CN210295150U

CN210295150U - Machine learning device for image classification and recognition

Info

Publication number: CN210295150U
Application number: CN201921735078.2U
Authority: CN
Inventors: 袁小琼; 陈春辉
Original assignee: Jiangsu Caibiao Information Technology Co ltd
Current assignee: Jiangsu Caibiao Information Technology Co ltd
Priority date: 2019-10-16
Filing date: 2019-10-16
Publication date: 2020-04-10
Anticipated expiration: 2029-10-16

Abstract

The utility model discloses a machine learning device for image classification and discernment, including base, plummer, singlechip, universal wheel and touch screen, the turning position department of base bottom all is equipped with the universal wheel, and the top of base is equipped with the plummer to the turning position department of plummer bottom all is equipped with elevation structure, the central point department of putting on plummer top is equipped with the power cavity, and the central point department of putting of power cavity bottom is equipped with the analysis appearance to be equipped with the memory on the power cavity inner wall of analysis appearance top, be equipped with the singlechip on the power cavity inner wall of memory one side, the output of singlechip respectively with the input electric connection of analysis appearance and memory, all be equipped with the louvre on two inside walls of power cavity. The utility model discloses not only improve machine learning's application scope, prolonged machine learning's life, received the phenomenon that the dust corrodes when having avoided machine learning to use moreover.

Description

Machine learning device for image classification and recognition

Technical Field

The utility model relates to a machine learning technical field specifically is a machine learning device for image classification and discernment.

Background

When manufacturing machines such as machine tools and robots are developed, in order to improve the reliability of the manufacturing machines, recognition processing is required to classify and store the manufacturing machines for human inquiry, and a machine learning device is required to improve the efficiency of the recognition and classification storage.

The machine learning devices on the market are various and can basically meet the use requirements of people, but certain defects still exist, and the specific problems are as follows.

(1) The traditional machine learning device is inconvenient for adjusting the distance between the bearing table and the base, is difficult to be suitable for workers at different heights to use, and has certain limitation;

(2) the traditional machine learning device is inconvenient to protect the touch screen, so that the touch screen is easy to break and damage due to external force impact, and the service life is short;

(3) the traditional machine learning device is inconvenient for dust prevention treatment, so that external dust is easy to enter the power cavity, and erosion is caused to internal elements of the power cavity, which often troubles people.

SUMMERY OF THE UTILITY MODEL

An object of the utility model is to provide a machine learning device for image classification and discernment to propose the machine learning device and be not convenient for adjust the interval between plummer and the base, be not convenient for protect and be not convenient for carry out dustproof problem of handling to the touch screen in solving above-mentioned background art.

In order to achieve the above object, the utility model provides a following technical scheme: a machine learning device for image classification and identification comprises a base, a bearing platform, a single chip microcomputer, universal wheels and a touch screen, wherein the universal wheels are arranged at the corner positions of the bottom end of the base, the bearing platform is arranged above the base, lifting structures are arranged at the corner positions of the bottom end of the bearing platform, a power cavity is arranged at the central position of the top end of the bearing platform, an analyzer is arranged at the central position of the bottom of the power cavity, a storage device is arranged on the inner wall of the power cavity above the analyzer, the single chip microcomputer is arranged on the inner wall of the power cavity on one side of the storage device, the output end of the single chip microcomputer is respectively electrically connected with the analyzer and the input end of the storage device, radiating holes are arranged on the two inner side walls of the power cavity, one ends of the radiating holes extend to the outside of the power cavity, the touch screen is arranged at one end, and the power cavity surface of touch screen top is equipped with miniature camera, and the input of miniature camera and the output electric connection of singlechip.

Preferably, all be equipped with the dust screen on the power cavity inner wall of louvre position department, and the outside of dust screen all is fixed with the linkage frame.

Preferably, elevation structure's inside is equipped with the forked tail in proper order and leads to groove, spacing dish, reference column, screw thread post and screw cap, the turning position department of plummer bottom all is fixed with the reference column, and the central point department of putting of locating column bottom all is equipped with the forked tail and leads to the groove to the inside that the forked tail led to the groove is equipped with the screw thread post, and the bottom of screw thread post extends to the outside that the forked tail led to the groove and with the top fixed connection of base.

Preferably, a limiting disc is fixed at the top end of the threaded column, and a threaded cap is connected to the surface of the threaded column below the limiting disc in a threaded mode.

Preferably, the outer wall of one side of the linkage frame is provided with catching grooves at equal intervals, the catching grooves are internally provided with catching columns, and one ends of the catching columns extend to the outer parts of the catching grooves and are fixedly connected with the inner wall of the power cavity.

Preferably, the top of touch-sensitive screen is equipped with the guard plate, and the power cavity surface of touch-sensitive screen both sides all is fixed with spacing frame to one side of spacing frame inside all is equipped with the stopper, the one end of stopper extend to the outside of spacing frame and with the outer wall fixed connection of guard plate, the power cavity surface of miniature camera both sides all is equipped with the second and fastens the hole, the both sides on guard plate surface all are equipped with first fastening hole, two-way fastening spare is all installed to the inside in first fastening hole, two-way fastening spare's one end extends to the inside in second fastening hole.

Compared with the prior art, the beneficial effects of the utility model are that: the machine learning device for image classification and recognition not only improves the application range of the machine learning device, prolongs the service life of the machine learning device, but also avoids the phenomenon that the machine learning device is corroded by dust when in use;

(1) the dovetail through groove, the limiting disc, the positioning column, the threaded column and the threaded cap are arranged, the threaded cap is rotated to be vertically moved on the surface of the threaded column, the threaded column can stretch out and draw back in the dovetail through groove, meanwhile, the limiting disc limits the threaded column to prevent the threaded column from being separated from the dovetail through groove, so that the distance between the bearing table and the base can be changed through the positioning column, and the application range of the machine learning device is widened;

(2) the limiting frame, the limiting block, the first fastening hole, the two-way fastening piece, the protection plate and the second fastening hole are arranged, the two-way fastening piece is pulled to be separated from the inside of the first fastening hole and the inside of the second fastening hole, the limiting block can move downwards in the limiting frame under the action of gravity, the protection plate synchronously moves downwards to shield the touch screen, so that the touch screen is protected and prevented from being cracked due to impact, and the service life of the machine learning device is prolonged;

(3) through being provided with dust screen, catching groove, interlock frame and detaining the post, will detain the post through the catching groove and firmly detain, make the interlock frame drive dust screen closely laminate on the inner wall of power cavity to shelter from the louvre, in order to avoid external dust to get into the inside of power cavity by the louvre, thereby received the phenomenon of dust erosion when having avoided machine learning device to use.

Drawings

Fig. 1 is a schematic front view of a cross-sectional structure of the present invention;

fig. 2 is an enlarged schematic structural view of a point a in fig. 1 according to the present invention;

FIG. 3 is a schematic view of the sectional view of the elevating structure of the present invention;

FIG. 4 is an enlarged schematic view of the power cavity of the present invention;

fig. 5 is a schematic diagram of the system framework structure of the present invention.

In the figure: 1. a base; 2. a bearing table; 3. heat dissipation holes; 4. a dust screen; 5. a single chip microcomputer; 6. an analyzer; 7. a power cavity; 8. a memory; 9. a lifting structure; 901. dovetail through grooves; 902. a limiting disc; 903. a positioning column; 904. a threaded post; 905. a threaded cap; 10. a universal wheel; 11. buckling grooves; 12. a linkage frame; 13. buckling a column; 14. a limiting frame; 15. a limiting block; 16. a first fastening hole; 17. a bi-directional fastener; 18. a miniature camera; 19. a protection plate; 20. a second fastening hole; 21. a touch screen is provided.

Detailed Description

The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention.

Referring to fig. 1-5, the present invention provides an embodiment: a machine learning device for image classification and identification comprises a base 1, a bearing platform 2, a singlechip 5, universal wheels 10 and a touch screen 21, wherein the universal wheels 10 are arranged at the corner positions of the bottom end of the base 1, the bearing platform 2 is arranged above the base 1, and the corner position of the bottom end of the bearing table 2 is provided with a lifting structure 9, the interior of the lifting structure 9 is provided with a dovetail through groove 901, a limiting disc 902, a positioning column 903, a threaded column 904 and a threaded cap 905 in sequence, the corner position of the bottom end of the bearing table 2 is fixed with the positioning column 903, the center position of the bottom of the positioning column 903 is provided with a dovetail through groove 901, and the inside of the dovetail through groove 901 is provided with a threaded column 904, the bottom end of the threaded column 904 extends to the outside of the dovetail through groove 901 and is fixedly connected with the top end of the base 1, the top end of the threaded column 904 is fixed with a limiting disc 902, a threaded cap 905 is connected to the surface of the threaded column 904 below the positioning column 903 in a threaded manner;

the threaded cap 905 is rotated to move up and down on the surface of the threaded column 904, the threaded column 904 can stretch out and draw back in the dovetail through groove 901, meanwhile, the limiting disc 902 limits the threaded column 904 to prevent the threaded column 904 from separating from the dovetail through groove 901, so that the distance between the bearing table 2 and the base 1 is changed through the positioning column 903, and the bearing table is suitable for workers with different heights to use;

a power cavity 7 is arranged AT the central position of the top end of the bearing table 2, an analyzer 6 is arranged AT the central position of the bottom of the power cavity 7, the type of the analyzer 6 can be ZWY-010, a memory 8 is arranged on the inner wall of the power cavity 7 above the analyzer 6, the type of the memory 8 can be AT24C04, a single chip microcomputer 5 is arranged on the inner wall of the power cavity 7 AT one side of the memory 8, the type of the single chip microcomputer 5 can be SH69P25, the output end of the single chip microcomputer 5 is respectively electrically connected with the input ends of the analyzer 6 and the memory 8, heat dissipation holes 3 are arranged on the two inner side walls of the power cavity 7, one ends of the heat dissipation holes 3 extend to the outside of the power cavity 7, a dust screen 4 is arranged on the inner wall of the power cavity 7 AT the position of the heat dissipation holes 3, linkage frames 12 are fixed on the outer sides of the dust screen 4, catching grooves 11 with equal intervals are arranged on the outer wall AT one, one end of the buckling column 13 extends to the outside of the buckling groove 11 and is fixedly connected with the inner wall of the power cavity 7 so as to prevent external dust from entering the inside of the power cavity 7;

a touch screen 21 is arranged at one end of the surface of the power cavity 7, the type of the touch screen 21 can be T215HVN01.1, the touch screen 21 is electrically connected with the single chip microcomputer 5 in a bidirectional mode, a protection plate 19 is arranged above the touch screen 21, the surfaces of the power cavities 7 on the two sides of the touch screen 21 are both fixed with a limiting frame 14, one side of the inside of the limiting frame 14 is provided with a limiting block 15, one end of the limiting block 15 extends to the outside of the limiting frame 14 and is fixedly connected with the outer wall of the protection plate 19, the surfaces of the power cavities 7 on the two sides of the miniature camera 18 are both provided with second fastening holes 20, the two sides of the surface of the protection plate 19 are both provided with first fastening holes 16, bidirectional fasteners 17 are mounted inside the first fastening holes 16, and one ends of the bidirectional fasteners 17 extend to the inside of the second fastening holes;

and the surface of the power cavity 7 above the touch screen 21 is provided with a micro camera 18, the model of the micro camera 18 can be IMX220, and the input end of the micro camera 18 is electrically connected with the output end of the singlechip 5.

The working principle is as follows: when the machine learning device is used, firstly, the threaded cap 905 is rotated to move up and down on the surface of the threaded column 904, the threaded column 904 can stretch out and draw back in the dovetail through groove 901, meanwhile, the limiting disc 902 limits the threaded column 904 to prevent the threaded column 904 from separating from the dovetail through groove 901, so that the distance between the bearing table 2 and the base 1 is changed through the positioning column 903, the bearing table is suitable for workers with different heights to use, then the micro camera 18 shoots images by touching the touch screen 21 to enable the micro camera to send corresponding instructions to the singlechip 5, the images are analyzed and processed by the analyzer 6 and are stored in the memory 8 in a classified manner, if corresponding images are needed, the partial images are displayed by the touch screen 21, then the buckling columns 13 are firmly buckled through the buckling grooves 11, and the connecting frame 12 drives the dustproof net 4 to be tightly attached to the inner wall of the power cavity 7, and shelter from louvre 3 to avoid external dust to get into the inside of power cavity 7 by louvre 3, avoid the machine learning device to receive the phenomenon of dust erosion to take place, through pulling two-way fastener 17 at last, make it break away from the inside in first fastening hole 16 and second fastening hole 20, because of the action of gravity, stopper 15 can move down in the inside of spacing frame 14, make guard plate 19 move down in step and shelter from touch screen 21, so as to protect it, avoid it to appear cracked phenomenon because of assaulting, prolong the life of machine learning device, thereby accomplish the use of machine learning device.

It is obvious to a person skilled in the art that the invention is not restricted to details of the above-described exemplary embodiments, but that it can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims

1. The utility model provides a machine learning device for image classification and discernment, includes base (1), plummer (2), singlechip (5), universal wheel (10) and touch screen (21), its characterized in that: the universal wheels (10) are arranged at the corner positions of the bottom end of the base (1), the bearing table (2) is arranged above the base (1), the lifting structures (9) are arranged at the corner positions of the bottom end of the bearing table (2), the power cavity (7) is arranged at the center position of the top end of the bearing table (2), the analyzer (6) is arranged at the center position of the bottom of the power cavity (7), the memory (8) is arranged on the inner wall of the power cavity (7) above the analyzer (6), the single chip microcomputer (5) is arranged on the inner wall of the power cavity (7) at one side of the memory (8), the output end of the single chip microcomputer (5) is electrically connected with the analyzer (6) and the input end of the memory (8) respectively, the heat dissipation holes (3) are arranged on the two inner side walls of the power cavity (7), one end of each heat dissipation hole (3) extends to the outside of, and one end on the surface of the power cavity (7) is provided with a touch screen (21), the touch screen (21) is electrically connected with the single chip microcomputer (5) in a two-way mode, the surface of the power cavity (7) above the touch screen (21) is provided with a micro camera (18), and the input end of the micro camera (18) is electrically connected with the output end of the single chip microcomputer (5).

2. The machine learning apparatus for image classification and recognition according to claim 1, wherein: the inner wall of the power cavity (7) at the position of the heat dissipation hole (3) is provided with a dustproof net (4), and the outer side of the dustproof net (4) is fixed with a linkage frame (12).

3. The machine learning apparatus for image classification and recognition according to claim 1, wherein: the inside of elevation structure (9) is equipped with forked tail logical groove (901), spacing dish (902), reference column (903), screw thread post (904) and screw cap (905) in proper order, the corner position department of plummer (2) bottom all is fixed with reference column (903), and the central point department of reference column (903) bottom all is equipped with forked tail logical groove (901) to the inside that the forked tail led to groove (901) is equipped with screw thread post (904), the bottom of screw thread post (904) extend to the outside that the forked tail led to groove (901) and with the top fixed connection of base (1).

4. A machine learning apparatus for image classification and recognition according to claim 3, characterized by: a limiting disc (902) is fixed at the top end of the threaded column (904), and a threaded cap (905) is connected to the surface of the threaded column (904) below the limiting disc (903) in a threaded mode.

5. The machine learning apparatus for image classification and recognition according to claim 2, wherein: the outer wall of one side of the linkage frame (12) is provided with catching grooves (11) at equal intervals, the inside of each catching groove (11) is provided with a catching column (13), and one end of each catching column (13) extends to the outside of each catching groove (11) and is fixedly connected with the inner wall of the power cavity (7).

6. The machine learning apparatus for image classification and recognition according to claim 1, wherein: the utility model discloses a two-way fastener, including touch screen (21), power cavity (7) surface of touch screen (21) both sides all is fixed with spacing frame (14), and the inside one side of spacing frame (14) all is equipped with stopper (15), the one end of stopper (15) extend to the outside of spacing frame (14) and with the outer wall fixed connection of protection plate (19), power cavity (7) surface of miniature camera (18) both sides all is equipped with second fastening hole (20), the both sides on protection plate (19) surface all are equipped with first fastening hole (16), two-way fastener (17) are all installed to the inside of first fastening hole (16), the one end of two-way fastener (17) extends to the inside of second fastening hole (20).