Disclosure of Invention
The application provides a method, a system and an electronic device for detecting defects of a power transmission line, and aims to solve at least one of the technical problems in the prior art to a certain extent.
In order to solve the above problems, the present application provides the following technical solutions:
a method for detecting defects of a power transmission line is characterized by constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of power transmission line elements, and specifically comprises the following steps:
step a: constructing a virtual sample generation and labeling model of virtual-real integration, integrating abundant ground feature information in virtual data and real image data, and fusing the virtual data and the real data;
step b: constructing a deep learning transfer learning model, and completing model optimization based on transfer learning;
step c: and training a deep learning model based on a target detection algorithm, and diagnosing the abnormality of the power transmission line element on the basis of the target detection of the deep learning.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the image sample data of the power transmission line element comprises visible light, infrared and ultraviolet sample data, and further comprises a normal labeling image and a defect labeling image.
The technical scheme adopted by the embodiment of the application further comprises the following steps: in the step c, the deep learning model includes: and respectively constructing a defect target detection model, a multi-model ensemble learning model and a fusion detection model aiming at the visible light, infrared and ultraviolet image sample data, completing model training and parameter adjustment optimization, outputting a power transmission line defect detection model, and identifying the defects of the power transmission line elements.
The technical scheme adopted by the embodiment of the application further comprises the following steps: constructing a risk assessment early warning model based on deep reinforcement learning and space-time weak correlation analysis according to the power transmission line defect detection model, and performing strategy learning of disaster information, disaster multi-source information fusion and analysis and risk assessment disaster early warning; the method for constructing the risk assessment early warning model based on the deep reinforcement learning and the space-time weak correlation analysis specifically comprises the following steps:
step d: constructing a power transmission line fault space-time weak correlation analysis model;
step e: constructing a risk assessment and fault prediction model of the hidden danger of the line defect;
step f: and establishing a reinforcement learning risk assessment early warning model by adopting a deep reinforcement learning algorithm.
The technical scheme adopted by the embodiment of the application further comprises the following steps: constructing a defect detection model distribution deployment system and a model optimization system based on deep learning according to the power transmission line defect detection model and the risk assessment early warning model, and applying model mobile deployment, defect identification and risk evaluation; the method specifically comprises the following steps:
step g: deploying a mobile terminal of the terminal based on a Caffe2 framework, wherein the deployment comprises weight pruning, weight quantification, model storage, forward acceleration calculation improvement and application, equipment identification and a power transmission line defect detection model are deployed at the mobile terminal;
step h: performing online defect detection on the mobile terminal by using a trained and tested defect detection model, and identifying and marking a defect element in a detection image;
step i: constructing a multi-source heterogeneous mass big data platform for defects and risks of the power transmission line, and acquiring and accessing mass data;
step j: interface specifications are formulated, real-time acquisition, access verification and reinforcement learning model optimization adjustment of various streaming data are realized at a server side, distribution and deployment are realized through the interface specifications aiming at an optimized model, and a terminal receives the data to update the model.
Another technical scheme adopted by the embodiment of the application is as follows: a transmission line defect detection system, comprising:
a defect detection model construction module: the method comprises the steps of constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of power transmission line elements; the defect detection model building module comprises:
virtual and real integrated units: the virtual sample generation and labeling model is used for constructing a virtual-real integrated model, integrating abundant ground feature information in virtual data and real image data, and fusing the virtual data and the real data;
a transfer learning unit: the method is used for constructing a deep learning transfer learning model and finishing model optimization based on transfer learning;
a model training unit: the method is used for training a deep learning model based on a target detection algorithm and diagnosing the abnormity of the power transmission line element on the basis of the target detection of the deep learning.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the image sample data of the power transmission line element comprises visible light, infrared and ultraviolet sample data, and further comprises a normal labeling image and a defect labeling image.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the deep learning model comprises: and respectively constructing a defect target detection model, a multi-model ensemble learning model and a fusion detection model aiming at the visible light, infrared and ultraviolet image sample data, completing model training and parameter adjustment optimization, outputting a power transmission line defect detection model, and identifying the defects of the power transmission line elements.
The technical scheme adopted by the embodiment of the application further comprises a risk assessment early warning model construction module: the risk assessment early warning model is used for constructing a risk assessment early warning model based on deep reinforcement learning and space-time weak correlation analysis according to the power transmission line defect detection model, and is used for carrying out strategy learning of disaster information, disaster multi-source information fusion and analysis and risk assessment disaster early warning; the risk assessment early warning model building module specifically comprises:
a first model construction unit: the method is used for constructing a power transmission line fault space-time weak correlation analysis model;
a second model construction unit: the method is used for constructing a risk assessment and fault prediction model of the hidden danger of the line defect;
a third model construction unit: the method is used for establishing the reinforcement learning risk assessment early warning model by adopting a deep reinforcement learning algorithm.
The technical scheme adopted by the embodiment of the application further comprises a deployment and application module: the system comprises a fault detection model distribution and deployment system and a model optimization system, wherein the fault detection model distribution and deployment system and the model optimization system are used for constructing a fault detection model distribution and deployment system and a model optimization system based on deep learning according to the power transmission line fault detection model and the risk assessment early warning model and are used for model mobile deployment, fault identification and risk evaluation application; the deployment and application module specifically includes:
a model deployment unit: the method is used for deploying the mobile terminal of the terminal based on the Caffe2 framework, and comprises weight pruning, weight quantification, model storage, forward acceleration calculation improvement and application, equipment identification and a power transmission line defect detection model are deployed at the mobile terminal;
a defect identification unit: the defect detection module is used for carrying out online defect detection on the mobile terminal by using the trained and tested defect detection model, and identifying and marking the defect elements in the detected image;
a risk evaluation unit: the multi-source heterogeneous mass big data platform is used for constructing defects and risks of the power transmission line and is used for acquiring and accessing mass data;
an optimization updating unit: the method is used for formulating interface specifications, realizing real-time acquisition, access verification and reinforcement learning model optimization adjustment of various streaming data at a server end, realizing distribution and deployment through the interface specifications aiming at an optimized model, and updating the model after receiving by a terminal.
The embodiment of the application adopts another technical scheme that: an electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the following operations of the transmission line defect detection method described above:
the method comprises the following steps of constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of power transmission line elements, and specifically comprising the following steps:
step a: constructing a virtual sample generation and labeling model of virtual-real integration, integrating abundant ground feature information in virtual data and real image data, and fusing the virtual data and the real data;
step b: constructing a deep learning transfer learning model, and completing model optimization based on transfer learning;
step c: and training a deep learning model based on a target detection algorithm, and diagnosing the abnormality of the power transmission line element on the basis of the target detection of the deep learning.
Compared with the prior art, the embodiment of the application has the advantages that: according to the method, the system and the electronic equipment for detecting the defects of the power transmission line, a power transmission line defect detection model based on visible light, infrared, ultraviolet and other multi-image fusion is established by performing deep learning distributed training on a mass of image samples; aiming at the characteristics of multi-dimension and multi-source isomerism of disaster information, a real-time high-efficiency processing big data platform of multi-mode isomerism mass data is constructed, a reinforcement learning risk assessment model is established, strategy learning of disaster information is carried out, and disaster multi-source information fusion and analysis and risk assessment disaster early warning are achieved. Compared with the prior art, the defect identification accuracy can be improved, and the inspection work efficiency and quality are improved.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Please refer to fig. 1, which is a flowchart of a method for detecting defects of a power transmission line according to an embodiment of the present application. The method for detecting the defects of the power transmission line comprises the following steps:
step 100: constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of the power transmission line element, and performing abnormity diagnosis on the power transmission line element;
in step 100, image sample data of the power transmission line elements comprise sample data of visible light, infrared, ultraviolet and the like, and comprise normal annotation images and defect annotation images, wherein the image sample data comprise multi-source images of all types of elements, and the number of the images of each type of elements meets the requirements of deep learning network training. The power transmission line defect detection model based on virtual and real sample integration and transfer learning can realize a learning mode that a source task of target recognition in a virtual scene is transferred to a target task of target recognition in a real scene, realize the fusion of an element automatic marking sample and an artificial marking sample and iterative incremental learning, reduce the workload of an artificial marking training data set and improve overfitting caused by too little defect data. Specifically, the method for constructing the power transmission line defect detection model based on virtual and real sample integration and transfer learning mainly comprises the following steps:
step 101: constructing a virtual sample generation and labeling model of virtual-real integration, which is used for integrating abundant ground feature information in virtual data and real image data to realize effective fusion of the virtual data and the real data;
step 102: constructing a deep learning transfer learning model, and realizing model optimization based on transfer learning;
in step 102, after a virtual sample generation and labeling model of virtual-real integration is constructed, the model is migrated to actual data training, migration learning is realized based on a deep learning framework, a source task of a virtual data learning model is firstly performed, a target task of an actual data learning optimization model is then performed, and model optimization based on migration learning is realized.
Step 103: training a deep learning model based on target detection algorithms such as Spark, TensorFlow, Caffe framework, FasterR-CNN, YOLO, SSD and the like, and carrying out abnormity diagnosis on the power transmission line element on the basis of target detection of deep learning;
in step 103, the deep learning model includes: and respectively constructing a defect target detection model, a multi-model integrated learning model and a fusion detection model aiming at sample data of visible light, infrared and ultraviolet images, completing model training and parameter adjustment optimization, outputting a power transmission line defect detection model, and realizing online intelligent identification of the element defects of the power transmission line.
Step 200: constructing a risk assessment early warning model based on deep reinforcement learning and space-time weak correlation analysis according to the power transmission line defect detection model, performing strategy learning of disaster information, and realizing disaster multi-source information fusion and analysis and risk assessment disaster early warning;
in step 200, constructing a risk assessment early warning model based on deep reinforcement learning and space-time weak correlation analysis mainly comprises the following steps:
step 201: constructing a power transmission line fault space-time weak correlation analysis model; based on deep mining of historical fault data of the overhead line, researching the space-time characteristics of state characteristics of the overhead line, analyzing the incidence relation between the defect development of the overhead line and the influence of a fault chain effect on the environment, screening different types of fault characteristics from multidimensional state quantities by adopting a characteristic matching algorithm, resolving the intrinsic incidence relation between the fault characteristics of the power transmission line and multidimensional data parameters such as environment information, meteorological information and body characteristic information, constructing a power transmission line fault space-time weak correlation analysis model, and realizing the risk assessment of the overhead line based on the space-time correlation characteristics;
step 202: constructing a risk assessment and fault prediction model of the hidden danger of the line defect;
in step 202, the environments of the transmission line are complex and various, and the wires, insulators, hardware fittings, towers and grounding devices are exposed outside, so that the transmission line is greatly damaged along with the alternation of seasons, the change of climate and the occurrence of extreme natural disasters. In the embodiment of the application, historical operation and maintenance data of the overhead transmission line are rooted on the basis of historical defect monitoring data, meteorological data, external hidden dangers and big data information of body defect conditions according to the environmental characteristics of a transmission corridor and the characteristic information of a tower body, the correlation characteristics of the defects of the transmission line and the meteorological data are analyzed, and the correlation relationship between meteorological factors and the defects and hidden dangers of the transmission line is analyzed by using a time-space data mining algorithm; analyzing the defect occurrence probability of different regions by researching the spatial characteristics of different defect types; and analyzing the occurrence probability of different defects of the overhead transmission line by combining the space-time correlation result and the overhead line defect space distribution characteristic, and constructing line defect hidden danger risk assessment and fault prediction.
Step 203: establishing a reinforcement learning risk assessment early warning model by adopting a deep reinforcement learning algorithm;
in step 203, the data preprocessing divides the input information into operation environment data and operation state data, the deep reinforcement learning algorithm adopts a mode of combining a competitive Q network and a dual Q network, the competitive Q network divides a return value into an operation environment return value and an operation state return value, and the dual Q network is responsible for selecting the operation state data and evaluating the operation state effect. The front part of the deep convolutional neural network model framework is used for learning the operation environment data by partial convolutional kernels, and the rest convolutional kernels are used for learning the operation state information data, so that the training efficiency is improved, a uniform standard environment is provided for disaster evaluation comparison under the same condition, and the result is more reasonable. In addition, the operation environment information can be correspondingly changed in different operation modes, and the competitive Q network can obtain different environment return values aiming at different operation modes, so that the generalization capability of the model is enhanced, and the algorithm performance is improved. The risk assessment method starts from power grid operation data directly, and does not need to adjust models for analysis of different defect faults, defect fault types and power grid operation modes, while the traditional method needs to adjust mathematical models according to different operation modes, fault types and topological results. In addition, the influence of various factors of the air environment such as weather and the like is considered at the same time, and more comprehensive auxiliary decision can be provided.
Step 300: a defect detection model distribution deployment system and a model optimization system based on deep learning are constructed according to the power transmission line defect detection model and the risk assessment early warning model, and model mobile deployment, defect identification and risk evaluation application are realized;
in step 300, constructing a defect detection model distribution deployment system and a model optimization system based on deep learning mainly comprises the following steps:
step 301: deploying a model; mobile terminal deployment of various types of terminals is realized based on a Caffe2 framework, and technologies such as weight pruning, weight quantification, model storage, forward acceleration calculation and the like are improved and applied, and equipment identification and a power transmission line defect detection model are deployed at the mobile terminal;
step 302: identifying defects; performing online defect detection on the mobile terminal by using a trained and tested defect detection model, and identifying and marking a defect element in a detection image;
step 303: evaluating the risk; constructing a multi-source heterogeneous mass big data platform of the defects and risks of the power transmission line, and realizing mass data acquisition access;
step 304: a data acquisition access verification and model optimization updating mechanism; the method comprises the steps of formulating interface specifications, realizing real-time acquisition, access verification and reinforcement learning model optimization adjustment of various streaming data at a server end, realizing distribution and deployment through the interface specifications aiming at an optimized model, updating the model after receiving the model by a terminal, and realizing model mobile deployment, defect identification and risk evaluation application.
Please refer to fig. 2, which is a schematic structural diagram of a power transmission line defect detection system according to an embodiment of the present application. The power transmission line defect detection system comprises a defect detection model building module, a risk assessment early warning model building module and a deployment and application module.
A defect detection model construction module: constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of the power transmission line element, and performing abnormity diagnosis on the power transmission line element; the image sample data of the power transmission line elements comprises sample data of visible light, infrared, ultraviolet and the like, and comprises normal annotation images and defect annotation images, wherein the image sample data comprises multi-source images of all types of elements, and the number of the images of each type of elements meets the requirement of deep learning network training. The power transmission line defect detection model based on virtual and real sample integration and transfer learning can realize a learning mode that a source task of target recognition in a virtual scene is transferred to a target task of target recognition in a real scene, realize the fusion of an element automatic marking sample and an artificial marking sample and iterative incremental learning, reduce the workload of an artificial marking training data set and improve overfitting caused by too little defect data.
Specifically, the defect detection model building module comprises:
virtual and real integrated units: the virtual sample generation and labeling model is used for constructing virtual and real integration, and is used for integrating abundant ground feature information in virtual data and real image data to realize effective fusion of the virtual data and the real data;
a transfer learning unit: the method is used for constructing a deep learning transfer learning model and realizing model optimization based on transfer learning; in the embodiment of the application, after a virtual sample generation and labeling model of virtual-real integration is constructed, the model is migrated to actual data training, migration learning is realized based on a deep learning framework, a source task of a virtual data learning model is firstly carried out, a target task of an actual data learning optimization model is then carried out, and model optimization based on the migration learning is realized.
A model training unit: the method is used for training a deep learning model based on Spark, TensorFlow, Caffe framework, FasterR-CNN, YOLO, SSD and other target detection algorithms, and carrying out abnormity diagnosis on the power transmission line element on the basis of target detection of deep learning; wherein, the deep learning model includes: and respectively constructing a defect target detection model, a multi-model integrated learning model and a fusion detection model aiming at sample data of visible light, infrared and ultraviolet images, completing model training and parameter adjustment optimization, outputting a power transmission line defect detection model, and realizing online intelligent identification of the element defects of the power transmission line.
A risk assessment early warning model construction module: the risk assessment early warning system is used for constructing a risk assessment early warning model based on deep reinforcement learning and space-time weak correlation analysis according to the power transmission line defect detection model, performing strategy learning of disaster information, and achieving disaster multi-source information fusion and analysis and risk assessment disaster early warning;
specifically, the risk assessment early warning model building module comprises:
a first model construction unit: the method is used for constructing a power transmission line fault space-time weak correlation analysis model; based on deep mining of historical fault data of the overhead line, researching the space-time characteristics of state characteristics of the overhead line, analyzing the incidence relation between the defect development of the overhead line and the influence of a fault chain effect on the environment, screening different types of fault characteristics from multidimensional state quantities by adopting a characteristic matching algorithm, resolving the intrinsic incidence relation between the fault characteristics of the power transmission line and multidimensional data parameters such as environment information, meteorological information and body characteristic information, constructing a power transmission line fault space-time weak correlation analysis model, and realizing the risk assessment of the overhead line based on the space-time correlation characteristics;
a second model construction unit: the method is used for constructing a risk assessment and fault prediction model of the hidden danger of the line defect; the transmission line is complex and diverse in environment, wires, insulators, hardware fittings, towers and grounding devices are exposed outside, and great damage is caused to the transmission line along with seasonal alternation, climate change and extreme natural disasters. In the embodiment of the application, historical operation and maintenance data of the overhead transmission line are rooted on the basis of historical defect monitoring data, meteorological data, external hidden dangers and big data information of body defect conditions according to the environmental characteristics of a transmission corridor and the characteristic information of a tower body, the correlation characteristics of the defects of the transmission line and the meteorological data are analyzed, and the correlation relationship between meteorological factors and the defects and hidden dangers of the transmission line is analyzed by using a time-space data mining algorithm; analyzing the defect occurrence probability of different regions by researching the spatial characteristics of different defect types; and analyzing the occurrence probability of different defects of the overhead transmission line by combining the space-time correlation result and the overhead line defect space distribution characteristic, and constructing line defect hidden danger risk assessment and fault prediction.
A third model construction unit: the system is used for establishing a reinforcement learning risk assessment early warning model by adopting a deep reinforcement learning algorithm; the data preprocessing divides input information into operation environment data and operation state data, the deep reinforcement learning algorithm adopts a mode of combining a competitive Q network and a dual Q network, the competitive Q network divides return values into operation environment return values and operation state return values, and the dual Q network is responsible for selecting the operation state data and evaluating operation state effects. The front part of the deep convolutional neural network model framework is used for learning the operation environment data by partial convolutional kernels, and the rest convolutional kernels are used for learning the operation state information data, so that the training efficiency is improved, a uniform standard environment is provided for disaster evaluation comparison under the same condition, and the result is more reasonable. In addition, the operation environment information can be correspondingly changed in different operation modes, and the competitive Q network can obtain different environment return values aiming at different operation modes, so that the generalization capability of the model is enhanced, and the algorithm performance is improved. The risk assessment method starts from power grid operation data directly, and does not need to adjust models for analysis of different defect faults, defect fault types and power grid operation modes, while the traditional method needs to adjust mathematical models according to different operation modes, fault types and topological results. In addition, the influence of various factors of the air environment such as weather and the like is considered at the same time, and more comprehensive auxiliary decision can be provided.
Deployment and application module: the method is used for constructing a defect detection model distribution deployment system and a model optimization system based on deep learning according to a defect detection model and a risk assessment early warning model of the power transmission line, and realizing model mobile deployment, defect identification and risk evaluation application;
specifically, the deployment and application module includes:
a model deployment unit: the method is used for realizing mobile terminal deployment of various types of terminals based on a Caffe2 framework, and comprises the improvement and application of technologies such as weight pruning, weight quantification, model storage, forward acceleration calculation and the like, and equipment identification and a power transmission line defect detection model are deployed at a mobile terminal;
a defect identification unit: the defect detection module is used for carrying out online defect detection on the mobile terminal by using the trained and tested defect detection model, and identifying and marking the defect elements in the detected image;
a risk evaluation unit: the multi-source heterogeneous mass big data platform is used for constructing defects and risks of the power transmission line, and mass data acquisition access is realized;
an optimization updating unit: the system is used for realizing data acquisition access verification and model optimization updating mechanism; the method comprises the steps of formulating interface specifications, realizing real-time acquisition, access verification and reinforcement learning model optimization adjustment of various streaming data at a server end, realizing distribution and deployment through the interface specifications aiming at an optimized model, updating the model after receiving the model by a terminal, and realizing model mobile deployment, defect identification and risk evaluation application.
Fig. 3 is a schematic structural diagram of hardware equipment of the power transmission line defect detection method provided in the embodiment of the present application. As shown in fig. 3, the device includes one or more processors and memory. Taking a processor as an example, the apparatus may further include: an input system and an output system.
The processor, memory, input system, and output system may be connected by a bus or other means, as exemplified by the bus connection in fig. 3.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor executes various functional applications and data processing of the electronic device, i.e., implements the processing method of the above-described method embodiment, by executing the non-transitory software program, instructions and modules stored in the memory.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processing system over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input system may receive input numeric or character information and generate a signal input. The output system may include a display device such as a display screen.
The one or more modules are stored in the memory and, when executed by the one or more processors, perform the following for any of the above method embodiments:
the method comprises the following steps of constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of power transmission line elements, and specifically comprising the following steps:
step a: constructing a virtual sample generation and labeling model of virtual-real integration, integrating abundant ground feature information in virtual data and real image data, and fusing the virtual data and the real data;
step b: constructing a deep learning transfer learning model, and completing model optimization based on transfer learning;
step c: and training a deep learning model based on a target detection algorithm, and diagnosing the abnormality of the power transmission line element on the basis of the target detection of the deep learning.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
Embodiments of the present application provide a non-transitory (non-volatile) computer storage medium having stored thereon computer-executable instructions that may perform the following operations:
the method comprises the following steps of constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of power transmission line elements, and specifically comprising the following steps:
step a: constructing a virtual sample generation and labeling model of virtual-real integration, integrating abundant ground feature information in virtual data and real image data, and fusing the virtual data and the real data;
step b: constructing a deep learning transfer learning model, and completing model optimization based on transfer learning;
step c: and training a deep learning model based on a target detection algorithm, and diagnosing the abnormality of the power transmission line element on the basis of the target detection of the deep learning.
Embodiments of the present application provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the following:
the method comprises the following steps of constructing a power transmission line defect detection model based on virtual and real sample integration and transfer learning according to image sample data of power transmission line elements, and specifically comprising the following steps:
step a: constructing a virtual sample generation and labeling model of virtual-real integration, integrating abundant ground feature information in virtual data and real image data, and fusing the virtual data and the real data;
step b: constructing a deep learning transfer learning model, and completing model optimization based on transfer learning;
step c: and training a deep learning model based on a target detection algorithm, and diagnosing the abnormality of the power transmission line element on the basis of the target detection of the deep learning.
According to the method, the system and the electronic equipment for detecting the defects of the power transmission line, a power transmission line defect detection model based on visible light, infrared, ultraviolet and other multi-image fusion is established by performing deep learning distributed training on a mass of image samples; aiming at the characteristics of multi-dimension and multi-source isomerism of disaster information, a real-time high-efficiency processing big data platform of multi-mode isomerism mass data is constructed, a reinforcement learning risk assessment model is established, strategy learning of disaster information is carried out, and disaster multi-source information fusion and analysis and risk assessment disaster early warning are achieved. Compared with the prior art, the defect identification accuracy can be improved, and the inspection work efficiency and quality are improved.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.