Neural network system and method suitable for portable power inspection
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of electric power inspection and neural network, applied in the field of neural network system of portable electric power inspection, can solve the problems of poor inspection effect and low efficiency, and achieve the benefits of portable application, reduce size, reduce model accuracy and hardware the effect of the demand
Inactive Publication Date: 2019-07-12
ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER +1
View PDF8 Cites 17 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The main purpose of the present invention is to provide a neural network system and method suitable for portable electric power inspection, which can effectively solve the problem that the existing electric power inspection in the background technology needs to rely on manual research and judgment or remote large-scale server analysis and judgment for the video processing process. Avoid the problem of poor inspection effect or low efficiency caused by inspection process relying on 4G network or storage media
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0029] like figure 1 As shown, a neural network system suitable for portable electric power inspection includes an image acquisition module, a convolutional neural network operation module and peripheral functional units. The image acquisition module includes a thermal infrared camera, a visible light camera and an anti-shake platform. The convolutional neural network operating module is mainly used to process the convolutional neural network operation of image information, and the convolutional neural network operating module mainly includes CPU, GPU, NPU, TPU, FPGA hardware or a system-on-chip composed of the above-mentioned hardware Composition, the peripheral functional unit mainly includes power management, wireless image transmission, satellite positioning and display (increase or decrease according to actual needs).
[0030] The satellite positioning is used to locate the geographical location of the power system fault.
[0031] The wireless video transmission is used ...
Embodiment 2
[0034] like figure 2 As shown, a neural network inspection method suitable for portable power inspection, the system completes the power inspection task under the control of a multi-core CPU, one of the main CPU cores is used for process control, and the other CPU cores assist the convolutional neural network operation unit Complete information processing, the specific method steps are as follows:
[0035]1) After starting up, the infrared thermal imaging camera collects images first, while the visible light camera is in a standby state;
[0036] 2) When a suspected inspection target is detected in the infrared image, it is compared with the infrared image detected last time. If it is a new target, the visible light camera is used to collect the visible light image synchronously;
[0037] 3) Obtain the coordinates of the area where the target is located in the infrared image;
[0038] 4), according to the parameters of the two cameras, determine the coordinates of the targe...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a neural network system and method suitable for portable power inspection. The system comprises an image acquisition module, a convolutional neural network operation module anda peripheral function unit. The image acquisition module comprises a thermal infrared camera, a visible light camera and an anti-shake holder. The convolutional neural network operation module is mainly used for the operation of a convolutional neural network for processing image information. The convolutional neural network operation module is mainly composed of a CPU and hardware of a GPU, an NPU, a TPU and an FPGA or a system-on-chip composed of the hardware. The invention discloses a neural network system and method suitable for portable power inspection. A thermal infrared camera is adopted to determine the position of the power equipment; the visible light camera is used for studying and judging the state of the power equipment at the position, the influence of a complex backgroundon target recognition is effectively reduced, the infrared image information is less than visible light image information, the image processing speed is higher when the convolutional neural network isused for processing the image, and therefore the requirements for model precision and hardware are reduced.
Description
technical field [0001] The invention relates to the field of electric power inspection, in particular to a neural network system and method suitable for portable electric power inspection. Background technique [0002] Electric power inspection is one of the important tasks to ensure power operation. Due to the problems of low efficiency, high labor cost, and difficulty in traditional manual inspection, the current more advanced method is to use drones equipped with high-definition cameras to shoot aerial inspections. Check the video, and determine the fault defect by studying and judging the video. There are three main methods of video research and judgment. 1. The video is transmitted to the ground through the wireless network, and the ground personnel analyze and determine fault defects in real time; 2. The video is remotely transmitted to the cloud through 4G or other public networks or self-built networks, and artificial intelligence analysis is performed to determine f...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/06G06T7/00G06N3/04
CPCG06Q50/06G06T7/0004G06N3/045
Inventor 杨罡姜敏原辉王帅王大伟张娜张兴忠
Owner ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER
Login to view more 
Login to view more