CN116489042A - Intelligent building risk early warning method and system device based on deep learning - Google Patents
Intelligent building risk early warning method and system device based on deep learning Download PDFInfo
- Publication number
- CN116489042A CN116489042A CN202310424359.0A CN202310424359A CN116489042A CN 116489042 A CN116489042 A CN 116489042A CN 202310424359 A CN202310424359 A CN 202310424359A CN 116489042 A CN116489042 A CN 116489042A
- Authority
- CN
- China
- Prior art keywords
- early warning
- risk
- monitoring
- data
- decision
- 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 35
- 238000013135 deep learning Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 215
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000007726 management method Methods 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 17
- 238000012790 confirmation Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 16
- 238000012423 maintenance Methods 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 241000700605 Viruses Species 0.000 claims description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 7
- 229910052760 oxygen Inorganic materials 0.000 claims description 7
- 239000001301 oxygen Substances 0.000 claims description 7
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000004907 flux Effects 0.000 claims description 6
- 230000005358 geomagnetic field Effects 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 239000013049 sediment Substances 0.000 claims description 6
- 231100000419 toxicity Toxicity 0.000 claims description 6
- 230000001988 toxicity Effects 0.000 claims description 6
- 238000003916 acid precipitation Methods 0.000 claims description 5
- 239000000779 smoke Substances 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 239000007789 gas Substances 0.000 claims description 4
- 238000004062 sedimentation Methods 0.000 claims description 4
- 239000002689 soil Substances 0.000 claims description 4
- 238000012550 audit Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 6
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 239000003570 air Substances 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 5
- 239000012080 ambient air Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 description 1
- 241000192700 Cyanobacteria Species 0.000 description 1
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- MMDJDBSEMBIJBB-UHFFFAOYSA-N [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] Chemical compound [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] MMDJDBSEMBIJBB-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- -1 fluoride ions Chemical class 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 231100000167 toxic agent Toxicity 0.000 description 1
- 239000003440 toxic substance Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q50/08—Construction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/20—Network architectures or network communication protocols for network security for managing network security; network security policies in general
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Alarm Systems (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
Abstract
The invention aims to provide an intelligent building risk monitoring and early warning method and system device based on deep learning, which are used for solving the problems that cloud computing and edge computing are used for cooperative processing in a building risk monitoring and early warning system, a large amount of data transmission and cloud computing work are reduced, high-timeliness data transmission and early warning information are sent, and building risks are predicted by combining artificial intelligence with a risk model. The early-stage data are set manually, and when the early-warning decision-making case base data reach a certain degree, the early-warning decision-making case base data do not need manual setting and intervention, so that the accuracy and timeliness of risk monitoring early warning are improved, and a large amount of manpower monitoring and equipment investment is saved. The front-end sensor adopts the low-power-consumption intelligent sensor of the Internet of things, has small volume, supports various wireless transmission protocols, greatly facilitates engineering construction and saves engineering construction quantity, and can be widely applied to safety risk monitoring of various self-building houses, historical buildings, cultural building, complex and other buildings.
Description
Technical Field
The invention relates to the technical field of big data artificial intelligent building risk monitoring, in particular to an intelligent building risk early warning method and system device based on deep learning.
Background
As cities develop, numerous high-rise and old buildings appear, which play a major role as architectural signs for cities or for business. In the long history of human construction, high-rise buildings as the youngest member have only a hundred years of history since the birth of the twentieth century. The high-rise building has special structural form, multiple functions and complex vertical traffic, not only reflects the structural design and construction level of the building, but also needs comprehensive solutions of various problems, such as fire protection, earthquake resistance, traffic and the like. The higher the high-rise building is, the more problems of safety, durability and the like are revealed, and the higher requirements are put on the building, the structure and the matched facilities. For high-rise buildings, people and lives and properties caused by accidents are far more damaged than those of ordinary buildings. Therefore, the stability of the high-rise building must be sufficiently ensured to avoid collapse. However, the conventional method is far from sufficient to ensure the stability of the high-rise building. Therefore, the building structure comprehensive risk early warning and monitoring system for the high-rise building has very important practical significance for guaranteeing the stability judgment of the high-rise building structure. Building risk monitoring is a comprehensive technology with multiple subjects and multiple professions, and the purpose of monitoring the health state of a structure is achieved by arranging a small number of test elements at key parts of the structure and collecting stress and displacement values of the structure which are generated along with the action of load in the operation process. As the high-sensitivity sensor is adopted for monitoring, the method is high in price, is initially used in special engineering such as aerospace engineering, nuclear engineering and the like, and is also used in engineering such as bridges, tunnels, high-rise buildings and the like in large scale along with the development of network technology and sensing technology. The application of the building risk early warning and monitoring technology can intuitively observe the change trend of each reliability index in the use process, and provide reliable basis for daily maintenance and risk early warning of the structure through data collection, processing and analysis, so that the engineering risk is directly reduced, and the engineering service life is guaranteed and prolonged. At present, most buildings are not provided with building risk monitoring systems, only a small number of buildings are provided with building risk monitoring systems, the building risk monitoring systems which are applied are basically separated, the sensors use independent single sensors, and analog signals are often output after data acquisition. The sensor sends the analog signal to the collector, and the collector converts the signal into a digital signal after collecting the signal and sends the digital signal to the industrial control computer. The industrial computer sends the independent monitoring data to the control center for calculation, the central computer analyzes the risk monitoring condition and transmits the risk monitoring condition to the monitoring display system, the display computer, the LED large-screen display system, the television wall display system and the like. The disadvantage is that numerous devices are required, including sensors, collectors, industrial control computers, server systems, data display systems, network transmission systems (switches, optical fiber transceivers, routers, etc.), etc., which are expensive, and the data processing capacity is poor, requiring a large number of manual monitoring. The system safety coefficient is not high, the local system is damaged, and the maintenance and recovery time is long. In practical application, a large amount of equipment investment, installation and debugging manpower investment, later-period management personnel investment and high later-period maintenance cost investment are caused. At present, a large number of used building risk monitoring systems do not use artificial intelligence, big data and edge computing technologies of the Internet of things, and aiming at the problems, the inventor provides an intelligent building risk early warning method and a system device based on deep learning, which are used for solving the problems.
Disclosure of Invention
The method aims to solve the problems of low accuracy, poor timeliness and high equipment investment cost of risk monitoring and early warning; the invention aims to provide an intelligent building risk early warning method and system device based on deep learning.
In order to solve the technical problems, the invention adopts the following technical scheme: an intelligent building risk early warning method based on deep learning comprises the following steps:
s1, building risk monitoring data are collected by sensing equipment of the Internet of things, different monitoring data collected by the sensing equipment correspond to different risk coefficients, and the risk coefficients correspond to risk levels. When risk factors are correspondingly extracted after risk monitoring data are received, risk levels are correspondingly determined after the risk factors are determined, after the risk levels are determined, risk factors and the risk levels corresponding to the monitoring data are formed into early warning case retrieval data, the early warning case retrieval data are transmitted into an early warning decision case library for comparison screening, decision cases with the same risk factors and the same risk levels are screened out, the screened decision cases are determined to be current early warning decisions to form an initial early warning decision scheme, when decision cases with the same or similar data (the comparison data proximity degree is manually set according to different monitoring data types) are not found in the early warning decision case library, an initial early warning decision scheme is formed in the next step, and the initial early warning decision scheme is set and determined manually according to the risk factors and the risk levels corresponding to the monitoring data;
S2, after the initial early warning decision scheme is determined, the next step is carried out, the early warning decision scheme is revised, and the personnel are set to audit and revise the early warning decision scheme according to different risk monitoring data types and factors of the building, such as floor height, building age, geographical area and the like;
s3, after the early warning decision scheme is corrected, entering a next step of alternative early warning decision scheme, and in addition to the first early warning decision scheme, whether an alternative early warning decision scheme is needed or not is checked, if one alternative early warning decision scheme is insufficient, a plurality of alternative early warning decision schemes are set according to factors, environmental parameters and the like of the building;
s4, after forming a plurality of early warning decision schemes, the personnel evaluate the early warning decision schemes, the personnel can be one or more persons, and final early warning decision scheme determination is made;
s5, carrying out data storage on relevant data parameters of final early warning decision cases and the whole decision process, and storing the early warning cases into an early warning decision case library;
and S6, simultaneously making an early warning decision, sending early warning decision related data and parameters to a cloud service system through a high-performance edge computing core control system for database storage, and sending to a local monitoring end, an APP monitoring end and a centralized control monitoring end. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level.
Preferably, the intelligent building risk early warning method based on deep learning comprises the following steps:
s1, when multiple building risk early warning of different categories occur simultaneously, an artificial intelligent deep learning algorithm adopts the following risk early warning decision method:
s2, receiving a plurality of different types of risk early-warning data, correspondingly extracting risk coefficients corresponding to the plurality of types of monitoring data, determining risk coefficients, correspondingly determining risk levels, after determining the risk levels, searching risk early-warning case by inputting risk coefficients corresponding to the monitoring data and risk level formation data and parameter information, transmitting the early-warning case search data into an early-warning decision case library for comparison screening, screening case data and parameters with the same risk index and risk level, and revealing the degree of building risks according to the risk index by the system;
s3, screening out risk indexes and corresponding risk grades of the same or similar multiple risk early-warning monitoring data, and finding out an early-warning scheme;
s4, the early warning scheme finds that the condition is met and the next step is carried out;
s5, forming an initial early warning decision scheme, entering a manual processing confirmation early warning decision scheme, forming a final early warning decision scheme after manual confirmation, and making an early warning decision. The next step is to store relevant data parameters of the final early warning decision case and the data of the whole decision process, and store the early warning case into an early warning decision case library;
And S6, after early warning decision making, sending early warning decision-related data and parameters to a cloud service system through a high-performance edge computing core control system for database storage, and sending to a local monitoring end, an APP monitoring end and a centralized control monitoring end. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
s7, the early warning scheme finds that the condition is not satisfied and goes to the next step;
s8, entering a data adaptation link, namely adapting a plurality of items of risk monitoring early warning information, extracting a plurality of items of early warning monitoring data, and sequencing the items according to importance (the early importance sequencing rule is manually set and is regularly corrected);
s9, entering the next step according to the manual experience by the adaptive early warning information data: evaluating early warning decision schemes, manually referencing a plurality of early warning sudden cases and performing rationality analysis, and simultaneously manually performing early warning decision scheme correction (scheme correction can be performed by one or more persons of different staff), wherein the early warning decision scheme correction is performed according to early warning decision scheme correction rules, and the correction rules are manually set and periodically updated;
S10, after the early warning decision scheme is evaluated, the early warning decision scheme is sent to an early warning scheme discovery step, namely the early warning scheme discovery condition is met and the next step is carried out;
s11, forming an initial early warning decision scheme, entering a manual processing confirmation early warning decision scheme, forming a final early warning decision scheme after manual confirmation, and making an early warning decision. The next step is to store relevant data parameters of the final early warning decision case and the data of the whole decision process, and store the early warning case into an early warning decision case library;
and S12, after early warning decision is made, sending early warning decision related data and parameters to a cloud service system through a high-performance edge computing core control system for database storage, and sending to a local monitoring end, an APP monitoring end and a centralized control monitoring end. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
and S13, when a certain number of early warning cases are accumulated, the manually corrected amplitude of the risk early warning decision scheme is smaller and smaller, and the risk early warning decision scheme which is made under the condition that manual intervention is not needed can ensure that the risk early warning decision scheme which is automatically made by the system is ensured to be in an acceptable safety range after being implemented, the manual intervention can be gradually reduced, so that the system automatically makes decisions, and a large amount of manual workload is reduced.
Preferably, the intelligent building risk early warning system device based on deep learning comprises a high-performance edge computing core control system, wherein terminals of the high-performance edge computing core control system are respectively connected with a local monitoring end, a cloud service system and an artificial intelligent deep learning building risk early warning big data algorithm, and terminals of the cloud service system are respectively connected with an APP monitoring end and a centralized control monitoring end.
Preferably, the terminal of the high-performance edge computing core control system is respectively connected with a low-power-consumption digital temperature sensor, a low-power-consumption digital humidity sensor, a low-power-consumption digital wind sensor, a low-power-consumption digital air pressure sensor, a low-power-consumption digital air monitoring system, a low-power-consumption air oxygen content monitoring sensor and a laser air virus monitoring system.
Preferably, the terminal of the high-performance edge computing core control system is respectively connected with a low-power consumption digital rainfall sensor, a low-power consumption digital water level sensor, a water quality toxicity monitoring system, a sediment content monitoring system, an acid rain monitoring system and a solar radiation and illumination monitoring system.
Preferably, the terminal of the high-performance edge computing core control system is respectively connected with a low-power-consumption digital stress and strain sensor, a low-power-consumption digital displacement sensor, a low-power-consumption digital structural deformation sensor, a low-power-consumption digital triaxial vibration sensor, a low-power-consumption digital magnetic flux sensor and a low-power-consumption digital smoke sensor.
Preferably, the terminal of the high-performance edge computing core control system is respectively connected with a low-power-consumption digital water pressure sensor, a low-power-consumption fire-fighting temperature monitoring sensor, a low-power-consumption digital sedimentation sensor, a low-power-consumption digital inclination sensor, a geomagnetic field monitoring system and other sensors and a low-power-consumption building soil humidity monitoring sensor.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, an artificial intelligent deep learning algorithm is applied to intelligent building risk early warning monitoring for the first time, when a certain number of early warning cases are accumulated, the manually corrected amplitude of a risk early warning decision scheme is smaller and smaller, and the risk early warning decision scheme which is made under the condition that manual intervention is not needed can ensure that the risk early warning decision scheme which is automatically made by a system is ensured to be within an acceptable safety range after being implemented, so that the manual intervention can be gradually reduced, and the system can automatically make decisions, thereby reducing a large amount of manual workload. The intelligent sensor for the cloud computing and edge computing collaborative processing is based on the embedded low-power consumption system, part of the sensors can be powered by batteries, the structure is small, the data can be transmitted by using the Internet of things in a wireless mode, and a large amount of engineering quantities such as engineering construction wiring and the like are reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a diagram of a system component framework of the present invention.
Fig. 2 is a diagram of a basic decision process of building risk early warning based on user set case learning in the present invention.
FIG. 3 is a diagram showing a basic decision process when risk early warning of multiple different categories of the present invention occurs simultaneously.
In the figure: 301. a high performance edge computing core control system; 302. a local monitoring end; 303. a cloud service system; 304. an artificial intelligent deep learning building risk early warning big data algorithm; 305. an APP monitoring end; 306. a centralized control monitoring end; 307. a low power consumption digital temperature sensor; 308. a low power consumption digital humidity sensor; 309. a low-power consumption digital wind sensor; 310. a low-power consumption digital air pressure sensor; 311. a low power consumption digital gas monitoring system; 312. a low-power consumption air oxygen content monitoring sensor; 313. a laser air virus monitoring system; 314. a low power consumption digital rainfall sensor; 315. a low power consumption digital water level sensor; 316. a water toxicity monitoring system; 317. a sediment content monitoring system; 318. an acid rain monitoring system; 319. solar radiation and illuminance monitoring systems; 320. low power digital stress and strain sensors; 321. a low-power consumption digital displacement sensor; 322. a low-power digital structure deformation sensor; 323. a low-power digital triaxial vibration sensor; 324. a low power digital magnetic flux sensor; 325. a low power digital smoke sensor; 326. a low-power digital water pressure sensor; 327. a low-power consumption fire control temperature monitoring sensor; 328. a low power consumption digital sedimentation sensor; 329. a low power digital tilt sensor; 330. a geomagnetic field monitoring system and other sensors; 331. low power consumption building soil humidity monitoring sensor.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples: as shown in fig. 1, the invention provides an intelligent building risk early warning method based on deep learning, which comprises the following steps:
s1, building risk monitoring data are collected by sensing equipment of the Internet of things, different monitoring data collected by the sensing equipment correspond to different risk coefficients, and the risk coefficients correspond to risk levels. When risk factors are correspondingly extracted after risk monitoring data are received, risk levels are correspondingly determined after the risk factors are determined, after the risk levels are determined, risk factors and the risk levels corresponding to the monitoring data are formed into early warning case retrieval data, the early warning case retrieval data are transmitted into an early warning decision case library for comparison screening, decision cases with the same risk factors and the same risk levels are screened out, the screened decision cases are determined to be current early warning decisions to form an initial early warning decision scheme, when decision cases with the same or similar data (the comparison data proximity degree is manually set according to different monitoring data types) are not found in the early warning decision case library, an initial early warning decision scheme is formed in the next step, and the initial early warning decision scheme is set and determined manually according to the risk factors and the risk levels corresponding to the monitoring data;
S2, after the initial early warning decision scheme is determined, the next step is carried out, the early warning decision scheme is revised, and the personnel are set to audit and revise the early warning decision scheme according to different risk monitoring data types and factors of the building, such as floor height, building age, geographical area and the like;
s3, after the early warning decision scheme is corrected, entering a next step of alternative early warning decision scheme, and in addition to the first early warning decision scheme, whether an alternative early warning decision scheme is needed or not is checked, if one alternative early warning decision scheme is insufficient, a plurality of alternative early warning decision schemes are set according to factors, environmental parameters and the like of the building;
s4, after forming a plurality of early warning decision schemes, the personnel evaluate the early warning decision schemes, the personnel can be one or more persons, and final early warning decision scheme determination is made;
s5, carrying out data storage on relevant data parameters of final early warning decision cases and the whole decision process, and storing the early warning cases into an early warning decision case library;
and S6, simultaneously making early warning decisions, sending early warning decision-related data and parameters to a cloud service system 303 through a high-performance edge computing core control system 301 for database storage, and sending to a local monitoring end 302, an APP monitoring end 305 and a centralized control monitoring end 306. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level.
An intelligent building risk early warning method based on deep learning comprises the following steps:
s1, when multiple building risk early warning of different categories occur simultaneously, an artificial intelligent deep learning algorithm adopts the following risk early warning decision method:
s2, receiving a plurality of different types of risk early-warning data, correspondingly extracting risk coefficients corresponding to the plurality of types of monitoring data, determining risk coefficients, correspondingly determining risk levels, after determining the risk levels, searching risk early-warning case by inputting risk coefficients corresponding to the monitoring data and risk level formation data and parameter information, transmitting the early-warning case search data into an early-warning decision case library for comparison screening, screening case data and parameters with the same risk index and risk level, and revealing the degree of building risks according to the risk index by the system;
s3, screening out risk indexes and corresponding risk grades of the same or similar multiple risk early-warning monitoring data, and finding out an early-warning scheme;
s4, the early warning scheme finds that the condition is met and the next step is carried out;
s5, forming an initial early warning decision scheme, entering a manual processing confirmation early warning decision scheme, forming a final early warning decision scheme after manual confirmation, and making an early warning decision. The next step is to store relevant data parameters of the final early warning decision case and the data of the whole decision process, and store the early warning case into an early warning decision case library;
And S6, after early warning decision is made, the early warning decision related data and parameters are sent to a cloud service system 303 through a high-performance edge computing core control system 301 to be stored in a database, and are sent to a local monitoring end 302, an APP monitoring end 305 and a centralized control monitoring end 306. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
s7, the early warning scheme finds that the condition is not satisfied and goes to the next step;
s8, entering a data adaptation link, namely adapting a plurality of items of risk monitoring early warning information, extracting a plurality of items of early warning monitoring data, and sequencing the items according to importance (the early importance sequencing rule is manually set and is regularly corrected);
s9, entering the next step according to the manual experience by the adaptive early warning information data: evaluating early warning decision schemes, manually referencing a plurality of early warning sudden cases and performing rationality analysis, and simultaneously manually performing early warning decision scheme correction (scheme correction can be performed by one or more persons of different staff), wherein the early warning decision scheme correction is performed according to early warning decision scheme correction rules, and the correction rules are manually set and periodically updated;
S10, after the early warning decision scheme is evaluated, the early warning decision scheme is sent to an early warning scheme discovery step, namely the early warning scheme discovery condition is met and the next step is carried out;
s11, forming an initial early warning decision scheme, entering a manual processing confirmation early warning decision scheme, forming a final early warning decision scheme after manual confirmation, and making an early warning decision. The next step is to store relevant data parameters of the final early warning decision case and the data of the whole decision process, and store the early warning case into an early warning decision case library;
and S12, after early warning decision is made, the early warning decision related data and parameters are sent to a cloud service system 303 through a high-performance edge computing core control system 301 to be stored in a database, and are sent to a local monitoring end 302, an APP monitoring end 305 and a centralized control monitoring end 306. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
and S13, when a certain number of early warning cases are accumulated, the manually corrected amplitude of the risk early warning decision scheme is smaller and smaller, and the risk early warning decision scheme which is made under the condition that manual intervention is not needed can ensure that the risk early warning decision scheme which is automatically made by the system is ensured to be in an acceptable safety range after being implemented, the manual intervention can be gradually reduced, so that the system automatically makes decisions, and a large amount of manual workload is reduced.
The intelligent building risk early warning system device based on deep learning comprises a high-performance edge computing core control system 301, wherein terminals of the high-performance edge computing core control system 301 are respectively connected with a local monitoring end 302, a cloud service system 303 and an artificial intelligent deep learning building risk early warning big data algorithm 304, and terminals of the cloud service system 303 are respectively connected with an APP monitoring end 305 and a centralized control monitoring end 306.
The intelligent building risk early warning system device adopts a design framework of cooperation of cloud computing and edge computing, and the cloud service system 303 mainly comprises the following functional modules: equipment management, label grouping, mirror image management, application release, edge computing end monitoring, calculation power scheduling, code warehouse, release management, user management, cluster management, safety management, disaster recovery backup and digital report form, and is responsible for application release and data synchronization; the high-performance edge computing core control system 301 mainly comprises the following functional modules: protocol management (MQTT, MODBUS, CAN, WIFI, 5G communication), device management (device discovery, device driving), access authorization, protocol driving, and is responsible for data acquisition, control output, implementation of artificial intelligent deep learning intelligent building risk early warning algorithm, and database management.
The terminals of the high-performance edge computing core control system 301 are respectively connected with a low-power consumption digital temperature sensor 307, a low-power consumption digital humidity sensor 308, a low-power consumption digital wind sensor 309, a low-power consumption digital air pressure sensor 310, a low-power consumption digital air monitoring system 311, a low-power consumption air oxygen content monitoring sensor 312 and a laser air virus monitoring system 313.
By adopting the technical scheme, the low-power consumption digital temperature sensor 307 is used for monitoring the ambient air temperature and the building surface temperature, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, the monitoring signals are converted into digital signals and sent to the core control system, the low-power consumption digital humidity sensor 308 is used for monitoring the ambient air humidity, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, the monitoring signals are converted into digital signals and sent to the core control system, the low-power consumption digital air pressure sensor 309 is used for monitoring the ambient air speed and the wind direction, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, the monitoring signals are converted into digital signals and sent to the core control system, the low-power consumption digital air pressure sensor 310 is used for monitoring the ambient air pressure, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, and the monitoring signals are converted into digital signals and sent to the core control system, the low power consumption digital gas monitoring system 311 is used for monitoring the concentration of gases such as environmental carbon dioxide, sulfur dioxide, ozone, hydrogen sulfide, dust particles, VOC and the like, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, and the monitoring signals are converted into digital signals and sent to the core control system, the low power consumption air oxygen content monitoring sensor 312 is used for sealing the oxygen content monitoring in a building, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, and the monitoring signals are converted into digital signals and sent to the core control system, the laser air virus monitoring system 313 is used for monitoring the concentration of molecules containing virus proteins in the air (monitoring epidemic viruses), the system adopts an ultra-low power consumption signal acquisition and control chip of the Internet of things and an embedded control system, and converts monitoring signals into digital signals to be sent to a core control system.
The terminals of the high-performance edge computing core control system 301 are respectively connected with a low-power consumption digital rainfall sensor 314, a low-power consumption digital water level sensor 315, a water quality toxicity monitoring system 316, a sediment content monitoring system 317, an acid rain monitoring system 318 and a solar radiation and illumination monitoring system 319.
By adopting the above technical scheme, the low-power consumption digital rainfall sensor 314 is used for rainfall monitoring, the ultra-low power consumption signal acquisition and control chip of the internet of things and the embedded control system are adopted, and the monitoring signals are converted into digital signals and sent to the core control system, the low-power consumption digital water level sensor 315 is used for monitoring the ground surface water level of the bottom layer of the building, the ultra-low power consumption signal acquisition and control chip of the internet of things and the embedded control system are adopted, and the monitoring signals are converted into digital signals and sent to the core control system, the water quality toxicity monitoring system 316 is used for overall toxicity monitoring of heavy metals, toxic agents, nerve agents, pesticide preparations and other substances in water, the monitoring signals are converted into digital signals and sent to the core control system, the sediment content monitoring system 317 is used for environmental ground surface and sediment content monitoring, and the monitoring signals are converted into digital signals and sent to the core control system, the acid rain monitoring system 318 is used for monitoring parameters such as pH, ORP, conductivity, turbidity, dissolved oxygen, chlorophyll, blue-green algae, ammonia nitrogen, nitrate nitrogen, fluoride ions and chloride ions and the like, and the monitoring signals are converted into digital signals to the core control system, the solar radiation and the illumination system 319 is used for solar radiation, illumination intensity and total illumination time period and total illumination monitoring are sent to the core control system.
The terminals of the high-performance edge computing core control system 301 are respectively connected with a low-power-consumption digital stress sensor 320, a low-power-consumption digital displacement sensor 321, a low-power-consumption digital structural deformation sensor 322, a low-power-consumption digital triaxial vibration sensor 323, a low-power-consumption digital magnetic flux sensor 324 and a low-power-consumption digital smoke sensor 325.
By adopting the technical scheme, the low-power consumption digital stress and strain sensor 320 is used for monitoring stress and strain of a building structure, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, and monitoring signals are converted into digital signals and sent to the core control system, the low-power consumption digital displacement sensor 321 is used for monitoring displacement of the building, the ultra-low power consumption signal acquisition and control chip of the Internet of things and the embedded control system are adopted, and monitoring signals are converted into digital signals and sent to the core control system, the ultra-low power consumption digital three-axis vibration sensor 323 is used for monitoring three-dimensional vibration of the building, the ultra-low power consumption digital magnetic flux sensor 324 is used for monitoring of a guy cable, a ground anchor, a tie rod and a cable tension member, the ultra-low power consumption signal is adopted for monitoring the core control system, the ultra-low power consumption digital magnetic flux sensor 324 is used for cable, the ultra-low power consumption signal acquisition and the embedded control system is adopted for monitoring the building structure deformation of the building, the monitoring signals are converted into digital signals and sent to the embedded control system, the monitoring signals are converted into digital signals and sent to the core control system, the low-power consumption digital three-axis vibration sensor 323 is adopted for monitoring the three-dimensional vibration of the building, the ultra-low power consumption signal acquisition and the embedded control system is converted into digital signals, the digital signals are sent to the core control system is sent to the ultra-low power consumption signal of the core control system, and the low power consumption digital signal is sent to the ultra-low power consumption digital control system.
The terminals of the high-performance edge computing core control system 301 are respectively connected with a low-power-consumption digital water pressure sensor 326, a low-power-consumption fire-fighting temperature monitoring sensor 327, a low-power-consumption digital sedimentation sensor 328, a low-power-consumption digital inclination sensor 329, a sensor 330 such as a geomagnetic field monitoring system and the like and a low-power-consumption building soil humidity monitoring sensor 331.
By adopting the technical scheme, the low-power-consumption digital water pressure sensor 326 is used for monitoring the water pressure of the building fire-fighting facility, the ultra-low-power-consumption signal acquisition and control chip and the embedded control system of the Internet of things are adopted, and the monitoring signal is converted into a digital signal and sent to the core control system, the low-power-consumption fire-fighting temperature monitoring sensor 327 is used for monitoring the building fire smoke, the ultra-low-power-consumption signal acquisition and control chip and the embedded control system of the Internet of things are adopted, and the monitoring signal is converted into a digital signal and sent to the core control system, the low-power-consumption digital tilt sensor 329 is used for monitoring the building tilt, the ultra-low-power-consumption signal acquisition and control chip and the embedded control system of the Internet of things are adopted, and the monitoring signal is converted into a digital signal and sent to the core control system, the sensor 330 such as the geomagnetic field monitoring system is used for monitoring the building geomagnetic field and the monitoring is converted into a digital signal and sent to the core control system.
Working principle: building risk monitoring data 101 (refer to fig. 2) are collected by the sensors of the internet of things, the building risk monitoring data are sent, different monitoring data collected by the sensors correspond to different risk coefficients, and the risk coefficients are in corresponding risk levels. When the risk monitoring data is received, the risk coefficient corresponding to 102 is extracted, the risk level analysis is corresponding to 103, the risk level is correspondingly determined after the risk coefficient is determined, the early warning case retrieval is performed 104 after the risk level is determined, the risk coefficient corresponding to the monitoring data and the risk level are formed into 104 early warning case retrieval data, the early warning case retrieval data are transmitted to 112 early warning decision case library for comparison screening, decision cases with the same risk coefficient and the same risk level are screened out, the screened decision cases are determined to be current early warning decisions, and 105 initial early warning decision schemes are formed;
when the early warning risk data does not find the same or decision cases with data approaching (the comparison data approaching degree is manually set according to different monitoring data types) in the early warning decision case library, entering a next step to initially form 105 an initial early warning decision scheme, and setting and determining the initial early warning decision scheme manually according to risk coefficients and risk grades corresponding to the monitoring data;
After the initial early warning decision scheme is determined, the next step is carried out, 106 the early warning decision scheme is revised, and a setting staff formulates 107 an early warning decision scheme revision rule according to different risk monitoring data types and factors of the building, such as floor height, building age, geographical area and the like, and reviews and revises the early warning decision scheme;
after the early warning decision scheme is corrected, the next step 108 is carried out to select an early warning decision scheme, whether the early warning decision scheme needs to be selected or not is judged, and if the early warning decision scheme is insufficient, a plurality of alternative early warning decision schemes are set according to factors, environmental parameters and the like of the building;
after forming a plurality of early warning decision schemes, entering 109 early warning decision scheme evaluation, evaluating the early warning decision scheme by staff, wherein the evaluation staff can be 1 person or more persons, and making 110 final early warning decision scheme determination;
the next step is to store 111 early warning decision cases, store the relevant data parameters of the final early warning decision cases and the whole decision process data, and store 112 the early warning cases into an early warning decision case library;
and meanwhile, making 113 early warning decisions, sending relevant data and parameters of the early warning decisions to a cloud service system for end database storage, and sending to a local monitoring end, a user APP monitoring end and a centralized monitoring end. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
When multiple building risk early warning of different categories occur simultaneously, the artificial intelligence deep learning algorithm adopts the following risk early warning decision method (refer to fig. 3):
the method comprises the steps of sending 201 multiple building risk monitoring data, receiving multiple risk early warning data of different types, extracting 202 corresponding risk coefficients, correspondingly extracting risk coefficients corresponding to the multiple types of monitoring data, analyzing 203 corresponding risk levels, correspondingly determining risk levels after determining the risk coefficients, inputting 206 multiple risk early warning information after determining the risk levels, inputting 205 risk early warning case retrieval data of risk coefficient and risk level formation data and parameter information corresponding to the monitoring data, and transmitting 204 early warning case retrieval data to an early warning decision case library for comparison screening, and screening case data and parameters with the same risk coefficients and risk levels;
screening risk coefficients and corresponding risk grades of the same or similar multiple risk early-warning monitoring data, and finding 207 early-warning schemes;
207, the early warning scheme finds that the condition is met and yes, and then the next step is entered;
214 forms an initial early warning decision scheme, and enters 215 a manual processing confirmation early warning decision scheme, forms 216 a final early warning decision scheme after manual confirmation, and makes 219 early warning decisions. Storing the early warning case in the next step 217, storing relevant data parameters of the final early warning decision case and data of the whole decision process, and storing the early warning case in a 218 early warning decision case library;
After making the early warning decision, the relevant data and parameters of the early warning decision are sent to a cloud service system for terminal database storage, and are sent to a local monitoring terminal, a user APP monitoring terminal and a centralized monitoring terminal. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
207, the early warning scheme finds that the condition is not satisfied, and enters the next step;
208 adaptation, namely entering a data adaptation link, and 209 adaptation of multiple items of early warning information, namely adapting multiple items of risk monitoring early warning information, extracting multiple items of early warning monitoring data, and sequencing the items according to importance (the early importance sequencing rule is manually set and periodically corrected);
the adaptive early warning information data enters the next step according to the manual experience: and (2) evaluating the early warning decision scheme, wherein the early warning decision scheme is evaluated by manually referring to the previous 211 multiple early warning sudden case analysis references and reasonably selecting, and simultaneously, manually making 212 early warning decision scheme correction (scheme correction can be carried out by 1 or more persons of different staff), wherein the early warning decision scheme correction is carried out according to 213 early warning decision scheme correction rules, and the correction rules are manually set and periodically updated.
After the early warning decision scheme is evaluated, the early warning decision scheme is sent to 207 an early warning scheme discovery step, namely the early warning scheme discovery condition is met, and the next step is entered:
214 forms an initial early warning decision scheme, and enters 215 a manual processing confirmation early warning decision scheme, forms 216 a final early warning decision scheme after manual confirmation, and makes 219 early warning decisions. Storing the early warning case in the next step 217, storing relevant data parameters of the final early warning decision case and data of the whole decision process, and storing the early warning case in a 218 early warning decision case library;
after making the early warning decision, the relevant data and parameters of the early warning decision are sent to a cloud service system for terminal database storage, and are sent to a local monitoring terminal, a user APP monitoring terminal and a centralized monitoring terminal. Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
when a certain number (5000, 50000, 100000 and 100000) of early warning cases are accumulated, the manually corrected amplitude of the risk early warning decision scheme is smaller and smaller, the risk early warning decision scheme which is made under the condition that manual intervention is not needed can ensure that the risk early warning decision scheme which is automatically made by the system is ensured to be within an acceptable safety range after being implemented, the manual intervention can be gradually reduced, even the manual intervention is not needed, and the system can automatically make decisions, so that a large amount of manual workload is reduced;
Meanwhile, the artificial intelligent deep learning algorithm is applied to intelligent building risk early warning monitoring for the first time, when a certain number of early warning cases are accumulated, the manually corrected amplitude of the risk early warning decision scheme is smaller and smaller, the risk early warning decision scheme which is made under the condition that manual intervention is not needed can ensure that the risk early warning decision scheme which is automatically made by a system is ensured to be within an acceptable safety range after being implemented, the manual intervention can be gradually reduced, and the system can automatically make decisions, so that a large amount of manual workload is reduced. The intelligent sensor for the cloud computing and edge computing collaborative processing is based on the embedded low-power consumption system, part of the sensors can be powered by batteries, the structure is small, the data can be transmitted by using the Internet of things in a wireless mode, and a large amount of engineering quantities such as engineering construction wiring and the like are reduced.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. An intelligent building risk early warning method based on deep learning is characterized by comprising the following steps:
s1, building risk monitoring data are collected by sensing equipment of the Internet of things, different monitoring data collected by the sensing equipment correspond to different risk coefficients, and the risk coefficients correspond to risk levels. When risk factors are correspondingly extracted after risk monitoring data are received, risk levels are correspondingly determined after the risk factors are determined, after the risk levels are determined, risk factors and the risk levels corresponding to the monitoring data are formed into early warning case retrieval data, the early warning case retrieval data are transmitted into an early warning decision case library for comparison screening, decision cases with the same risk factors and the same risk levels are screened out, the screened decision cases are determined to be current early warning decisions to form an initial early warning decision scheme, when decision cases with the same or similar data (the comparison data proximity degree is manually set according to different monitoring data types) are not found in the early warning decision case library, an initial early warning decision scheme is formed in the next step, and the initial early warning decision scheme is set and determined manually according to the risk factors and the risk levels corresponding to the monitoring data;
S2, after the initial early warning decision scheme is determined, the next step is carried out, the early warning decision scheme is revised, and the personnel are set to audit and revise the early warning decision scheme according to different risk monitoring data types and factors of the building, such as floor height, building age, geographical area and the like;
s3, after the early warning decision scheme is corrected, entering a next step of alternative early warning decision scheme, and in addition to the first early warning decision scheme, whether an alternative early warning decision scheme is needed or not is checked, if one alternative early warning decision scheme is insufficient, a plurality of alternative early warning decision schemes are set according to factors, environmental parameters and the like of the building;
s4, after forming a plurality of early warning decision schemes, the personnel evaluate the early warning decision schemes, the personnel can be one or more persons, and final early warning decision scheme determination is made;
s5, carrying out data storage on relevant data parameters of final early warning decision cases and the whole decision process, and storing the early warning cases into an early warning decision case library;
s6, early warning decision is made at the same time, and early warning decision related data and parameters are sent to a cloud service system (303) through a high-performance edge computing core control system (301) to be stored in a database and sent to a local monitoring end (302), an APP monitoring end (305) and a centralized control monitoring end (306). Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level.
2. An intelligent building risk early warning method based on deep learning is characterized by comprising the following steps:
s1, when multiple building risk early warning of different categories occur simultaneously, an artificial intelligent deep learning algorithm adopts the following risk early warning decision method:
s2, receiving a plurality of different types of risk early-warning data, correspondingly extracting risk coefficients corresponding to the plurality of types of monitoring data, determining risk coefficients, correspondingly determining risk levels, after determining the risk levels, searching risk early-warning case by inputting risk coefficients corresponding to the monitoring data and risk level formation data and parameter information, transmitting the early-warning case search data into an early-warning decision case library for comparison screening, screening case data and parameters with the same risk index and risk level, and revealing the degree of building risks according to the risk index by the system;
s3, screening out risk indexes and corresponding risk grades of the same or similar multiple risk early-warning monitoring data, and finding out an early-warning scheme;
s4, the early warning scheme finds that the condition is met and the next step is carried out;
s5, forming an initial early warning decision scheme, entering a manual processing confirmation early warning decision scheme, forming a final early warning decision scheme after manual confirmation, and making an early warning decision. The next step is to store relevant data parameters of the final early warning decision case and the data of the whole decision process, and store the early warning case into an early warning decision case library;
And S6, after early warning decision is made, the early warning decision related data and parameters are sent to a cloud service system (303) through a high-performance edge computing core control system (301) to be stored in a database and sent to a local monitoring end (302), an APP monitoring end (305) and a centralized control monitoring end (306). Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
s7, the early warning scheme finds that the condition is not satisfied and goes to the next step;
s8, entering a data adaptation link, namely adapting a plurality of items of risk monitoring early warning information, extracting a plurality of items of early warning monitoring data, and sequencing the items according to importance (the early importance sequencing rule is manually set and is regularly corrected);
s9, entering the next step according to the manual experience by the adaptive early warning information data: evaluating early warning decision schemes, manually referencing a plurality of early warning sudden cases and performing rationality analysis, and simultaneously manually performing early warning decision scheme correction (scheme correction can be performed by one or more persons of different staff), wherein the early warning decision scheme correction is performed according to early warning decision scheme correction rules, and the correction rules are manually set and periodically updated;
S10, after the early warning decision scheme is evaluated, the early warning decision scheme is sent to an early warning scheme discovery step, namely the early warning scheme discovery condition is met and the next step is carried out;
s11, forming an initial early warning decision scheme, entering a manual processing confirmation early warning decision scheme, forming a final early warning decision scheme after manual confirmation, and making an early warning decision. The next step is to store relevant data parameters of the final early warning decision case and the data of the whole decision process, and store the early warning case into an early warning decision case library;
and S12, after early warning decision is made, early warning decision related data and parameters are sent to a cloud service system (303) through a high-performance edge computing core control system (301) to be stored in a database and sent to a local monitoring end (302), an APP monitoring end (305) and a centralized control monitoring end (306). Building management personnel or engineering operation maintenance personnel take corresponding protection and control measures according to the building risk early warning level;
and S13, when a certain number of early warning cases are accumulated, the manually corrected amplitude of the risk early warning decision scheme is smaller and smaller, and the risk early warning decision scheme which is made under the condition that manual intervention is not needed can ensure that the risk early warning decision scheme which is automatically made by the system is ensured to be in an acceptable safety range after being implemented, the manual intervention can be gradually reduced, so that the system automatically makes decisions, and a large amount of manual workload is reduced.
3. An intelligent building risk early warning system device based on deep learning, includes high performance edge calculation core control system (301), its characterized in that: the intelligent deep learning building risk early warning system is characterized in that a terminal of the high-performance edge computing core control system (301) is connected with a local monitoring end (302), a cloud service system (303) and an artificial intelligent deep learning building risk early warning big data algorithm (304) respectively, and a terminal of the cloud service system (303) is connected with an APP monitoring end (305) and a centralized control monitoring end (306) respectively.
4. A deep learning-based intelligent building risk early warning system device according to claim 3, wherein the terminals of the high-performance edge computing core control system (301) are respectively connected with a low-power digital temperature sensor (307), a low-power digital humidity sensor (308), a low-power digital wind sensor (309), a low-power digital air pressure sensor (310), a low-power digital gas monitoring system (311), a low-power air oxygen content monitoring sensor (312) and a laser air virus monitoring system (313).
5. A deep learning-based intelligent building risk early warning system device according to claim 3, wherein the terminals of the high-performance edge computing core control system (301) are respectively connected with a low-power digital rainfall sensor (314), a low-power digital water level sensor (315), a water quality toxicity monitoring system (316), a sediment content monitoring system (317), an acid rain monitoring system (318) and a solar radiation and illumination monitoring system (319).
6. A deep learning-based intelligent building risk early warning system device according to claim 3, characterized in that the terminals of the high-performance edge computing core control system (301) are respectively connected with a low-power digital stress and strain sensor (320), a low-power digital displacement sensor (321), a low-power digital structural deformation sensor (322), a low-power digital triaxial vibration sensor (323), a low-power digital magnetic flux sensor (324) and a low-power digital smoke sensor (325).
7. A deep learning-based intelligent building risk early warning system device according to claim 3, wherein the terminals of the high-performance edge computing core control system (301) are respectively connected with a low-power digital water pressure sensor (326), a low-power fire-fighting temperature monitoring sensor (327), a low-power digital sedimentation sensor (328), a low-power digital inclination sensor (329), a geomagnetic field monitoring system and other sensors (330) and a low-power building soil humidity monitoring sensor (331).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310424359.0A CN116489042A (en) | 2023-04-20 | 2023-04-20 | Intelligent building risk early warning method and system device based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310424359.0A CN116489042A (en) | 2023-04-20 | 2023-04-20 | Intelligent building risk early warning method and system device based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116489042A true CN116489042A (en) | 2023-07-25 |
Family
ID=87217199
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310424359.0A Pending CN116489042A (en) | 2023-04-20 | 2023-04-20 | Intelligent building risk early warning method and system device based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116489042A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117973705A (en) * | 2024-04-02 | 2024-05-03 | 山东省建筑科学研究院有限公司 | Data processing and analyzing system and method for intelligent building site monitoring system |
-
2023
- 2023-04-20 CN CN202310424359.0A patent/CN116489042A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117973705A (en) * | 2024-04-02 | 2024-05-03 | 山东省建筑科学研究院有限公司 | Data processing and analyzing system and method for intelligent building site monitoring system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113804598B (en) | Construction environment monitoring system and monitoring method based on big data | |
CN110081930A (en) | A kind of land, sea and air integration ecological environmental monitoring system | |
CN114650512A (en) | Intelligent city ecological environment monitoring system based on digital twins | |
CN105824280A (en) | IoT (Internet of Things) environment protective monitoring system | |
CN113709598B (en) | Carbon emission monitoring and management system based on Internet of things | |
CN112785458A (en) | Intelligent management and maintenance system for bridge health big data | |
CN116489042A (en) | Intelligent building risk early warning method and system device based on deep learning | |
CN106297252B (en) | A kind of industrial park air pollution surveillance system | |
CN203204793U (en) | River water quality monitoring and alarm system | |
CN102262144A (en) | Remote environment monitoring system | |
CN209545749U (en) | A kind of land, sea and air integration ecological environmental monitoring system | |
CN116539829A (en) | Water quality monitoring sensing analysis method | |
CN203053480U (en) | Bridge safety monitoring and pre-warning system based on wireless sensor network | |
CN108303132A (en) | A kind of monitoring system for air pollution | |
CN202133421U (en) | Monitoring system of poisonous and harmful gas in chemical zone | |
CN101958057A (en) | Monitoring method for protecting submarine cable from being damaged by transient ships | |
CN114118847A (en) | Chemical industry park danger source on-line monitoring platform | |
CN113970627A (en) | Water quality monitoring and early warning method and system | |
CN116307673A (en) | Underground pipe network interaction risk early warning system for urban lifeline | |
CN201780647U (en) | Remote monitoring alarm system for forest fire protection | |
CN108806201A (en) | A kind of air quality method for early warning and device | |
CN117611414A (en) | Urban lifeline sensing and safe operation system | |
CN102200456B (en) | System for monitoring toxic and harmful gases in chemical industry park | |
Haris et al. | Design and Development of IoT Based Weather and Air Quality Monitoring Station | |
CN111815106A (en) | Power grid emergency method based on multi-source information |
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 |