CN114964367A - LNG tank fault forecasting method and system based on time-varying parameters - Google Patents
LNG tank fault forecasting method and system based on time-varying parameters Download PDFInfo
- Publication number
- CN114964367A CN114964367A CN202210557168.7A CN202210557168A CN114964367A CN 114964367 A CN114964367 A CN 114964367A CN 202210557168 A CN202210557168 A CN 202210557168A CN 114964367 A CN114964367 A CN 114964367A
- Authority
- CN
- China
- Prior art keywords
- fault
- value
- tank
- analysis result
- forecasting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013277 forecasting method Methods 0.000 title description 2
- 238000004458 analytical method Methods 0.000 claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 238000005070 sampling Methods 0.000 claims abstract description 21
- 239000007788 liquid Substances 0.000 claims abstract description 20
- 230000001133 acceleration Effects 0.000 claims abstract description 18
- 239000007791 liquid phase Substances 0.000 claims abstract description 18
- 239000012071 phase Substances 0.000 claims abstract description 16
- 238000012417 linear regression Methods 0.000 claims abstract description 13
- 230000003068 static effect Effects 0.000 claims abstract description 9
- 238000010835 comparative analysis Methods 0.000 claims abstract description 4
- 238000000611 regression analysis Methods 0.000 claims description 18
- 230000003247 decreasing effect Effects 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Filling Or Discharging Of Gas Storage Vessels (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a method and a system for forecasting faults of an LNG tank based on time-varying parameters, wherein the method comprises the following steps of S100: setting sampling frequency, collecting main dynamic monitoring parameters TVP such as liquid phase temperature, gas phase pressure, liquid level, acceleration and floating frequency, and collecting main static parameters t; s200: performing unit third-order linear regression analysis on the main dynamic monitoring parameter TVP by taking t as an independent variable; s300: using the long-time monitoring data, repeatedly performing third-order linear regression analysis to obtain a value of Tank ═ M (D, b, e) of the storage Tank in a given State (State ═ S ()), taking the value as a standard value, recording the value as tand ═ mstad (D, b, e) as the 'fingerprint feature' of the storage Tank, performing comparative analysis on the value of actually monitored Tankt and tankstan, and determining the type of fault by using RSS analysis to analyze the difference value caused by the fault. The method of the invention can accurately forecast the LNG fault in real time and improve the safety of the LNG in the whole life cycle range.
Description
Technical Field
The invention belongs to the technical field of fault prediction, and particularly relates to a method, a system, a terminal and a storage medium for predicting faults of an LNG tank based on time-varying parameters.
Background
The multi-mode combined transportation of the LNG tank and the water (waterway, railway and road) is a third novel LNG logistics mode which is parallel to pipeline transportation and LNG bulk transport ships, and is gradually converted into normalized operation from previous test points under the national carbon emission reduction and carbon peak reaching tactical backgrounds. And LNG transportation also belongs to dangerous goods transportation field, and for this kind of concentrated mass transportation mode of pipeline transportation, boats and ships bulk transport, the LNG tank transportation also has the characteristics of a small amount of many batches, and the spatial-temporal distribution is very dispersed when nimble convenient, and this has brought great challenge to LNG tank safety monitoring.
At present, the following technical problems exist in the monitoring of the state information of the LNG tank: (1) in order to monitor each physical parameter in the LNG tank transportation, set up multiple monitoring sensor on the LNG tank if: temperature, pressure, liquid level height, acceleration sensor. Due to various factors such as the marine environment of the tank, the quality of the sensor and the like, the sensor fails inevitably, so that data cannot be acquired or acquired data is not credible; (2) LNG tank is for pressing cryrogenic equipment, and tank design adopts a series of technical means and equipment instrument to keep this type of state initially, because damage that product quality, maintenance state, transportation operating mode lead to all takes place, for the safety of guaranteeing tank transportation, monitors the trouble, reports and latent trouble early warning in advance is indispensable.
Disclosure of Invention
In view of the above drawbacks or needs for improvement in the prior art, the present invention provides a method for predicting a failure of an LNG Tank based on time-varying parameters, which includes collecting dynamic monitoring parameters such as liquid phase temperature, gas phase pressure, liquid level, acceleration, and floating frequency of the LNG Tank, performing unit third-order linear regression analysis on the dynamic monitoring parameters using constant parameters as arguments, obtaining a value of Tank M (D, b, e) in a given State ()) by regression using long-time monitoring data, and recording the value as a standard value as a "fingerprint feature" of the Tank. And comparing and analyzing the actually monitored Tankt value and Tankstand, analyzing a difference value caused by the fault by adopting RSS (residual error square sum), judging the type of the fault, accurately forecasting the LNG fault in real time, and improving the safety of the full life cycle range of the LNG.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a time-varying parameter-based LNG tank fault prediction method, including the steps of:
s100: setting sampling frequency, collecting main dynamic monitoring parameters TVP such as liquid phase temperature, gas phase pressure, liquid level, acceleration and floating frequency, and collecting main static parameters t;
s200: performing unit third-order linear regression analysis on the main dynamic monitoring parameter TVP by taking t as an independent variable;
s300: using the long-time monitoring data, repeatedly performing third-order linear regression analysis to obtain the Tank value of M (D, b, e) under a given State (State of S ()), taking the value as a standard value, recording the value as Tankstand as Mstand (D, b, e) as the 'fingerprint characteristic' of the Tank, comparing the actually monitored Tankt value with Tankstand, analyzing the difference value caused by faults by RSS, and judging the type of the faults.
Further, in step S100, the acquiring of the liquid phase temperature data and the forecasting of the fault include:
s101: setting sampling frequency, collecting liquid phase temperature data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s102: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S103;
s103: comparing the analysis result with the actual measurement value, and judging whether the temperature of the LNG exceeds the temperature range of liquid LNG from-165 ℃ to-140 ℃, if so, predicting the fault of the temperature sensor; if not, the step S104 is carried out;
s104: judging whether the numerical trends of the intercept D, the slope b and the error term e of the analysis result are increased or decreased, and if the numerical trends of the error term e are decreased D, b, ending the fault prediction; if D, b rises, the forecast tank heat leakage rate rises.
Further, in step S100, the data acquisition and fault prediction of the gas phase pressure includes:
s105: setting sampling frequency, collecting gas phase pressure data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s106: judging whether the sum of the squares of the residual errors exceeds the threshold range or not, and if not, ending the fault prediction; if yes, go to step S107;
s107: comparing the analysis result with the measured value, judging whether the analysis result exceeds a normal threshold range, and if so, forecasting the fault of the pressure touch sensor; if not, the step S108 is carried out;
s108: judging whether the numerical trends of the intercept D, the slope b and the error term e of the analysis result are increased or decreased, and if the numerical trends of the error term e are decreased D, b, ending the fault prediction; if D, b rises, the valve jump is predicted.
Further, in step S100, the liquid phase data collection and fault prediction includes:
s109: setting sampling frequency, collecting liquid level data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s110: judging whether the sum of the squares of the residual errors exceeds the threshold range or not, and if not, ending the fault prediction; if yes, go to step S110;
s111: comparing the analysis result with the measured value, and judging whether the analysis result exceeds a normal threshold range, if so, predicting tank overcharge or sensor fault; if not, the fault prediction is ended.
Further, in step S100, the acceleration data collection and fault prediction includes:
s112: setting sampling frequency, collecting acceleration data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s113: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S114;
s114: comparing the analysis result with the measured value, judging whether the analysis result exceeds a normal threshold range, and if so, forecasting the fault of the touch sensor; and if the minimum value is 0, forecasting the tank to be in a static state.
Further, in step S100, the data acquisition and fault prediction of the floating frequency includes:
s115: setting sampling frequency, collecting floating frequency data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s116: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S117;
s117: and comparing the analysis result with the measured value, judging whether the analysis result exceeds the normal threshold range, if so, predicting the fault of the sensor, otherwise, predicting the tank to stand if the analysis result is lower than the lower limit.
According to a second aspect of the present invention, there is provided a time-varying parameter-based LNG tank fault prediction system, comprising:
the data acquisition module is used for setting sampling frequency, acquiring main dynamic monitoring parameters TVP such as liquid phase temperature, gas phase pressure, liquid level, acceleration and floating frequency and the like, and acquiring a main static parameter t;
the regression analysis module is used for carrying out unit third-order linear regression analysis on the main dynamic monitoring parameter TVP by taking t as an independent variable;
the fault forecasting module repeatedly performs third-order linear regression analysis by using long-time monitoring data to obtain a value of Tank & ltM (D, b, e) of the storage Tank in a given State (State & ltS ()), takes the value as a standard value and takes Tankstand & ltMstand (D, b, e) as the fingerprint characteristic of the storage Tank, performs comparative analysis on the actually monitored value of Tankt and Tankstand, and judges the type of the fault by adopting RSS (received signal strength) analysis on the difference value caused by the fault.
According to a third aspect of the present invention, there is provided an electronic apparatus comprising:
at least one processor, at least one memory, and a communication interface; wherein,
the processor, the memory and the communication interface are communicated with each other;
the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any of claims 1 to 6.
According to a fourth aspect of the present invention, there is provided a non-transitory computer readable storage medium characterized in that it stores computer instructions which cause the computer to perform the method of any one of claims 1 to 6.
Generally, compared with the prior art, the above technical solution conceived by the present invention mainly has the following technical advantages:
1. the method of the invention collects dynamic monitoring parameters such as liquid phase temperature, gas phase pressure, liquid level, acceleration and floating frequency of the LNG Tank, performs unit third-order linear regression analysis on the dynamic monitoring parameters by using constant parameters as independent variables, obtains a Tank value M (D, b, e) of the storage Tank in a given State (State (S ()), and takes the Tank value M (D, b, e) as a standard value and takes the Tank value M (D, b, e) as the fingerprint characteristic of the storage Tank. And comparing and analyzing the actually monitored Tankt value and Tankstand, analyzing a difference value caused by the fault by adopting RSS (residual error square sum), judging the type of the fault, accurately forecasting the LNG fault in real time, and improving the safety of the full life cycle range of the LNG.
Drawings
Fig. 1 is a flowchart of a method for predicting a failure of an LNG tank based on time-varying parameters according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a liquid phase temperature fault prediction process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a gas phase pressure fault prediction process according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a liquid level fault prediction process in an embodiment of the present invention;
FIG. 5 is a schematic flow chart of acceleration fault prediction according to an embodiment of the present invention;
fig. 6 is a schematic flow chart of a floating frequency fault forecasting process according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, a method for forecasting a fault of an LNG tank based on time-varying parameters according to an embodiment of the present invention includes the following steps:
the method comprises the following steps: and (6) collecting parameters.
(1) Collecting main dynamic monitoring parameters, namely instantaneous variable parameters (TVP):
a liquid phase temperature sensor T101 (. degree. C.);
a gas phase pressure sensor P102 (MPa);
liquid level data m103 (kg);
acceleration a104(m/s 2);
a floating frequency s105 (HZ);
(2) the main static parameter, i.e. the constant parameter (t), is collected with a frequency t of 15 minutes.
Step two: performing unit third-order linear regression analysis on the TVP by taking t as an independent variable, wherein the calculation formula of the analysis is as follows:
TVP＝D+b 1 t 3 +b 2 t 2 +b 3 t+e
where D is the intercept, b is the slope, and e is the error term.
Step three: using long-time supervisionData is measured, and a value M (D, b, e) of the Tank in a given State (State) is obtained by regression, and the value is taken as a standard value and recorded as "fingerprint feature" of the Tank. Will actually monitor Tank t Value of and Tank stand And performing comparative analysis, and judging the type of the fault by analyzing the difference caused by the fault by using RSS (residual square sum).
Specifically, as shown in fig. 2, the data acquisition and fault prediction of the liquidus temperature includes:
s101: setting sampling frequency, collecting liquid phase temperature data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s102: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S103;
s103: comparing the analysis result with the actual measurement value, and judging whether the temperature of the liquid LNG is beyond the temperature range of-165 ℃ to-140 ℃, if so, predicting the fault of the temperature sensor; if not, the step S104 is carried out;
s104: judging whether the numerical trends of the intercept D, the slope b and the error term e of the analysis result are increased or decreased, and if the numerical trends of the error term e are decreased D, b, ending the fault prediction; if D, b is increased, the heat leakage rate of the tank box is forecasted to be increased.
In the embodiment of the present invention, the liquid phase temperature sensor T101 failure determination: wherein D is a regression intercept and is mainly influenced by the initial temperature of liquid filling; slope b123 reflects primarily the insulating capability of the tank itself, and may be affected as the tank ages; e is an error term. After LNG is filled into the tank, data analysis is carried out, TankState which is MState (D, b, e) under the current liquid filling working condition is calculated and obtained, the TankState and the MStand (D, b, e) are compared with the value under the same condition D, and if the deviation value of bState and the bstind exceeds a given range, a fault is determined to occur.
As shown in fig. 3, the data collection and fault prediction of the gas phase pressure include:
s105: setting sampling frequency, collecting gas phase pressure data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s106: judging whether the sum of the squares of the residual errors exceeds the threshold range or not, and if not, ending the fault prediction; if yes, go to step S107;
s107: comparing the analysis result with the measured value, judging whether the analysis result exceeds a normal threshold range, and if so, forecasting the fault of the pressure touch sensor; if not, the step S108 is carried out;
s108: judging whether the numerical trends of the intercept D, the slope b and the error term e of the analysis result are increased or decreased, and if the numerical trends of the error term e are decreased D, b, ending the fault prediction; if D, b rises, the valve jump is predicted.
In the embodiment of the invention, the failure determination of the gas-phase pressure sensor P102: wherein D is a regression intercept and is mainly influenced by the initial temperature of liquid filling; slope b123 reflects primarily the insulating capability of the tank itself, and may be affected as the tank ages; e is an error term. After LNG is filled into the tank, data analysis is carried out, TankState which is MState (D, b, e) under the current liquid filling working condition is calculated and obtained, the TankState and the MStand (D, b, e) are compared with the value under the same condition D, and if the deviation value of bState and the bstind exceeds a given range, a fault is determined to occur.
As shown in fig. 4, the liquid phase data collection and fault prediction includes:
s109: setting sampling frequency, collecting liquid level data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s110: judging whether the sum of the squares of the residual errors exceeds a threshold range or not, and if not, ending the fault prediction; if yes, go to step S110;
s111: comparing the analysis result with the measured value, and judging whether the analysis result exceeds a normal threshold range, if so, predicting tank overcharge or sensor fault; if not, the fault prediction is ended.
In the embodiment of the invention, the sampling frequency is set, the floating frequency data is collected and subjected to regression analysis, the analysis result is compared with a standard value to obtain the square sum of the residual errors, whether the square sum of the residual errors exceeds the threshold range or not is judged, if the square sum of the residual errors exceeds the threshold range, the fault prediction is finished, if the square sum of the residual errors exceeds the threshold range, the analysis result is compared with an actual measurement value, whether the square sum of the residual errors exceeds the normal threshold range or not is judged, if the square sum of the residual errors exceeds the normal threshold range, the fault of a sensor is predicted, and if the minimum value is 0, the display tank box is output and placed.
As shown in fig. 5, the acceleration data collection and fault prediction includes:
s112: setting sampling frequency, collecting acceleration data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s113: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S114;
s114: comparing the analysis result with the measured value, judging whether the analysis result exceeds a normal threshold range, and if so, forecasting the fault of the touch sensor; and if the minimum value is 0, forecasting the tank to be in a static state.
In the embodiment of the present invention, the failure determination of the acceleration sensor a 104: wherein D is the regression intercept, which is mainly influenced by the position of the tank on the vessel; the slope b123 mainly reflects the change state of the motion acceleration of the tank; e is an error term. After the tank is filled with LNG, data analysis is carried out, the TankState in the current transportation state of the tank is calculated and obtained to be MState (D, b, e), the value is compared with the value in the transportation standard value TankStand (Mstand) (D, b, e) under the condition of equal D, and if the deviation value of the bState and the bstand is beyond a given range, the fault is considered to occur. In addition, the fault can be judged by comparing and detecting the data of other tank boxes in the same state (such as the tank box close to the position transported by the same ship)
As shown in fig. 6, the data acquisition and fault prediction of the floating frequency includes:
s115: setting sampling frequency, collecting floating frequency data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s116: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S117;
s117: and comparing the analysis result with the measured value, judging whether the analysis result exceeds the normal threshold range, if so, predicting the fault of the sensor, otherwise, predicting the tank to stand if the analysis result is lower than the lower limit.
In the embodiment of the present invention, the floating frequency s105 fault determination: wherein D is the regression intercept, which is mainly influenced by the position of the tank on the vessel; the slope b123 mainly reflects the movement, swing and floating change state of the tank; e is an error term. After the tank is filled with LNG, data analysis is carried out, the TankState in the current transportation state of the tank is calculated and obtained to be MState (D, b, e), the value is compared with the value in the transportation standard value TankStand (Mstand) (D, b, e) under the condition of equal D, and if the deviation value of the bState and the bstand is beyond a given range, the fault is considered to occur. In addition, the fault determination can also compare the data of other tanks in the same state (such as the tank close to the position transported by the ship).
The method of the embodiment of the invention is realized by depending on the electronic equipment, so that the related electronic equipment is necessarily introduced. With this object in mind, an embodiment of the present invention provides an electronic apparatus including: the system comprises at least one processor (processor), a communication Interface (communication Interface), at least one memory (memory) and a communication bus, wherein the at least one processor, the communication Interface and the at least one memory are communicated with each other through the communication bus. The at least one processor may invoke logic instructions in the at least one memory to perform all or a portion of the steps of the methods provided by the various method embodiments described above.
In addition, the logic instructions in the at least one memory may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A method for forecasting faults of an LNG tank based on time-varying parameters is characterized by comprising the following steps:
s100: setting sampling frequency, collecting main dynamic monitoring parameters TVP such as liquid phase temperature, gas phase pressure, liquid level, acceleration and floating frequency, and collecting main static parameters t;
s200: performing unit third-order linear regression analysis on the main dynamic monitoring parameter TVP by taking t as an independent variable;
s300: the method comprises the steps of repeatedly carrying out third-order linear regression analysis by utilizing long-time monitoring data to obtain a Tank-M (D, b, e) value of the storage Tank in a given state, taking the Tankstand-Mstand (D, b, e) as a standard value as a 'fingerprint characteristic' of the storage Tank, carrying out comparative analysis on the actually monitored Tankt value and the Tankstand, and analyzing a difference value caused by a fault by RSS (really simple syndication).
2. The method for forecasting the tank fault of the LNG tank based on the time-varying parameters as claimed in claim 1, wherein the step S100 of collecting the liquid phase temperature and forecasting the fault comprises:
s101: setting sampling frequency, collecting liquid phase temperature data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s102: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to a step S103;
s103: comparing the analysis result with the actual measurement value, and judging whether the temperature of the liquid LNG is beyond the temperature range of-165 ℃ to-140 ℃, if so, predicting the fault of the temperature sensor; if not, the step S104 is carried out;
s104: judging whether the numerical trends of the intercept D, the slope b and the error term e of the analysis result are increased or decreased, and if the numerical trends of the error term e are decreased D, b, ending the fault prediction; if D, b rises, the forecast tank heat leakage rate rises.
3. The method for forecasting the tank fault of the LNG tank based on the time-varying parameters as claimed in claim 1, wherein the step S100 of collecting the gas phase pressure and forecasting the fault comprises:
s105: setting sampling frequency, collecting gas phase pressure data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s106: judging whether the sum of the squares of the residual errors exceeds the threshold range or not, and if not, ending the fault prediction; if yes, go to step S107;
s107: comparing the analysis result with the measured value, judging whether the analysis result exceeds a normal threshold range, and if so, forecasting the fault of the pressure touch sensor; if not, the step S108 is carried out;
s108: judging whether the numerical trends of the intercept D, the slope b and the error term e of the analysis result are increased or decreased, and if the numerical trends of the error term e are decreased D, b, ending the fault prediction; if D, b rises, the valve jump is predicted.
4. The method for forecasting the tank fault of the LNG tank based on the time-varying parameters as claimed in claim 1, wherein in step S100, the liquid phase data collection and fault forecasting comprises:
s109: setting sampling frequency, collecting liquid level data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s110: judging whether the sum of the squares of the residual errors exceeds the threshold range or not, and if not, ending the fault prediction; if yes, go to step S110;
s111: comparing the analysis result with the measured value, and judging whether the analysis result exceeds a normal threshold range, if so, predicting tank overcharge or sensor fault; if not, the fault prediction is ended.
5. The method for forecasting the fault of the LNG tank based on the time-varying parameters as claimed in any one of claims 1-4, wherein in the step S100, the acceleration data collection and fault forecasting comprises:
s112: setting sampling frequency, collecting acceleration data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s113: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S114;
s114: comparing the analysis result with the measured value, judging whether the analysis result exceeds a normal threshold range, and if so, forecasting the fault of the touch sensor; and if the minimum value is 0, forecasting the tank to be in a static state.
6. The method for forecasting the tank fault of the LNG tank based on the time-varying parameters as claimed in any one of claims 1-4, wherein the data acquisition of the floating frequency and the fault forecasting in step S100 comprise:
s115: setting sampling frequency, collecting floating frequency data, performing regression analysis, and comparing an analysis result with a standard value to obtain a residual square sum;
s116: judging whether the sum of the squares of the residual errors exceeds the threshold range, if not, ending the fault prediction, and if so, turning to the step S117;
s117: and comparing the analysis result with the measured value, judging whether the analysis result exceeds the normal threshold range, if so, predicting the fault of the sensor, otherwise, predicting the tank to stand if the analysis result is lower than the lower limit.
7. An LNG tank fault prediction system based on time-varying parameters, comprising:
the data acquisition module is used for setting sampling frequency, acquiring main dynamic monitoring parameters TVP such as liquid phase temperature, gas phase pressure, liquid level, acceleration and floating frequency and the like, and acquiring a main static parameter t;
the regression analysis module is used for carrying out unit third-order linear regression analysis on the main dynamic monitoring parameter TVP by taking t as an independent variable;
and the fault forecasting module is used for repeatedly carrying out third-order linear regression analysis by utilizing long-time monitoring data to obtain a Tank-M (D, b, e) value of the storage Tank in a given state, taking the Tankstand-Mstand (D, b, e) value as a standard value and taking the Tankstand-Mstand (D, b, e) value as the fingerprint characteristic of the storage Tank, comparing and analyzing the actually monitored Tankt value with the Tankstand, and judging the type of the fault by adopting RSS analysis to analyze the difference value caused by the fault.
8. An electronic device, comprising:
at least one processor, at least one memory, and a communication interface; wherein,
the processor, the memory and the communication interface are communicated with each other;
the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any of claims 1 to 6.
9. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210557168.7A CN114964367B (en) | 2022-05-20 | 2022-05-20 | LNG tank fault prediction method and system based on time-varying parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210557168.7A CN114964367B (en) | 2022-05-20 | 2022-05-20 | LNG tank fault prediction method and system based on time-varying parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114964367A true CN114964367A (en) | 2022-08-30 |
| CN114964367B CN114964367B (en) | 2024-02-23 |
Family
ID=82972509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210557168.7A Active CN114964367B (en) | 2022-05-20 | 2022-05-20 | LNG tank fault prediction method and system based on time-varying parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114964367B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4042813A (en) * | 1973-02-23 | 1977-08-16 | Westinghouse Electric Corporation | Secondary system modeling and method for a nuclear power plant training simulator |
| CN102107591A (en) * | 2010-12-17 | 2011-06-29 | 吉林大学 | Abnormal condition identification method for tire pressure of goods wagon |
| CN105512812A (en) * | 2015-12-02 | 2016-04-20 | 中广核工程有限公司 | Nuclear power plant equipment fault early warning analysis method and system based on dynamic simulation model |
| CN110084481A (en) * | 2019-03-29 | 2019-08-02 | 北京摩拜科技有限公司 | Monitor the method, apparatus and server of vehicle-state |
| CN112267979A (en) * | 2020-10-26 | 2021-01-26 | 积成电子股份有限公司 | Early warning method and system for judging failure of yaw bearing |
| KR102352588B1 (en) * | 2020-10-14 | 2022-01-18 | (주) 티이에프 | Apparatus and method for deriving inverter efficiency information in solar power generation using linear regression model |
-
2022
- 2022-05-20 CN CN202210557168.7A patent/CN114964367B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4042813A (en) * | 1973-02-23 | 1977-08-16 | Westinghouse Electric Corporation | Secondary system modeling and method for a nuclear power plant training simulator |
| CN102107591A (en) * | 2010-12-17 | 2011-06-29 | 吉林大学 | Abnormal condition identification method for tire pressure of goods wagon |
| CN105512812A (en) * | 2015-12-02 | 2016-04-20 | 中广核工程有限公司 | Nuclear power plant equipment fault early warning analysis method and system based on dynamic simulation model |
| CN110084481A (en) * | 2019-03-29 | 2019-08-02 | 北京摩拜科技有限公司 | Monitor the method, apparatus and server of vehicle-state |
| KR102352588B1 (en) * | 2020-10-14 | 2022-01-18 | (주) 티이에프 | Apparatus and method for deriving inverter efficiency information in solar power generation using linear regression model |
| CN112267979A (en) * | 2020-10-26 | 2021-01-26 | 积成电子股份有限公司 | Early warning method and system for judging failure of yaw bearing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114964367B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104764869B (en) | Transformer gas fault diagnosis and alarm method based on multidimensional characteristics | |
| CN112101764B (en) | Ship technical condition comprehensive evaluation system based on state monitoring | |
| CN115729761B (en) | Hard disk fault prediction method, system, equipment and medium | |
| CN117434372B (en) | Electromagnetic compatibility immunity test method and system for electronic product | |
| CN110808864A (en) | Communication early warning method, device and system | |
| CN110647924A (en) | GIS equipment state evaluation method based on support vector description and K-nearest neighbor algorithm | |
| CN110319957A (en) | The irregular exceptional value method for diagnosing faults of Ship Structure stress monitoring system sensor | |
| JP2012018623A (en) | Abnormality data analysis system | |
| CN116933592A (en) | Intelligent ship structure safety assessment method and system | |
| CN103999316A (en) | Method for generating a signal indicating an oscillation in an electrical energy supply network | |
| CN116337135A (en) | Instrument fault diagnosis method, system, electronic equipment and readable storage medium | |
| CN114964367A (en) | LNG tank fault forecasting method and system based on time-varying parameters | |
| CN115311829A (en) | Accurate alarm method and system based on mass data | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN116447514A (en) | Hydrogen storage tank intelligent early warning device and method | |
| CN116861356A (en) | Abnormal data detection method and device, electronic equipment and storage medium | |
| CN103954742B (en) | In diesel engine, diesel oil is mixed into machine oil measurement mechanism and measuring method | |
| CN116380228A (en) | Method, system, terminal and storage medium for monitoring operation of weighing apparatus | |
| CN113326610B (en) | Gas station oil tank leakage detection early warning method based on oil height soft measurement prediction | |
| CN115864310A (en) | Multi-parameter fusion power transformer defect identification, state classification and active safety protection method | |
| CN115208745A (en) | Fault positioning method and device for power system and fault positioning equipment | |
| CN113240157A (en) | Truck scale maintenance management method and system based on machine learning | |
| US20230221693A1 (en) | Systems and methods for integrated condition monitoring for power system asset health scoring | |
| CN116388403B (en) | Intelligent power distribution on-line monitoring and early warning method and system | |
| CN116878728B (en) | Pressure sensor fault detection analysis processing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhou Guoqiang Inventor after: Wang Sihu Inventor after: Luo Xiaofeng Inventor after: Tian Yuzhong Inventor after: Wang Xi Inventor after: Cao Jiaolong Inventor after: Jin Ding Inventor after: Chen Qingren Inventor after: Zhuang Linlu Inventor before: Wang Sihu Inventor before: Luo Xiaofeng Inventor before: Tian Yuzhong Inventor before: Wang Xi Inventor before: Cao Jiaolong Inventor before: Jin Ding Inventor before: Zhou Guoqiang Inventor before: Chen Qingren Inventor before: Zhuang Linlu |