CN113305840A

CN113305840A - Intelligent electric power overhaul robot visual identification system based on raspberry group

Info

Publication number: CN113305840A
Application number: CN202110579207.9A
Authority: CN
Inventors: 陈忠孝; 陈家瑞; 冯怡菲; 卢峰宇; 马卓
Original assignee: Xian Technological University
Current assignee: Xian Technological University
Priority date: 2021-05-26
Filing date: 2021-05-26
Publication date: 2021-08-27

Abstract

The application belongs to the robot vision field, discloses an intelligence electric power overhauls robot vision identification system based on raspberry group, including camera, raspberry group, K60 singlechip, computer and robot, the camera passes through USB and connects the raspberry group, the raspberry group carries out data communication interconnection through the Socket with the computer, the computer link K60 singlechip, the robot is connected to the K60 singlechip. The system collects field surrounding data through the camera, sends the data to the computer for image processing and identification, and sends the data to the K60 singlechip control robot, and the system has an image identification function, can greatly improve the automation rate, reduces the manpower consumption, and accords with the modern power development trend; and the whole system is light and flexible, and has higher speed compared with the traditional method.

Description

Intelligent electric power overhaul robot visual identification system based on raspberry group

Technical Field

The application belongs to the robot vision field, concretely relates to intelligent electric power overhauls robot vision identification system based on raspberry group.

Background

The traditional intelligent electric power overhaul robot mostly adopts a method of manually identifying control or multi-sensor fruit identification to identify the internal circuit of the power distribution cabinet, the efficiency is low, a large amount of manpower is needed to complete the work, and the safety of operators can not be guaranteed to a great extent.

The image recognition technology of artificial intelligence is the most widely used technology at present, and has the characteristics of high flexibility, high accuracy and high automation degree. Meanwhile, the robot can be communicated and interconnected with a computer, the working condition can be checked on the computer, the human-computer interaction experience is good, and people can observe the robot working more intuitively. The method breaks through the traditional intelligent electric power overhaul robot line identification method, introduces an artificial intelligence method, and performs mode identification on fruits to complete picking.

Disclosure of Invention

To the above-mentioned not enough that prior art exists, the aim at of this application provides an intelligent electric power overhauls robot vision identification system based on raspberry group.

For the purpose above the realization, the utility model provides a visual identification system of intelligent electric power overhaul robot based on raspberry group adopts following technical scheme:

the utility model provides an intelligence electric power overhauls robot visual identification system based on raspberry group, includes camera, raspberry group, K60 singlechip, computer and robot, the camera passes through USB and connects the raspberry group, the raspberry group carries out the data communication interconnection through Socket with the computer, the computer link K60 singlechip, the robot is connected to the K60 singlechip.

Further, the computer is equipped with a Windows system.

Further, the computer is connected with the K60 single chip microcomputer through WIFI communication.

Further, the K60 single chip microcomputer is connected with the robot mechanical part and controls the robot mechanical part by outputting PWM waves.

Preferably, the camera is a 360-degree D70 intelligent camera kernel, the camera supports 1080P high-definition resolution, the diagonal angle of the lens view is 118 degrees, the rotation angle is 360 degrees horizontally and 260 degrees vertically, and dead-angle-free monitoring of a monitored area can be ensured; and secondly, the camera supports infrared and USB interface input, so that the integration of each module in the project system is facilitated.

Preferably, the K60 singlechip is a chip K60 singlechip of Feichka, the chip comprises a hardware FPU unit and a DSP instruction, and the kernel provides the DSP instruction of 1.25DMIPS/MHz based on an ARM Cortex-M4 kernel (the floating point unit is available in kinetis series). The chip K60 singlechip of Feichka's has optimized to the sensitive application of cost, can provide the selection of low pin, and has the operating condition of extremely low consumption for the K60 singlechip is particularly useful for the application that needs floating point operation or DSP processing, is fit for the processing of bionical four-footed control algorithm, and the quick operational capability of K60 singlechip can satisfy the complicated operation of four groups of robot image processing of making a video recording. Kinetis EA series MCU products share similar peripheral equipment and pins are compatible, and abundant division of the size of the memory size provides convenience for developers from excessive redundancy design to Kinetis compact design. The compatibility and expansibility of Kinetis EA series MCU can make the developer develop its products standardly, reuse hardware and software to the maximum extent, thus shorten the development cycle.

Compared with the prior art, the intelligent power overhaul robot visual identification system based on the raspberry group has the advantages that the data around the site are collected through the camera, sent to the computer for image processing and identification, and then sent to the K60 single chip microcomputer operation robot, the automatic rate can be greatly improved, the labor consumption is reduced, and the modern power development trend is met; the whole system is light and flexible, and has higher speed compared with the traditional method; can apply to automation fields such as electric power overhaul, can the open-air switch board of automatic identification and accomplish the function to switch board automatic overhaul, especially under the comparatively dangerous condition in open-air environment, can accomplish the design that unmanned operation repaired the switch board.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments with reference to the attached drawings in which:

FIG. 1 is a block diagram of a raspberry pi-based visual identification system of an intelligent power overhaul robot in the present application;

FIG. 2 is a schematic diagram of an autonomous power supply module with which the raspberry is equipped;

fig. 3 is a schematic diagram of Socket communication.

Detailed Description

The present application will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present application, but are not intended to limit the present application in any way. It should be noted that various changes and modifications can be made by one skilled in the art without departing from the spirit of the application. All falling within the scope of protection of the present application.

Example 1

As shown in figure 1, an intelligent electric power overhaul robot visual identification system based on a raspberry group comprises a camera, the raspberry group, a K60 single chip microcomputer, a computer with a Windows system and a robot mechanical part, wherein the camera is connected with the raspberry group through a USB, the raspberry group and the computer (an upper computer) are interconnected through Socket in a data communication mode, the computer is connected with the K60 single chip microcomputer through WIFI communication, the K60 single chip microcomputer (a lower computer) is connected with the robot mechanical part, and the robot mechanical part is controlled through output PWM waves.

The Raspberry PI is an ARM-based microcomputer mainboard, takes an SD/MicroSD card as a memory hard disk, and has the basic functions and interfaces of a personal computer host. The raspberry pie has small volume, is suitable for various small intelligent devices, has complete computer processing function, and supports the application of large-scale data calculation, graphic image processing and the like. The raspberry pie is provided with a GPIO interface and a USB interface, can directly use a written program with a specific function to control corresponding hardware equipment through the GPIO interface, and can also be connected with various peripheral hardware equipment through the USB. And the WIFI sending computer is used for carrying out centralized processing and calculation on the collected information, and then, the WIFI sending computer is connected with the K60 single chip microcomputer to send the collected data. The WIFI module used by the system conforms to IEEE802.11b, IEEE802.11g and IEEE802.11n network standards. The raspberry group is provided with an autonomous power supply module, free movement and portability can be realized, and the whole module is more flexible and portable. The schematic diagram of the autonomous power supply module is shown in fig. 2, the positive electrode of the 7.2V power supply voltage is connected with an inductor L6, an inductor L6 is connected with an encoder power supply, and the power output end of the encoder is connected with capacitors C2 and C3 in parallel.

The language pre-loaded and adopted by the raspberry and the computer is Python programming language, the Python is an object-oriented open-source cross-platform programming language, the raspberry and the computer pre-loaded and adopted by the raspberry and the computer pre-loaded and adopts Python, the Python is an object-oriented open-source cross-platform programming language, the raspberry and the computer pre-loaded and adopted by the computer pre-loaded and adopted by the raspberry and the computer pre-loaded and adopted by the Python is an object-oriented open-source cross-platform programming language, the raspberry and the computer pre-loaded and adopted by the computer pre-loaded and the computer pre-loaded and adopted by the computer pre-loaded and the Python is an object-oriented open-oriented cross-platform programming language, and the raspberry and the computer pre-loaded and the computer pre-loaded and adopting the raspberry and the computer pre-loaded and the computer.

The camera is a 360-degree D70 intelligent camera core, supports 1080P high-definition resolution, has a lens visual angle opposite angle visual angle of 118 degrees, is rotated by 360 degrees horizontally and 260 degrees vertically, and can ensure no dead angle monitoring of a monitoring area; and secondly, the camera supports infrared and USB interface input, so that the integration of each module in the project system is facilitated.

The K60 singlechip is a chip K60 singlechip of Feichka, the chip comprises a hardware FPU unit and a DSP instruction, and the kernel provides the DSP instruction of 1.25DMIPS/MHz based on an ARM Cortex-M4 kernel (the floating point unit is available in kinetis series). The chip K60 singlechip of Feichka's has optimized to the sensitive application of cost, can provide the selection of low pin, and has the operating condition of extremely low consumption for the K60 singlechip is particularly useful for the application that needs floating point operation or DSP processing, is fit for the processing of bionical four-footed control algorithm, and the quick operational capability of K60 singlechip can satisfy the complicated operation of four groups of robot image processing of making a video recording. Kinetis EA series MCU products share similar peripheral equipment and pins are compatible, and abundant division of the size of the memory size provides convenience for developers from excessive redundancy design to Kinetis compact design. The compatibility and expansibility of Kinetis EA series MCU can make the developer develop its products standardly, reuse hardware and software to the maximum extent, thus shorten the development cycle.

Intelligence electric power overhauls robot visual identification system based on raspberry group, operation process as follows:

(1) the data of the surrounding environment are collected through the camera and transmitted to the raspberry group through the data line for data preprocessing. The data is binarized, the gray value of the point on the image is 0 or 255, namely the whole image shows obvious black and white effect. That is, a gray scale image with 256 brightness levels is selected by a proper threshold value to obtain a binary image which can still reflect the whole and local features of the image.

Gary(i,j)＝(r(i,j)+g(i,j)+b(i,j))/3

(2) And performing Socket data communication interconnection on the binarized data through a WIFI module, and packaging and sending the data to a computer. The image information is evaluated and predicted according to the data obtained by the application program by writing the application software of the Windows operating system. And unpacking the data in a computer, and performing image processing by using an OpenCV platform to accurately identify the difference of each line. OpenCV is a BSD license (open source) based distributed cross-platform computer vision library that can run on Linux, Windows, Android, and Mac OS operating systems. The image processing system is light in weight and high in efficiency, is composed of a series of C functions and a small number of C + + classes, provides interfaces of languages such as Python, Ruby, MATLAB and the like, realizes a plurality of general algorithms in the aspects of image processing and computer vision, and can perform various self-developed image processing algorithm simulations on the platform. Referring to fig. 3, a TCP server creates a Socket first, then binds an ip and a port number (bind) to the Socket, monitors a set port (listen) to wait for a request of a client, and calls an accept block until the client is connected. If a client initiates a Socket and then connects to the server (Connect), if the connection is successful, the connection between the client and the server is established. The client sends a data request, the server receives the request and processes the request, then response data is sent to the client, the client reads the data, finally, the connection is closed, and one-time interaction is finished.

(3) And establishing a space model for the data, and sending the space model to the K60 singlechip through a wireless module. And establishing a coordinate system in the space to finish fruit grabbing work.

Specific embodiments of the present application have been described above. It is to be understood that the present application is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the present application.

Claims

1. The utility model provides an intelligence electric power overhauls robot visual identification system based on raspberry group, a serial communication port, including camera, raspberry group, K60 singlechip, computer and robot, the camera passes through USB and connects the raspberry group, the raspberry group carries out data communication interconnection with the computer through the Socket, the computer link K60 singlechip, the robot is connected to the K60 singlechip.

2. The raspberry pi based intelligent power overhaul robot visual identification system of claim 1, wherein the computer is equipped with a Windows system.

3. The raspberry pi based intelligent power overhaul robot visual identification system of claim 1, wherein the computer is connected to a K60 single chip microcomputer through WIFI communication.

4. The raspberry pi based intelligent visual identification system for electric power overhaul robots of claim 1, wherein the K60 single chip microcomputer is connected with the robotic mechanical part and controls the robotic mechanical part through outputting a PWM wave.

5. The raspberry pi based intelligent power overhaul robot visual identification system of claim 1, wherein the camera is a 360 degree D70 smart camera kernel.

6. The raspberry pi based intelligent power overhaul robot visual identification system of claim 1 wherein the K60 singlechip is a chip K60 singlechip of fickial.