CN117975696A - Linkage type fire alarm control system and method - Google Patents
Linkage type fire alarm control system and method Download PDFInfo
- Publication number
- CN117975696A CN117975696A CN202410361567.5A CN202410361567A CN117975696A CN 117975696 A CN117975696 A CN 117975696A CN 202410361567 A CN202410361567 A CN 202410361567A CN 117975696 A CN117975696 A CN 117975696A
- Authority
- CN
- China
- Prior art keywords
- resource allocation
- fire
- module
- fire alarm
- alarm control
- 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 32
- 238000013468 resource allocation Methods 0.000 claims abstract description 79
- 230000004927 fusion Effects 0.000 claims abstract description 33
- 230000007613 environmental effect Effects 0.000 claims abstract description 31
- 239000013598 vector Substances 0.000 claims abstract description 27
- 239000011159 matrix material Substances 0.000 claims abstract description 21
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 230000000739 chaotic effect Effects 0.000 claims abstract description 11
- 230000005540 biological transmission Effects 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 7
- 230000008713 feedback mechanism Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 9
- 230000001419 dependent effect Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 6
- 239000000779 smoke Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Fire Alarms (AREA)
Abstract
The invention relates to the technical field of alarm devices, in particular to a linkage type fire alarm control system and method. Comprising the following steps: acquiring original data, and carrying out heterogeneous data coding on the original data; fusing vectors after heterogeneous data encoding by adopting a concept of a chaotic dynamic system, and further preliminarily predicting the occurrence probability of fire; constructing a resource allocation matrix, and designing an optimization objective function of the resource allocation matrix to obtain an optimized resource allocation scheme; and further obtaining final fire prediction probability based on the environment robustness enhancement fusion strategy, and judging whether to trigger fire alarm based on the final fire prediction probability. The problem that the accuracy of fire early detection in the prior art is insufficient and is often dependent on a single data source is solved; the resource scheduling lacks dynamic optimization capability; and the adaptability to environmental changes is not strong, the influence of environmental factors on fire detection is not fully considered, false alarm or missing alarm is easy to occur, and the stability and reliability of the system are affected.
Description
Technical Field
The invention relates to the technical field of alarm devices, in particular to a linkage type fire alarm control system and method.
Background
In modern society, with the acceleration of the urban process and the increase of high-density living areas, fire safety becomes an important problem in public safety management. Once a fire occurs, it often causes significant casualties and property loss. Therefore, how to effectively prevent and control the fire, discover the fire as soon as possible and respond in time becomes an important point of research and technical development.
Although the existing fire alarm and control system can deal with fire accidents to a certain extent, the existing fire alarm and control system still has the defects of insufficient accuracy, inflexible resource scheduling, weak adaptability to environmental changes and the like. These drawbacks limit the effectiveness of the system in practical applications and do not meet the ever-increasing fire safety management needs. Especially when facing complex environmental conditions and changeable fire development conditions, the prior art is often difficult to provide timely and accurate fire early warning, and also difficult to realize effective scheduling and utilization of rescue resources, not to mention dynamically adjusting strategies according to environmental changes so as to reduce false alarm rate.
Chinese patent application number: CN202311177447.1, publication date: 2023.11.10 discloses a control method for fire alarm, an alarm and a storage medium. The method comprises the following steps: acquiring a use scene of the alarm; setting different alarm thresholds according to the use scenes, wherein the different use scenes correspond to the different alarm thresholds; acquiring environmental parameters detected in a use scene; and when the detected environmental parameter reaches an alarm threshold value, sending out an alarm prompt. The embodiment of the application can reduce the probability of fire misjudgment of the alarm.
However, the above technology has at least the following technical problems: the prior art has insufficient accuracy in early detection of fire, and often depends on a single data source, such as temperature or smoke concentration, so that early fire signs cannot be effectively identified, and the risk of fire spread is increased; the resource scheduling lacks dynamic optimization capability, so that rescue resources can not be effectively allocated to the most needed places in time, and the rescue efficiency and effect are reduced; the adaptability to environmental changes is not strong, the influence of environmental factors such as temperature fluctuation, humidity change and the like on fire detection is not fully considered, false alarm or missing alarm is easy to occur, and the stability and reliability of the system are affected.
Disclosure of Invention
The invention provides a linkage type fire alarm control system and method, which solve the problems that the accuracy of early detection of fire in the prior art is insufficient, and the early fire signs cannot be effectively identified due to the fact that single data sources such as temperature or smoke concentration are often relied on, so that the risk of fire spread is increased; the resource scheduling lacks dynamic optimization capability, so that rescue resources can not be effectively allocated to the most needed places in time, and the rescue efficiency and effect are reduced; the adaptability to environmental changes is not strong, the influence of environmental factors such as temperature fluctuation, humidity change and the like on fire detection is not fully considered, and the technical problems of false alarm or missing alarm and influence on the stability and reliability of the system are easily caused. The method realizes the improvement of the accuracy of early detection of fire, the dynamic optimized allocation of rescue resources and the high adaptability to different environmental conditions, and remarkably improves the efficiency, the intelligent level and the reliability of a fire alarm and control system.
The invention provides a linkage type fire alarm control system and a method, which concretely comprise the following technical scheme:
a linked fire alarm control system comprising the following:
the system comprises a data acquisition module, a coding module, a dynamic fusion module, a preliminary prediction module, a resource allocation module, an environment enhancement prediction module and a fire alarm control module;
The data acquisition module is used for acquiring original data from the record of the actual operation of the fire alarm control system; the data acquisition module is connected with the coding module in a data transmission mode;
the coding module is used for carrying out heterogeneous data coding on the original data by utilizing a Gaussian sine function mixed model; the coding module is connected with the dynamic fusion module in a data transmission mode;
The dynamic fusion module is used for fusing vectors after heterogeneous data encoding by adopting the concept of a chaotic dynamic system to obtain fused feature vectors; the dynamic fusion module is connected with the preliminary prediction module in a data transmission mode;
the primary prediction module is used for inputting the fused feature vectors into a neural network and primarily predicting the occurrence probability of fire; the preliminary prediction module is connected with the resource allocation module and the environment enhancement prediction module in a data transmission mode;
The resource allocation module is used for constructing a resource allocation matrix, and determining an optimal resource allocation strategy by calculating the optimized weight corresponding to each resource and the optimized resource allocation scheme; the resource allocation module is connected with the environment enhancement prediction module in a data transmission mode;
the environment enhancement prediction module is used for combining the resource optimization weight and the optimized resource allocation scheme to design an environment robustness enhancement fusion strategy; the environment enhancement prediction module is connected with the fire alarm control module in a data transmission mode;
the fire alarm control module is used for performing overall mobilization control on fire alarms.
A linkage type fire alarm control method comprises the following steps:
S1, acquiring original data, and carrying out heterogeneous data coding on the original data; fusing vectors after heterogeneous data encoding by adopting a concept of a chaotic dynamic system, and primarily predicting fire occurrence probability based on the fused feature vectors;
s2, constructing a resource allocation matrix, and designing an optimization objective function of the resource allocation matrix to obtain an optimized resource allocation scheme; and further obtaining final fire prediction probability based on the environment robustness enhancement fusion strategy, and judging whether to trigger fire alarm based on the final fire prediction probability.
Preferably, the S1 specifically includes:
and introducing a Gaussian sine function mixed model in the process of carrying out heterogeneous data coding on the original data to obtain vectors after heterogeneous data coding.
Preferably, the S1 further includes:
and sending the fused feature vectors into a neural network for fire early warning judgment, and carrying out self-adjustment on the neural network through a double-layer feedback mechanism to obtain the primary predicted fire occurrence probability.
Preferably, the S2 specifically includes:
constructing resource demand prediction based on a prediction model, and adjusting a resource allocation strategy according to a prediction result and a current resource state; the core of the resource allocation strategy is to construct a resource allocation matrix.
Preferably, the S2 further includes:
The resource allocation matrix describes the relation between the resources and the tasks through a mathematical model, and finds an optimal resource allocation scheme by utilizing an optimization algorithm, and dynamically adjusts the resource allocation.
Preferably, the S2 further includes:
The resource allocation matrix determines an optimal resource allocation strategy by calculating the optimized weight corresponding to each resource and the optimized resource allocation scheme; the optimized weight is dynamically adjusted according to the current fire occurrence probability and the total amount of available rescue resources.
Preferably, the S2 further includes:
and combining the resource optimization weight and the optimized resource allocation scheme, and designing an environment robustness enhancement fusion strategy.
Preferably, the S2 further includes:
When the final fire prediction probability exceeds a preset fire probability threshold value, the linkage type fire alarm control system automatically triggers a fire alarm and notifies a fire department; meanwhile, the rescue resources are mobilized and scheduled according to the optimal resource allocation scheme; during rescue actions, the linkage type fire alarm system continuously monitors environmental conditions, and rescue is adjusted in real time by utilizing an environmental robustness enhancement fusion strategy to form a dynamic feedback loop; after fire control, field evaluation and data analysis are performed to update training materials and emergency plans.
The technical scheme of the invention has the beneficial effects that:
1. By introducing a multisource fusion sensing network and combining temperature, smoke concentration and video monitoring data, the system can effectively improve the accuracy of early detection of fire; particularly, the application of heterogeneous data coding and chaotic dynamic fusion enhances the identification capability of early signs of weak fires, and is beneficial to realizing more timely fire early warning;
2. The system dynamically adjusts and optimizes the allocation of rescue resources according to the fire early warning probability and the current resource condition; not only improves the utilization efficiency of rescue resources, but also ensures that key resources can be rapidly allocated to the most needed place under emergency conditions, thereby improving the effect of rescue actions;
3. The environment robustness enhancement fusion strategy effectively reduces false alarm rate caused by environment change by considering the influence of environment factors on fire prediction, enhances the stability and reliability of the system under different environment conditions, and ensures that the accuracy of fire alarm is not interfered by external environment; through a double-layer feedback mechanism of the neural network and an optimization algorithm in the resource allocation process, the system can be self-adjusted and optimized according to data and feedback in actual operation, so that the system is continuously improved, and the system is suitable for complex and changeable fire situations and environmental conditions.
Drawings
FIG. 1 is a block diagram of a coordinated fire alarm control system according to one embodiment of the present invention;
Fig. 2 is a flowchart of a linkage type fire alarm control method according to an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, 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.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a linkage type fire alarm control system and method provided by the invention with reference to the accompanying drawings.
Referring to FIG. 1, a block diagram of a linked fire alarm control system according to one embodiment of the present invention is shown, the system comprising:
the system comprises a data acquisition module, a coding module, a dynamic fusion module, a preliminary prediction module, a resource allocation module, an environment enhancement prediction module and a fire alarm control module;
The data acquisition module is used for acquiring original data from the record of the actual operation of the fire alarm control system; the data acquisition module is connected with the coding module in a data transmission mode;
the coding module is used for carrying out heterogeneous data coding on the original data by utilizing a Gaussian sine function mixed model; the coding module is connected with the dynamic fusion module in a data transmission mode;
The dynamic fusion module is used for fusing vectors after heterogeneous data encoding by adopting the concept of a chaotic dynamic system to obtain fused feature vectors; the dynamic fusion module is connected with the preliminary prediction module in a data transmission mode;
the primary prediction module is used for inputting the fused feature vectors into a designed neural network, and primarily predicting the fire occurrence probability by adopting a double-layer feedback mechanism; the preliminary prediction module is connected with the resource allocation module and the environment enhancement prediction module in a data transmission mode;
The resource allocation module is used for constructing a resource allocation matrix, and determining an optimal resource allocation strategy by calculating an optimized weight corresponding to each resource and an optimized resource allocation scheme; the resource allocation module is connected with the environment enhancement prediction module in a data transmission mode;
The environment enhancement prediction module is used for considering the influence of environmental factors on fire probability prediction, reducing false alarm rate, and designing an environment robustness enhancement fusion strategy by combining resource optimization weights and an optimized resource allocation scheme; the environment enhancement prediction module is connected with the fire alarm control module in a data transmission mode;
the fire alarm control module is used for performing overall mobilization control on fire alarms.
Referring to fig. 2, a flow chart of a linkage type fire alarm control method according to an embodiment of the present invention is shown, and the method includes the following steps:
S1, acquiring original data, and carrying out heterogeneous data coding on the original data; fusing vectors after heterogeneous data encoding by adopting a concept of a chaotic dynamic system, and primarily predicting fire occurrence probability based on the fused feature vectors;
The data acquisition module acquires original data from the record of the actual operation of the fire alarm control system, including temperature change, smoke concentration, video monitoring images and the like. According to the method, heterogeneous data encoding is carried out on original data from different sources through an encoding module, so that not only can the data be normalized, but also the representation diversity of the data is increased, and encoding vectors in a unified format are formed.
The heterogeneous data encoding process utilizes a Gaussian sine function hybrid model to not only perform standardized processing on original data, but also introduce periodic variation characteristics to enhance the capturing capability of periodic and abnormal variations hidden in the data, which may indicate the occurrence of a fire. For each data type, the following encoding function is used for conversion:
,
Wherein, Representing the raw data; /(I)Is a coded vector representing processed data, which may be a temperature changeSmoke concentration/>Video surveillance image/>Any one of the following; /(I)And/>Respectively refer to/>Is used for data normalization; /(I)And/>The frequency and phase parameters of the sine wave are used for enhancing the expression of the periodic characteristics of the data; /(I)Is a constant for logarithmic correction.
The dynamic fusion module fuses the coded vectors by adopting the concept of a chaotic dynamic system, and the sensitivity and response speed of the model to early weak signals of fire are enhanced by considering the weight distribution of each data source through the dynamic property of the chaotic system. The feature vector after chaos fusion is sent to a neural network for fire early warning judgment, and the neural network carries out self-adjustment through a double-layer feedback mechanism, so that the early warning accuracy is optimized. Based on the Lorentz attractor model, dynamic fusion of different data source characteristics is realized:
,
Wherein, Representing the fused feature vector; /(I)And/>Is a parameter of the chaotic system and is used for regulating and controlling the dynamic property and the stability of the fusion process; /(I)Representing the element-wise product of the vectors emphasizes the interactions between the different data sources.
The primary prediction module fuses the feature vectorsThe method is input into a designed neural network, adopts a double-layer feedback mechanism, and aims to improve the prediction accuracy of the fire occurrence probability, and preliminarily predicts the fire occurrence probability, wherein the specific implementation formula is as follows:
,
Wherein, The fire occurrence probability is preliminarily predicted; /(I)And/>Is a model parameter for adjusting the feedback intensity; Representing a loss function; /(I) The gradient of the loss relative to the fusion characteristic is calculated, and the self-adjustment of the model is realized.
S2, constructing a resource allocation matrix, and designing an optimization objective function of the resource allocation matrix to obtain an optimized resource allocation scheme; and further obtaining final fire prediction probability based on the environment robustness enhancement fusion strategy, and judging whether to trigger fire alarm based on the final fire prediction probability.
When a fire disaster occurs, available rescue resources are required to be dynamically optimized and scheduled according to the actual situation and the development trend of the fire disaster. By analyzing historical fire data and current fire conditions, a resource demand prediction based on a prediction model is constructed, and a resource allocation strategy is adjusted according to a prediction result and a current resource state.
The core of the resource allocation strategy is to construct a resource allocation matrix, describe the relation between the resources and the tasks through a mathematical model, and find the optimal resource allocation scheme by using an optimization algorithm. The resource allocation matrix not only considers the availability of resources and the emergency of tasks, but also introduces comprehensive evaluation indexes for the resource allocation efficiency and rescue effect. By dynamically adjusting the resource allocation, the key resources can be timely and effectively allocated to the most needed place in the fire disaster coping process, so that the rescue effect is maximized.
The resource allocation module constructs a resource allocation matrix for dynamically optimizing the allocation of rescue resourcesBy calculating the optimization weight/>, corresponding to each resourceAnd optimized resource allocation scheme/>To determine an optimal resource allocation policy. Optimizing weights/>Based on preliminary prediction of probability of fire occurrence/>And the total amount of available rescue resources. The calculation formula is as follows:
,
Wherein, The fire probability threshold is preset and is used for judging the emergency degree of the fire. The optimization weight formula converts the fire occurrence probability into a resource-optimized adjustment factor so as to ensure that the priority and the strength of resource allocation can be reasonably adjusted under different fire emergency degrees. Optimized resource allocation scheme/>Is calculated by the following optimization target formula:
,
,
,
Wherein, Representing resource allocation matrix/>Is an optimized objective function of/>Represents the/>Seed resource allocation to the/>The number of individual tasks; /(I),/>,/>And/>The parameters of the formula weight are adjusted to balance the influence of different factors; /(I)Represents the/>Seed resources and/>The adaptation degree of each task considers the difference of different resources on the utility of different tasks; /(I)Is a constant; Represents the/> Total amount of seed resources. The resource allocation optimization problem aims at finding a resource allocation scheme/>, which maximizes the overall rescue efficiencyWhile meeting the constraints of total amount of resources and non-negative allocation.
In order to adapt to fire detection under different environmental conditions, the false alarm rate is reduced by considering the influence of environmental factors on fire probability prediction, and an environmental robustness enhancement fusion strategy is designed by combining resource optimization weights and an optimized resource allocation scheme by an environmental enhancement prediction module, wherein the specific formula is as follows:
,
Wherein, The fire disaster prediction probability is obtained after the environmental factors are integrated; /(I)Represents the/>Numerical value of individual environmental factor,/>Is/>Weight parameters corresponding to the environmental factors; /(I)To adjust the parameters, for balancing the fire probability with the influence of environmental factors,And/>The final fire prediction probability adjustment is directly affected, the effective fusion among the fire occurrence probability, the resource allocation scheme and the environmental factors is ensured, and the adaptability and the flexibility of the whole linkage type fire alarm control system to the fire are improved.
The fire alarm control module carries out full-scale mobilization control on fire alarm: fire prediction probability after integrating environmental factorsWhen the fire probability threshold exceeds the preset fire probability threshold, the linkage type fire alarm control system automatically triggers fire alarm, including sound alarm, visual alarm signal and the like, and notifies the fire department. At the same time, rescue resources, such as firefighters and firefighting vehicles, are quickly mobilized and scheduled according to an optimal resource allocation scheme. During rescue actions, the linkage type fire alarm control system continuously monitors environmental conditions such as wind speed, temperature and the like, and utilizes an environmental robustness enhancement fusion strategy to adjust rescue in real time, so that a dynamic feedback loop is formed to cope with environmental changes and unforeseen challenges. After fire control, field evaluation and data analysis are carried out, training materials and emergency plans are updated, and the overall fire response capability is improved.
In summary, a linkage type fire alarm control system and method are completed.
The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (9)
1. A linked fire alarm control system, comprising:
the system comprises a data acquisition module, a coding module, a dynamic fusion module, a preliminary prediction module, a resource allocation module, an environment enhancement prediction module and a fire alarm control module;
The data acquisition module is used for acquiring original data from the record of the actual operation of the fire alarm control system; the data acquisition module is connected with the coding module in a data transmission mode;
the coding module is used for carrying out heterogeneous data coding on the original data by utilizing a Gaussian sine function mixed model; the coding module is connected with the dynamic fusion module in a data transmission mode;
The dynamic fusion module is used for fusing vectors after heterogeneous data encoding by adopting the concept of a chaotic dynamic system to obtain fused feature vectors; the dynamic fusion module is connected with the preliminary prediction module in a data transmission mode;
the primary prediction module is used for inputting the fused feature vectors into a neural network and primarily predicting the occurrence probability of fire; the preliminary prediction module is connected with the resource allocation module and the environment enhancement prediction module in a data transmission mode;
The resource allocation module is used for constructing a resource allocation matrix, and determining an optimal resource allocation strategy by calculating the optimized weight corresponding to each resource and the optimized resource allocation scheme; the resource allocation module is connected with the environment enhancement prediction module in a data transmission mode;
the environment enhancement prediction module is used for combining the resource optimization weight and the optimized resource allocation scheme to design an environment robustness enhancement fusion strategy; the environment enhancement prediction module is connected with the fire alarm control module in a data transmission mode;
the fire alarm control module is used for performing overall mobilization control on fire alarms.
2. The linkage type fire alarm control method is characterized by comprising the following steps of:
S1, acquiring original data, and carrying out heterogeneous data coding on the original data; fusing vectors after heterogeneous data encoding by adopting a concept of a chaotic dynamic system, and primarily predicting fire occurrence probability based on the fused feature vectors;
s2, constructing a resource allocation matrix, and designing an optimization objective function of the resource allocation matrix to obtain an optimized resource allocation scheme; and further obtaining final fire prediction probability based on the environment robustness enhancement fusion strategy, and judging whether to trigger fire alarm based on the final fire prediction probability.
3. The linkage type fire alarm control method according to claim 2, wherein the step S1 specifically comprises:
and introducing a Gaussian sine function mixed model in the process of carrying out heterogeneous data coding on the original data to obtain vectors after heterogeneous data coding.
4. The linked fire alarm control method according to claim 2, wherein S1 further comprises:
and sending the fused feature vectors into a neural network for fire early warning judgment, and carrying out self-adjustment on the neural network through a double-layer feedback mechanism to obtain the primary predicted fire occurrence probability.
5. The linkage type fire alarm control method according to claim 2, wherein the S2 specifically comprises:
constructing resource demand prediction based on a prediction model, and adjusting a resource allocation strategy according to a prediction result and a current resource state; the core of the resource allocation strategy is to construct a resource allocation matrix.
6. The linked fire alarm control method according to claim 5, wherein S2 further comprises:
The resource allocation matrix describes the relation between the resources and the tasks through a mathematical model, and finds an optimal resource allocation scheme by utilizing an optimization algorithm, and dynamically adjusts the resource allocation.
7. The linked fire alarm control method according to claim 2, wherein S2 further comprises:
The resource allocation matrix determines an optimal resource allocation strategy by calculating the optimized weight corresponding to each resource and the optimized resource allocation scheme; the optimized weight is dynamically adjusted according to the current fire occurrence probability and the total amount of available rescue resources.
8. The linked fire alarm control method according to claim 7, wherein S2 further comprises:
and combining the resource optimization weight and the optimized resource allocation scheme, and designing an environment robustness enhancement fusion strategy.
9. The linked fire alarm control method according to claim 2, wherein S2 further comprises:
When the final fire prediction probability exceeds a preset fire probability threshold value, the linkage type fire alarm control system automatically triggers a fire alarm and notifies a fire department; meanwhile, the rescue resources are mobilized and scheduled according to the optimal resource allocation scheme; during rescue actions, the linkage type fire alarm system continuously monitors environmental conditions, and rescue is adjusted in real time by utilizing an environmental robustness enhancement fusion strategy to form a dynamic feedback loop; after fire control, field evaluation and data analysis are performed to update training materials and emergency plans.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410361567.5A CN117975696A (en) | 2024-03-28 | 2024-03-28 | Linkage type fire alarm control system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410361567.5A CN117975696A (en) | 2024-03-28 | 2024-03-28 | Linkage type fire alarm control system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117975696A true CN117975696A (en) | 2024-05-03 |
Family
ID=90853725
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410361567.5A Pending CN117975696A (en) | 2024-03-28 | 2024-03-28 | Linkage type fire alarm control system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117975696A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140280190A1 (en) * | 2013-03-13 | 2014-09-18 | Salesforce.Com, Inc. | Systems, methods, and apparatuses for implementing data upload, processing, and predictive query api exposure |
CN113378464A (en) * | 2021-06-09 | 2021-09-10 | 国网天津市电力公司营销服务中心 | Method and device for predicting service life of electric energy meter field tester |
TW202141359A (en) * | 2020-04-28 | 2021-11-01 | 樹德科技大學 | Ambulance and fire event prediction system based on neural network and method thereof |
CN116523002A (en) * | 2023-05-22 | 2023-08-01 | 之江实验室 | Method and system for predicting dynamic graph generation countermeasure network track of multi-source heterogeneous data |
DE202023104113U1 (en) * | 2023-07-24 | 2023-08-10 | Sudhakara Sundeep Menon | Integrated geospatial decision-making system for real-time fire detection and emergency management |
CN116675277A (en) * | 2023-08-03 | 2023-09-01 | 济南山源环保科技有限公司 | Control method of low-energy-consumption wastewater concentration system based on Internet of things |
CN116887212A (en) * | 2023-09-07 | 2023-10-13 | 北京航天常兴科技发展股份有限公司 | Fire situation information processing and transmitting method based on wireless communication network |
CN117450635A (en) * | 2023-12-21 | 2024-01-26 | 深圳市祥帆电子科技有限公司 | Fresh air system control method based on big data analysis |
CN117533356A (en) * | 2024-01-09 | 2024-02-09 | 北京市北太机电设备工贸有限公司 | Intelligent driving assistance system and method |
-
2024
- 2024-03-28 CN CN202410361567.5A patent/CN117975696A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140280190A1 (en) * | 2013-03-13 | 2014-09-18 | Salesforce.Com, Inc. | Systems, methods, and apparatuses for implementing data upload, processing, and predictive query api exposure |
TW202141359A (en) * | 2020-04-28 | 2021-11-01 | 樹德科技大學 | Ambulance and fire event prediction system based on neural network and method thereof |
CN113378464A (en) * | 2021-06-09 | 2021-09-10 | 国网天津市电力公司营销服务中心 | Method and device for predicting service life of electric energy meter field tester |
CN116523002A (en) * | 2023-05-22 | 2023-08-01 | 之江实验室 | Method and system for predicting dynamic graph generation countermeasure network track of multi-source heterogeneous data |
DE202023104113U1 (en) * | 2023-07-24 | 2023-08-10 | Sudhakara Sundeep Menon | Integrated geospatial decision-making system for real-time fire detection and emergency management |
CN116675277A (en) * | 2023-08-03 | 2023-09-01 | 济南山源环保科技有限公司 | Control method of low-energy-consumption wastewater concentration system based on Internet of things |
CN116887212A (en) * | 2023-09-07 | 2023-10-13 | 北京航天常兴科技发展股份有限公司 | Fire situation information processing and transmitting method based on wireless communication network |
CN117450635A (en) * | 2023-12-21 | 2024-01-26 | 深圳市祥帆电子科技有限公司 | Fresh air system control method based on big data analysis |
CN117533356A (en) * | 2024-01-09 | 2024-02-09 | 北京市北太机电设备工贸有限公司 | Intelligent driving assistance system and method |
Non-Patent Citations (3)
Title |
---|
王贝伦: "《机器学习》", vol. 1, 30 November 2021, 东南大学出版社 * |
袁惠群等: "《混沌及其控制基础》", vol. 1, 30 September 2016, 东北大学出版社 * |
谭博等: ""基于正弦高斯混合模型的磁目标通用快速检测"", 《仪器仪表学报》, vol. 40, no. 2, 28 February 2019 (2019-02-28) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
CN107911653A (en) | The module of intelligent video monitoring in institute, system, method and storage medium | |
CN113673459B (en) | Video-based production and construction site safety inspection method, system and equipment | |
CN116777713B (en) | Intelligent park safety management method and system based on data analysis | |
CN110661861A (en) | Wisdom logistics business system | |
KR102340644B1 (en) | AI Type Total Security And Monitoring Service System | |
CN109657003A (en) | A method of hardware data is directly accessed big data platform | |
KR101377029B1 (en) | The apparatus and method of monitoring cctv with control moudule | |
CN111223263A (en) | Full-automatic comprehensive fire early warning response system | |
CN110135564A (en) | Coal mine gas sensing data method for detecting abnormality based on edge calculations | |
CN113642403B (en) | Crowd abnormal intelligent safety detection system based on edge calculation | |
CN116761049B (en) | Household intelligent security monitoring method and system | |
CN115457446A (en) | Abnormal behavior supervision system based on video analysis | |
CN114979585A (en) | Filling station intelligent safety system based on edge calculation | |
CN117975696A (en) | Linkage type fire alarm control system and method | |
CN117197726B (en) | Important personnel accurate management and control system and method | |
CN117612060A (en) | Video early warning system, method, equipment and medium based on artificial intelligent detection | |
CN116645587A (en) | Image recognition model generation method, image recognition method, system and chip | |
KR20230167549A (en) | The apparatus and method of monitoring cctv with control moudule | |
CN112907885B (en) | Distributed centralized household image fire alarm system and method based on SCNN | |
KR101088153B1 (en) | Combo type video surveillance system and method thereof | |
CN112969057A (en) | 5G MEC shunted electric power system personnel action automatic identification system | |
Zhu et al. | Design and Implementation of Elevator Cloud Monitoring System | |
CN117389937B (en) | Calculation method of obstacle avoidance data of vehicle, computer and readable storage medium | |
CN117499272B (en) | Intelligent operation and maintenance cloud platform control method and control system thereof |
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 |