CN116187740A - Mountain fire monitoring method and system along power transmission line - Google Patents
Mountain fire monitoring method and system along power transmission line Download PDFInfo
- Publication number
- CN116187740A CN116187740A CN202211497304.4A CN202211497304A CN116187740A CN 116187740 A CN116187740 A CN 116187740A CN 202211497304 A CN202211497304 A CN 202211497304A CN 116187740 A CN116187740 A CN 116187740A
- Authority
- CN
- China
- Prior art keywords
- fire
- transmission line
- mountain fire
- mountain
- power transmission
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention belongs to the technical field of power transmission line monitoring, and particularly relates to a mountain fire monitoring method and system along a power transmission line. Acquiring current microclimate data for identifying fire hazards along the transmission line, and inputting the microclimate data into a constructed mountain fire hazard classification model to obtain mountain fire hazard classes along the transmission line under current microclimate conditions; the mountain fire dangerous case grading model is an improved neural network model, and the improvement point of the improved neural network model is that the weight and the threshold value of the neural network are obtained by using a genetic algorithm and updated according to a set fitness function. The method does not need to consume excessive manpower, not only makes early analysis and prediction on the dangerous situations of the mountain fires possibly occurring in the power transmission line, has the ability of early sensing the fire risks, but also strives for more rescue time for the dangerous situations of the mountain fires possibly occurring.
Description
Technical Field
The invention belongs to the technical field of power transmission line monitoring, and particularly relates to a mountain fire monitoring method and system along a power transmission line.
Background
At present, for the problem that a power transmission line crossing a mountain area has dangerous cases of mountain fires along the periphery of the line, the traditional inspection method comprises two modes of manual periodic mountain area inspection and traditional video image monitoring, the manual periodic mountain area inspection is difficult, manpower is consumed, the inspection range is limited, and many high-altitude areas cannot be reached; the traditional video image monitoring needs to rely on the on-duty personnel to take duty for 24 hours in turn, monitor and judge the on-site video image transmitted by each monitoring point day and night, not only consumes manpower, but also is difficult to accurately predict and find the dangerous mountain fire situation of early burst, and in serious cases, the rescue time is delayed, so that irreparable loss is caused.
Disclosure of Invention
The invention aims to provide a mountain fire monitoring method and system along a power transmission line, which are used for solving the problems that the monitoring method in the prior art consumes manpower and is difficult to find smoke rescue time caused by early mountain fire danger.
In order to solve the technical problems, the invention provides a mountain fire monitoring method along a power transmission line, which is used for acquiring microclimate data of the power transmission line along the current line for identifying fire hazards, and inputting the microclimate data into a constructed mountain fire hazard class classification model to obtain the mountain fire hazard class of the power transmission line under the current microclimate condition; the mountain fire dangerous case grading model is an improved neural network model, and the improvement point of the improved neural network model is that a genetic algorithm is adopted to optimize the weight and the threshold value of the neural network, and the weight and the threshold value are updated according to a set fitness function.
The beneficial effects are as follows: according to the invention, the neural network is improved by utilizing a genetic algorithm, namely, the weight and the threshold of the neural network are optimized by utilizing the genetic algorithm, the optimized neural network model is trained by utilizing training data, the process is updated according to a fitness function, and the process is repeated continuously, so that the optimal network weight and the optimal threshold are obtained, and the optimal neural network model, namely, a mountain fire danger class division model, is obtained, and further, microclimate data, which is used for identifying fire hazards along a power transmission line, is input into the mountain fire danger class division model, so that the mountain fire danger class along the power transmission line under the current microclimate condition can be obtained. The method does not need to consume excessive manpower, not only makes early analysis and prediction on the dangerous situations of the mountain fire possibly occurring in the power transmission line, has the capability of early sensing the fire risk, but also strives for more rescue time for the dangerous situations of the mountain fire possibly occurring, so as to reduce the difficulty of coping with the prevention and control of the power transmission line in the mountain area and the loss of the mountain fire to the power transmission line.
Further, microclimate data for identifying a fire hazard includes temperature, atmospheric humidity, and rainfall.
The beneficial effects are as follows: the data with great influence on the mountain fire by using three items of temperature, atmospheric humidity and rainfall are utilized to analyze and predict the mountain fire danger in advance, so that the mountain fire danger level along the transmission line under the current microclimate condition can be accurately predicted.
Further, when the dangerous mountain fire level along the power transmission line is higher than a set dangerous mountain fire level threshold under the current microclimate condition, acquiring an image of the periphery of the power transmission line, identifying sample points which accord with mountain fire characteristics and smoke characteristics in the image to find potential mountain fire explosion points, acquiring the temperature of the potential mountain fire explosion points, and judging the potential mountain fire explosion points as mountain fire explosion points when the temperature is higher than the set temperature threshold; wherein, the higher the dangerous mountain fire level, the higher the probability of mountain fire.
The beneficial effects are as follows: under the condition that the dangerous mountain fire hazard level along the transmission line is higher under the current microclimate condition, the potential mountain fire explosion point is further found through the visible light image, and the potential mountain fire explosion point is further determined by utilizing the temperature so as to accurately find the mountain fire explosion point.
Further, after the mountain fire explosion point is identified, the distance between the power transmission line and the mountain fire explosion point is measured.
The beneficial effects are as follows: the distance between the power transmission line and the mountain fire explosion point is measured, and the method can be used for detecting the fire spreading trend, so that a foundation is laid for reducing the influence of the mountain fire on the operation of the power transmission line as much as possible.
Further, microclimate data for identifying a fire spreading trend is also required to be obtained, the microclimate data for identifying a fire spreading trend includes wind speed and wind direction data along a power transmission line, a fire spreading speed of a mountain fire explosion point is determined, and a calculation formula of the fire spreading speed is as follows:
V＝V 0 ×K 0 ×K f
wherein V represents the speed of fire spreading in downwind direction; v (V) 0 Indicating the fire spreading speed in no wind, V 0 ＝aT+bV w +cH-D, T represents the highest daily air temperature，V w Mean wind level in noon, H minimum humidity in day, a, b, c, D are all coefficients; k (K) 0 Representing a velocity correction coefficient; k (K) f Indicating the combustible configuration correction factor.
The beneficial effects are as follows: by combining the wind speed, the wind direction and the position of the mountain fire explosion point, the fire spreading trend of the mountain fire explosion point can be accurately determined, early warning is carried out along the line of the area of the possible mountain fire path, and the influence of the mountain fire on the operation of the power transmission line is reduced as much as possible.
In order to solve the technical problems, the invention also provides a mountain fire monitoring system along the transmission line, which comprises a power supply module, a microclimate sensor and a data processing module; the power supply module is used for supplying power to equipment needing power supply in the monitoring system; the microclimate sensor is used for collecting microclimate data which is currently used for identifying fire risks along the transmission line and sending the microclimate data to the data processing module; the data processing module is used for inputting the acquired microclimate data currently used for identifying the fire risk into the constructed mountain fire risk classification model to obtain the mountain fire risk level along the transmission line under the current microclimate condition, wherein the mountain fire risk classification model is an improved neural network model, and the improvement point of the improved neural network model is that the weight and the threshold of the neural network are optimized by adopting a genetic algorithm, and the improved neural network model is updated according to the set fitness function.
The beneficial effects are as follows: the data processing module is arranged in the mountain fire monitoring system along the line of the power transmission line, the data processing module can predict the mountain fire dangerous condition level by utilizing microclimate data, and in addition, when in prediction, a genetic algorithm is used for improving the neural network, namely, the weight and the threshold value of the neural network are optimized by utilizing the genetic algorithm, further, the optimized neural network model is trained by utilizing training data, and updated according to the fitness function, and the process is repeated continuously, so that the optimal network weight and the optimal threshold value are obtained, and the optimal neural network model, namely, the mountain fire dangerous condition level classification model is obtained. The method does not need to consume excessive manpower, not only makes early analysis and prediction on the dangerous situations of the mountain fires possibly occurring in the power transmission line, has the ability of early sensing the fire risks, but also strives for more rescue time for the dangerous situations of the mountain fires possibly occurring.
Further, microclimate data input to the constructed mountain fire hazard classification model includes temperature, air relative humidity and rainfall.
The beneficial effects are as follows: the data with great influence on the mountain fire by using three items of temperature, atmospheric humidity and rainfall are utilized to analyze and predict the mountain fire danger in advance, so that the mountain fire danger level along the transmission line under the current microclimate condition can be accurately predicted.
Further, the monitoring system also comprises a visible light module and an infrared thermal imaging module; the visible light module is used for shooting images around the power transmission line in real time when the mountain fire dangerous condition level along the power transmission line is higher than a set mountain fire dangerous condition level threshold value so as to identify sample points which accord with mountain fire characteristics and smoke characteristics in the shot images and find potential mountain fire explosion points, and shooting images around the power transmission line at regular time when the mountain fire dangerous condition level along the power transmission line is lower than or equal to the set mountain fire dangerous condition level threshold value; the infrared thermal imaging module is used for acquiring the temperature of the potential mountain fire explosion points so as to find the mountain fire explosion points from the potential mountain fire explosion points.
The beneficial effects are as follows: under the condition that the dangerous mountain fire hazard level along the transmission line is higher under the current microclimate condition, the potential mountain fire explosion point is further found through the visible light image, and the potential mountain fire explosion point is further determined by utilizing the temperature so as to accurately find the mountain fire explosion point. Moreover, the working modes of the visible light module are divided into a timing mode and a real-time mode, so that the power consumption of the mountain fire monitoring system along the whole power transmission line is reduced, and the duration of the system in bad weather is prolonged.
Further, the monitoring system further comprises a ranging module for measuring the distance between the power transmission line and the mountain fire explosion point.
The beneficial effects are as follows: the distance between the power transmission line and the mountain fire explosion point is measured, and the method can be used for detecting the fire spreading trend, so that a foundation is laid for reducing the influence of the mountain fire on the operation of the power transmission line as much as possible.
Further, the microclimate sensor is further used for collecting microclimate data for identifying a fire spreading trend, the microclimate data for identifying the fire spreading trend comprises wind speed and wind direction data along a power transmission line, the data processing module is further used for determining the fire spreading speed of a mountain fire explosion point by combining the wind speed and the wind direction data along the power transmission line, and a calculation formula of the fire spreading speed is as follows:
V＝V 0 ×K 0 ×K f
wherein V represents the speed of fire spreading in downwind direction; v (V) 0 Indicating the fire spreading speed in no wind, V 0 ＝aT+bV w +cH-D, T represents the highest daily air temperature, V w Mean wind level in noon, H minimum humidity in day, a, b, c, D are all coefficients; k (K) 0 Representing a velocity correction coefficient; k (K) f Indicating the combustible configuration correction factor.
The beneficial effects are as follows: by combining the wind speed, the wind direction and the position of the mountain fire explosion point, the fire spreading trend of the mountain fire explosion point can be accurately determined, early warning is carried out along the line of the area of the possible mountain fire path, and the influence of the mountain fire on the operation of the power transmission line is reduced as much as possible.
Drawings
Fig. 1 is a schematic structural diagram of a forest fire monitoring system along a power transmission line of the present invention;
fig. 2 is a schematic structural diagram of an internet of things gateway according to the present invention;
FIG. 3 is a block diagram of a three-view pan/tilt monitoring apparatus of the present invention;
FIG. 4 is a flow chart of mountain fire hazard prediction of the present invention;
fig. 5 is a flow chart of a method of mountain fire monitoring along a transmission line of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the particular embodiments described herein are illustrative only and are not intended to limit the invention, i.e., the embodiments described are merely some, but not all, of the embodiments of the invention. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
Mountain fire monitoring system embodiment along transmission line:
the invention discloses a mountain fire monitoring system for a power transmission line, which has an overall structure shown in figure 1 and comprises a photovoltaic energy storage integrated battery box, a microclimate sensor, a three-mesh holder monitoring device and an edge internet-of-things gateway. The photovoltaic energy storage integrated battery box supplies power to all the connecting devices through the edge internet-of-things gateway. The microclimate sensor is used for collecting microclimate data of the periphery of the transmission line along the line, including temperature, atmospheric humidity, rainfall, wind speed, wind direction and other information, and sending the collected data to the edge internet of things gateway through RS 485. The temperature, the atmospheric humidity and the rainfall are microclimate data for identifying the fire hazard, and the wind speed and the wind direction are microclimate data for identifying the spreading trend of the fire hazard.
The edge internet of things is used for analyzing and early warning whether mountain danger is likely to occur under the current microclimate condition based on microclimate data for identifying the fire danger. As shown in fig. 2, the edge internet of things gateway comprises a main control module, a neural network analysis module, a sensor unified interface communication module and a 4G/5G APN private network communication module. The edge internet of things receives data acquired by the microclimate sensor through the sensor unified interface communication module and sends the data to the main control module, the main control module sends the data to the neural network analysis module for analysis and processing, as shown in fig. 4, a genetic algorithm is adopted to optimize the weight and the threshold of a mountain fire danger class division model based on the BP neural network, so that accurate assessment is made on whether the mountain fire occurs currently, the whole system has the capability of perceiving the fire danger in advance, the assessment result is sent to the main control module, and the main control module sends the assessment result to the mountain fire prevention monitoring platform of the power transmission line through the 4G/5G APN private network communication module.
The three-view tripod head monitoring device is used for detecting mountain fire points in real time and sending various data of the detected mountain fire points to the power transmission line mountain fire prevention monitoring platform through the edge internet of things gateway. As shown in fig. 3, the three-eye pan-tilt monitoring device comprises a core control board, a visible light module, an infrared thermal imaging module, a laser ranging module, an AI artificial intelligent module and a pan-tilt control module. The visible light module is used for shooting and monitoring areas nearby the power transmission line in real time, can carry out horizontal 360-degree and vertical 90-degree omnibearing monitoring on the power transmission line, and sends shooting contents to the core control board, and the core control board sends the AI artificial intelligent module to identify mountain fires, smoke and the like to the shot pictures. The infrared thermal imaging module is used for sensing the heat of the photographed area and sending the heat to the core control board. The laser ranging module is used for ranging the distance between the mountain fire point and the power transmission line and sending the distance to the core control board. The start-up time of the tripod head monitoring apparatus and the working time requirements of each module included in the tripod head monitoring apparatus will be described below when the whole process is introduced.
The following describes in detail a method for monitoring mountain fire along a power transmission line, which is adopted by the system for monitoring mountain fire along a power transmission line, with reference to fig. 5.
Step one, current microclimate data including temperature, air relative humidity and rainfall along a power transmission line are collected through a microclimate sensor for identifying fire hazards, and the collected microclimate data are sent to an edge internet-of-things gateway.
And secondly, the edge internet of things receives current microclimate data acquired by the microclimate sensor through the sensor unified interface module, and transmits the current microclimate data to the neural network analysis module through the main control module for analysis and processing, wherein a mountain fire dangerous situation grade classification model is stored in the neural network analysis module, and the current microclimate data is input into the mountain fire dangerous situation grade classification model, so that the mountain fire dangerous situation grade along the transmission line under the current microclimate condition can be obtained.
In this embodiment, the fire danger level is divided into 5 levels, which are respectively: grade 1, probability of occurrence of mountain fire is less than 25%, and no danger is considered; 2, the probability of mountain fire is 25% -50%, and the low risk is considered; grade 3, the probability of mountain fire is between 50% and 75%, and moderate danger is considered; grade 4, the probability of mountain fire is 75% -90%, and the danger is considered to be higher; grade 5, with a probability of occurrence of mountain fires greater than 90%, considered highly dangerous.
The construction of the mountain fire hazard classification model and the training process are described in detail below with reference to fig. 4.
1. And determining a BP neural network model.
2. Encoding the weight and the threshold value in the BP neural network to obtain an initial population (comprising a plurality of individuals) and taking the initial population as a contemporary population;
3. decoding the contemporary population, and assigning weights and thresholds to the BP neural network model after decoding, wherein a plurality of BP neural network models exist at the moment.
4. Acquiring a data set, wherein the data set comprises microclimate data at different moments and corresponding mountain fire danger grade division results, dividing the data set into a training set and a testing set according to a certain proportion, training a plurality of BP neural network models in the step 3 by using the training set, and testing the BP neural network models by using the testing set to obtain errors.
5. And (3) calculating the fitness of each trained BP neural network model in the step (3) by using the set fitness function, and selecting a better individual from the fitness. The fitness function is set to:
wherein Error represents the fitness function value; i=1, 2 · t is the sum of the values of, t represents the number of neurons in the output layer; d and Y represent an actual value and an output layer predicted value, respectively.
6. And carrying out selection operation, crossover operation and mutation operation in genetic operation on individuals in the current generation population to obtain a new population, namely the next generation population.
7. Judging whether the iteration termination condition is satisfied: if yes, decoding the current population to obtain an optimal network weight and a threshold, wherein a BP neural network model corresponding to the optimal network weight and the threshold is a final mountain fire dangerous case grading model; if not, the next generation population is taken as the current generation population, the steps 3-7 are restarted to be executed, and the iteration is repeated until the iteration termination condition is met.
Step three, for the estimated result in the step two, if the mountain fire dangerous condition grade is 1-2, the edge internet of things close timing starts a three-mesh holder monitoring device to monitor the transmission line at timing; if the mountain fire dangerous situation grade is 3-5, the edge internet of things is closed to start the three-view holder monitoring device in real time, and the three-view holder monitoring device is controlled to monitor the mountain fire along the periphery of the transmission line in real time.
Step four, the three-eye holder monitoring device shoots the periphery of the power transmission line in 360-degree multi-azimuth by utilizing the visible light module, then transmits the shot image into the AI artificial intelligent module, and analyzes and identifies the sample points which accord with the characteristics of mountain fire and smoke (the AI intelligent algorithm is utilized to identify and judge whether the visible light or infrared photo has the appearance and the outline similar to the mountain fire or smoke) so as to identify whether the shot image has potential mountain fire burst points or not: if the potential mountain fire explosion point exists, executing a step five; if no potential mountain fire explosion point exists, the AI artificial intelligent module is continuously used for identifying and judging the shot image.
Fifthly, when the AI artificial intelligence module identifies that potential mountain fire explosion points exist in the shot image, the three-eye cradle head monitoring device immediately starts the infrared thermal imaging module to conduct infrared temperature sensing on the potential mountain fire explosion points: if the temperature reaches the threshold condition, judging the point as a mountain fire explosion point, and executing the step six; if no mountain fire explosion point exists, the infrared thermal imaging module is continuously used for monitoring the temperature of the potential mountain fire explosion point.
Step six, after the mountain fire explosion points are confirmed, the three-mesh holder monitoring device starts a laser ranging module to measure distance information and position information of the mountain fire explosion points, and divides fire alarms into 3 grades according to the distance between the mountain fire and the power transmission lines, wherein the three grades are respectively: class 1, the distance is more than 3 km, set as the general risk fire alarm; 2, setting the distance between 1 km and 3 km as a serious risk fire alarm; and 3, setting the distance within 1 km as critical risk fire alarm. The three-mesh holder monitoring device sends various monitored information to the edge internet of things gateway.
And seventhly, determining the fire spreading speed of the mountain fire explosion point according to a self-built mountain fire spreading analysis model by combining the wind speed, the wind direction, the position of the mountain fire explosion point and the distance between the power transmission line and the mountain fire explosion point by the edge Internet of things. The specific fire spreading speed formula is as follows:
V＝V 0 ×K 0 ×K f
wherein V represents the speed of fire spreading in downwind direction; v (V) 0 Indicating the fire spreading speed in no wind, V 0 ＝aT+bV w +cH-D, T represents the highest daily air temperature, V w The average noon wind level is represented, H represents the minimum daily humidity, a, b, c, D are coefficients, and the coefficients can be respectively 0.03, 0.05, 0.01 and 0.3; k (K) 0 Indicating the velocity correction coefficient(s),
K f indicating a combustible fuel configuration correction factor that is between 0.8 and 2, depending on the combustible.
And the edge internet of things gateway sends collected microclimate information, estimated fire grade, fire alarm grade information, distance information, fire spreading speed and other information near the mountain fire explosion point along the line of the power transmission line to the mountain fire prevention monitoring background of the power transmission line through the 4G/5G APN private network communication module, so that rescue can be carried out as soon as possible when the mountain fire is exploded.
In summary, the invention has the following characteristics:
1) According to the invention, the possibility of mountain fire of the current power transmission line is predicted by adopting an optimized neural network mountain fire prediction algorithm according to microclimate data, so that early warning can be performed on the mountain fire in advance, and more rescue time is obtained for mountain fire dangerous cases which possibly burst.
2) According to the invention, the visible light module and the AI artificial intelligent module are adopted to identify mountain fires AI nearby the transmission line, and the infrared thermal imaging module is adopted to reconfirm the temperature threshold value of the mountain fires found, so that the accurate identification of the early mountain fires can be realized, and the false alarm rate is reduced.
3) According to the invention, the laser ranging module is adopted to measure the distance of the mountain fire explosion point in real time, so that the accuracy is higher compared with the monocular ranging and binocular ranging.
4) According to the invention, real-time analysis can be carried out on the spreading trend of the mountain fire according to the information such as microclimate data and the mountain fire distance and the like and according to the self-built mountain fire spreading analysis model, and early warning is carried out on the area along the possible path of the mountain fire, so that the influence of the mountain fire on the operation of the power transmission line is reduced as much as possible.
5) When the mountain fire prediction level is low, the three-mesh holder monitoring device is started at fixed time; when the mountain fire prediction level is higher, a three-mesh holder monitoring device is started in real time to monitor the power transmission line in real time; the overall power consumption of the device is reduced to a great extent, and the duration of the device in bad weather is prolonged.
In the embodiment, the mountain fire danger grading model is obtained by improving the BP neural network model by using a genetic algorithm. As other embodiments, other types of neural network models, such as convolutional neural network models, may be improved by using genetic algorithms, and weights and thresholds in the convolutional neural network models may be optimized by using genetic algorithms as well.
The embodiment of the mountain fire monitoring method along the transmission line comprises the following steps:
the embodiment of the mountain fire monitoring method along the transmission line is realized based on the mountain fire monitoring system along the transmission line shown in fig. 1, and the method is characterized in that the mountain fire dangerous condition grade along the transmission line under the current microclimate condition can be determined by utilizing microclimate data and a constructed mountain fire dangerous condition grade classification model. And when the mountain fire dangerous situation is found to be higher in grade, the mountain fire explosion point is accurately identified and detected by the temperature reflected by the visible light image and the infrared image, and then the distance between the mountain fire explosion point and the power transmission line is measured, so that the fire spreading trend of the fire explosion point is determined. The specific implementation process of the method is consistent with the implementation process of the power transmission line mountain fire monitoring method introduced in the power transmission line mountain fire monitoring system embodiment, and the embodiment is not repeated.
Specific embodiments are given above, but the invention is not limited to the described embodiments. The basic idea of the invention is that the above basic scheme, it is not necessary for a person skilled in the art to design various modified models, formulas, parameters according to the teaching of the invention to take creative effort. Variations, modifications, substitutions and alterations are also possible in the embodiments without departing from the principles and spirit of the present invention.
Claims (10)
1. The mountain fire monitoring method along the transmission line is characterized by obtaining microclimate data currently used for identifying fire hazards along the transmission line, and inputting the microclimate data into a constructed mountain fire hazard class classification model to obtain the mountain fire hazard class along the transmission line under the current microclimate condition; the mountain fire dangerous case grading model is an improved neural network model, and the improvement point of the improved neural network model is that a genetic algorithm is adopted to optimize the weight and the threshold value of the neural network, and the weight and the threshold value are updated according to a set fitness function.
2. The method of claim 1, wherein the microclimate data for identifying fire hazards includes temperature, atmospheric humidity and rainfall.
3. The method for monitoring mountain fires along the transmission line according to claim 1, wherein when the mountain fire risk level along the transmission line is higher than a set mountain fire risk level threshold under the current microclimate condition, an image around the transmission line is acquired, sample points which accord with the mountain fire characteristics and smoke characteristics in the image are identified to find potential mountain fire explosion points, the temperature of the potential mountain fire explosion points is acquired, and when the temperature is higher than the set temperature threshold, the potential mountain fire explosion points are judged to be mountain fire explosion points; wherein, the higher the dangerous mountain fire level, the higher the probability of mountain fire.
4. A method of monitoring a mountain fire along a power transmission line as claimed in claim 3, wherein the distance between the power transmission line and the mountain fire break-out point is measured after the mountain fire break-out point is identified.
5. The method for monitoring mountain fires along a power transmission line according to claim 4, further comprising obtaining microclimate data for identifying a trend of fire spread, wherein the microclimate data for identifying a trend of fire spread comprises wind speed and wind direction data along the power transmission line, a fire spread rate of a mountain fire burst point is determined, and a calculation formula of the fire spread rate is:
V＝V 0 ×K 0 ×K f
wherein V represents the speed of fire spreading in downwind direction; v (V) 0 Indicating the fire spreading speed in no wind, V 0 ＝aT+bV w +cH-D, T represents the highest daily air temperature, V w Mean wind level in noon, H minimum humidity in day, a, b, c, D are all coefficients; k (K) 0 Representing a velocity correction coefficient; k (K) f Indicating the combustible configuration correction factor.
6. The mountain fire monitoring system along the transmission line is characterized by comprising a power supply module, a microclimate sensor and a data processing module; the power supply module is used for supplying power to equipment needing power supply in the monitoring system; the microclimate sensor is used for collecting microclimate data which is currently used for identifying fire risks along the transmission line and sending the microclimate data to the data processing module;
the data processing module is used for inputting the acquired microclimate data currently used for identifying the fire risk into the constructed mountain fire risk classification model to obtain the mountain fire risk level along the transmission line under the current microclimate condition, wherein the mountain fire risk classification model is an improved neural network model, and the improvement point of the improved neural network model is that the weight and the threshold of the neural network are optimized by adopting a genetic algorithm, and the improved neural network model is updated according to the set fitness function.
7. The transmission line mountain fire monitoring system of claim 6 wherein the microclimate data input to the constructed mountain fire risk classification model includes temperature, air relative humidity and rainfall.
8. The transmission line fire monitoring system of claim 6, further comprising a visible light module and an infrared thermal imaging module; the visible light module is used for shooting images around the power transmission line in real time when the mountain fire dangerous condition level along the power transmission line is higher than a set mountain fire dangerous condition level threshold value so as to identify sample points which accord with mountain fire characteristics and smoke characteristics in the shot images and find potential mountain fire explosion points, and shooting images around the power transmission line at regular time when the mountain fire dangerous condition level along the power transmission line is lower than or equal to the set mountain fire dangerous condition level threshold value; the infrared thermal imaging module is used for acquiring the temperature of the potential mountain fire explosion points so as to find the mountain fire explosion points from the potential mountain fire explosion points.
9. The transmission line fire monitoring system of claim 8, further comprising a ranging module for measuring a distance between the transmission line and a fire burst point.
10. The system for monitoring mountain fires along a power transmission line of claim 9, wherein the microclimate sensor is further configured to collect microclimate data for identifying a trend of fire spread, the microclimate data for identifying a trend of fire spread includes wind speed and wind direction data along the power transmission line, the data processing module is further configured to determine a fire spread rate at a mountain fire burst point in combination with the wind speed and wind direction data along the power transmission line, and the calculation formula of the fire spread rate is:
V＝V 0 ×K 0 ×K f
wherein V represents the spread of fire in the direction of windA speed; v (V) 0 Indicating the fire spreading speed in no wind, V 0 ＝aT+bV w +cH-D, T represents the highest daily air temperature, V w Mean wind level in noon, H minimum humidity in day, a, b, c, D are all coefficients; k (K) 0 Representing a velocity correction coefficient; k (K) f Indicating the combustible configuration correction factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497304.4A CN116187740A (en) | 2022-11-27 | 2022-11-27 | Mountain fire monitoring method and system along power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497304.4A CN116187740A (en) | 2022-11-27 | 2022-11-27 | Mountain fire monitoring method and system along power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116187740A true CN116187740A (en) | 2023-05-30 |
Family
ID=86444959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211497304.4A Pending CN116187740A (en) | 2022-11-27 | 2022-11-27 | Mountain fire monitoring method and system along power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187740A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236671A (en) * | 2023-11-15 | 2023-12-15 | 深圳金三立视频科技股份有限公司 | Dynamic real-time monitoring method and system for mountain fire of power transmission line |
| CN117689520A (en) * | 2024-02-01 | 2024-03-12 | 青岛山科智汇信息科技有限公司 | Grassland fire extinguishing bomb coverage capability evaluation method, medium and system |
| CN117689520B (en) * | 2024-02-01 | 2024-05-10 | 青岛山科智汇信息科技有限公司 | Grassland fire extinguishing bomb coverage capability evaluation method, medium and system |
-
2022
- 2022-11-27 CN CN202211497304.4A patent/CN116187740A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236671A (en) * | 2023-11-15 | 2023-12-15 | 深圳金三立视频科技股份有限公司 | Dynamic real-time monitoring method and system for mountain fire of power transmission line |
| CN117236671B (en) * | 2023-11-15 | 2024-03-19 | 深圳金三立视频科技股份有限公司 | Dynamic real-time monitoring method and system for mountain fire of power transmission line |
| CN117689520A (en) * | 2024-02-01 | 2024-03-12 | 青岛山科智汇信息科技有限公司 | Grassland fire extinguishing bomb coverage capability evaluation method, medium and system |
| CN117689520B (en) * | 2024-02-01 | 2024-05-10 | 青岛山科智汇信息科技有限公司 | Grassland fire extinguishing bomb coverage capability evaluation method, medium and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110321853B (en) | Distributed cable external-damage-prevention system based on video intelligent detection | |
| CN104966372B (en) | The forest fire intelligent identifying system and method for multi-data fusion | |
| CN104581076A (en) | Mountain fire monitoring and recognizing method and device based on 360-degree panoramic infrared fisheye camera | |
| CN106485868A (en) | The monitoring server of the monitoring method of the condition of a fire, system and the condition of a fire | |
| CN109448292A (en) | A kind of power grid mountain fire monitoring and pre-alarming method | |
| CN107240216A (en) | Based on 3DGIS+BIM technologies and artificial intelligence O＆M emergent alarm and fast response method | |
| CN104410839B (en) | A kind of mobile power transmission line bar tower region mountain fire and disaster of mountain massif coast on-line monitoring system and monitoring method | |
| CN117037406B (en) | Intelligent monitoring and early warning system for forest fire | |
| CN117319451B (en) | Urban fire-fighting Internet of things supervision system based on multi-mode big data and method thereof | |
| CN116187740A (en) | Mountain fire monitoring method and system along power transmission line | |
| CN115310882B (en) | Visual fire-fighting strategy planning method and system | |
| CN116664359A (en) | Intelligent fire early warning decision system and method based on multi-sensor fusion | |
| CN113936413A (en) | Early fire monitoring and early warning method and device | |
| CN116189372A (en) | Forest fire prevention multilayer early warning and monitoring system and method applying big data technology | |
| CN117114406A (en) | Emergency event intelligent early warning method and system based on equipment data aggregation | |
| CN113469098B (en) | Intelligent visual monitoring device for organic hazardous chemical leakage | |
| CN114519304A (en) | Multi-target fire scene temperature prediction method based on distributed optical fiber temperature measurement | |
| CN113990018A (en) | Safety risk prediction system | |
| CN115664006B (en) | Intelligent management and control integrated platform for incremental power distribution network | |
| CN117197978A (en) | Forest fire monitoring and early warning system based on deep learning | |
| CN114235082B (en) | Intelligent metering method based on sand production monitoring system | |
| CN115049988A (en) | Edge calculation method and device for power distribution network monitoring and prejudging | |
| CN113673377A (en) | Construction and working method of multi-target spontaneous combustion point identification and positioning model of coal pile of thermal power plant | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN115345371A (en) | Intelligent fire safety assistant decision-making method |
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 |