in this first-order difference sequence as the contribution difference degree of the storage tank; since liquefied natural gas (LNG) flows out uniformly, therefore, the greater the contribution difference degree, the greater the possibility of reflecting the inconsistent growth of the storage tank pressure due to the inconsistent gasification efficiency of the supercharger.

[0101] Furthermore, since when liquefied natural gas (LNG) is gasified, it will cause the pressure inside the supercharger to rise, so the internal pressure of the supercharger can also reflect the degree of gasification of the supercharger for liquefied natural gas (LNG). At the same time, because there is also a time delay between the gasification of liquefied natural gas (LNG) in the supercharger and the injection of gaseous natural gas into the storage tank, therefore, by analyzing the differences between the pressure data of the supercharger at all times and all elements in the internal pressure correction sequence to analyze the influence of the gasification change of the supercharger on the storage tank pressure, specifically:

[0102] Calculate the differences between the pressure data at all times inside the supercharger and all elements in the internal pressure correction sequence as the pressure difference of the storage tank;

[0103] It should be noted that there are many methods to measure the differences between data groups. In this embodiment, the dynamic time warping (DTW) distance between the corrected values of all elements in the internal pressure growth sequence and all pressure data is used as the difference between the corrected values of all elements in the internal pressure growth sequence and all pressure data; in the actual application process, as other implementation manners, the implementer can also use other methods to measure the differences between data groups, such as Euclidean distance or Manhattan distance. Regarding the selection of the method to measure the differences between data groups, this embodiment does not make special restrictions.

[0104] Among them, the calculation method of the dynamic time warping (DTW) distance is a well-known technology, and its specific calculation process will not be elaborated here.

[0105] Furthermore, the ratio of the contribution difference degree of the storage tank to the pressure difference is used as the pressurization influence coefficient of the storage tank.

[0106] It can be understood from the pressurization influence coefficient of the storage tank that the pressurization influence coefficient can reflect the influence degree of the gasification speed of the pressurizer on the pressure of the storage tank. If the contribution difference degree is larger and the pressure difference is smaller, the obtained pressurization influence coefficient is larger, which reflects that in the pressurization process of the storage tank, the influence of the gasification of the pressurizer is greater; on the contrary, if the contribution difference degree is smaller and the pressure difference is larger, the obtained pressurization influence coefficient is smaller, which reflects that in the pressurization process of the storage tank, the influence of the gasification of the pressurizer is smaller.

[0107] Furthermore, calculate the sum value of the pressurization influence coefficient and the temperature influence coefficient of the storage tank, and respectively record the ratio of the temperature influence coefficient to the sum value and the ratio of the pressurization influence coefficient to the sum value as the temperature weight and the pressurization weight.

[0108] Preferably, the schematic diagram of the extraction process of the temperature weight and the pressurization weight provided in this embodiment is as Figure 2 shown.

[0109] S304: Based on the change trend of the pressure data difference between all adjacent moments in the storage tank after the injection moment, determine the pressure fluctuation index of the storage tank.

[0110] Furthermore, in order to accurately predict the pressure of the storage tank at subsequent moments, it is necessary to evaluate the rising rate of the pressure of the storage tank after the injection of gaseous natural gas and detect whether its rising rate is relatively consistent and stable.

[0111] Obtain the first-order difference sequence of the pressure data at all moments inside the storage tank after the injection moment, and use the variance of all elements in this first-order difference sequence as the pressure fluctuation index of the storage tank. The pressure fluctuation index can reflect whether the rising rate of the pressure of the storage tank is consistent after the gaseous natural gas is injected into the storage tank.

[0112] Step S4: Based on the pressure fluctuation index, the temperature weight, and the pressurization weight, perform pressurization control on the LNG storage tank.

[0113] After the liquefied natural gas (LNG) starts to flow out of the storage tank and is vaporized into gaseous natural gas, it is not injected into the storage tank until the injection moment. Therefore, if the outflow moment of the liquefied natural gas (LNG) is taken as the start moment, and the time duration between the injection moment and the start moment is denoted as h, then the time difference between the inflow moment of the liquefied natural gas and the start moment is h. Therefore, it is possible to evaluate when to stop the outflow of LNG in the storage tank by predicting the pressure in the storage tank h hours after each moment and calculating the difference between the upper limit set for the storage tank pressure and the predicted storage tank pressure.

[0114] When the liquefied natural gas (LNG) starts to flow out of the storage tank, the pressure data, liquid level data, temperature data inside the storage tank at all moments before the t-th moment, and the pressure data inside the booster are respectively formed into an internal pressure cut-off sequence, a liquid level cut-off sequence, a temperature cut-off sequence, and a pressure cut-off sequence.

[0115] In this embodiment, the internal pressure cut-off sequence, the liquid level cut-off sequence, the temperature cut-off sequence, the pressure cut-off sequence, as well as the temperature weight, the boosting weight, and the pressure fluctuation index of the storage tank are used as the inputs of the BP neural network. There are a total of 7 input nodes in the input layer and only one output node in the output layer, which outputs pressure data as the predicted pressure data at the corresponding moment when translating backward by the moment t from the injection moment.

[0116] Among them, the optimization algorithm of the BP neural network is the SGD algorithm, and the loss function is MSE; the division of the training set and the test set is 7:3, the hidden layer is 5 layers, and the number of iterations is 50 times.

[0117] The deviation between the predicted pressure data at the j-th moment after the injection moment and the preset upper limit of the storage tank pressure is denoted as the upper limit difference. If the upper limit difference is less than the preset threshold, it means that the liquefied natural gas (LNG) in the booster can already meet the boosting of the subsequent storage tank pressure at this time, so the input of liquefied natural gas (LNG) into the booster is stopped at the j-th moment. Otherwise, the input of liquefied natural gas (LNG) into the booster continues.

[0118] It should be noted that in this embodiment, the lower limit of the LNG storage tank pressure is taken as 0.2 MPa, and the upper limit is taken as 0.5 MPa. Therefore, the value of the preset upper limit of the storage tank pressure in this embodiment is 0.5 MPa, and the implementer can also set it according to the specific situation without special limitation in this embodiment. In addition, the value of the preset threshold in this embodiment is also set manually. The value of the preset threshold in this embodiment is 0.005 MPa, and the implementer can also set it according to the specific situation without special limitation in this embodiment.

[0119] Based on the same inventive concept as the above method, the embodiment of the present application also provides an LNG storage tank boosting control system, including:

[0120] The storage tank data acquisition module is used to collect data when liquefied natural gas (LNG) starts to flow out of the storage tank, and to collect in real time the pressure and liquid level data inside the storage tank, the temperature data outside the storage tank, and the pressure data inside the booster;

[0121] The storage tank weight acquisition module is used to extract the mutation points in the pressure data at all times inside the storage tank, and take the time corresponding to the last mutation point in the time series as the injection time;

[0122] Before the injection time, analyze the correlation between the pressure and temperature data, determine the optimal time delay, and combine the change trends of the pressure data differences and temperature data differences between all adjacent times to determine the temperature influence coefficient of the storage tank;

[0123] After the injection time, form an internal pressure growth sequence with the pressure data inside the storage tank within a preset time period, and extract the characteristic temperature data from all the temperature data in combination with the optimal time delay and the injection time;

[0124] Compare the differences between each characteristic temperature data and the average distribution of all the temperature data before the injection time, correct all the elements in the internal pressure growth sequence, and form an internal pressure correction sequence;

[0125] Based on the change trend of the differences between all adjacent elements in the internal pressure correction sequence, and the differences between the pressure data of the booster and all the elements in the internal pressure correction sequence, in combination with the temperature influence coefficient, determine the temperature weight and booster weight of the storage tank;

[0126] Based on the change trend of the differences between the pressure data at all adjacent times inside the storage tank after the injection time, determine the pressure fluctuation index of the storage tank;

[0127] The storage tank booster control module is used to control the boosting of the LNG storage tank based on the pressure fluctuation index, the temperature weight, and the booster weight.

[0128] The block diagram of a LNG storage tank boosting control system provided by an embodiment of the present application is as Figure 3 shown.

[0129] Based on the same inventive concept as the above method, an embodiment of the present application also provides a LNG storage tank boosting control device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods for a LNG storage tank boosting control method.

[0130] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the specific embodiments of this specification have been described. Further, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0131] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0132] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling the pressurization of an LNG storage tank, characterized in that, The method includes the following steps: Collect data when liquefied natural gas (LNG) starts to flow out of the storage tank, and collect the pressure and liquid level data inside the storage tank, the temperature data outside the storage tank, and the pressure data inside the booster in real time; Extract the mutation points of the pressure data at all times inside the storage tank, and use the time corresponding to the last mutation point in time series as the injection time; Before the injection time, analyze the correlation between the pressure and temperature data, determine the optimal time delay, and combine the change trends of the pressure data differences and temperature data differences between all adjacent times to determine the temperature influence coefficient of the storage tank; After the injection moment, the pressure data in the storage tank within a preset time period are used to form an internal pressure growth sequence. The moment corresponding to the last element in the internal pressure growth sequence is taken as the reference moment, and the temperature data at the moment located within are extracted from the temperature data at all moments as the characteristic temperature data, where w represents the reference moment, z represents the injection moment, represents the optimal time delay; Compare the differences between the distributions of each characteristic temperature data and all temperature data before the injection time, correct all elements in the internal pressure growth sequence, and form an internal pressure correction sequence; Based on the change trend of the differences between all adjacent elements in the internal pressure correction sequence, the difference between the pressure data of the booster and all elements in the internal pressure correction sequence, and combined with the temperature influence coefficient, determine the temperature weight and booster weight of the storage tank; Based on the change trend of the pressure data differences between all adjacent times after the injection time inside the storage tank, determine the pressure fluctuation index of the storage tank; Based on the pressure fluctuation index, temperature weight and booster weight, perform booster control on the LNG storage tank.

2. The LNG storage tank pressure boosting control method according to claim 1, wherein, The method for determining the optimal time delay is as follows: Before the injection moment, the ordinal number corresponding to the median of the pressure data at all moments inside the storage tank is used as the upper limit of the value range of the time delay k, denoted as a, and the time delay , and the value of k is all integers in; Before the injection time, shift the temperature data at all times backward in time sequence according to the time delay k, calculate the correlation coefficient between the result after the shift and the intersection part of the pressure data at all times in time, and record it as the correlation value at the time delay k; Among the correlation values at all time delays, take the time delay corresponding to the maximum correlation value as the optimal time delay.

3. The LNG storage tank pressure boosting control method according to claim 1, characterized in that The method for determining the temperature influence coefficient of the storage tank is as follows: Respectively obtain the first-order difference sequences of the pressure data at all times inside the storage tank before the injection time and the first-order difference sequence of the temperature data, and remove the first preset number of elements from the first-order difference sequence of the pressure data and the first-order difference sequence of the temperature data respectively. The remaining elements form the internal pressure change sequence and the temperature change sequence respectively; Calculate the ratio between all elements in the internal pressure change sequence and all elements in the temperature change sequence, and take the mean value of all the ratios as the temperature-pressure ratio index of the storage tank; Temperature influence coefficient of the storage tank The expression is as follows: ; In the formula, represents the temperature-pressure ratio index of the storage tank; represents the correlation coefficient between the pressure change sequence and the temperature change sequence; represents the optimal time delay.

4. The LNG storage tank pressure boosting control method according to claim 3, characterized in that, The method for correcting all elements in the internal pressure growth sequence is as follows: If there is characteristic temperature data at the moment corresponding to element i in the internal pressure growth sequence, the correction value of element i is expressed as: ; where represents the value of element i in the internal pressure growth sequence; represents the characteristic temperature data at the moment corresponding to element i in the internal pressure growth sequence; represents the mean value of the temperature data at all moments before the injection moment; represents the temperature-pressure ratio index of the storage tank; norm( ) represents the normalization function; If there is no characteristic temperature data at the moment corresponding to element i in the internal pressure growth sequence, the correction value of element i is expressed as: .

5. The LNG storage tank pressure boosting control method according to claim 1, characterized in that The method for determining the temperature weight and booster weight of the storage tank is as follows: Obtain the first-order difference sequence of all elements in the internal pressure correction sequence, and take the variance of all elements in the first-order difference sequence as the contribution difference degree of the storage tank; Calculate the difference between the pressure data at all times inside the booster and all elements in the internal pressure correction sequence, as the pressure difference of the storage tank; Take the ratio of the contribution difference degree of the storage tank and the pressure difference as the booster influence coefficient of the storage tank; Calculate the sum value of the booster influence coefficient and the temperature influence coefficient of the storage tank, and record the ratio of the temperature influence coefficient to the sum value and the ratio of the booster influence coefficient to the sum value as the temperature weight and booster weight respectively.

6. The LNG storage tank pressure boosting control method according to claim 1, characterized in that, The method for determining the pressure fluctuation index of the storage tank is as follows: Obtain the first-order difference sequence of the pressure data at all times inside the storage tank after the injection moment, and take the variance of all elements in this first-order difference sequence as the pressure fluctuation index of the storage tank.

7. The LNG storage tank pressure boosting control method according to claim 1, characterized in that, The boosting control of the LNG storage tank includes: Starting from when the liquefied natural gas (LNG) flows out of the storage tank, compose the internal pressure cut-off sequence, liquid level cut-off sequence, temperature cut-off sequence, and pressure cut-off sequence respectively with the pressure data, liquid level data, temperature data inside the storage tank, and the pressure data inside the booster at all times before the t-th moment. Take the internal pressure cut-off sequence, liquid level cut-off sequence, temperature cut-off sequence, pressure cut-off sequence, and the temperature weight, boosting weight, and pressure fluctuation index of the storage tank as the input of the neural network, and output the pressure data as the predicted pressure data at the corresponding moment when translating backward by the moment t from the injection moment. Record the deviation between the predicted pressure data at the j-th moment after the injection moment and the preset upper limit of the storage tank pressure as the upper limit difference. If the upper limit difference is less than the preset threshold, stop inputting liquefied natural gas (LNG) into the booster at the j-th moment; otherwise, continue to input liquefied natural gas (LNG) into the booster.

8. An LNG storage tank pressure boosting control system, which implements an LNG storage tank pressure boosting control method as described in claim 1, characterized in that, The system includes: A storage tank data acquisition module, which is used to collect data when the liquefied natural gas (LNG) starts to flow out of the storage tank, and collect the pressure, liquid level data inside the storage tank, the temperature data outside the storage tank, and the pressure data inside the booster in real time. A storage tank weight acquisition module, which is used to extract the mutation points in the pressure data at all times inside the storage tank, and take the moment corresponding to the last mutation point in time series as the injection moment. Before the injection moment, determine the optimal time delay by analyzing the correlation between the pressure and temperature data, and determine the temperature influence coefficient of the storage tank in combination with the change trends of the differences between the pressure data and the temperature data at all adjacent moments. After the injection moment, the pressure data in the storage tank within a preset time period are used to form an internal pressure growth sequence. The moment corresponding to the last element in the internal pressure growth sequence is taken as the reference moment, and the temperature data at the moment located are extracted from the temperature data at all moments as the characteristic temperature data, where w represents the reference moment, z represents the injection moment, represents the optimal time delay; Compare the differences between each characteristic temperature data and the average distribution of all temperature data before the injection moment, correct all elements in the internal pressure growth sequence, and compose the internal pressure correction sequence. Based on the change trend of the differences between all adjacent elements in the internal pressure correction sequence, and the differences between the pressure data of the booster and all elements in the internal pressure correction sequence, and in combination with the temperature influence coefficient, determine the temperature weight and boosting weight of the storage tank. Based on the change trend of the differences between the pressure data at all adjacent moments inside the storage tank after the injection moment, determine the pressure fluctuation index of the storage tank. A storage tank boosting control module, which is used to perform boosting control on the LNG storage tank based on the pressure fluctuation index, temperature weight, and boosting weight.

9. An LNG storage tank pressure boosting control device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it realizes the steps of a method for boosting control of an LNG storage tank according to any one of claims 1-7.

Images