CN112637451A - Based on AI image recognition sensor probe mends limit control system - Google Patents
Based on AI image recognition sensor probe mends limit control system Download PDFInfo
- Publication number
- CN112637451A CN112637451A CN202011429662.2A CN202011429662A CN112637451A CN 112637451 A CN112637451 A CN 112637451A CN 202011429662 A CN202011429662 A CN 202011429662A CN 112637451 A CN112637451 A CN 112637451A
- Authority
- CN
- China
- Prior art keywords
- kernel
- image recognition
- sensor probe
- bit mcu
- recognition sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/54—Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/044—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means by capacitive means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P6/00—Arrangements for controlling synchronous motors or other dynamo-electric motors using electronic commutation dependent on the rotor position; Electronic commutators therefor
- H02P6/08—Arrangements for controlling the speed or torque of a single motor
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/56—Cameras or camera modules comprising electronic image sensors; Control thereof provided with illuminating means
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Power Engineering (AREA)
- Color Television Image Signal Generators (AREA)
Abstract
The invention relates to the technical field of automatic control, and discloses an AI-based image recognition sensor probe edge supplementing control system, which comprises an AI image recognition sensor probe, a motor driver and an edge supplementing controller, wherein the AI image recognition sensor probe comprises an image acquisition element, an RGB (red, green and blue) three-color background light source and a RISC-V (reduced instruction-set computer-graphics) kernel 64-bit MCU (micro controller unit); the motor driver comprises an electric push rod and a drive board, wherein the drive board comprises a three-phase drive bridge consisting of a power supply conversion module, an ARM core-M4 kernel 32-bit MCU, a magnetic angle position sensor, a high-speed ADC and six power MOS (metal oxide semiconductor) tubes; the edge-supplementing controller comprises a human-computer interaction panel, a high-precision A/D converter, an ARM Cotex-M3 kernel 32-bit MCU, a PWM pulse amplification power device, a remote IO and a remote serial communication interface. The invention is not only suitable for real-time detection of materials with various specifications and shapes, but also greatly improves the positioning precision while solving the signal interference and also provides a friendly human-computer interaction effect.
Description
Technical Field
The invention relates to the technical field of automatic control, in particular to an AI image recognition sensor-based probe edge repairing control system.
Background
In most of the existing automatic production lines, in the links of material transmission, transportation, processing and the like, in order to avoid the material from deviating, an automatic edge-repairing control system consisting of a sensor probe, a driving mechanism, a matched controller and an algorithm is required to track, monitor and adjust the advancing track of the material.
In the existing automatic edge-repairing control system, the commonly used displacement detection sensors generally include three types, namely an ultrasonic sensor, an infrared photoelectric sensor and a CCD image sensor. The image scanning detection element adopted by the CCD image sensor detection probe is a color or gray-scale linear array CCD image sensor, but the linear array CCD image sensor can only track continuous and tidy edges or lines, and for some materials without tidy edges or lines, the existing linear array CCD image sensor tracking technology cannot be realized.
In addition, in the conventional automatic trimming control system, the brushless motor adopts a switch hall sensor as a rotor position detection element of the motor. The device has the advantages of simple structure and convenience in control, but has the defect of low positioning accuracy, and in the field use process of a user, because a certain distance may exist between a motor driver and the installation position of a motor, strong electromagnetic interference generally exists in some fields with a large amount of electrical equipment (such as frequency converters), if the field wiring is unreasonable, the signal of a Hall switch position sensor carried by the motor is interfered, so that the motor driver cannot detect an accurate commutation signal, and the normal operation of the motor is influenced.
In addition, in order to further improve the human-computer interaction effect, the input and output ports of the controller need to be improved, so that the problems of unstable signals, high delay, single control mode and the like are avoided.
Accordingly, those skilled in the art have provided an AI image recognition-based sensor probe edge repair control system to solve the above-mentioned problems in the background art.
Disclosure of Invention
The invention aims to provide an AI image recognition based sensor probe edge repairing control system to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
an AI-based image recognition sensor probe edge supplementing control system comprises an AI image recognition sensor probe, a motor driver and an edge supplementing controller, wherein the AI image recognition sensor probe comprises an image acquisition element, an RGB (red, green and blue) three-color background light source and a RISC-V (reduced instruction-set computer-graphics) kernel 64-bit MCU, the output end of the image acquisition element is electrically connected with the input end of the RISC-V kernel 64-bit MCU, and the input end of the RGB three-color background light source is electrically connected with the output end of the RISC-V kernel 64-bit MCU; the motor driver comprises an electric push rod and a drive board, the output end of the electric push rod is fixedly connected with the shell of the brushless motor, the drive board is integrally installed on the shell of the brushless motor, and the drive board comprises a power supply conversion module, an ARM core-M4 kernel 32-bit MCU, a magnetic angle position sensor, a high-speed ADC and a three-phase drive bridge consisting of six power MOS (metal oxide semiconductor) tubes; the edge-supplementing controller comprises a human-computer interaction panel, a high-precision A/D converter, an ARM Cotex-M3 kernel 32-bit MCU, a PWM pulse amplification power device, a remote IO and a remote serial communication interface.
As a still further scheme of the invention: the image acquisition element adopts a two-dimensional color area array CMOS type digital image sensor, in particular to a 500 ten thousand pixel high-definition high-speed CMOS type digital image sensor lens module.
As a still further scheme of the invention: and the RISC-V kernel 64-bit MCU acquires images through a CMOS digital image sensor and outputs offset data to the edge supplement controller in a mode of analog output or a CAN communication interface.
As a still further scheme of the invention: the power supply conversion module is used for converting the 24V power supply from the edge supplement controller into a plurality of paths of low-voltage power supplies in a voltage reduction mode and supplying power to various functional modules; the ARM core-M4 kernel 32-bit MCU receives data signals in a CAN communication interface mode; the ARM core-M4 kernel 32-bit MCU acquires the rotor position information of the brushless motor in real time through the magnetic angle position sensor; the ARM core-M4 kernel 32-bit MCU collects working current and voltage signals of the brushless motor through the high-speed ADC.
As a still further scheme of the invention: the ARM core-M4 kernel 32-bit MCU executes the FOC algorithm to perform comprehensive operation, then six paths of SVPWM driving pulse signals are synthesized, a three-phase driving bridge formed by the six power MOS tubes is used for power amplification, and the amplified driving signals are used for driving the brushless motor to rotate and operate.
As a still further scheme of the invention: the human-computer interaction panel adopts a 2.8-inch TFT color liquid crystal display screen and a full-lamination capacitive touch screen.
As a still further scheme of the invention: the ARM Cotex-M3 kernel 32-bit MCU receives input signals through the high-precision A/D converter, converts and compares the input signals after AD sampling, outputs operation results to the PWM pulse amplification power device, and controls the motor driver by using output three-phase PWM modulated driving signals.
As a still further scheme of the invention: the edge repairing controller is simultaneously provided with the remote IO communication interface and the remote serial communication interface which are respectively used for two working modes of automatic control and manual control.
Compared with the prior art, the invention has the beneficial effects that:
1. the method comprises the following steps of automatically adjusting light supplement by adopting an RGB (red, green and blue) three-color background light source, performing range acquisition on a material image by adopting a two-dimensional color area array CMOS (complementary metal oxide semiconductor) type digital image sensor, and calculating the offset of a tracked material in real time through DSP (digital signal processor) image processing and AI (analog to digital) image recognition algorithm operation, so that the method is suitable for materials with various specifications and shapes;
2. the magnetic angle position sensor is adopted to detect the rotor position of the brushless motor, so that the installation volume and the maintenance cost are greatly reduced, and the positioning accuracy is greatly improved while the signal interference of the position sensor is solved by matching with an FOC control algorithm; the brushless motor can be ensured to be stable in a high-speed or low-speed state, so that the running noise is effectively reduced;
3. adopt the human-computer interaction panel of 2.8 cun TFT color liquid crystal display + full laminating electric capacity touch-sensitive screen, provide friendly human-computer interaction effect to utilize optimum PID to adjust the operation, drive brushless motor after power amplification with the PWM pulse signal of output again, improve control accuracy by a wide margin, still support two kinds of control methods of long-range IO, remote communication simultaneously, so that automatic or manual work mode.
Drawings
FIG. 1 is a schematic diagram of the working principle of an AI image recognition sensor-based probe edge-filling control system;
fig. 2 is a schematic system flow diagram of an AI image recognition-based sensor probe edge-filling control system.
Detailed Description
Referring to fig. 1-2, in an embodiment of the present invention, an AI image recognition sensor probe based edge supplement control system includes an AI image recognition sensor probe, a motor driver, and an edge supplement controller, the AI image recognition sensor probe includes an image acquisition element, a RGB three-color background light source, and a RISC-V kernel 64-bit MCU, an output end of the image acquisition element is electrically connected to an input end of the RISC-V kernel 64-bit MCU, and an input end of the RGB three-color background light source is electrically connected to an output end of the RISC-V kernel 64-bit MCU; the motor driver comprises an electric push rod and a drive board, the output end of the electric push rod is fixedly connected with the shell of the brushless motor, the drive board is integrally installed on the shell of the brushless motor, and the drive board comprises a three-phase drive bridge consisting of a power supply conversion module, an ARM core-M4 kernel 32-bit MCU, a magnetic angle position sensor, a high-speed ADC and six power MOS (metal oxide semiconductor) tubes; the edge-supplementing controller comprises a human-computer interaction panel, a high-precision A/D converter, an ARM Cotex-M3 kernel 32-bit MCU, a PWM pulse amplification power device, a remote IO and a remote serial communication interface.
In fig. 1 and 2: the image acquisition element adopts a two-dimensional color area array CMOS type digital image sensor, in particular to a 500 ten thousand pixel high-definition high-speed CMOS type digital image sensor (the model can be OV5640) lens module; RISC-V kernel 64-bit MCU (the model CAN be K210) carries on the image acquisition through CMOS digital image sensor, and then loop through DSP image processing, AI image recognition algorithm to calculate the offset of the tracked material in real time, then output the offset data to the edge-filling controller in the way of analog output or CAN communication interface;
in fig. 1 and 2: the power supply conversion module is used for converting the 24V power supply from the edge supplement controller into a plurality of paths of low-voltage power supplies in a voltage reduction mode to supply power to various functional modules; an ARM core-M4 kernel 32-bit MCU (the model CAN be STM32F303CCT6) receives control action instructions (starting, stopping, forward rotating and reverse rotating) from the edge supplementing controller in a CAN communication interface mode, and returns state data in operation to the edge supplementing controller in real time; the ARM core-M4 inner core 32-bit MCU collects the rotor position information of the brushless motor in real time through a magnetic angle position sensor (the model can be SC60228 DC); the ARM core-M4 kernel 32-bit MCU collects working current and voltage signals of the brushless motor through the high-speed ADC; the ARM core-M4 kernel 32-bit MCU executes an FOC algorithm by taking an action instruction, position information and a voltage and current signal as input conditions to carry out comprehensive operation, then synthesizes six paths of SVPWM driving pulse signals according to an operation result, is used for driving a three-phase driving bridge consisting of six power MOS (metal oxide semiconductor) tubes to amplify power, and then drives a brushless motor to rotate and operate by using the amplified driving signals;
in fig. 1 and 2: the human-computer interaction panel adopts a 2.8-inch TFT color liquid crystal display screen and a full-lamination capacitive touch screen; the ARM Cotex-M3 kernel 32-bit MCU receives an input signal through a high-precision A/D converter, converts the input signal into the offset of an actual tracked material after AD sampling, compares the offset with a set target position value, performs PID (proportion integration differentiation) regulation operation, outputs an operation result to a PWM (pulse-width modulation) pulse amplification power device, controls a motor driver by using an output three-phase PWM (pulse-width modulation) modulated driving signal, and finally achieves the edge supplementing control effect on the material; the edge repairing controller is simultaneously provided with a remote IO communication interface and a remote serial communication interface which are respectively used for two working modes of automatic control and manual control.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention are equivalent to or changed within the technical scope of the present invention.
Claims (8)
1. An AI-based image recognition sensor probe edge supplementing control system comprises an AI image recognition sensor probe, a motor driver and an edge supplementing controller, and is characterized in that the AI image recognition sensor probe comprises an image acquisition element, an RGB (red, green and blue) three-color background light source and a RISC-V (reduced instruction-set computer-graphics) kernel 64-bit MCU, the output end of the image acquisition element is electrically connected with the input end of the RISC-V kernel 64-bit MCU, and the input end of the RGB three-color background light source is electrically connected with the output end of the RISC-V kernel 64-bit MCU; the motor driver comprises an electric push rod and a drive board, the output end of the electric push rod is fixedly connected with the shell of the brushless motor, the drive board is integrally installed on the shell of the brushless motor, and the drive board comprises a power supply conversion module, an ARM core-M4 kernel 32-bit MCU, a magnetic angle position sensor, a high-speed ADC and a three-phase drive bridge consisting of six power MOS (metal oxide semiconductor) tubes; the edge-supplementing controller comprises a human-computer interaction panel, a high-precision A/D converter, an ARM Cotex-M3 kernel 32-bit MCU, a PWM pulse amplification power device, a remote IO and a remote serial communication interface.
2. The AI-based image recognition sensor probe edging control system of claim 1, wherein the image capturing element is a two-dimensional color area array CMOS type digital image sensor, in particular a 500-megapixel high-definition high-speed CMOS type digital image sensor lens module.
3. The AI-based image recognition sensor probe edging control system as claimed in claim 2, wherein said RISC-V kernel 64-bit MCU performs image acquisition by CMOS digital image sensor and outputs offset data to said edging controller in analog output or CAN communication interface mode.
4. The AI-based image recognition sensor probe edging control system of claim 1, wherein the power conversion module down-converts the 24V power from the edging controller into multiple low voltage power supplies to power various functional modules; the ARM core-M4 kernel 32-bit MCU receives data signals in a CAN communication interface mode; the ARM core-M4 kernel 32-bit MCU acquires the rotor position information of the brushless motor in real time through the magnetic angle position sensor; the ARM core-M4 kernel 32-bit MCU collects working current and voltage signals of the brushless motor through the high-speed ADC.
5. The AI-based image recognition sensor probe edge-filling control system of claim 4, wherein said ARM cotex-M4 kernel 32-bit MCU executes FOC algorithm for comprehensive operation, then synthesizes six SVPWM driving pulse signals, utilizes a three-phase driving bridge composed of said six power MOS transistors for power amplification, and then utilizes the amplified driving signal to drive the brushless motor to rotate.
6. The AI-based image recognition sensor probe edging control system of claim 1, wherein said human-computer interaction panel is 2.8 inches TFT color LCD + full-face capacitive touch screen.
7. The AI-based image recognition sensor probe edging control system as claimed in claim 1, wherein said ARM Cotex-M3 kernel 32-bit MCU receives input signal through said high precision A/D converter, after AD sampling, conversion and comparison, outputs the operation result to said PWM pulse amplification power device, and controls said motor driver by the output three-phase PWM modulated driving signal.
8. The AI-image-recognition-based sensor probe edge supplement control system as claimed in claim 1, wherein the edge supplement controller is provided with the remote IO communication interface and the remote serial communication interface simultaneously, and is respectively used for two modes of operation, namely automatic control and manual control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011429662.2A CN112637451A (en) | 2020-12-09 | 2020-12-09 | Based on AI image recognition sensor probe mends limit control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011429662.2A CN112637451A (en) | 2020-12-09 | 2020-12-09 | Based on AI image recognition sensor probe mends limit control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112637451A true CN112637451A (en) | 2021-04-09 |
Family
ID=75308950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011429662.2A Pending CN112637451A (en) | 2020-12-09 | 2020-12-09 | Based on AI image recognition sensor probe mends limit control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112637451A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201562165U (en) * | 2009-10-28 | 2010-08-25 | 广西工学院 | Networked brushless direct current motor sensorless intelligent control system |
| CN101877525A (en) * | 2009-04-30 | 2010-11-03 | 浙江关西电机有限公司 | Electric motor |
| CN206037944U (en) * | 2016-07-15 | 2017-03-22 | 西安得鑫光电科技有限公司 | CCD sensor of rectifying picture position |
| CN106773991A (en) * | 2016-12-30 | 2017-05-31 | 常州光电技术研究所 | A kind of embedded deviation-rectifying system and its method for correcting error based on cmos sensor |
| CN108919725A (en) * | 2018-08-09 | 2018-11-30 | 南京梵科智能科技有限公司 | A kind of adjustable servomotor controller of high-precision |
| CN110460735A (en) * | 2019-08-05 | 2019-11-15 | 上海理工大学 | Large format scanner control system based on line array CCD |
-
2020
- 2020-12-09 CN CN202011429662.2A patent/CN112637451A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101877525A (en) * | 2009-04-30 | 2010-11-03 | 浙江关西电机有限公司 | Electric motor |
| CN201562165U (en) * | 2009-10-28 | 2010-08-25 | 广西工学院 | Networked brushless direct current motor sensorless intelligent control system |
| CN206037944U (en) * | 2016-07-15 | 2017-03-22 | 西安得鑫光电科技有限公司 | CCD sensor of rectifying picture position |
| CN106773991A (en) * | 2016-12-30 | 2017-05-31 | 常州光电技术研究所 | A kind of embedded deviation-rectifying system and its method for correcting error based on cmos sensor |
| CN108919725A (en) * | 2018-08-09 | 2018-11-30 | 南京梵科智能科技有限公司 | A kind of adjustable servomotor controller of high-precision |
| CN110460735A (en) * | 2019-08-05 | 2019-11-15 | 上海理工大学 | Large format scanner control system based on line array CCD |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108834576B (en) | Citrus picking robot based on binocular vision and implementation method thereof | |
| CN102188311B (en) | Embedded visual navigation control system and method of intelligent wheelchair | |
| CN103699134A (en) | Position loop control-based electric steering engine system | |
| CN103544714A (en) | Visual tracking system and method based on high-speed image sensor | |
| CN102431034A (en) | Color recognition-based robot tracking method | |
| CN115159217A (en) | Coiled material deviation rectifying system based on direct current servo drive | |
| CN112637451A (en) | Based on AI image recognition sensor probe mends limit control system | |
| CN2935084Y (en) | Central processor for photoelectric centering rectification and detecting apparatus | |
| CN107263485B (en) | Cargo robot based on machine vision factory | |
| CN110901372A (en) | Mecanum wheel AGV trolley applied to limited space logistics sorting | |
| CN206993268U (en) | A kind of camera control circuit | |
| CN207097060U (en) | A kind of image detection device | |
| CN106933181B (en) | Electrical control system of small-sized engine dismounting device | |
| CN108762163B (en) | Motion control system of mobile robot based on QT human-computer interaction interface and motor servo system | |
| CN205343149U (en) | Manipulator wireless control system based on discernment is felt to body | |
| CN202105114U (en) | Embedded visual guidance control system of intelligent wheel chairs | |
| CN206848811U (en) | A kind of intelligent mobile robot based on DSP | |
| CN212541103U (en) | Solar cell panel robot walking control system | |
| CN216769151U (en) | Visual light source structure | |
| CN221351984U (en) | Transfer robot motion system of welding workstation | |
| CN111175785A (en) | High-resolution uncooled photoelectric radar based on spiral line scanning | |
| CN205068159U (en) | Based on 32 MCU intelligence photoelectricity dolly control system | |
| CN215026289U (en) | A measurement system for be used for mud scraper instant operation load | |
| CN216301295U (en) | Power distribution room inspection device | |
| CN218648747U (en) | Oxygenation pump control system with impeller direction self-learning function |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210409 |
|
| WD01 | Invention patent application deemed withdrawn after publication |