CN114880935A - Tunnel fire advanced prediction method - Google Patents
Tunnel fire advanced prediction method Download PDFInfo
- Publication number
- CN114880935A CN114880935A CN202210522409.4A CN202210522409A CN114880935A CN 114880935 A CN114880935 A CN 114880935A CN 202210522409 A CN202210522409 A CN 202210522409A CN 114880935 A CN114880935 A CN 114880935A
- Authority
- CN
- China
- Prior art keywords
- fire
- data
- prediction
- model
- tunnel
- 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 44
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000012795 verification Methods 0.000 claims abstract description 24
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 26
- 230000004913 activation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 12
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention discloses a method for predicting a fire disaster in a tunnel in advance, which comprises the following steps: establishing a fire model, and acquiring fire data under different working conditions according to the fire model; processing fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions; establishing a fire prediction model, and dividing fire data under different working conditions in a fire database into a training set, a verification set and a test set so as to train the fire prediction model according to the training set and the verification set to obtain a trained fire prediction model; inputting the test set into a trained fire prediction module to obtain prediction data; establishing a data assimilation model, and performing data fusion on the prediction data and the real-time observation data according to the data assimilation model so as to correct the prediction data and obtain the optimal state estimation of the real-time fire; therefore, the method can be used for predicting the tunnel fire in advance, so that the real-time performance and the accuracy of the prediction of the tunnel fire are improved.
Description
Technical Field
The present invention relates to the field of fire detection technologies, and in particular, to a method for predicting a tunnel fire in advance, a computer-readable storage medium, and a computer device.
Background
In recent years, with the rapid development of cities in China, the number and complexity of tunnels are continuously increased, and tunnel fires are different from general industrial and civil building fires due to the unique space characteristics, traffic transportation modes and the like of the tunnels; tunnel fires are affected by factors such as vehicles, vehicle-mounted goods, tunnel types, traffic conditions in the case of fires and the like, so that the mobility of vehicles can cause the ignition point to change along with the driving of the vehicles; simultaneously, along with tunnel structure's richness gradually, the increase of bifurcation tunnel quantity leads to tunnel conflagration flue gas to stretch the condition and control means all more complicated to personnel's safe evacuation and the rescue degree of difficulty of putting out a fire can be higher than ordinary ground building when making the tunnel take place the conflagration.
The tunnel fire prediction can not only provide technical support for fire scene risk assessment and fire suppression, but also has great significance for emergency rescue, but the existing tunnel fire prediction method usually performs prediction according to a fire image, so that the prediction effect is poor.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, an object of the present invention is to provide a method for predicting a tunnel fire in advance, which can predict a tunnel fire in advance, thereby improving the real-time performance and accuracy of the prediction.
A second object of the invention is to propose a computer-readable storage medium.
A third object of the invention is to propose a computer device.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for predicting a tunnel fire in advance, including establishing a fire model, and obtaining fire data under different working conditions according to the fire model; processing the fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions; establishing a fire prediction model, and dividing fire data under different working conditions in the fire database into a training set, a verification set and a test set so as to train the fire prediction model according to the training set and the verification set to obtain a trained fire prediction model; inputting the test set into the trained fire prediction module to obtain prediction data; and establishing a data assimilation model, and performing data fusion on the prediction data and the real-time observation data according to the data assimilation model so as to correct the prediction data and obtain the optimal state estimation of the real-time fire.
According to the method for predicting the tunnel fire in advance, disclosed by the embodiment of the invention, a fire model is established at first, and fire data under different working conditions are obtained according to the fire model; then processing fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions; then establishing a fire prediction model, and dividing fire data under different working conditions in a fire database into a training set, a verification set and a test set so as to train the fire prediction model according to the training set and the verification set to obtain a trained fire prediction model; inputting the test set into a trained fire prediction module to obtain prediction data; finally, a data assimilation model is established, and data fusion is carried out on the prediction data and the real-time observation data according to the data assimilation model so as to correct the prediction data and obtain the optimal state estimation of the real-time fire; therefore, the method can predict the fire in the tunnel in advance, thereby improving the real-time performance and accuracy of prediction.
In addition, the method for predicting the fire disaster in the tunnel according to the above embodiment of the present invention may further have the following additional technical features:
optionally, establishing a fire model, and obtaining fire data under different working conditions according to the fire model, includes: building a full-size tunnel simulation model in numerical simulation software according to a tunnel drawing; the method comprises the steps of presetting a plurality of different fire working conditions, and simulating the fire occurrence and development conditions under various fire working conditions to obtain corresponding fire data, wherein the fire working conditions comprise fire source positions, fire source power and longitudinal wind speed, and the fire data comprise fire temperature, CO concentration and visibility.
Optionally, the processing the fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions includes: classifying the fire temperature, CO concentration and visibility under different working conditions obtained based on the numerical simulation software, and establishing a fire database according to the classified fire temperature, CO concentration and visibility under different working conditions.
Optionally, establishing a fire prediction model, comprising: selecting a machine learning model based on a fire database; determining the number of layers and the number of neurons of the neural network of the selected machine learning model based on a fire database, and selecting an appropriate activation function and a loss function so as to construct the fire prediction model, wherein the activation function can be Sigmoid, Tanh or ReLU, and the loss function can be root mean square error.
Optionally, dividing the fire data under different working conditions in the fire database into a training set, a verification set and a test set, including: performing shuffle operation on the fire data to break up the sequence; and selecting different proportions to divide the disordered fire data into a training set, a verification set and a test set.
Optionally, training the fire prediction model according to the training set and the verification set to obtain a trained fire prediction model, including: presetting the learning rate of a fire prediction model, the training turn of a data set and the number of samples of each training; inputting the fire source position, the fire source power and the longitudinal wind speed in the training set into the fire prediction model to obtain tunnel temperatures at different positions at any time; and carrying out accuracy analysis on the fire prediction model according to the decision coefficient and the relative error by adopting the verification set.
Optionally, the fire prediction model is analyzed for accuracy according to the following formula:
wherein R is 2 Representing the coefficient of determination, RE representing the relative error, R 2 The value range is [0,1 ]]The larger the value is, the better the model prediction effect is; y is i The values of the samples are represented and,representation model pair sample y i The predicted value of (a) is determined,represents the average value of samples, and m represents the number of samples.
Optionally, establishing a data assimilation model, and performing data fusion on the prediction data and the real-time observation data according to the data assimilation model, so as to correct the prediction data to obtain an optimal state estimation of the real-time fire, including: constructing a data assimilation model; presetting an initial value of a data assimilation algorithm, and performing data fusion on the predicted data and real-time observation data obtained by a sensor by adopting the data assimilation algorithm to obtain corrected predicted data; and iteratively updating the prediction data until the optimal state estimation of the fire in real time is obtained.
To achieve the above object, a second embodiment of the present invention provides a computer-readable storage medium having a tunnel fire advance prediction program stored thereon, wherein the tunnel fire advance prediction program, when executed by a processor, implements the tunnel fire advance prediction method as described above.
According to the computer-readable storage medium of the embodiment of the invention, the tunnel fire advance prediction program is stored, so that the processor can realize the tunnel fire advance prediction method when executing the tunnel fire advance prediction program, thereby the advance rapid prediction of the tunnel fire can be carried out, and the real-time performance and the accuracy of the prediction can be improved.
In order to achieve the above object, a third embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method for predicting a tunnel fire ahead as described above.
According to the computer equipment provided by the embodiment of the invention, the tunnel fire advance prediction program is stored through the memory, so that the processor realizes the tunnel fire advance prediction method when executing the tunnel fire advance prediction program, and therefore, the tunnel fire can be quickly predicted in advance, and the real-time performance and the accuracy of prediction are improved.
Drawings
FIG. 1 is a flow chart illustrating a method for predicting a fire in a tunnel according to an embodiment of the present invention;
FIG. 2 is a diagram of tunnel fires under different operating conditions simulated by numerical simulation software according to one embodiment of the present invention;
FIG. 3 is a diagram of a neural network prediction model, according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of a fire prediction model training and prediction process according to one embodiment of the present invention;
fig. 5 is a schematic diagram illustrating a real-time tunnel fire prediction process according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a flowchart illustrating a method for predicting a tunnel fire in advance according to an embodiment of the present invention, as shown in fig. 1, the method for predicting a tunnel fire in advance includes the following steps:
and S101, establishing a fire model, and acquiring fire data under different working conditions according to the fire model.
As an embodiment, a full-size tunnel simulation model is built in numerical simulation software according to a tunnel drawing; the method comprises the steps of presetting a plurality of different fire working conditions, simulating fire occurrence and development conditions under various fire working conditions to obtain corresponding fire data, wherein the fire working conditions comprise fire source positions, fire source power and longitudinal wind speeds, and the fire data comprise fire temperature, CO concentration and visibility.
That is, firstly, building a full-size tunnel simulation model in numerical simulation software according to a tunnel drawing based on a planned or built tunnel, wherein the numerical simulation software comprises but is not limited to regional simulation or field simulation software such as FDS (floor planning system), Fluent and CFAST (computational fluid dynamics); then presetting more fire working conditions such as 50-500 groups of fire working conditions in advance, and simulating the fire occurrence and development conditions under various working conditions such as different fire source positions, fire source power, fire time, longitudinal wind speed and the like; and finally, simulating the changes of fire parameters such as real-time temperature, CO concentration and visibility of the tunnel fire under different working conditions so as to obtain corresponding fire data under different working conditions, wherein tunnel fire graphs under different working conditions based on numerical simulation software simulation are shown in FIG. 2.
And S102, processing the fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions.
As an embodiment, the fire temperature, the CO concentration and the visibility under different working conditions obtained based on the numerical simulation software are classified, and a fire database is established according to the classified fire temperature, the CO concentration and the visibility under different working conditions.
It should be noted that a specific fire model is established based on a planned or constructed tunnel, so as to create a fire database, so that the tunnel data is more real, complete and sufficient.
S103, building a fire prediction model, and dividing fire data under different working conditions in a fire database into a training set, a verification set and a test set so as to train the fire prediction model according to the training set and the verification set to obtain the trained fire prediction model.
As an example, a fire prediction model is built, including: selecting a machine learning model based on a fire database; and determining the number of layers and the number of neurons of the neural network of the selected machine learning model based on a fire database, and selecting a proper activation function and a proper loss function so as to construct a fire prediction model, wherein the activation function can be Sigmoid, Tanh or ReLU, and the loss function can be root mean square error.
That is, based on the tunnel fire database, a machine learning model is selected, the number of layers and the number of neurons of the selected neural network are determined, a proper activation function and a proper loss function are selected, and a neural network model is constructed, wherein common activation functions generally comprise Sigmoid, hyperbolic tangent activation functions Tanh, ReLU and the like,
the expression of the activation function Sigmoid is:
the expression of the hyperbolic tangent activation function Tanh is:
the expression of the activation function ReLU is:
the loss function can be Root Mean Square Error (RMSE) in the training process, and the function expression is as follows:
in the formula, y i For the sample values, the values of the samples,representation model pair sample y i The predicted value of (a) is determined,is the average value of the samples, and m is the number of the samples.
It should be noted that the machine learning model may be a neural network model such as a BP network, a CNN, a TCNN, or a CAE, and the present invention is not limited thereto.
As an example, the fire data under different conditions in the fire database are divided into a training set, a verification set and a test set, including: performing shuffle operation on the fire data to disorder the sequence; and selecting different proportions to divide the disordered fire data into a training set, a verification set and a test set.
Before division, a shuffle operation is performed on the fire data set first to disorder the sequence, so that the randomness of the training data is increased, and based on the scrambled fire data set, different proportions are selected according to actual needs to divide the scrambled fire data into a training set, a verification set and a test set.
As an example, training a fire prediction model according to a training set and a validation set to obtain a trained fire prediction model includes: presetting the learning rate of a fire prediction model, the training turn of a data set and the number of samples of each training; inputting the fire source position, the fire source power and the longitudinal wind speed in the training set into a fire prediction model to obtain tunnel temperatures at different positions at any time; and carrying out accuracy analysis on the fire prediction model by adopting a verification set according to the decision coefficient and the relative error.
As an example, the fire prediction model is analyzed for accuracy according to the following formula:
wherein R is 2 Representing the coefficient of determination, RE representing the relative error, R 2 The value range is [0,1 ]]The larger the value is, the better the model prediction effect is; y is i The values of the samples are represented and,representation model pair sample y i The predicted value of (a) is determined,represents the average value of samples, and m represents the number of samples.
That is, before training a fire prediction model, a learning rate of the model, a round of training of the entire data set, and the number of samples trained at each time are set, variables such as a fire location, a heat release rate, and a longitudinal wind speed in the training set are input to the fire prediction model to quickly obtain tunnel temperatures at different locations at any time, and finally a dimensionless index, a Coefficient of Determination (R) is used 2 And quantifying the accuracy of the fire prediction model by two different parameters of Relative Error (RE), and evaluating the quality of the fire prediction model from multiple angles, namely performing accuracy analysis on the fire prediction model through a verification set.
And S104, inputting the test set into a trained fire prediction module to obtain prediction data.
That is, as shown in fig. 3 to 4, the variables such as the location of the fire, the heat release rate, the ignition time, and the longitudinal wind speed, which are collected in the test, are input into the fire prediction model, so that the tunnel temperatures at different locations at any time can be rapidly obtained, and the prediction result can be obtained.
It should be noted that the neural network-based tunnel fire prediction model can acquire information such as temperature, CO concentration, visibility and the like at any time and at any position in a tunnel within millisecond time, has strong real-time performance, accuracy and generalization capability, can meet the real-time fire prediction requirement, and can be applied to fire development trend prediction under emergency conditions.
And S105, establishing a data assimilation model, and performing data fusion on the prediction data and the real-time observation data according to the data assimilation model so as to correct the prediction data and obtain the optimal state estimation of the real-time fire.
As one example, a data assimilation model is built; presetting an initial value of a data assimilation algorithm, and performing data fusion on the predicted data and real-time observation data obtained by a sensor by adopting the data assimilation algorithm to obtain corrected predicted data; and iteratively updating the prediction data until the optimal state estimation of the fire in real time is obtained.
That is, as shown in fig. 5, a data assimilation model is constructed based on a fire database, a data assimilation algorithm includes, but is not limited to, kalman filtering, particle filtering, histogram filtering, and the like, and an initial value of a data assimilation algorithm system is set; inputting variables such as the position of the fire, the heat release rate, the tunnel wind speed and the like into a tunnel fire rapid prediction model, and rapidly obtaining tunnel temperatures at different positions at any time; inputting observation data obtained by a sensor or other means and prediction model data into a data assimilation algorithm for data fusion to obtain optimal estimation of temperature; and (4) iteratively updating data assimilation parameters, updating parameters such as tunnel heat release rate, fire source position and wind speed, bringing the parameters into a new prediction model, and entering the next round of data assimilation process.
As a specific embodiment, the initial time temperature of the data assimilation model is set as the system initial value, when the next time T1 is reached, a tunnel temperature state vector T1 is obtained through prediction according to a trained temperature prediction model, a new kalman gain K1 is calculated, and meanwhile, the next time temperature state T2 is predicted; repeating the iteration in such a loop, and continuously correcting and updating a Kalman filtering formula; the iteration times of each working condition are set automatically; for example, each operating condition may be set to iterate 50 times, and the predicted result may be displayed after the iteration is finished.
It should be noted that the data assimilation model can effectively fuse the real-time sensor data of the fire scene and the machine learning model according to the actual fire scene change, correct the prediction deviation in time, has high algorithm speed and high precision, can meet the actual requirements of the fire scene, and obtains the optimal state estimation of the complex fire.
In summary, according to the method for predicting the tunnel fire in advance of the embodiment of the invention, a fire model is established first, and fire data under different working conditions are obtained according to the fire model; then processing fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions; then establishing a fire prediction model, and dividing fire data under different working conditions in a fire database into a training set, a verification set and a test set so as to train the fire prediction model according to the training set and the verification set to obtain a trained fire prediction model; inputting the test set into a trained fire prediction module to obtain prediction data; finally, a data assimilation model is established, and data fusion is carried out on the prediction data and the real-time observation data according to the data assimilation model so as to correct the prediction data and obtain the optimal state estimation of the real-time fire; therefore, the method can predict the fire in the tunnel in advance, thereby improving the real-time performance and accuracy of prediction.
In order to achieve the above embodiments, an embodiment of the present invention proposes a computer-readable storage medium having stored thereon a tunnel fire advance prediction program that, when executed by a processor, implements the tunnel fire advance prediction method as described above.
According to the computer-readable storage medium of the embodiment of the invention, the tunnel fire advance prediction program is stored, so that the processor can realize the tunnel fire advance prediction method when executing the tunnel fire advance prediction program, thereby the advance rapid prediction of the tunnel fire can be carried out, and the real-time performance and the accuracy of the prediction can be improved.
In order to implement the above embodiments, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the method for predicting a tunnel fire ahead is implemented as described above.
According to the computer equipment provided by the embodiment of the invention, the tunnel fire advance prediction program is stored through the memory, so that the processor realizes the tunnel fire advance prediction method when executing the tunnel fire advance prediction program, and therefore, the tunnel fire can be quickly predicted in advance, and the real-time performance and the accuracy of prediction are improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood according to specific situations by those of ordinary skill in the art.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above should not be understood to necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method for predicting fire in a tunnel in advance is characterized by comprising the following steps:
establishing a fire model, and acquiring fire data under different working conditions according to the fire model;
processing the fire data under different working conditions, and establishing a fire database according to the processed fire data under different working conditions;
establishing a fire prediction model, and dividing fire data under different working conditions in the fire database into a training set, a verification set and a test set so as to train the fire prediction model according to the training set and the verification set to obtain a trained fire prediction model;
inputting the test set into the trained fire prediction module to obtain prediction data;
and establishing a data assimilation model, and performing data fusion on the prediction data and the real-time observation data according to the data assimilation model so as to correct the prediction data and obtain the optimal state estimation of the real-time fire.
2. The method for predicting the fire disaster in the tunnel according to claim 1, wherein the step of establishing a fire disaster model and obtaining fire disaster data under different working conditions according to the fire disaster model comprises the following steps:
building a full-size tunnel simulation model in numerical simulation software according to a tunnel drawing;
the method comprises the steps of presetting a plurality of different fire working conditions, and simulating the fire occurrence and development conditions under various fire working conditions to obtain corresponding fire data, wherein the fire working conditions comprise fire source positions, fire source power and longitudinal wind speed, and the fire data comprise fire temperature, CO concentration and visibility.
3. The method for advanced prediction of tunnel fire as claimed in claim 2, wherein the processing of the fire data under different working conditions and the building of the fire database according to the processed fire data under different working conditions comprises:
classifying the fire temperature, CO concentration and visibility under different working conditions obtained based on the numerical simulation software, and establishing a fire database according to the classified fire temperature, CO concentration and visibility under different working conditions.
4. The method of claim 1, wherein the building of the fire prediction model comprises:
selecting a machine learning model based on a fire database;
determining the number of layers and the number of neurons of the neural network of the selected machine learning model based on a fire database, and selecting an appropriate activation function and a loss function so as to construct the fire prediction model, wherein the activation function can be Sigmoid, Tanh or ReLU, and the loss function can be root mean square error.
5. The method of claim 1, wherein the dividing of the fire data under different conditions in the fire database into a training set, a verification set and a test set comprises:
performing shuffle operation on the fire data to disorder the sequence;
and selecting different proportions to divide the disordered fire data into a training set, a verification set and a test set.
6. The method of claim 2, wherein training the fire prediction model according to the training set and the validation set to obtain a trained fire prediction model comprises:
presetting the learning rate of a fire prediction model, the training turn of a data set and the number of samples of each training;
inputting the fire source position, the fire source power and the longitudinal wind speed in the training set into the fire prediction model to obtain tunnel temperatures at different positions at any time;
and carrying out accuracy analysis on the fire prediction model according to the decision coefficient and the relative error by adopting the verification set.
7. The method of claim 6, wherein the accuracy of the fire prediction model is analyzed according to the following formula:
wherein R is 2 Representing the coefficient of determination, RE representing the relative error, R 2 The value range is [0,1 ]]The larger the value is, the better the model prediction effect is; y is i The values of the samples are represented and,representation model pair sample y i ToThe value of the measured value is measured,represents the average value of samples, and m represents the number of samples.
8. The method of claim 1, wherein the step of establishing a data assimilation model and performing data fusion between the prediction data and the real-time observation data according to the data assimilation model to modify the prediction data to obtain an optimal state estimation of the real-time fire comprises:
constructing a data assimilation model;
presetting an initial value of a data assimilation algorithm, and performing data fusion on the predicted data and real-time observation data obtained by a sensor by adopting the data assimilation algorithm to obtain corrected predicted data;
and iteratively updating the prediction data until the optimal state estimation of the fire in real time is obtained.
9. A computer-readable storage medium, having stored thereon a tunnel fire advance prediction program which, when executed by a processor, implements the tunnel fire advance prediction method according to any one of claims 1 to 8.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the method of tunnel fire advance prediction according to any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210522409.4A CN114880935A (en) | 2022-05-13 | 2022-05-13 | Tunnel fire advanced prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210522409.4A CN114880935A (en) | 2022-05-13 | 2022-05-13 | Tunnel fire advanced prediction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114880935A true CN114880935A (en) | 2022-08-09 |
Family
ID=82674881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210522409.4A Pending CN114880935A (en) | 2022-05-13 | 2022-05-13 | Tunnel fire advanced prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114880935A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116882268A (en) * | 2023-06-15 | 2023-10-13 | 重庆大学 | Data-driven tunnel fire smoke development prediction method and intelligent control system |
CN117291293A (en) * | 2023-08-29 | 2023-12-26 | 西南交通大学 | Tunnel fire scene disaster perception and situation development prediction method |
CN117371836A (en) * | 2023-09-28 | 2024-01-09 | 长沙理工大学 | Highway tunnel fire rescue capability assessment method and system based on regional visual angle |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101581940A (en) * | 2009-06-05 | 2009-11-18 | 西安电子科技大学 | Tunnel event detection method based on integrated learning time sequence prediction |
CN109356652A (en) * | 2018-10-12 | 2019-02-19 | 深圳市翌日科技有限公司 | Adaptive fire grading forewarning system method and system under a kind of mine |
CN111368771A (en) * | 2020-03-11 | 2020-07-03 | 四川路桥建设集团交通工程有限公司 | Tunnel fire early warning method and device based on image processing, computer equipment and computer readable storage medium |
CN113990018A (en) * | 2021-09-15 | 2022-01-28 | 上海腾盛智能安全科技股份有限公司 | Safety risk prediction system |
CN114021501A (en) * | 2021-11-09 | 2022-02-08 | 华东理工大学 | Fire temperature field reconstruction method, system, computer equipment, medium and terminal |
CN114187728A (en) * | 2021-12-09 | 2022-03-15 | 香港理工大学 | Fire monitoring method and system based on artificial intelligence and digital twin technology |
US20220108622A1 (en) * | 2020-10-07 | 2022-04-07 | Lghorizon, Llc | Predictive building emergency training and guidance system |
-
2022
- 2022-05-13 CN CN202210522409.4A patent/CN114880935A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101581940A (en) * | 2009-06-05 | 2009-11-18 | 西安电子科技大学 | Tunnel event detection method based on integrated learning time sequence prediction |
CN109356652A (en) * | 2018-10-12 | 2019-02-19 | 深圳市翌日科技有限公司 | Adaptive fire grading forewarning system method and system under a kind of mine |
CN111368771A (en) * | 2020-03-11 | 2020-07-03 | 四川路桥建设集团交通工程有限公司 | Tunnel fire early warning method and device based on image processing, computer equipment and computer readable storage medium |
US20220108622A1 (en) * | 2020-10-07 | 2022-04-07 | Lghorizon, Llc | Predictive building emergency training and guidance system |
CN113990018A (en) * | 2021-09-15 | 2022-01-28 | 上海腾盛智能安全科技股份有限公司 | Safety risk prediction system |
CN114021501A (en) * | 2021-11-09 | 2022-02-08 | 华东理工大学 | Fire temperature field reconstruction method, system, computer equipment, medium and terminal |
CN114187728A (en) * | 2021-12-09 | 2022-03-15 | 香港理工大学 | Fire monitoring method and system based on artificial intelligence and digital twin technology |
Non-Patent Citations (3)
Title |
---|
CHAO GUO ET AL.: "Study on real-time heat release rate inversion for dynamic reconstruction and visualization of tunnel fire scenarios" * |
XIQIANG WU ET AL.: "A real-time forecast of tunnel fire based on numerical database and artificial intelligence" * |
何苗: "隧道火灾烟气发展进程预报方法研究" * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116882268A (en) * | 2023-06-15 | 2023-10-13 | 重庆大学 | Data-driven tunnel fire smoke development prediction method and intelligent control system |
CN116882268B (en) * | 2023-06-15 | 2024-02-06 | 重庆大学 | Data-driven tunnel fire smoke development prediction method and intelligent control system |
CN117291293A (en) * | 2023-08-29 | 2023-12-26 | 西南交通大学 | Tunnel fire scene disaster perception and situation development prediction method |
CN117371836A (en) * | 2023-09-28 | 2024-01-09 | 长沙理工大学 | Highway tunnel fire rescue capability assessment method and system based on regional visual angle |
CN117371836B (en) * | 2023-09-28 | 2024-04-09 | 长沙理工大学 | Highway tunnel fire rescue capability assessment method and system based on regional visual angle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114880935A (en) | Tunnel fire advanced prediction method | |
Al-Qizwini et al. | Deep learning algorithm for autonomous driving using googlenet | |
JP6693938B2 (en) | Appearance inspection device | |
CN110377447A (en) | A kind of abnormal deviation data examination method, device and server | |
CN111240350A (en) | Unmanned aerial vehicle pilot dynamic behavior evaluation system | |
Ossen et al. | Validity of trajectory-based calibration approach of car-following models in presence of measurement errors | |
CN107862331A (en) | It is a kind of based on time series and CNN unsafe acts recognition methods and system | |
Nik et al. | Hybrid PSO and GA approach for optimizing surveyed asphalt pavement inspection units in massive network | |
KR20170052344A (en) | Method and apparatus for searching new material | |
CN105844384A (en) | Road safety evaluation method and apparatus | |
KR20220026804A (en) | Apparatus and method for detecting delivery vehicle based on Inverse Reinforcement Learning | |
CN109657077A (en) | Model training method, lane line generation method, equipment and storage medium | |
CN111797572A (en) | Urban accident disaster evolution simulation and risk prediction early warning method | |
CN113777952A (en) | Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle | |
WO2021146905A1 (en) | Deep learning-based scene simulator construction method and apparatus, and computer device | |
Ramakrishna et al. | Anti-carla: An adversarial testing framework for autonomous vehicles in carla | |
Zhang et al. | Smart real-time forecast of transient tunnel fires by a dual-agent deep learning model | |
CN116011670A (en) | Fire prediction model training, using method, equipment and medium | |
Rojas et al. | Performance evaluation of an autonomous vehicle using resilience engineering | |
Park et al. | Source term estimation using deep reinforcement learning with Gaussian mixture model feature extraction for mobile sensors | |
CN116973523B (en) | MEMS gas sensor array-based gas detection method and system | |
NL2018125B1 (en) | Assessment system and assessment method | |
CN110995461B (en) | Network fault diagnosis method | |
Neves et al. | An environment to support structural testing of autonomous vehicles | |
CN111160594B (en) | Method and device for estimating arrival time and storage medium |
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 |