CN116931428A - LNG storage tank and risk control method of supporting structure - Google Patents
LNG storage tank and risk control method of supporting structure Download PDFInfo
- Publication number
- CN116931428A CN116931428A CN202310888523.3A CN202310888523A CN116931428A CN 116931428 A CN116931428 A CN 116931428A CN 202310888523 A CN202310888523 A CN 202310888523A CN 116931428 A CN116931428 A CN 116931428A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- storage tank
- supporting structure
- information
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012954 risk control Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 81
- 230000036541 health Effects 0.000 claims abstract description 22
- 230000008859 change Effects 0.000 claims abstract description 17
- 230000003993 interaction Effects 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 17
- 239000007788 liquid Substances 0.000 claims description 14
- 230000005856 abnormality Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000012502 risk assessment Methods 0.000 abstract description 8
- 230000026676 system process Effects 0.000 abstract 1
- 239000003949 liquefied natural gas Substances 0.000 description 39
- 238000010586 diagram Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- BULVZWIRKLYCBC-UHFFFAOYSA-N phorate Chemical compound CCOP(=S)(OCC)SCSCC BULVZWIRKLYCBC-UHFFFAOYSA-N 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C1/00—Pressure vessels, e.g. gas cylinder, gas tank, replaceable cartridge
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
- F17C13/08—Mounting arrangements for vessels
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2205/00—Vessel construction, in particular mounting arrangements, attachments or identifications means
- F17C2205/01—Mounting arrangements
- F17C2205/0103—Exterior arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Development Economics (AREA)
- Automation & Control Theory (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of LNG storage tank risk control, in particular to a risk control method for an LNG storage tank and a supporting structure, which comprises the following steps: monitoring the change parameters of the LNG storage tank and the change parameters of the supporting structure of the LNG storage tank in real time and transmitting the change parameters to the information interaction module; the information interaction module receives real-time information and packages the real-time information and sends the real-time information to the health monitoring system; the health monitoring system processes the real-time information, then evaluates and controls the potential risks of the LNG storage tank and the supporting structure in real time, adjusts parameters according to the needs in real time, and outputs the evaluation result to the state expression system; the state expression system displays the current states of the LNG storage tank and the supporting structure and the estimated health conditions in real time, and sends out corresponding responses according to different estimation results. The method provided by the invention can enhance the accuracy of risk assessment of different storage tanks, thereby saving labor cost and improving safety through intelligent monitoring and preventing disasters caused by human factors.
Description
Technical Field
The invention relates to the technical field of LNG storage tank risk control, in particular to a risk control method for an LNG storage tank and a support structure.
Background
Liquefied Natural Gas (LNG) is a relatively clean, efficient source of energy, accounting for approximately one-fourth of the global energy structures. Since LNG is in liquid form during transportation and storage, the safety of the LNG receiving station that mainly performs this task is particularly important, in which the LNG storage tank is an extremely critical storage device, and once the LNG storage tank leaks, volatilized gas can be mixed with air to form combustible materials, and serious fire and explosion accidents can be caused when the LNG storage tank encounters a fire source, which can cause a disaster that is difficult to estimate. In addition, the LNG storage tank has a volume of tens of thousands to hundreds of thousands of cubic meters, and the safety of the storage tank supporting structure is also particularly important. At present, risk assessment is mainly carried out by methods such as event trees aiming at accidents and overall safety ratings at home and abroad, and although the method can be used for identifying and quantifying potential safety risks, the method has certain subjectivity, can not make timely and accurate judgment aiming at running conditions, and has no universality for different subjects.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a risk control method for an LNG storage tank and a support structure, which is based on real-time monitoring information, real-time assessment and control of potential risks of the LNG storage tank and the support structure based on a small sample learning model, and real-time display of health conditions of the LNG storage tank and the support structure through a digital twin technology, so that the purposes of effectively monitoring and assessing states of the LNG storage tank and the support structure are achieved, and meanwhile, a parameter adjustment module continuously iterates and updates parameters, so that accuracy of risk assessment of different storage tanks is enhanced.
The invention is realized by the following technical scheme:
a risk control method for an LNG storage tank and a support structure, comprising the steps of:
d1: the data acquisition equipment monitors the change parameters of the LNG storage tank and the change parameters of the supporting structure of the LNG storage tank in real time, and transmits the real-time information of the change parameters to the information interaction module;
d2: the information interaction module receives real-time information of the change parameters transmitted by the data acquisition equipment and packages and sends the real-time information to the health monitoring system;
d3: after the health monitoring system receives and processes the real-time information, the potential risks of the LNG storage tank and the supporting structure are evaluated and controlled in real time by using a preset small sample learning model, parameters are adjusted in real time according to the needs, and the evaluation result is output to the state expression system;
d4: the state expression system receives the evaluation result, displays the current states of the LNG storage tank and the supporting structure and the evaluated health conditions in real time through the intelligent digital twin technology, and sends out corresponding responses according to the evaluation result. Preferably, the data acquisition device comprises a temperature sensor, a pressure sensor, a liquid level sensor, a deformation sensor, a vibration sensor, an acceleration sensor and a monitoring camera.
The optimized health monitoring system comprises a data preprocessing module, an image recognition module, a feature extraction module, an intelligent monitoring module, a parameter adjustment module and an encryption storage module;
the image recognition module receives the information of the monitoring camera sent by the information interaction module, recognizes and processes the information of the monitoring camera and sends the information to the feature extraction module;
the data preprocessing module receives real-time information of each sensor sent by the information interaction module, performs data preprocessing and then sends the processed information to the feature extraction module;
the feature extraction module receives the information of the data preprocessing module and the image recognition module, performs feature extraction on the information of the data preprocessing module and the image recognition module, converts the information into data features and transmits the data features to the intelligent monitoring module; the intelligent monitoring module calculates index scores of risk levels of the LNG storage tank and the supporting structure based on the small sample learning model, and after judging corresponding risk levels, transmits the index scores of the risk levels and the corresponding risk levels to the encryption storage module, and sends parameters and calculation results in the calculation process based on the small sample learning model to the parameter adjustment module;
the parameter adjustment module judges whether the parameters need to be adjusted or not according to the received parameters and calculation results in the calculation process through parameter adjustment evaluation indexes, if the parameters need to be adjusted, the parameters are adjusted, the adjusted parameters are fed back to the intelligent monitoring module, and the index scores of the risk grades of the LNG storage tank and the supporting structure are calculated based on the adjusted parameters when the small sample learning model in the intelligent monitoring module operates next time;
the encryption storage module encrypts and stores the data and transmits the data to the state expression system.
Further, the parameter adjustment module calculates a calibration base B based on equation (1), adjusts the parameter when B is equal to or less than a preset parameter adjustment base, and does not adjust the parameter when B is greater than the preset parameter adjustment base:
wherein: b is a calibration base number, alpha is an evaluation and check coefficient, A is the recording accuracy of each hundred pieces, S is the recording redundancy of each hundred pieces, and R is the recording redundancy influence factor of each hundred pieces.
Further, when the parameter adjustment module determines that parameter adjustment is required, parameter adjustment is performed according to formula (2):
wherein: c' is the adjusted parameter value, and C is the original parameter value.
The data preprocessing module preprocesses the data of each sensor by adopting the following method:
e1: data sequence t= [ T ] to be continuously monitored for a set period of time 1 ,T 2 ,......,T n ]And a set threshold T f After comparison, a new standard data sequence T is generated S =[T S1 ,T S2 ,......,T Sn ],
And make it(i=1,2,3...,n);
Wherein: n is the number of data continuously monitored in a set period of time, T n For the nth data continuously monitored in the set time period, i is the data sequence number continuously monitored in the set time period; t (T) Sn For continuously monitoring the generated nth standard data in a set time period, T Si Continuously monitoring generated standard data with the sequence number i in a set time period; e2: removal of T Si The corresponding monitoring data when the value is 1 is calculated to appear T according to the formula (3) Si Taking the average value of a plurality of data before the moment of 1 as a correction value, and sending the correction value to the feature extraction module after replacing the original monitoring value;
wherein: t (T) δ For t=t δ Correction value of time t δ To monitor the abnormal time of data, N x For a set period of timet δ Monitoring the number of data before the moment, T t Is the monitored data value at time t.
The intelligent digital twin module reflects the current state of the supporting structure, the temperature, the pressure, the liquid level, the deformation dangerous degree of the supporting structure and the overall risk level in real time, and when abnormality occurs, the intelligent digital twin module sends information to the abnormality warning device for warning and displays the position and the content of the specific occurrence of the abnormality.
Further, the encryption storage module is connected with a log reading interface of the debugging assisting system, and the parameter adjusting module is connected with a parameter adjusting interface of the debugging assisting system.
The invention has the beneficial effects that:
according to the risk control method for the LNG storage tank and the support structure, provided by the invention, based on the feedback parameters of the data acquisition equipment placed at each part of the LNG storage tank and the support structure, parameter data are preprocessed to improve accuracy, continuous monitoring is achieved through a preset monitoring interval, and a current risk control result is calculated by combining a small sample learning model, so that operation and maintenance personnel of a receiving station are effectively helped to know the health states of the LNG storage tank and the support structure in real time, potential safety hazards are eliminated in time, and meanwhile, a parameter adjustment module continuously iterates and updates parameters to enhance the accuracy of risk assessment of different storage tanks, thereby intelligently monitoring saves labor cost and improves safety, and disaster caused by human factors is prevented.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
FIG. 2 is a schematic block diagram of an intelligent monitoring module according to the present invention.
Detailed Description
A specific principle and structure block diagram of the risk control method for the LNG storage tank and the supporting structure is shown in figure 1: the method comprises the following steps:
d1: the data acquisition equipment monitors the change parameters of the LNG storage tank and the change parameters of the supporting structure of the LNG storage tank in real time, and transmits the real-time information of the change parameters to the information interaction module; the data acquisition equipment comprises a temperature sensor, a pressure sensor, a liquid level sensor, a deformation sensor, a vibration sensor, an acceleration sensor and a monitoring camera, wherein the temperature sensor, the pressure sensor and the liquid level sensor are distributed around the LNG storage tank and used for monitoring temperature, pressure and liquid level change parameters, the deformation sensor, the vibration sensor and the acceleration sensor are installed at specific positions of the supporting structure and used for monitoring deformation, vibration and the like of the supporting structure, the monitoring camera is installed around the LNG storage tank and the supporting structure and used for acquiring monitoring pictures, the monitoring camera can adopt a rotatable wireless security monitoring camera with certain definition, the information interaction module can adopt a working condition machine or other computer equipment and realize a set function through pre-installed software, specific information transmission can adopt a wired or wireless mode to transmit and receive, adjacent equipment is connected in a wired mode and is uniformly received in a wireless mode.
D2: the information interaction module receives real-time information of the change parameters transmitted by the data acquisition equipment and packages and sends the real-time information to the health monitoring system;
d3: after the health monitoring system receives and processes the real-time information, the potential risks of the LNG storage tank and the supporting structure are evaluated and controlled in real time by using a preset small sample learning model, parameters are adjusted in real time according to the needs, and the evaluation result is output to the state expression system;
d4: the state expression system receives the evaluation results, displays the current states of the LNG storage tank and the supporting structure and the evaluated health conditions in real time through the intelligent digital twin technology, and sends out corresponding responses according to different evaluation results. The optimized health monitoring system comprises a data preprocessing module, an image recognition module, a feature extraction module, an intelligent monitoring module, a parameter adjustment module and an encryption storage module;
the image recognition module receives the information of the monitoring camera sent by the information interaction module, recognizes and processes the information of the monitoring camera and sends the information to the feature extraction module; the image recognition module can use a tool library of the existing machine learning vision algorithm, cut frames of the ROI (Region Of Interest region of interest) as input to predict gesture marks in the ROI, adopts a human gesture recognition model to judge whether an operation and maintenance worker reaches a designated position and whether monitoring operation is in compliance or not, and can send a control command to the information interaction module, and the information interaction module transmits the control command to the monitoring camera to control the monitoring camera to change monitoring angles or other actions.
The data preprocessing module receives real-time information of each sensor sent by the information interaction module, performs data preprocessing and then sends the information to the feature extraction module, so that noise in transmission can be removed, and data anomalies caused by collision, sensor noise, poor contact, data acquisition and reception faults and the like of the sensors are reduced;
specifically, the data preprocessing module may preprocess the data of each sensor by the following method:
e1: data sequence t= [ T ] to be continuously monitored for a set period of time 1 ,T 2 ,......,T n ]And a set threshold T f After comparison, a new standard data sequence T is generated S =[T S1 ,T S2 ,......,T Sn ],
And make it(i=1,2,3...,n);
Wherein: n is the number of data continuously monitored in a set period of time, T n For the nth data continuously monitored in the set time period, i is the data sequence number continuously monitored in the set time period; t (T) Sn For continuously monitoring the generated nth standard data in a set time period, T Si Continuously monitoring generated standard data with the sequence number i in a set time period; e2: removal of T Si The corresponding monitoring data when the value is 1 is calculated to appear T according to the formula (3) Si Taking the average value of a plurality of data before the moment of 1 as a correction value, and sending the correction value to the feature extraction module after replacing the original monitoring value;
wherein: t (T) δ For t=t δ Correction value of time t δ To monitor the abnormal time of the data, and the number of the abnormal data is less, N x For t in a set period of time δ Monitoring the number of data before the moment, T t Is the monitored data value at time t.
Because parameters such as temperature, storage tank pressure, liquid level are important monitoring data of LNG storage tank and bearing structure, often can take place serious trouble when above-mentioned data appear unusual, need realize fault alarm through setting up the threshold value, because the storage tank running condition is complicated, monitored control system receives various external interference factor influence relatively easily, still can meet the influence of sensor and power, network transmission, electromagnetic interference scheduling problem, has caused the data that monitored control system gathered to take place unusual or missing phenomenon. The phenomenon often contains various environmental noises and shows complex and nonlinear characteristics, and the monitoring data is processed in advance by adopting the method, so that the data with obvious abnormality in the original measurement data can be removed, the monitoring noise is removed, and the accuracy of risk control is improved.
The removed data is replaced by the calculated moving average value and then is subjected to subsequent calculation, so that a data curve can be smoothed, and the monitoring accuracy is further improved.
The feature extraction module receives the information of the data preprocessing module and the image recognition module, performs feature extraction on the information, converts the information into data features and transmits the data features to the intelligent monitoring module;
the extracted characteristic parameters comprise characteristic parameters of the temperature, the pressure and the liquid level of the storage tank, characteristic parameters of deformation, vibration and acceleration of each key supporting structure, inspection frequency, effective rate, risk treatment qualification rate and the like.
The intelligent monitoring module calculates index scores of risk levels of the LNG storage tank and the supporting structure based on the small sample learning model, and after judging corresponding risk levels, transmits the index scores of the risk levels and the corresponding risk levels to the encryption storage module, and sends parameters and calculation results in the calculation process based on the small sample learning model to the parameter adjustment module;
the specific schematic structural block diagram of the specific intelligent monitoring module is shown in fig. 2, and comprises a small sample learning model, a risk assessment module and a risk control module, wherein the small sample learning model is a support vector machine model, before the intelligent monitoring module is put into use, learning is performed according to the operation data of the existing LNG storage tank and the supporting structure, important parameters can be adjusted through a parameter adjustment module, monitoring data in practical application are used as data of the small sample learning model, assessment indexes in the risk assessment module comprise storage tank pressure, liquid level, supporting structure deformation and the like, and the risk control module can remind a user to take corresponding control measures according to an assessment result of the risk assessment module, wherein the specific control measures comprise: the temperature, pressure and liquid level of the storage tank are timely adjusted, the support structure is reinforced, the inspection frequency is increased, the specified position is overhauled, warning and alarming are achieved, the support structure can be divided into the thickness of the material of the support structure and the number of the support structures, potential safety hazards are timely eliminated, accordingly the operation safety of the LNG storage tank is improved, and disasters caused by human factors are prevented.
The parameter adjustment module judges whether the parameters need to be adjusted or not according to the received parameters and calculation results in the calculation process through parameter adjustment evaluation indexes, if the parameters need to be adjusted, the parameters are adjusted, the adjusted parameters are fed back to the intelligent monitoring module, and the index scores of the risk grades of the LNG storage tank and the supporting structure are calculated based on the adjusted parameters when the small sample learning model in the intelligent monitoring module operates next time;
the encryption storage module encrypts and stores the data and transmits the data to the state expression system.
Specifically, the parameter adjustment module may calculate the calibration base B based on the formula (1), and when B is less than or equal to a preset parameter adjustment base, the parameter needs to be adjusted, and when B is greater than the preset parameter adjustment base, the parameter does not need to be adjusted:
wherein: b is a calibration base number, alpha is an evaluation and check coefficient, A is the recording accuracy of each hundred pieces, S is the recording redundancy of each hundred pieces, and R is the recording redundancy influence factor of each hundred pieces.
Further, when the parameter adjustment module determines that parameter adjustment is required, parameter adjustment is performed according to formula (2):
wherein: c' is the adjusted parameter value, and C is the original parameter value.
Therefore, parameters can be adjusted in real time, the matching degree of the small sample learning model is further optimized, and the accuracy of the monitoring result is improved.
The intelligent digital twin module reflects the current state of the supporting structure, the temperature, the pressure, the liquid level, the deformation dangerous degree of the supporting structure and the overall risk level in real time, and when abnormality occurs, the intelligent digital twin module sends information to the abnormality warning device for warning and displays the position and the content of the specific occurrence of the abnormality.
The state expression system can reflect the current structure state in real time, express the health monitoring system result in real time, and send out different responses when the result reaches different set thresholds, and the state expression system reflects the current structure state including the temperature, pressure, liquid level and deformation danger degree of the supporting structure in real time, and expresses the health monitoring system result including the whole risk level, the running state of the health monitoring system and other contents in real time; when an abnormality occurs, the abnormality is prompted by an abnormality warning device such as an audible and visual alarm and the like, and the specific occurrence position and content of the abnormality are displayed by digital twinning, so that on-site operation and maintenance personnel can observe and maintain in time.
Further, the encryption storage module is connected with a log reading interface of the debugging assisting system, and the parameter adjusting module is connected with a parameter adjusting interface of the debugging assisting system. The debugging assisting system can read the data of the encryption storage module, permit the user to maintain the health monitoring system by remote or local highest authority, and can control and adjust parameters manually by manpower to realize manual and intelligent bidirectional control.
In summary, the risk control method for the LNG storage tank and the support structure provided by the invention can effectively help the operation and maintenance personnel of the receiving station to accurately know the health states of the LNG storage tank and the support structure in real time, eliminates potential safety hazards in time, and simultaneously, the parameter adjustment module continuously and iteratively updates parameters to enhance the accuracy of risk assessment of different storage tanks, thereby intelligently monitoring, saving labor cost, improving safety and preventing disasters caused by human factors.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The risk control method for the LNG storage tank and the supporting structure is characterized by comprising the following steps of: the method comprises the following steps:
d1: the data acquisition equipment monitors the change parameters of the LNG storage tank and the change parameters of the supporting structure of the LNG storage tank in real time, and transmits the real-time information of the change parameters to the information interaction module;
d2: the information interaction module receives real-time information of the change parameters transmitted by the data acquisition equipment and packages and sends the real-time information to the health monitoring system;
d3: after the health monitoring system receives and processes the real-time information, the potential risks of the LNG storage tank and the supporting structure are evaluated and controlled in real time by using a preset small sample learning model, parameters are adjusted in real time according to the needs, and the evaluation result is output to the state expression system;
d4: the state expression system receives the evaluation result, displays the current states of the LNG storage tank and the supporting structure and the evaluated health conditions in real time through the intelligent digital twin technology, and sends out corresponding responses according to the evaluation result.
2. The risk control method for an LNG storage tank and supporting structure according to claim 1, wherein: the data acquisition equipment comprises a temperature sensor, a pressure sensor, a liquid level sensor, a deformation sensor, a vibration sensor, an acceleration sensor and a monitoring camera.
3. The risk control method for an LNG tank and supporting structure according to claim 2, wherein: the health monitoring system comprises a data preprocessing module, an image recognition module, a feature extraction module, an intelligent monitoring module, a parameter adjustment module and an encryption storage module;
the image recognition module receives the information of the monitoring camera sent by the information interaction module, recognizes and processes the information of the monitoring camera and sends the information to the feature extraction module;
the data preprocessing module receives real-time information of each sensor sent by the information interaction module, performs data preprocessing and then sends the processed information to the feature extraction module;
the feature extraction module receives the information of the data preprocessing module and the image recognition module, performs feature extraction on the information of the data preprocessing module and the image recognition module, converts the information into data features and transmits the data features to the intelligent monitoring module;
the intelligent monitoring module calculates index scores of risk levels of the LNG storage tank and the supporting structure based on the small sample learning model, and after judging corresponding risk levels, transmits the index scores of the risk levels and the corresponding risk levels to the encryption storage module, and transmits parameters and calculation results in the calculation process based on the small sample learning model to the parameter adjustment module;
the parameter adjustment module judges whether the parameters need to be adjusted or not according to the received parameters and calculation results in the calculation process through parameter adjustment evaluation indexes, if the parameters need to be adjusted, the parameters are adjusted, the adjusted parameters are fed back to the intelligent monitoring module, and the index scores of the risk grades of the LNG storage tank and the supporting structure are calculated based on the adjusted parameters when the small sample learning model in the intelligent monitoring module operates next time;
and the encryption storage module encrypts and stores the data and transmits the data to the state expression system.
4. A risk control method for LNG tanks and support structures according to claim 3, characterized by: the parameter adjustment module calculates a calibration base B based on equation (1), adjusts the parameter when |b| is equal to or less than a preset parameter adjustment base, and does not adjust the parameter when |b| is greater than the preset parameter adjustment base:
wherein: b is a calibration base number, alpha is an evaluation and check coefficient, A is the recording accuracy of each hundred pieces, S is the recording redundancy of each hundred pieces, and R is the recording redundancy influence factor of each hundred pieces.
5. The risk control method for an LNG tank and supporting structure according to claim 4, wherein: when the parameter adjustment module judges that parameter adjustment is needed, parameter adjustment is carried out according to the formula (2):
wherein: c' is the adjusted parameter value, and C is the original parameter value.
6. A risk control method for LNG tanks and support structures according to claim 3, characterized by: the data preprocessing module preprocesses the data of each sensor by adopting the following method:
e1: data sequence t= [ T ] to be continuously monitored for a set period of time 1 ,T 2 ,......,T n ]And a set threshold T f After comparison, a new standard data sequence T is generated S =[T S1 ,T S2 ,......,T Sn ],
And make it
Wherein: n is the number of data continuously monitored in a set period of time, T n For the nth data continuously monitored in the set time period, i is the data sequence number continuously monitored in the set time period; t (T) Sn For continuously monitoring the generated nth standard data in a set time period, T Si Continuously monitoring generated standard data with the sequence number i in a set time period; e2: removal of T Si The corresponding monitoring data when the value is 1 is calculated to appear T according to the formula (3) Si Taking the average value of a plurality of data before the moment of 1 as a correction value, and sending the correction value to the feature extraction module after replacing the original monitoring value;
wherein: t (T) δ For t=t δ Correction value of time t δ To monitor the abnormal time of data, N x For t in a set period of time δ Monitoring the number of data before the moment, T t Is the monitored data value at time t.
7. The risk control method for an LNG storage tank and supporting structure according to claim 1, wherein: the state expression system comprises an intelligent digital twin module and an abnormal warning device, wherein the intelligent digital twin module reflects the current state of the supporting structure, the temperature, the pressure, the liquid level, the deformation dangerous degree and the overall risk level of the supporting structure in real time, and when the abnormality occurs, the intelligent digital twin module sends information to the abnormal warning device to give an alarm, and the intelligent digital twin module displays the position and the content of the specific occurrence of the abnormality.
8. A risk control method for LNG tanks and support structures according to claim 3, characterized by: the encryption storage module is connected with a log reading interface of the debugging assisting system, and the parameter adjusting module is connected with a parameter adjusting interface of the debugging assisting system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310888523.3A CN116931428A (en) | 2023-07-19 | 2023-07-19 | LNG storage tank and risk control method of supporting structure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310888523.3A CN116931428A (en) | 2023-07-19 | 2023-07-19 | LNG storage tank and risk control method of supporting structure |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116931428A true CN116931428A (en) | 2023-10-24 |
Family
ID=88380038
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310888523.3A Pending CN116931428A (en) | 2023-07-19 | 2023-07-19 | LNG storage tank and risk control method of supporting structure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116931428A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117405296A (en) * | 2023-12-15 | 2024-01-16 | 康利源科技(天津)股份有限公司 | LNG marine anti-moving block balance performance monitoring system |
-
2023
- 2023-07-19 CN CN202310888523.3A patent/CN116931428A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117405296A (en) * | 2023-12-15 | 2024-01-16 | 康利源科技(天津)股份有限公司 | LNG marine anti-moving block balance performance monitoring system |
CN117405296B (en) * | 2023-12-15 | 2024-03-01 | 康利源科技(天津)股份有限公司 | LNG marine anti-moving block balance performance monitoring system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116931428A (en) | LNG storage tank and risk control method of supporting structure | |
CN206058455U (en) | A kind of Fire Images Recognition System for possessing three kinds of grade smog identifications | |
CN111882071A (en) | Prestress steel member monitoring method based on machine learning | |
CN116006908A (en) | Intelligent gas pipe network reliability monitoring method and Internet of things system | |
CN107657390A (en) | A kind of special safety equipment hidden danger management and control big data monitoring system and monitoring method | |
CN111811582A (en) | Intelligent factory building safety in production detecting system | |
CN107782785B (en) | Underground pipeline safety assessment method | |
CN113935645A (en) | High-risk operation management and control system and method based on identification analysis technology | |
CN114137302B (en) | Electric energy metering instrument verification whole process monitoring system | |
CN114569927A (en) | Fire-fighting equipment safety on-line monitoring system | |
CN117933808A (en) | Production quality assessment method and system based on production process monitoring | |
CN116966468A (en) | Intelligent fire-fighting equipment supervision system | |
CN117078072A (en) | Multi-dimensional environment data supervision method and supervision system | |
CN111178693B (en) | Fire-fighting equipment management system based on two-dimension code | |
CN116229660B (en) | Distributed fire alarm system for large oil depot | |
CN117670050A (en) | Risk assessment management system and method for hazardous chemicals | |
CN116859842A (en) | Chemical production line safety evaluation system | |
CN106774073A (en) | A kind of SF6 electrical equipments automatic air supply device long distance control system | |
CN214948265U (en) | Safety monitoring and emergency management system for hydrogenation station | |
CN115392506A (en) | Management system, method and storage medium for chemical engineering safety maintenance operation | |
CN114120468A (en) | Chemical industry operation personnel safety inspection system | |
CN210246807U (en) | BIM-based road tunnel real-time monitoring system | |
CN115083110A (en) | Limited space operation advanced early warning system based on Internet of things means | |
CN113869712A (en) | Intelligent system for large-scale industrial gas production | |
CN207246798U (en) | A kind of oiling aerating monitor device and monitor 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 |