CN115034578A - Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning - Google Patents
Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning Download PDFInfo
- Publication number
- CN115034578A CN115034578A CN202210557484.4A CN202210557484A CN115034578A CN 115034578 A CN115034578 A CN 115034578A CN 202210557484 A CN202210557484 A CN 202210557484A CN 115034578 A CN115034578 A CN 115034578A
- Authority
- CN
- China
- Prior art keywords
- metal structure
- data
- hydraulic
- hydraulic metal
- intelligent management
- 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
- 239000002184 metal Substances 0.000 title claims abstract description 110
- 238000010276 construction Methods 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 59
- 238000012423 maintenance Methods 0.000 claims abstract description 30
- 238000007726 management method Methods 0.000 claims description 65
- 238000004458 analytical method Methods 0.000 claims description 46
- 238000011156 evaluation Methods 0.000 claims description 44
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 238000007405 data analysis Methods 0.000 claims description 18
- 229910000831 Steel Inorganic materials 0.000 claims description 16
- 239000010959 steel Substances 0.000 claims description 16
- 230000007797 corrosion Effects 0.000 claims description 15
- 238000005260 corrosion Methods 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 15
- 230000036541 health Effects 0.000 claims description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 10
- 238000004088 simulation Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 4
- 230000007547 defect Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 2
- 230000003628 erosive effect Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 231100000279 safety data Toxicity 0.000 claims description 2
- 230000003068 static effect Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 18
- 230000010354 integration Effects 0.000 abstract 2
- 230000008520 organization Effects 0.000 abstract 1
- 238000012800 visualization Methods 0.000 abstract 1
- 238000007689 inspection Methods 0.000 description 29
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 239000011248 coating agent Substances 0.000 description 3
- 238000000576 coating method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 230000009897 systematic effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005536 corrosion prevention Methods 0.000 description 2
- 238000011157 data evaluation Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000010207 Bayesian analysis Methods 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000010813 municipal solid waste Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000009991 scouring Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Images
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
- G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/40—Maintenance of things
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Toxicology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a hydraulic metal structure equipment intelligent management construction method and system based on digital twinning, wherein the method comprises the following steps: and constructing a physical space comprising a hydraulic engineering physical environment and a hydraulic metal structure physical entity, and simultaneously constructing an information space comprising a hydraulic engineering twin environment and a hydraulic metal structure digital twin body, wherein the physical space and the information space are interacted through twin data comprising historical data, online data and prediction data. According to the invention, by constructing the hydraulic metal structure equipment and the digital twin body of the operating environment, the state monitoring, the operation maintenance and the safety assessment of the hydraulic metal structure equipment in the whole life cycle can be realized, and the formed intelligent management system of the hydraulic metal structure equipment has the characteristics of organization, digitization, integration and visualization, and can reduce the problems of incomplete safety monitoring, incomplete information integration, low resource regulation and control efficiency and untimely risk early warning of the hydraulic metal structure equipment in the operating service period to a certain extent.
Description
Technical Field
The invention relates to the field of hydraulic metal structure equipment management, in particular to a hydraulic metal structure equipment intelligent management construction method and system based on digital twinning.
Technical Field
Hydraulic metal structure equipment such as gates, opening and closing machines, penstock and the like is used as key equipment for regulating and controlling water flow in water conservancy and hydropower engineering, and the safety of the hydraulic metal structure equipment is extremely important. Compared with a civil engineering structure, the hydraulic metal structure has the advantages of high equipment failure rate, quick change of failure state, high real-time requirement on monitoring and emergency treatment, and capability of efficiently carrying out operation and maintenance and management of the metal structure to directly influence the stable operation of hydraulic and hydroelectric engineering.
For the detection, evaluation and management of hydraulic metal structure equipment, relevant specifications are formed in the industry, such as 'corrosion prevention specification of hydraulic metal structure' SL105-2016 ',' safety detection technical specification of hydraulic steel gate and hoist 'SL 101-2014', 'detection and evaluation technical specification of hydraulic engineering building' JTS304-2019, and 'corrosion prevention technical specification of hydraulic steel structure' JTS153-3-2007 harbor engineering, and the like, but the specification standards do not form a unified comprehensive system for safety management, various detection and evaluation means mainly comprise manual periodic inspection, information exchange is not timely, and comprehensive evaluation on the operation state, corrosion state and the like of the hydraulic metal structure is also lacked. In the aspect of safety management, a systematic system is not formed, and a safety information intelligent management method aiming at hydraulic metal structure equipment is lacked.
Therefore, in order to better realize the state supervision of the full life cycle of the hydraulic metal structure equipment and comprehensively evaluate the health and safety of the hydraulic metal structure equipment, the traditional management mode needs to be changed urgently, various work services are integrated in an informationized manner, an intelligent management system of the hydraulic metal structure equipment is built, and the comprehensive operation and maintenance management of each metal structure equipment is realized.
Disclosure of Invention
The invention aims to provide a hydraulic metal structure equipment intelligent management construction method based on digital twinning, and forms a hydraulic metal structure equipment intelligent management system with functions of data management, dynamic monitoring, global display, state diagnosis, risk assessment and comprehensive regulation and control.
Therefore, the above purpose of the invention is realized by the following technical scheme:
a hydraulic metal structure equipment intelligent management construction method based on digital twinning is characterized in that: the construction method comprises the following steps:
s1, constructing a physical space, wherein the physical space comprises a hydraulic engineering physical environment and a hydraulic metal structure physical entity; the hydraulic metal structure physical entity comprises at least one of a gate, a hoist, a steel pipe and a unit volute;
s2, constructing an information space, wherein the information space comprises a hydraulic engineering twin environment and a hydraulic metal structure digital twin body;
and S3, forming twin data to interact between the physical space and the information space, wherein the twin data comprises historical data, online data and prediction data.
While adopting the technical scheme, the invention can also adopt or combine the following technical scheme:
as a preferred technical scheme of the invention: in step S2, constructing an information space, including constructing an environment model, a geometric model, a physical model, and a rule model; the environmental model parameters comprise water level, rainfall, temperature, humidity, pH value, medium flow rate and solution conductivity; the geometric model includes geometric dimensions, constituent materials, composite structures, and assembly logic.
As a preferred technical scheme of the invention: the rule model is constructed based on a management system, a standard, a standard gallery, expert experience and intelligent comparison.
As a preferred technical scheme of the invention: in step S3, real-time information formed by the physical environment of the hydraulic engineering and the physical entity of the hydraulic metal structure is compared with the output information of the information space in real time;
when the comparison result does not meet the rule model, performing data analysis, on one hand, when the analysis result is that the information space has model defects, performing model correction; on the other hand, when the analysis result is that the physical entity of the hydraulic metal structure is abnormal, behavior control is carried out.
As a preferred technical scheme of the invention: the data analysis includes historical failure analysis, safety state assessment, and risk accident prediction.
As a preferred technical scheme of the invention: and the safety state evaluation is based on the working condition history and the fault history, the fault type and the reason of the hydraulic metal structure equipment are mined and deduced, and the safety state evaluation is carried out by combining real-time data to finally form the safety state evaluation of the hydraulic metal structure equipment.
As a preferred technical scheme of the invention: the risk accident prediction aims at a hydraulic metal structure digital twin body in an information space, and depends on an artificial neural network technology, the input parameters are environment data in an environment model and metal structure equipment on-line monitoring data in a physical model, multi-scene training of different gate opening degrees, different opening and closing forces, different vibration types, different structure stress states, different structure corrosion degrees and different part actions is carried out on the basis of working condition history and fault history, a fault probability model is formed, twin data is formed according to real-time data, and the twin data is fused with the fault probability model to obtain the probability prediction of the risk accident.
The safety state assessment and risk accident prediction rely on an artificial neural network technology, and input parameters are environmental data in an environmental model and metal structure equipment on-line monitoring data in a physical model.
In the implementation process of the scheme, firstly, aiming at the selected hydraulic metal structure equipment, real-time data is acquired; the acquired parameters are used as input parameters to generate digital twin analog data; constructing an environment model, a geometric model, a physical model and a regular model by contrasting the physical space; after a model is formed, twin data are used for training, and then data analysis including historical fault analysis, safety state evaluation and risk accident prediction is carried out; comparing the rule models based on the data analysis result, and performing model correction and behavior control; the behavior control comprises fault early warning, feedback control, fault operation, halt error reporting and information return.
Based on risk accident prediction, early failure early warning is formed, a degradation unit is identified and positioned, and the risk of failure is eliminated in time through active behavior control; particularly, for the gate structure, a resonance danger-avoiding movement interval is formed through water level-opening degree-vibration analysis, and safe operation is carried out; for the structure of the hoist, through the analysis of 'water level-opening and closing force', the capacity prediction of the hoist under equivalent weight is formed, and the insufficient opening and closing or overload is avoided.
After the artificial neural network technology analysis, accurate fault point positioning, state maintenance and maintenance reminding can be formed on the data twin physical model; and the visual accurate scheduling is realized through comprehensive monitoring and twin scenes.
As a preferred technical scheme of the invention: risk accident prediction is based on a multi-dimensional multi-parameter criterion, wherein the multi-dimension is embodied as an engineering-structure/equipment-parameter three-level pyramid mode, the top layer is an engineering safety dimension, the middle layer is a structure/equipment safety dimension, and the bottom layer is a parameter safety dimension. The overall degree of safety of the "project" can be expressed as:
Γ＝F{f 1 ,f 2 ,f 3 ,f 4 ,f 5 }
wherein f is i (i ═ 1, 2, 3, 4, 5) represents the "structure/equipment" at the middle level of the pyramid, i.e. including gates, hoists, valves, steel pipes, ship lifts. The overall safety degree of the top engineering is related to the weight assignment priority of the middle structure/equipment, and the high-frequency dynamic structure/equipment has higher priority than the low-frequency static structure/equipment, namely, the gate and the hoist have the weight assignment priority. The overall safety degree of the "engineering" after the weight assignment can be calculated according to the following formula:
wherein p is i (i ═ 1, 2, 3, 4, 5) represents the weight assignment for each "structure/device" and satisfies:
as a preferred technical scheme of the invention: the multiparameter is embodied as "definite quantity" and "indefinite quantity" included in the "quantity" of the bottom layer, and thus the security of the "structure/device" of the middle layer can be expressed as:
p i ＝P{Q 1 ,Q 2 }
wherein Q 1 Representing "determined parameters", i.e. including instantaneous determined parameter information obtained on the basis of monitoring, detecting, observing, etc., while Q 2 And the system represents an "indefinite parameter", namely, the system comprises non-instantaneous definite parameter information such as an evaluation value, reliability, probability value and the like obtained based on simulation, training, judgment and the like.
The bottom layer parameters have weight assignment priority difference, namely the safety direct association parameters are larger than the safety indirect association parameters and are larger than the safety potential association parameters, and the weight assignment is carried out according to the reference structure safety analysis result, the historical safety data tracing and the artificial neural network analysis.
Thus, the degree of security of the "structure/device" of the middle layer may be further expressed as
p i ＝P{Q i,j }＝P{Q 1,1 ,Q 1,2 ,Q 1,3 ,Q 2,1 ,Q 2,2 ,Q 2,3 }
i＝1,2；j＝1,2,3
Wherein Q i,j I in (1) represents a "definite quantity" or an "indefinite quantity", and j represents a "security direct association parameter" or a "security indirect association parameter" or a "security potential association parameter".
Further, the security level of the "structure/device" of the middle layer after the weight assignment can be calculated as follows:
wherein q is i,j (i ═ 1, 2; j ═ 1, 2, 3) represents the weight assignment for each "parameter" and satisfies:
since the "security direct association parameter" or the "security indirect association parameter" or the "security potential association parameter" is not limited to 1 item, r i,j Weight assignment representing a certain "security direct association parameter" or "security indirect association parameter" or "security potential association parameter", i.e.
Wherein S is i (i ═ 1, 2, …, n) represents a certain "security direct association parameter" or "security indirect association parameter" or "security potential association parameter", s i (i-1, 2, …, n) represents the parameter value, t i (i ═ 1, 2, …, n) represents the weight assignment for this parameter, and satisfies:
as a preferred technical scheme of the invention: in risk accident prediction based on a multi-dimension multi-parameter criterion, parameters with higher priority comprise a water drainage state, a concrete emptying state, door body deformation, gate stress, hinge deformation, main rail damage and gate erosion thickness.
As a preferred technical scheme of the invention: digital twin-based security assessment follows three processing modes, respectively: the method comprises the steps of immediate data judgment, margin analysis and simulation based on data, and safety evaluation based on a neural network model.
The real-time data judgment is to set standard parameter ranges for data such as environmental parameters, gate state parameters, hoist state parameters and the like, and compare the monitored real-time data with the standard parameters to carry out safety assessment.
The margin analysis and simulation based on data are realized by correcting theoretical calculation results and optimizing a finite element calculation model by using historical data and instant data, performing online calculation under design conditions and developing action simulation under a preset state so as to investigate the margin of parameters including a motion range, structural stress, deformation, hoist capacity and the like.
The safety evaluation based on the neural network model is realized by modeling in Matlab mathematical software through the following steps.
The first step is as follows: and determining the type of the basic data. The method comprises the steps of setting environmental parameters, gate opening, passing gate flow, opening and closing force, structural stress, structural deformation and the like as input data, and setting the passing gate flow, the structural stress, the structural deformation and the like as output data. Based on the basic data, structural strength analysis and scheduling analysis are performed.
The second step is that: and (4) normalizing the data. Input data are limited within the range of 0-1 or-1 after being processed by an algorithm. The dimensionalized expression is changed into a dimensionless expression, so that indexes of different units or orders of magnitude can be compared and weighted conveniently.
The third step: algorithm training based on BP (Back propagation) neural network.
The second purpose of the present invention is to provide an intelligent management system for hydraulic metal structure equipment based on digital twins, which aims at overcoming the defects existing in the prior art.
Therefore, the above purpose of the invention is realized by the following technical scheme:
a hydraulic metal structure equipment intelligent management system based on digital twins comprises a basic equipment layer, a sensing layer, a data resource layer, a system application layer and a user display layer;
the sensing layer comprises an intelligent sensing, intelligent control and measurement and control integrated device;
the data resource layer is derived from factory data, monitoring data, historical data and operation and maintenance data;
the system application layer comprises a digital archive module, a state monitoring module, an operation maintenance module and a health assessment module.
While adopting the above technical solutions, the present invention can also adopt or combine the following technical solutions:
as a preferred technical scheme of the invention: the digital archive module is internally provided with a management system and a standard, adds a three-dimensional model, a standard gallery and a structural equipment dismounting animation of common metal structural equipment, integrates equipment account, offline data and online monitoring data, integrates a regular monitoring and detecting report and a state evaluation report, and recommends common fault types, operation suggestions and fault processing schemes.
As a preferred technical scheme of the invention: the state monitoring module comprises an environmental parameter monitoring unit, a gate monitoring unit, a hoist monitoring unit, a steel pipe monitoring unit, a trash rack detecting unit and a unit volute monitoring unit.
As a preferred technical scheme of the invention: the operation maintenance module comprises functions of an electronic sand table, video monitoring, inspection projects, inspection plans, task distribution, inspection statistics and inspection report.
As a preferred technical scheme of the invention: the health evaluation module comprises functions of off-line data analysis, historical fault analysis, safety state evaluation and wind accident risk prediction.
In addition, the invention also provides an intelligent management operation process of the hydraulic metal structure equipment, which is formed by depending on the intelligent management system of the hydraulic metal structure equipment and is characterized by comprising the following steps of:
s1, setting monitoring sensors and equipment by taking different metal structure equipment as objects;
s2, setting sampling period and frequency of the collector through an industrial personal computer, and automatically storing the collected data to a digital archive module;
s3, monitoring results can be observed and reviewed on line on the security information management platform through the state monitoring module;
s4, the offline inspection data and results are manually input into the digital archive module through the digital archive module;
s5, selecting specific metal structure equipment through the operation maintenance module, and calling state conditions and parameter information of corresponding periods;
s6, selecting specific metal structure equipment through a health evaluation module, deducing the type and probability of the sudden risk accident after data analysis and evaluation, and deriving a corresponding conclusion report;
and S7, making a patrol maintenance plan based on the operation maintenance module and the health assessment module, and arranging staff division.
The invention can at least comprise the following beneficial effects:
the method is based on accurate sensing, and develops a systematic safety management scheme for hydraulic metal structure equipment through data twinning by means of data mining. On one hand, systematic analysis and management can be carried out on a plurality of existing data accumulated in more than ten years of operation, such as historical water levels, opening and closing force, gate opening, maintenance implementation schemes, fault processing schemes and the like, with the aim of operation and maintenance; on the other hand, a monitoring scheme is supplemented and customized for the data type which is hidden in the position and is related to the safety, and a safety management analysis method which combines the existing data and the instant data is further perfected. Specifically, (1) a safety information management scheme of a hydraulic metal structure device in an engineering-structure/device-parameter three-level pyramid mode is formulated, a target structure/device hierarchy of a gate, a hoist, a valve, a steel pipe and a ship lift is definitely included, and an instant 'determined parameter' obtained based on monitoring, detection, observation and the like and an instant 'uncertain parameter' such as an evaluation value, reliability, probability value and the like obtained based on simulation, training, judgment and the like are divided so as to perfect safety management and evaluation indexes. (2) A digital twin body based on environmental data and metal structure equipment state data is formed, namely a twin model with linkage of key environmental hydrological parameters, equipment state parameters and structure motion postures is constructed according to a 'parameter' type selected by a user, and accurate fault point positioning, headstock gear opening and closing force state evaluation, engineering safety maintenance and maintenance reminding in the opening and closing process of the gate are visually carried out by combining gate opening and closing condition history, equipment fault history and water retaining scheduling real-time data. (3) Accurate operation and regulation prediction based on digital twins is formed, and for a gate structure, a gate movement process is simulated through 'water level-opening degree-vibration' analysis to form a resonance risk-avoiding movement interval to guide safe operation; for the structure of the hoist, through the analysis of 'water level-opening and closing force' trained by a neural network, the capacity prediction of the hoist under equivalent weight is formed, and the insufficient opening and closing or overload is avoided.
Drawings
FIG. 1 is a digital twinning relationship of the hydraulic metal structure equipment and the environment provided by the invention.
FIG. 2 is a diagram of an information space model construction format provided by the present invention.
Fig. 3 shows the system operation mode provided by the present invention.
Fig. 4 is a frame structure provided by the present invention.
Fig. 5 is a diagram of a system application layer provided by the present invention.
FIG. 6 is a block diagram of a health assessment module according to the present invention.
FIG. 7 is a diagram of a digital twin mode based on an artificial neural network technology provided by the present invention.
Fig. 8 is a flow chart of intelligent management of hydraulic metal structure equipment provided by the invention.
Fig. 9 is a schematic diagram of a plant metal structure equipment management system.
FIGS. 10a-10c are schematic diagrams of condition monitoring, health assessment, and operation maintenance functions, respectively, in a plant metallic structure equipment management system.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
It is to be noted that the experimental methods described in the following embodiments are all conventional methods unless otherwise specified, and the reagents and materials, if not otherwise specified, are commercially available; in the description of the present invention, the terms indicating orientation or positional relationship are based on the orientation or positional relationship shown in the drawings only for the convenience of description and simplification of description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
As shown in fig. 1, the digital twinning relationship between hydraulic metal structure equipment and the environment mainly includes the construction of a physical space including a hydraulic engineering physical environment and a hydraulic metal structure physical entity, and the construction of an information space including a hydraulic engineering twinning environment and a hydraulic metal structure digital twinning body. The physical space and the information space interact through twin data including historical data, online data and prediction data.
In order to complete the digital twin, an information space needs to be constructed, and a model of an environment where the hydraulic metal structure equipment is located, a geometric model of the hydraulic metal structure equipment, a physical model of the hydraulic metal structure equipment, and a rule model of a hydraulic metal structure equipment management system are constructed, as shown in fig. 2. Firstly, constructing an environment model of the hydraulic metal structure equipment, wherein the environment model comprises parameters such as water level, rainfall, temperature, humidity, pH value, medium flow rate, solution conductivity and the like; furthermore, the geometric model of the constructed hydraulic metal structure equipment needs to meet the requirements of geometric dimension, composition materials, composite structures and assembly logic; further, the physical model of the hydraulic metal structure equipment mainly comprises a gate, a hoist, a steel pipe and a unit volute. The parameters required to be designed for constructing the physical model of the gate comprise gate opening, gate inclination angle, gate vibration, hinge shaft torque, stress strain, coating state, corrosion depth, bolt torque, hinge shaft running state, expansion joint running state and the like; parameters needing to be designed for building the physical model of the hoist comprise opening and closing force, hoist vibration, hydraulic pressure, stress strain, acceleration, bolt torque, steel wire rope state, coating state, corrosion state and the like; parameters needing to be designed for building the steel pipe physical model comprise steel pipe vibration, coating state, corrosion depth, scouring degree, flow velocity in the pipe and the like; parameters required to be designed for the physical model construction of the unit volute comprise unit vibration, stress strain, bolt torque and the like. Further, the construction of the rule model of the hydraulic metal structure equipment management system needs to be based on a management system, a standard, a standard gallery, expert experience, intelligent comparison and the like.
In order to realize the intelligent management of the hydraulic metal structure equipment, after the hydraulic engineering physical environment and the hydraulic metal structure physical entity are formed, real-time information is acquired and is compared with the output information of an information space in real time. When the comparison result does not meet the rule model, performing data analysis, and on one hand, when the analysis result is that the information space has model defects, performing model correction; on the other hand, when the analysis result is that the physical entity of the hydraulic metal structure is abnormal, behavior control is carried out. The data analysis comprises historical fault analysis, safety state evaluation and risk accident prediction; the behavior control comprises fault warning, fault operation, halt error reporting, feedback control and information return.
Specifically, the safety state evaluation comprises the steps of mining and deducing the fault type and reason of the hydraulic metal structure equipment based on the working condition history and the fault history, carrying out evaluation analysis by combining with real-time data, and finally forming the safety state evaluation of the hydraulic metal structure equipment; and predicting the risk accident, wherein the risk accident prediction comprises the steps of carrying out multi-scene training of different gate opening degrees, different opening and closing forces, different vibration types, different structural stress states, different structural corrosion degrees and different part actions aiming at a hydraulic metal structure digital twin body in an information space based on working condition history and fault history, further forming a fault probability model, forming twin data according to real-time data, and fusing the twin data with the fault probability model to obtain probability prediction of the risk accident.
A system operation mode of the above technical solution is as shown in fig. 3, and first, for a selected hydraulic metal structure device, real-time data is acquired; the acquired parameters are used as input parameters to generate digital twin analog data; constructing an environment model, a geometric model, a physical model and a regular model by contrasting the physical space; after a model is formed, twin data are used for training, and then data analysis including historical fault analysis, safety state evaluation and risk accident prediction is carried out; comparing the rule models based on the data analysis result, and performing model correction and behavior control; the behavior control comprises fault early warning, feedback control, fault operation, halt error reporting and information return. Furthermore, based on risk accident prediction, early failure warning is formed, a degradation unit is identified and positioned, and the failure risk is timely eliminated through active behavior control.
Digital twin-based security assessment follows three processing modes, respectively: the method comprises the steps of immediate data judgment, margin analysis and simulation based on data, and safety evaluation based on a neural network model.
The real-time data judgment is to set standard parameter ranges for data such as environmental parameters, gate state parameters, hoist state parameters and the like, and compare the monitored real-time data with the standard parameters to carry out safety assessment.
The margin analysis and simulation based on data are realized by correcting theoretical calculation results and optimizing a finite element calculation model by using historical data and instant data, performing online calculation under design conditions and developing action simulation under a preset state so as to investigate the margin of parameters including a motion range, structural stress, deformation, hoist capacity and the like.
The safety evaluation based on the neural network model is realized by modeling in Matlab mathematical software through the following steps.
The first step is as follows: and determining the type of the basic data. The method comprises the steps of setting environmental parameters, gate opening, passing gate flow, opening and closing force, structural stress, structural deformation and the like as input data, and setting the passing gate flow, the structural stress, the structural deformation and the like as output data. Based on the basic data, structural strength analysis and scheduling analysis are performed.
The second step is that: and (4) normalizing the data. Input data are limited within the range of 0-1 or-1 after being processed by an algorithm. The dimensionalized expression is changed into a dimensionless expression, so that indexes of different units or orders of magnitude can be compared and weighted conveniently. The normalization process is as follows:
X scale ＝(X-X min )/(X max -X min )
wherein, X scale Is normalized data, X is input data, X max And X min Respectively, a maximum value and a minimum value in the input data.
The third step: algorithm training based on BP (Back propagation) neural network. The first layer of the BP neural network is the input layer (x) 1 、x 2 、…x i ) Input instant data and calculation data; the middle layer is one or more hidden layers, and the number of layers is adjusted according to the result obtained by training; finally, the output layer (y) 1 、y 2 、…y i ) And the data comprises output monitoring flow, structural strength and the like. Each layer is composed of several neurons (corresponding to each hidden layer), and the output value of each layer is composed of input value, action function and connection weight w i Determining all input quantity x of input layer according to threshold value theta i And a weight w i Algebraic sum of products, final output value y i Equal to the difference between the algebraic sum and the possible value theta.
And finally, the output data needs to be processed by a sigmoid and other activating functions, and the processing process is as follows:
inputting data into matlab for neural network training, wherein the used codes are as follows:
net＝newff(minmax(Y scale ),X scale ,[a,b]{ 'logsig', 'purelin' }, 'traingdm'), where X is scale And Y scale The normalized input and output data are respectively represented, a represents the number of hidden layer neurons, b represents the number of output layer neurons, 'logsig' is the hidden layer transfer function of the neural network, and 'purelin' is the transfer function of the output layer.
After the neural network training, the input data should be subjected to inverse normalization processing to ensure that the scalar is converted into a dimensional number again in the subsequent prediction, so as to avoid the deviation of the result, and the used processing codes are as follows:
Y re-scale ＝mapminmax(‘reverse’,Y train PS) in which Y train To use the output value of the trained neural network, Y re-scale For the data after the denormalization, PS is a setting parameter.
The fourth step: based on the safety evaluation of the trained BP neural network, the implementation process is as follows:
pnew ═ a1 … an, where a1 through an are the actual input data;
pnewn ═ mapminmax (pnew), where this step represents normalizing the data;
where this step represents the use of a BP neural network that has been trained;
and (4) anew ═ mapminmax ('reverse', anewn, ts), where this step represents the error between the comparable number and the number, which is the denormalized output of the result.
A system framework of the intelligent management method for the hydraulic metal structure equipment based on the digital twin is shown in figure 4, and comprises a basic equipment layer, a sensing layer, a data resource layer, a system application layer and a user display layer, can be used as an integrated, modularized and integrated safety monitoring platform for the hydraulic metal structure equipment, and is mainly used for data management, state diagnosis and risk assessment. The intelligent management system for the hydraulic metal structure equipment relies on and serves the hydraulic metal structure equipment, common system objects comprise a gate, a hoist, a diversion steel pipe/steel branch pipe and a unit volute, sensors are arranged in areas needing important attention on the hydraulic metal structure equipment, the sensors are collected and stored, and data obtained by on-line monitoring of a sensing layer are managed. The data resource layer collects monitoring results, offline inspection results, data analysis results and state evaluation reports of all the monitoring sensors; the user display layer can be used for displaying in scenes such as a computer end, a mobile end and a digital large screen according to function requirements.
Particularly, the system application layer has all functions of intelligent management, as shown in fig. 5, and mainly includes a digital archive module, a state monitoring module, an operation and maintenance module, and a health assessment module, and the user presentation layer needs to select a certain or partial function to design and use according to user characteristics and scene requirements, for example, for operation and maintenance personnel, only the operation and maintenance module needs to be started, and for background analysts, only the digital archive module needs to be started.
In this embodiment, the digital archive module function in the intelligent management system for hydraulic metal structure equipment is as shown in fig. 5, and includes the following contents: management system, standard, three-dimensional model, standard gallery, assembly and disassembly animation, equipment ledger, off-line data, on-line data, regular inspection report, common fault, operation suggestion, evaluation report and fault treatment suggestion. The management system and the standard are preset according to unit requirements supported by an intelligent management system of the hydraulic metal structure equipment; the three-dimensional model and the standard gallery can display the basic structural equipment information of a gate, a hoist, a diversion steel pipe/steel branch pipe and a unit volute, and for key moving parts, the internal structure and the motion principle can be known through structural equipment dismounting animations. The equipment ledger can select and display equipment parameters and functions in all systems. The off-line data and the on-line monitoring data are respectively recorded or stored in the digital archive module after off-line inspection and on-line monitoring of the sensor; in addition, the periodic monitoring report can be stored and read according to a fixed format in the module. Based on the standard and the monitoring result, the target structure equipment can be selected in the digital archive module for state evaluation or prediction and measure suggestion.
In this embodiment, the functions of the operation and maintenance module in the intelligent management system for hydraulic metal structure equipment are shown in fig. 5, and include the following contents: electronic sand table, video monitoring, inspection project, inspection plan, task allocation, inspection statistics and inspection report. The electronic sand table is used as a global state display window of the whole hydraulic metal structure equipment, and specifically can show stress strain distribution of key parts such as a gate running state, a welding line, a bearing and the like, corrosion potential distribution of a metal structure in a water-immersed or wet area and the like; the video monitoring is used for real-time online observation of key monitoring points; the method comprises the steps that parameterization, step setting and implementation are carried out on a polling project, a polling plan and task allocation in a folding project, a floating frame, a pull-down menu and other modes, preliminary scheme suggestion is carried out according to offline/online monitoring and detection data and by combining a standard and expert experience, and in the final implementation process, thought modification and optimization can be carried out in an operation maintenance module according to actual requirements; the routing inspection statistics and routing inspection reports can be consulted, compared and exported in an item mode. After the inspection is finished, the inspection statistics and the inspection report can be recorded through the operation maintenance module, and the inspection statistics and the inspection report can be stored in the digital archive module.
In this embodiment, the functions of the health assessment module in the intelligent management system for hydraulic metal structure equipment are shown in fig. 6, and include: historical fault analysis, offline/online data analysis, safety state evaluation and risk accident prediction.
And historical fault analysis, namely, screening fault types and judging fault reasons of specific metal structure equipment based on the inspection result and the off-line data. Specifically, historical failure analysis can be divided into structural deformation, structural instability, structural cracks, cable breaks, equipment wear, equipment failure, corrosion failures, and structural vibrations based on the characteristics of the failure.
And off-line data analysis, which is based on the inspection result and the sensor on-line monitoring data, primarily screening and optimizing to form classified data statistical results to be used as the basis of historical fault analysis, safety state evaluation and accident risk prediction. Specifically, offline/online data analysis is performed in combination with the fault type, and least square, time domain analysis, frequency domain analysis, factor analysis, association analysis, regression analysis, fuzzy analysis, Fourier transform, Bayesian analysis and other methods are adopted for analysis to sort and refine the data and provide a basis for subsequent safety state evaluation and risk accident prediction.
And safety state evaluation, namely after a specific metal structure device is selected, evaluating the safety state based on an operation condition, a standard, an analysis model and expert experience according to the opening, stress strain, inclination angle, acceleration, corrosion rate and other on-line values measured by a sensor and by combining an off-line periodic inspection result, and providing comprehensive health evaluation of different levels.
The risk accident prediction is to conjecture the type and probability of the sudden risk accident by combining a reliable risk assessment method after obtaining the running state of the specific metal structure equipment. Under the current safety state, comprehensive analysis is carried out by relying on various prediction models, such as combination of a gray model, vector machine analysis, Monte Carlo simulation, neural network analysis and the like.
As shown in fig. 7, twin data analysis data is performed by means of an artificial neural network technology, wherein input parameters are environmental data in an environmental model and online monitoring data of metal structure equipment in a physical model, and multi-scene training of different gate opening degrees, different opening and closing forces, different vibration types, different structure stress states, different structure corrosion degrees and different component actions is performed based on working condition history and fault history to form a fault probability model and obtain the residual life and the failure probability of the metal structure equipment; furthermore, a twin model and data analyzed by an artificial neural network technology are further combined, so that accurate state control, fault point positioning, state overhaul and maintenance reminding of metal structure equipment can be formed; and the visual and accurate scheduling is realized through comprehensive monitoring and twin scenes.
In the embodiment, risk accident prediction based on a multi-dimensional multi-parameter criterion is carried out, for example, only gate safety evaluation is carried out on certain engineering safety, and the 'structure/equipment' is uniquely defined as a gate, the weight of the gate is 1 for the engineering safety, and the gate is influenced by weight assignment of bottom 'parameters'. This embodiment can divide the "parameters" into the gate operation conditions (u) 1 ) Degree of corrosion (u) 2 ) Stress condition (u) 3 ) And detecting the appearance of the gate (u) 4 ) Inspection results (u) 5 ) Five classes, i.e.
u＝(u 1 ,u 2 ,u 3 ,u 4 ,u 5 )
The operation condition, the corrosion degree and the stress condition of the gate can be defined as a safety direct correlation parameter, the appearance detection of the gate can be defined as a safety indirect correlation parameter, and the inspection result of the patrol can be defined as a safety potential correlation parameter. Assigning priority and gate operation condition (u) according to weight of parameter 1 )>Degree of corrosion (u) 2 )>Stress condition (u) 3 )>Gate appearance detection (u) 4 )>Inspection results of patrol (u) 5 ). Furthermore, the running condition of the gate can be evaluated based on expert evaluation or neural network analysis by referring to 'uncertain parameters'; the gate appearance detection and inspection result can refer to 'indefinite parameters', and is assigned based on expert evaluation or empirical analysis; and the corrosion degree and the stress condition can refer to 'determination parameters', and the residual strength is calculated through the structural strength for assignment.
Further, during the parameter assignment process, part of the parameters or the weight assignment factors containing lower levels, such as the water flow posture (u) when the patrol inspection includes the gate drainage 5,1 ) And water leakage when the gate is closed (u) 5,2 ) Door slot concrete condition (u) 5,3 ) Gate pier-breast wall-corbel condition (u) 5,4 ) Unobstructed vent hole condition (u) 5,5 ) Etc., by establishing a weight vector:
u 5 ＝(u 5,1 ,u 5,2 ,u 5,3 ,u 5,4 ,u 5,5 )
and further through weight matrix calculation, obtain gate degree of safety:
by means of the intelligent management system for the hydraulic metal structure equipment, an intelligent management operation flow of the hydraulic metal structure equipment shown in fig. 8 can be formed, and the intelligent management operation flow is characterized by comprising the following steps:
s1, setting monitoring sensors and equipment by taking different metal structure equipment as objects;
s2, setting the sampling period and frequency of the collector through an industrial personal computer, and automatically storing the collected data to a digital archive module;
s3, monitoring results can be observed and reviewed on line on the security information management platform through the state monitoring module;
s4, the offline inspection data and results are manually input into the digital archive module through the digital archive module;
s5, selecting specific metal structure equipment through the operation maintenance module, and calling state conditions and parameter information of corresponding periods;
s6, selecting specific metal structure equipment through a health evaluation module, deducing the type and probability of the sudden risk accident after data analysis and evaluation, and deriving a corresponding conclusion report;
and S7, making a patrol maintenance plan based on the operation maintenance module and the health assessment module, and arranging personnel for division of labor.
As shown in fig. 9, the schematic diagram of the management system of the metal structure equipment of a certain power station is shown, monitoring objects are a gate and an opening and closing machine of the power station, monitoring components need to be arranged on the gate and the opening and closing machine by a state monitoring module, the monitoring components meet the working condition of long-term underwater operation, and the monitoring components are connected to an independent control cabinet in a wired mode. The monitoring module and the hoist control system are mutually independent, and the monitored data is transmitted to a remote monitoring terminal for display through a local switch. In this embodiment, the stress state observation of the device during operation is realized by means of stress sensors arranged on the structural device. As shown in fig. 10a, the online state monitoring data curve of a partial stress sensor can determine the current structural strength of the device according to the stress level, and determine whether the device is abnormal by determining whether the monitoring curve has a sudden change. Meanwhile, as shown in fig. 10b, the health of the gate and the hoist can be evaluated based on the off-line data, and an evaluation result and an evaluation report are formed. Based on the monitoring result and the evaluation result, the management system can also recommend subsequent operation maintenance, formulate a polling scheme, and perform operation control on line by referring to a preset operation instruction, as shown in fig. 10c, since the evaluation result of part of the metal structure equipment is unsafe, the management system calls a recent equipment polling record, and at the same time, formulate the subsequent operation scheme in the operation maintenance functional module.
The above embodiments are merely preferred embodiments of the present invention, and those skilled in the art will understand that modifications or substitutions of technical solutions or parameters in the embodiments can be made without departing from the principle and essence of the present invention, and all of them shall be covered by the protection scope of the present invention.
Claims (10)
1. A hydraulic metal structure equipment intelligent management construction method based on digital twinning is characterized in that: the construction method comprises the following steps:
s1, constructing a physical space, wherein the physical space comprises a hydraulic engineering physical environment and a hydraulic metal structure physical entity; the hydraulic metal structure physical entity comprises at least one of a gate, a hoist, a steel pipe and a unit volute;
s2, constructing an information space, wherein the information space comprises a hydraulic engineering twin environment and a hydraulic metal structure digital twin;
and S3, forming twin data to interact between the physical space and the information space, wherein the twin data comprises historical data, online data and prediction data.
2. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twin as claimed in claim 1, wherein the intelligent management and construction method comprises the following steps: in step S2, constructing an information space, including constructing an environment model, a geometric model, a physical model, and a rule model; the environmental model parameters comprise water level, rainfall, temperature, humidity, pH value, medium flow rate and solution conductivity; the geometric model includes geometry, constituent materials, composite structures, and assembly logic.
3. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twin as claimed in claim 2, wherein the intelligent management and construction method comprises the following steps: the rule model is constructed based on a management system, a standard gallery, expert experience and intelligent comparison.
4. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twin as claimed in claim 1, wherein the intelligent management and construction method comprises the following steps: in step S3, real-time information formed by the physical environment of the hydraulic engineering and the physical entity of the hydraulic metal structure is compared with the output information of the information space in real time;
when the comparison result does not meet the rule model, performing data analysis, and on one hand, when the analysis result is that the information space has model defects, performing model correction; on the other hand, when the analysis result is that the physical entity of the hydraulic metal structure is abnormal, behavior control is carried out.
5. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twin as claimed in claim 4, wherein the intelligent management and construction method comprises the following steps: the data analysis comprises historical fault analysis, safety state evaluation and risk accident prediction; the behavior control comprises fault warning, fault operation, halt error reporting, feedback control and information return.
6. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twinning as claimed in claim 5, characterized in that: digital twin-based security assessment follows three processing modes, respectively: judging instant data, analyzing and simulating margin based on data, and evaluating safety based on a neural network model; the training of the neural network model is based on the working condition history, the fault history and the real-time data.
7. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twinning as claimed in claim 5, characterized in that: the risk accident prediction aims at hydraulic metal structure digital twins in an information space, depends on an artificial neural network technology, inputs parameters of environmental data in an environmental model and metal structure equipment online monitoring data in a physical model, carries out multi-scene training of different gate opening degrees, different opening and closing forces, different vibration types, different structure stress states, different structure corrosion degrees and different part actions based on working condition history and fault history, forms a fault probability model, forms twins according to real-time data, and fuses with the fault probability model to obtain probability prediction of risk accidents.
8. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twin as claimed in claim 7, wherein the intelligent management and construction method comprises the following steps: predicting risk accidents based on a multidimensional multiparameter criterion, namely, the multidimensional condition is a three-level pyramid mode of 'engineering-structure/equipment-parameter', wherein the 'structure/equipment' comprises a gate, a hoist, a valve, a steel pipe and a ship lift; the multi-parameter is embodied as that the 'parameters' comprise 'determined parameters' and 'uncertain parameters', the 'determined parameters' comprise instant determined parameter information obtained based on monitoring, detection, observation and the like, and the 'uncertain parameters' comprise non-instant determined parameter information such as evaluation values, reliability, probability values and the like obtained based on simulation, training, judgment and the like.
9. The intelligent management and construction method for the hydraulic metal structure equipment based on the digital twinning as claimed in claim 8, characterized in that: based on risk accident prediction of a multidimensional multiparameter criterion, bottom layer parameters have weight assignment priority difference, namely, a safety direct association parameter is larger than a safety indirect association parameter and is larger than a safety potential association parameter, and weight assignment is carried out according to a reference structure safety analysis result, historical safety data tracing and artificial neural network analysis; the middle gate and the hoist in the middle layer of structure/equipment have weight assignment priority, namely the high-frequency dynamic priority is higher than the low-frequency static state;
based on risk accident prediction of a multi-dimensional and multi-parameter criterion, parameters with higher priority comprise a drainage state, a concrete emptying state, door body deformation, hinge deformation, main rail damage and gate erosion residual thickness.
10. A hydraulic metal structure equipment intelligent management system based on digital twins is characterized by comprising a basic equipment layer, a sensing layer, a data resource layer, a system application layer and a user display layer;
the sensing layer comprises an intelligent sensing, intelligent control and measurement and control integrated device;
the data resource layer is derived from manufacturer data, monitoring data, historical data and operation and maintenance data;
the system application layer comprises a digital archive module, a state monitoring module, an operation maintenance module and a health assessment module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210557484.4A CN115034578A (en) | 2022-05-20 | 2022-05-20 | Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210557484.4A CN115034578A (en) | 2022-05-20 | 2022-05-20 | Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115034578A true CN115034578A (en) | 2022-09-09 |
Family
ID=83120566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210557484.4A Pending CN115034578A (en) | 2022-05-20 | 2022-05-20 | Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115034578A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115408706A (en) * | 2022-10-28 | 2022-11-29 | 国科治慧(苏州)智能科技有限公司 | Digital twin model of aviation product and technical state two-way exchange method thereof |
| CN115422620A (en) * | 2022-11-08 | 2022-12-02 | 北自所(北京)科技发展股份有限公司 | Logistics equipment redesign method and device based on digital twinning and storage medium |
| CN115577641A (en) * | 2022-11-14 | 2023-01-06 | 成都飞机工业（集团）有限责任公司 | Training method, device, equipment and medium for digital twin model |
| CN115600438A (en) * | 2022-11-25 | 2023-01-13 | 河海大学（Cn） | Data processing method and system suitable for hydraulic engineering |
| CN115688227A (en) * | 2022-10-13 | 2023-02-03 | 长江空间信息技术工程有限公司(武汉) | Digital twin hydraulic engineering operation safety monitoring system and operation method |
| CN115827411A (en) * | 2022-12-08 | 2023-03-21 | 国家管网集团北方管道有限责任公司 | Online monitoring and operation and maintenance evaluation system and method for automation equipment |
| CN116150580A (en) * | 2023-04-17 | 2023-05-23 | 中国水利水电科学研究院 | Data resource evaluation method of digital twin drainage basin data base plate |
| CN116295654A (en) * | 2023-04-12 | 2023-06-23 | 广州三业科技有限公司 | Water shortage or overload state monitoring method and system based on mobile sewage disposal equipment |
| CN116502931A (en) * | 2023-02-06 | 2023-07-28 | 北京北投生态环境有限公司 | Detection system for preventing and controlling ecological environment risks of pollution sites of chemical plants |
| CN117049379A (en) * | 2023-08-16 | 2023-11-14 | 广东达丰机械工程有限公司 | Tower crane work monitoring system based on digital twin |
| CN117422450A (en) * | 2023-12-18 | 2024-01-19 | 贵州鸿达立信计量检测有限公司 | Digital maintenance system for metering equipment |
| WO2024055271A1 (en) * | 2022-09-16 | 2024-03-21 | 华东理工大学 | Anti-fatigue and safety regulation and control method for service structure having ultra-long service life in extreme environment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| CN112417619A (en) * | 2020-11-23 | 2021-02-26 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
-
2022
- 2022-05-20 CN CN202210557484.4A patent/CN115034578A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286572A1 (en) * | 2016-03-31 | 2017-10-05 | General Electric Company | Digital twin of twinned physical system |
| CN112417619A (en) * | 2020-11-23 | 2021-02-26 | 江苏大学 | Pump unit optimal operation adjusting system and method based on digital twinning |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024055271A1 (en) * | 2022-09-16 | 2024-03-21 | 华东理工大学 | Anti-fatigue and safety regulation and control method for service structure having ultra-long service life in extreme environment |
| CN115688227A (en) * | 2022-10-13 | 2023-02-03 | 长江空间信息技术工程有限公司(武汉) | Digital twin hydraulic engineering operation safety monitoring system and operation method |
| CN115408706A (en) * | 2022-10-28 | 2022-11-29 | 国科治慧(苏州)智能科技有限公司 | Digital twin model of aviation product and technical state two-way exchange method thereof |
| CN115408706B (en) * | 2022-10-28 | 2023-01-31 | 国科治慧(苏州)智能科技有限公司 | Bidirectional exchange method based on aviation product twin model and twin technical state |
| CN115422620A (en) * | 2022-11-08 | 2022-12-02 | 北自所(北京)科技发展股份有限公司 | Logistics equipment redesign method and device based on digital twinning and storage medium |
| CN115577641A (en) * | 2022-11-14 | 2023-01-06 | 成都飞机工业（集团）有限责任公司 | Training method, device, equipment and medium for digital twin model |
| CN115600438B (en) * | 2022-11-25 | 2023-03-07 | 河海大学 | Data processing method and system suitable for hydraulic engineering |
| CN115600438A (en) * | 2022-11-25 | 2023-01-13 | 河海大学（Cn） | Data processing method and system suitable for hydraulic engineering |
| CN115827411A (en) * | 2022-12-08 | 2023-03-21 | 国家管网集团北方管道有限责任公司 | Online monitoring and operation and maintenance evaluation system and method for automation equipment |
| CN116502931B (en) * | 2023-02-06 | 2024-02-09 | 北京北投生态环境有限公司 | Detection system for preventing and controlling ecological environment risks of pollution sites of chemical plants |
| CN116502931A (en) * | 2023-02-06 | 2023-07-28 | 北京北投生态环境有限公司 | Detection system for preventing and controlling ecological environment risks of pollution sites of chemical plants |
| CN116295654A (en) * | 2023-04-12 | 2023-06-23 | 广州三业科技有限公司 | Water shortage or overload state monitoring method and system based on mobile sewage disposal equipment |
| CN116295654B (en) * | 2023-04-12 | 2023-09-15 | 广州三业科技有限公司 | Water shortage or overload state monitoring method and system based on mobile sewage disposal equipment |
| CN116150580A (en) * | 2023-04-17 | 2023-05-23 | 中国水利水电科学研究院 | Data resource evaluation method of digital twin drainage basin data base plate |
| CN117049379B (en) * | 2023-08-16 | 2024-01-26 | 广东达丰机械工程有限公司 | Tower crane work monitoring system based on digital twin |
| CN117049379A (en) * | 2023-08-16 | 2023-11-14 | 广东达丰机械工程有限公司 | Tower crane work monitoring system based on digital twin |
| CN117422450A (en) * | 2023-12-18 | 2024-01-19 | 贵州鸿达立信计量检测有限公司 | Digital maintenance system for metering equipment |
| CN117422450B (en) * | 2023-12-18 | 2024-03-26 | 贵州鸿达立信计量检测有限公司 | Digital maintenance system for metering equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115034578A (en) | Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning | |
| CN110320892B (en) | Sewage treatment equipment fault diagnosis system and method based on L asso regression | |
| Dao et al. | Condition monitoring and fault detection in wind turbines based on cointegration analysis of SCADA data | |
| US9076106B2 (en) | Systems and methods for management of risk in industrial plants | |
| CN100470416C (en) | Power plant thermal equipment intelligent state diagnosing and analyzing system | |
| CN105096053A (en) | Health management decision-making method suitable for complex process system | |
| CN107153929A (en) | Gearbox of wind turbine fault monitoring method and system based on deep neural network | |
| CN105758661B (en) | Boiler heating surface service life evaluation system and method | |
| CN113900381B (en) | Steel structure remote health monitoring platform based on Internet of things and application method | |
| CN110764474B (en) | Method and system for monitoring running state of equipment | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN116228186A (en) | Ship cabin intelligent operation and maintenance system based on human engineering | |
| CN117196159A (en) | Intelligent water service partition metering system based on Internet big data analysis | |
| Abbate et al. | Maintenance Digital Twin using vibration data | |
| CN111178674A (en) | Industrial big data driven hoisting machinery health management and control service system | |
| CN114519923A (en) | Intelligent diagnosis and early warning method and system for power plant | |
| CN115456331B (en) | Application of multi-dimensional multi-measuring point model on-line monitoring algorithm to monitoring analysis system platform | |
| Sharma et al. | Modeling system behavior for risk and reliability analysis using KBARM | |
| CN115526375A (en) | Space flight equipment predictive maintenance system | |
| CN114897271A (en) | Central air conditioner predictive maintenance method based on fault propagation in digital twin environment | |
| Zeng et al. | Maintenance strategy based on reliability analysis and FMEA: a case study for hydraulic cylinders of traditional excavators with ERRS | |
| CN110765633A (en) | Intelligent management method and device for power device | |
| RU2668487C2 (en) | Management decision making information support system for operational personnel of a ship power plant | |
| Holmberg et al. | Prognostics for industrial machinery availability | |
| Chen et al. | BIM-and IoT-Based Data-Driven Decision Support System for Predictive Maintenance of Building Facilities |
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 |