CN113536938A - 5G-fused intelligent early warning method and system for forest fire of power transmission line - Google Patents
5G-fused intelligent early warning method and system for forest fire of power transmission line Download PDFInfo
- Publication number
- CN113536938A CN113536938A CN202110680030.1A CN202110680030A CN113536938A CN 113536938 A CN113536938 A CN 113536938A CN 202110680030 A CN202110680030 A CN 202110680030A CN 113536938 A CN113536938 A CN 113536938A
- Authority
- CN
- China
- Prior art keywords
- neural network
- convolutional neural
- images
- transmission line
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000005540 biological transmission Effects 0.000 title claims abstract description 45
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 81
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000012360 testing method Methods 0.000 claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 14
- 238000004891 communication Methods 0.000 claims abstract description 11
- 238000002372 labelling Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 40
- 238000011176 pooling Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 14
- 230000004913 activation Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 230000006870 function Effects 0.000 description 33
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a 5G-fused intelligent early warning method and system for forest fire of a power transmission line, which comprises the following steps: constructing a convolutional neural network; collecting a plurality of mountain fire images and a plurality of non-mountain fire images, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images; extracting the features of the images in the training set, and training the convolutional neural network based on the extracted image features; extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics, and calculating the accuracy of testing the convolutional neural network; acquiring a real-time power transmission line image in a 5G communication mode, extracting image characteristics of the power transmission line image, inputting the image characteristics into a convolutional neural network, and outputting a judgment result by the convolutional neural network; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network. The method can automatically identify and early warn whether mountain fire exists on the power transmission line, and continuous monitoring is realized.
Description
Technical Field
The invention belongs to the technical field of power transmission lines, and particularly relates to a 5G-fused intelligent early warning method and system for forest fire of a power transmission line.
Background
With the gradual development of the country, the power demand of underdeveloped economic areas, particularly mountainous areas, is gradually met. The power transmission line is limited by the geographical environment of an economically undeveloped area, in order to realize power supply for the economically undeveloped area, the power transmission line generally needs to pass through mountainous and sharp mountainous areas, mountain fire is easily caused by the unique landform and climate conditions of the areas, the power transmission line is tripped if the mountain fire is caused, an iron tower is burnt out if the mountain fire is caused, a long-time unrecoverable serious power accident is caused, and even the life and property safety of people can be threatened.
In the aspect of preventing transmission line forest fire, the mode of patrolling line or unmanned aerial vehicle remote control line patrolling line is generally adopted to the manual work now, but two kinds of modes can't realize lasting long-time forest fire control to transmission line, and also rely on the mode that people's eye observed, can't realize the automatic identification early warning. Therefore, how to overcome the defects of the prior art is a problem which needs to be solved urgently in the technical field of the current power transmission line.
Disclosure of Invention
The invention aims to solve the defects of the prior art and provides a 5G-fused intelligent early warning method and system for the forest fire of a power transmission line.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
A5G-fused intelligent early warning method for mountain fire of a power transmission line comprises the following steps:
firstly, constructing a convolution neural network;
secondly, respectively acquiring a plurality of mountain fire images and a plurality of non-mountain fire images as training sets and test sets, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images;
thirdly, extracting the features of the images in the training set, and training the convolutional neural network based on the extracted image features;
fourthly, extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics, and calculating the accuracy of testing the convolutional neural network; if the accuracy is greater than the set threshold, executing a fifth step, otherwise executing a third step; acquiring a real-time power transmission line image in a 5G communication mode, extracting image features of the power transmission line image, inputting the image features into a convolutional neural network, and outputting a judgment result by the convolutional neural network; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network.
The sample number ratio of the training set and the test set in the invention is not particularly limited, and generally 7:3 is selected.
In the second step, the feature extraction can select color features or gradient direction histogram features. The process of extracting features is well known.
The image of the test set comprises a mountain fire image and a plurality of non-mountain fire images, the mountain fire and the non-mountain fire are labels of the image, the characteristics of the image of the test set are transmitted to a neural network, the neural network outputs the class confidence of the labels, namely the probability that the labels belong to the mountain fire or the non-mountain fire respectively is shown, and then whether a judgment error exists is determined according to the fact that the output label has higher confidence compared with the real label, so that the statistical accuracy is calculated
Further, it is preferable that the process of training the convolutional neural network includes a forward propagation process, and the forward propagation process includes:
taking the difference value between the class confidence of the image output by the convolutional neural network and the label class of the image mark as a Softmax _ Loss Loss function;
performing enhanced feature extraction on the feature vector of the image through the convolutional neural network to obtain an enhanced feature vector of the image;
acquiring a reinforced feature vector center corresponding to each category;
calculating the Euclidean distance between the reinforced feature vector of the image and the Center of the reinforced feature vector of the corresponding category, and taking the square of the Euclidean distance as a Center _ Loss function;
calculating a final loss function, wherein the final loss function is formulated as:
the final Loss function Softmax _ Loss + λ Center _ Loss,
wherein, the lambda is a hyper-parameter, and the preferred value is 0.5-0.8.
The class confidence of the image is the probability that the label belongs to mountain fire or non-mountain fire.
Further, it is preferable that the process of training the convolutional neural network includes a back propagation process, and the back propagation process includes:
and calculating the partial derivative of the final loss function according to the final loss function, and updating the weight parameters in the convolutional neural network.
Further, preferably, the convolutional neural network is arranged according to input layers-convolutional layer-pooling layer-convolutional layer-pooling layer-full-connected layer, a ReLu function is selected as an activation function, pooling uses a maximum pooling method, and the output of the current layer is represented as:
xe＝f(ue)
ue＝Wexe-1+be
wherein xeRepresents the output of the current layer, ueRepresenting the input of an activation function, f () representing the activation function, WeIs the weight of the current layer, beMay be biased.
Further, it is preferable that Dropout is added after the pooling layer to perform a disconnection process on the network, selecting to disconnect the neurons with a probability of 0.3 and 0.45.
Further, it is preferable that the threshold in the fourth step is set to 0.94.
Further, preferably, in the fifth step, if it is determined that a mountain fire occurs as a result of the output of the convolutional neural network, whether the mountain fire exists is detected by an infrared video detection system installed on the site, and if so, a mountain fire warning is issued.
Further, preferably, in the fifth step, the infrared video detection system comprises an embedded DSP temperature analysis fire detection automatic alarm module and a scanning pan-tilt; the embedded DSP temperature analysis fire point detection automatic alarm module is used for automatically detecting an environmental heat source of a monitoring point and detecting a fire point in a sight line range in the scanning process of the scanning holder; an alarm signal is issued when the presence of a suspected fire is detected.
A5G-fused intelligent early warning system for the forest fire of the power transmission line comprises a convolutional neural network construction module, an image data acquisition module, a training module, a testing module and a monitoring module;
the convolutional neural network construction module is used for constructing a convolutional neural network;
the image data acquisition module is used for respectively acquiring a plurality of mountain fire images and a plurality of non-mountain fire images as training sets and test sets, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images;
the training module is used for extracting the features of the images in the training set, taking the extracted image features as input and taking the label marks of the images as output based on the extracted image features, and training the convolutional neural network;
the test module is used for extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics and calculating the accuracy of testing the convolutional neural network; then judging whether the accuracy is greater than a set threshold value;
the monitoring module is used for acquiring a real-time power transmission line image in a 5G communication mode, extracting image characteristics of the power transmission line image and inputting the image characteristics into the convolutional neural network, and the convolutional neural network outputs a judgment result; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network.
Compared with the prior art, the invention has the beneficial effects that:
the method provided by the invention realizes intelligent early warning of the forest fire by training the convolutional neural network to perform image recognition, has good persistence compared with the existing method, can realize long-time monitoring, and does not need to consume the energy of line patrol personnel by an automatic recognition mode. And the subsequent acquisition of real-time transmission line images is carried out in a 5G communication mode, and the reliability of the method can be ensured due to the characteristics of high data rate and low delay of the 5G communication.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a 5G-fused intelligent early warning method for forest fire of a power transmission line;
FIG. 2 is a schematic structural diagram of a 5G-fused intelligent early warning system for forest fire of a power transmission line;
FIG. 3 is a picture taken during operation of the system of the present invention;
fig. 4 is another picture acquired when the system of the present invention is running.
Detailed Description
The present invention will be described in further detail with reference to examples.
It will be appreciated by those skilled in the art that the following examples are illustrative of the invention only and should not be taken as limiting the scope of the invention. The examples do not specify particular techniques or conditions, and are performed according to the techniques or conditions described in the literature in the art or according to the product specifications. The materials or equipment used are not indicated by manufacturers, and all are conventional products available by purchase.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. Further, "connected" as used herein may include wirelessly connected. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In the description of the present invention, "a plurality" means two or more unless otherwise specified. The terms "inner," "upper," "lower," and the like, refer to an orientation or a state relationship based on that shown in the drawings, which is for convenience in describing and simplifying the description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "provided" are to be construed broadly, e.g., as being fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. To those of ordinary skill in the art, the specific meanings of the above terms in the present invention are understood according to specific situations.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Example 1
The embodiment of the invention provides a 5G-fused intelligent early warning method for mountain fire of a power transmission line, which can automatically identify and early warn whether mountain fire exists on the power transmission line and realize continuous monitoring.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the intelligent early warning method for the electric transmission line forest fire fused with 5G includes:
firstly, constructing a convolution neural network;
secondly, respectively acquiring a plurality of mountain fire images and a plurality of non-mountain fire images as training sets and test sets, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images;
thirdly, extracting the features of the images in the training set, and training the convolutional neural network based on the extracted image features;
fourthly, extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics, and calculating the accuracy of testing the convolutional neural network; if the accuracy is greater than the set threshold, executing a fifth step, otherwise executing a third step;
acquiring a real-time power transmission line image in a 5G communication mode, extracting image features of the power transmission line image, inputting the image features into a convolutional neural network, and outputting a judgment result by the convolutional neural network; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network.
In a specific implementation process, the process of training the convolutional neural network includes a forward propagation process, where the forward propagation process includes:
taking the difference value of the confidence level of the image class output by the convolutional neural network and the label class marked by the image as a Softmax _ Loss Loss function;
performing enhanced feature extraction on the feature vector of the image through the convolutional neural network to obtain an enhanced feature vector of the image;
acquiring a reinforced feature vector center corresponding to each category;
calculating the Euclidean distance between the reinforced feature vector of the image and the Center of the reinforced feature vector of the corresponding category, and taking the square of the Euclidean distance as a Center _ Loss function;
calculating a final loss function, wherein the final loss function is formulated as:
the final Loss function Softmax _ Loss + λ Center _ Loss,
wherein λ is a hyper-parameter.
In a specific implementation process, the process of training the convolutional neural network includes a back propagation process, and the back propagation process includes:
and according to the final loss function, calculating a partial derivative of the final loss function, and updating a weight parameter in the convolutional neural network.
In a specific implementation process, the structure of the convolutional neural network is arranged according to an input layer-convolutional layer-pooling layer-convolutional layer-full-connection layer, a ReLu function is selected as an activation function, pooling uses a maximum pooling method, and the output of a current layer is represented as:
xe＝f(ue)
ue＝Wexe-1+be
wherein xeRepresents the output of the current layer, ueRepresenting the input of an activation function, f () representing the activation function, WeIs the weight of the current layer, beMay be biased.
In a specific implementation, Dropout is added after the pooling layer to disconnect the network, and the connection between the neurons is selected to be disconnected with a probability of 0.3 and 0.45.
In a specific implementation, the threshold in step four is set to 0.94.
In a specific implementation process, in the fifth step, if the result output by the convolutional neural network is that the mountain fire occurs, detecting whether the mountain fire exists through an infrared video detection system arranged on the site, and if so, sending out a mountain fire early warning.
In a specific implementation process, in the fifth step, the infrared video detection system comprises an embedded DSP temperature analysis fire point detection automatic alarm module and a scanning holder; the automatic alarm module is used for automatically detecting an environmental heat source of a monitoring point and detecting an ignition point in a sight line range in the scanning process of the holder; an alarm signal is issued when the presence of a suspected fire is detected.
Example 2
This embodiment provides a mountain fire intelligence early warning system, as shown in fig. 2, it includes:
the system comprises a convolutional neural network construction module, an image data acquisition module, a training module, a test module and a monitoring module;
the convolutional neural network construction module is used for constructing a convolutional neural network;
the image data acquisition module is used for respectively acquiring a plurality of mountain fire images and a plurality of non-mountain fire images as training sets and test sets, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images;
the training module is used for extracting the features of the images in the training set and training the convolutional neural network based on the extracted image features;
the test module is used for extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics and calculating the accuracy of testing the convolutional neural network;
the monitoring module is used for acquiring a real-time power transmission line image in a 5G communication mode, extracting image characteristics of the power transmission line image and inputting the image characteristics into the convolutional neural network, and the convolutional neural network outputs a judgment result; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network.
In a specific implementation process, the process of training the convolutional neural network by the training module includes a forward propagation process, where the forward propagation process includes:
taking the difference value of the confidence level of the image class output by the convolutional neural network and the label class marked by the image as a Softmax _ Loss Loss function;
performing enhanced feature extraction on the feature vector of the image through the convolutional neural network to obtain an enhanced feature vector of the image;
acquiring a reinforced feature vector center corresponding to each category;
calculating the Euclidean distance between the reinforced feature vector of the image and the Center of the reinforced feature vector of the corresponding category, and taking the square of the Euclidean distance as a Center _ Loss function;
calculating a final loss function, wherein the final loss function is formulated as:
the final Loss function Softmax _ Loss + λ Center _ Loss,
wherein λ is a hyper-parameter.
In a specific implementation process, the process of training the convolutional neural network by the training module includes a back propagation process, and the back propagation process includes:
and according to the final loss function, calculating a partial derivative of the final loss function, and updating a weight parameter in the convolutional neural network.
In a specific implementation process, the structure of the convolutional neural network is arranged according to an input layer-convolutional layer-pooling layer-convolutional layer-full-connection layer, a ReLu function is selected as an activation function, pooling uses a maximum pooling method, and the output of a current layer is represented as:
xe＝f(ue)
ue＝Wexe-1+be
wherein xeRepresents the output of the current layer, ueRepresenting the input of an activation function, f () representing the activation function, WeIs the weight of the current layer, beMay be biased.
In a specific implementation, Dropout is added after the pooling layer to disconnect the network, and the connection between the neurons is selected to be disconnected with a probability of 0.3 and 0.45.
In a specific implementation process, in the monitoring module, if the result output by the convolutional neural network is that the mountain fire occurs, whether the mountain fire exists is detected by an infrared video detection system arranged on site, and if so, a mountain fire early warning is sent out.
In a specific implementation process, the infrared video detection system comprises an embedded DSP temperature analysis fire point detection automatic alarm module and a scanning holder; the automatic alarm module is used for automatically detecting an environmental heat source of a monitoring point and detecting an ignition point in a sight line range in the scanning process of the holder; an alarm signal is issued when the presence of a suspected fire is detected.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The transmission line debris flow intelligent early warning system fused with 5G is installed in Yunnan Zhaotong and operates from the beginning of the year so far, the operation state is good, the early warning of the forest fire is realized, the accuracy rate is good, and the collected pictures are shown in figures 3 and 4.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A5G-fused intelligent early warning method for mountain fire of a power transmission line is characterized by comprising the following steps: the method comprises the following steps:
firstly, constructing a convolution neural network;
secondly, respectively acquiring a plurality of mountain fire images and a plurality of non-mountain fire images as training sets and test sets, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images;
thirdly, extracting the features of the images in the training set, and training the convolutional neural network based on the extracted image features;
fourthly, extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics, and calculating the accuracy of testing the convolutional neural network; if the accuracy is greater than the set threshold, executing a fifth step, otherwise executing a third step;
acquiring a real-time power transmission line image in a 5G communication mode, extracting image features of the power transmission line image, inputting the image features into a convolutional neural network, and outputting a judgment result by the convolutional neural network; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network.
2. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to claim 1, characterized in that: the process of training the convolutional neural network comprises a forward propagation process, the forward propagation process comprising:
taking the difference value between the class confidence of the image output by the convolutional neural network and the label class of the image mark as a Softmax _ Loss Loss function;
performing enhanced feature extraction on the feature vector of the image through the convolutional neural network to obtain an enhanced feature vector of the image;
acquiring a reinforced feature vector center corresponding to each category;
calculating the Euclidean distance between the reinforced feature vector of the image and the Center of the reinforced feature vector of the corresponding category, and taking the square of the Euclidean distance as a Center _ Loss function;
calculating a final loss function, wherein the final loss function is formulated as:
the final Loss function Softmax _ Loss + λ Center _ Loss,
wherein λ is a hyper-parameter.
3. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to claim 2, characterized in that: the process of training the convolutional neural network comprises a back-propagation process, the back-propagation process comprising:
and calculating the partial derivative of the final loss function according to the final loss function, and updating the weight parameters in the convolutional neural network.
4. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to any one of claims 1 to 3, characterized by comprising the following steps: the structure of the convolutional neural network is arranged according to an input layer, a convolutional layer, a pooling layer, a convolutional layer, a pooling layer and a full-connection layer, a ReLu function is selected as an activation function, a maximum pooling method is used for pooling, and the output of the current layer is represented as:
xe＝f(ue)
ue＝Wexe-1+be
wherein xeRepresents the output of the current layer, ueRepresenting the input of an activation function, f () representing the activation function, WeIs the weight of the current layer, beMay be biased.
5. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to claim 4, characterized in that: dropout is added after the pooling layer to disconnect the network, choosing to disconnect neurons with a probability of 0.3 and 0.45.
6. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to claim 4, characterized in that: the threshold in step four is set to 0.94.
7. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to claim 4, characterized in that: and in the fifth step, if the result output by the convolutional neural network is judged to be the occurrence of the forest fire, detecting whether the forest fire exists or not through an infrared video detection system arranged on the site, and if so, sending out a forest fire early warning.
8. The intelligent early warning method for the forest fire of the 5G-fused power transmission line according to claim 7, characterized in that: in the fifth step, the infrared video detection system comprises an embedded DSP temperature analysis fire point detection automatic alarm module and a scanning holder; the embedded DSP temperature analysis fire point detection automatic alarm module is used for automatically detecting an environmental heat source of a monitoring point and detecting a fire point in a sight line range in the scanning process of the scanning holder; an alarm signal is issued when the presence of a suspected fire is detected.
9. The utility model provides a fuse transmission line mountain fire intelligence early warning system of 5G which characterized in that: the system comprises a convolutional neural network construction module, an image data acquisition module, a training module, a test module and a monitoring module;
the convolutional neural network construction module is used for constructing a convolutional neural network;
the image data acquisition module is used for respectively acquiring a plurality of mountain fire images and a plurality of non-mountain fire images as training sets and test sets, and labeling the mountain fire images and the non-mountain fire images according to whether mountain fire exists in the images;
the training module is used for extracting the features of the images in the training set and training the convolutional neural network based on the extracted image features;
the test module is used for extracting the characteristics of the images in the test set, testing the trained convolutional neural network based on the extracted image characteristics and calculating the accuracy of testing the convolutional neural network; then judging whether the accuracy is greater than a set threshold value;
the monitoring module is used for acquiring a real-time power transmission line image in a 5G communication mode, extracting image characteristics of the power transmission line image and inputting the image characteristics into the convolutional neural network, and the convolutional neural network outputs a judgment result; and judging whether to send out the mountain fire early warning according to the result output by the convolutional neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110680030.1A CN113536938A (en) | 2021-06-18 | 2021-06-18 | 5G-fused intelligent early warning method and system for forest fire of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110680030.1A CN113536938A (en) | 2021-06-18 | 2021-06-18 | 5G-fused intelligent early warning method and system for forest fire of power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113536938A true CN113536938A (en) | 2021-10-22 |
Family
ID=78125126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110680030.1A Pending CN113536938A (en) | 2021-06-18 | 2021-06-18 | 5G-fused intelligent early warning method and system for forest fire of power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536938A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762083A (en) * | 2022-11-11 | 2023-03-07 | 南方电网数字电网科技(广东)有限公司 | Line component identification alarm method and system based on unmanned detector |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228734A (en) * | 2016-07-29 | 2016-12-14 | 国网电力科学研究院武汉南瑞有限责任公司 | The monitoring of a kind of mountain fire based on miniradar and localization method |
| CN107330394A (en) * | 2017-06-27 | 2017-11-07 | 国网湖南省电力公司 | A kind of transmission line forest fire based on extreme learning machine sentences knowledge method |
| CN108205862A (en) * | 2017-12-11 | 2018-06-26 | 厦门亿力吉奥信息科技有限公司 | Transmission line forest fire guard system |
| CN109522819A (en) * | 2018-10-29 | 2019-03-26 | 西安交通大学 | A kind of fire image recognition methods based on deep learning |
| CN109886227A (en) * | 2019-02-27 | 2019-06-14 | 哈尔滨工业大学 | Inside fire video frequency identifying method based on multichannel convolutive neural network |
| CN111652021A (en) * | 2019-04-30 | 2020-09-11 | 上海铼锶信息技术有限公司 | Face recognition method and system based on BP neural network |
| WO2020239540A1 (en) * | 2019-05-27 | 2020-12-03 | Robert Bosch Gmbh | Method and apparatus for detecting smoke |
| CN112614130A (en) * | 2021-01-04 | 2021-04-06 | 东华大学 | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 |
-
2021
- 2021-06-18 CN CN202110680030.1A patent/CN113536938A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228734A (en) * | 2016-07-29 | 2016-12-14 | 国网电力科学研究院武汉南瑞有限责任公司 | The monitoring of a kind of mountain fire based on miniradar and localization method |
| CN107330394A (en) * | 2017-06-27 | 2017-11-07 | 国网湖南省电力公司 | A kind of transmission line forest fire based on extreme learning machine sentences knowledge method |
| CN108205862A (en) * | 2017-12-11 | 2018-06-26 | 厦门亿力吉奥信息科技有限公司 | Transmission line forest fire guard system |
| CN109522819A (en) * | 2018-10-29 | 2019-03-26 | 西安交通大学 | A kind of fire image recognition methods based on deep learning |
| CN109886227A (en) * | 2019-02-27 | 2019-06-14 | 哈尔滨工业大学 | Inside fire video frequency identifying method based on multichannel convolutive neural network |
| CN111652021A (en) * | 2019-04-30 | 2020-09-11 | 上海铼锶信息技术有限公司 | Face recognition method and system based on BP neural network |
| WO2020239540A1 (en) * | 2019-05-27 | 2020-12-03 | Robert Bosch Gmbh | Method and apparatus for detecting smoke |
| CN112614130A (en) * | 2021-01-04 | 2021-04-06 | 东华大学 | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 |
Non-Patent Citations (3)
| Title |
|---|
| JIE SHI 等: "Detection and Segmentation of Power Line Fires in Videos", 《2020 IEEE POWER & ENERGY SOCIETY INNOVATIVE SMART GRID TECHNOLOGIES CONFERENCE (ISGT)》 * |
| 吴雪等: "基于数据增强的卷积神经网络火灾识别", 《科学技术与工程》 * |
| 张骥等: "基于深度学习的输电线路外破图像识别技术", 《计算机系统应用》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762083A (en) * | 2022-11-11 | 2023-03-07 | 南方电网数字电网科技(广东)有限公司 | Line component identification alarm method and system based on unmanned detector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113516076B (en) | Attention mechanism improvement-based lightweight YOLO v4 safety protection detection method | |
| CN110827435A (en) | External damage monitoring method and system based on intelligent warning post and readable storage medium | |
| CN104737202A (en) | Fire detection method and apparatus | |
| CN112087528B (en) | Intelligent water environment monitoring system and method based on deep learning | |
| CN112697798B (en) | Infrared image-oriented diagnosis method and device for current-induced thermal defects of power transformation equipment | |
| CN208443773U (en) | A kind of unmanned plane line walking defect detecting device based on heat radiation | |
| CN110867046A (en) | Intelligent car washer video monitoring and early warning system based on cloud computing | |
| CN113177614A (en) | Image recognition system and method for power supply switch cabinet of urban rail transit | |
| CN113536938A (en) | 5G-fused intelligent early warning method and system for forest fire of power transmission line | |
| CN107153160A (en) | A kind of wind power generating set all-position safety monitoring system | |
| CN112614130A (en) | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 | |
| CN111126529B (en) | Barrel-turning data acquisition method and device, electronic equipment and garbage truck | |
| CN115700753A (en) | Unmanned aerial vehicle patrols and examines image defect identification system based on mobile terminal technique | |
| CN115841730A (en) | Video monitoring system and abnormal event detection method | |
| CN113723701A (en) | Forest fire monitoring and predicting method and system, electronic equipment and storage medium | |
| CN107527478A (en) | A kind of Yellow River dam shore monitoring alarm report danger system based on network communication platform | |
| CN111967419B (en) | Dam bank dangerous case prediction method, dam bank dangerous case prediction device, computer equipment and storage medium | |
| CN113222548A (en) | Community property eagle eye monitoring system and use method | |
| CN117789403A (en) | Real-time detection method and system for personnel invasion in dangerous area of driving operation | |
| Zheng et al. | Forest farm fire drone monitoring system based on deep learning and unmanned aerial vehicle imagery | |
| CN116363397A (en) | Equipment fault checking method, device and inspection system | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation | |
| CN115700644A (en) | Vision-based automatic inspection method and device for wind power station | |
| CN111289853A (en) | Channel-space attention mechanism-based insulator detection system and algorithm | |
| CN113657542A (en) | Multi-dimensional correlation early warning system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211022 |
|
| RJ01 | Rejection of invention patent application after publication |