CN113395661B - An Indoor Positioning System Based on Deep Neural Network - Google Patents

Abstract

The invention discloses an indoor positioning system based on a deep neural network. A positioning arm is connected directly under the system box, and a signal box is welded and fixed in the middle of the system box, and the outside of the signal box is connected through There is a rotating shaft, including: a lifting box, an LED light is connected directly below it, and electronic tags are arranged on the left and right sides of the LED light, a vertical arm is welded and fixed directly above the lifting box, and the vertical A guide slide bar is nested and connected to the outside of the force arm, and a ball screw is threaded on the outside of the vertical force arm; and a signal data line is connected to one side of the signal transmitter, and the upper surface of the alloy bracket is opened There are rectangular chutes. The indoor positioning system based on the deep neural network; using the vertical arm and the ball screw, using the ball screw to vertically raise or lower the vertical arm, according to the height of the building and the needs of ground navigation, the vertical Adjust the height of the arm.

Description

An Indoor Positioning System Based on Deep Neural Network

technical field

The invention relates to the technical field of indoor positioning, in particular to an indoor positioning system based on a deep neural network.

Background technique

In the outdoor environment, the Global Positioning System or Beidou positioning system based on the global satellite navigation system can already meet certain outdoor positioning requirements. However, indoors, especially in complex indoor environments, such as airport halls, exhibition halls, mines, etc., often It is necessary to determine the location information of mobile terminals or their holders, facilities and objects indoors, but due to the limitations of positioning time, positioning accuracy, and complex indoor environments, the existing positioning methods are not perfect.

Indoor positioning systems are generally scattered signal transmitters. During use, they can only guide and locate some important exits or departments. , to adjust the distance of the transmitter of the positioning system, resulting in the transmission of signals and the accuracy of indoor positioning during the use of the positioning system, which is not conducive to guiding and positioning inside large buildings, and the general navigation system can only couple The Internet system provides signal transmission, but the mobile system that cannot be connected to the Internet cannot read some information, resulting in relatively weak functionality of system navigation during use.

In view of the above problems, it is urgent to carry out innovative design on the basis of the original indoor positioning structure.

Contents of the invention

The purpose of the present invention is to provide a deep neural network-based indoor positioning system to solve the problem that the system proposed in the background technology is difficult to adjust the distance of the transmitter of the positioning system according to the height of the building and the width of the corridor. The system can only provide signal transmission to the networked system, but the mobile system that cannot be connected to the network cannot read some information, which leads to the problem that the functionality of the system navigation is relatively weak during use.

In order to achieve the above object, the present invention provides the following technical solutions: The present invention discloses an indoor positioning system based on a deep neural network. A positioning arm is connected directly below the system box, and a signal arm is welded and fixed in the middle of the system box. Box, the outside of the signal box is connected with a rotating shaft, including: lifting box, LED lights are connected directly below it, and electronic tags are arranged on the left and right sides of the LED lights, the lifting box A vertical arm is welded and fixed directly above, and the outer side of the vertical arm is nested and connected with a guide slider, and the outer thread of the vertical arm is connected with a ball screw; the signal transmitter is installed inside the alloy bracket , and one side of the signal transmitter is connected to a signal data line, the upper surface of the alloy bracket is provided with a rectangular chute, and a lifting panel is nested and connected directly above the rectangular chute; the positioning server is installed in the system The inside of the box body, and the gauze panel is fixed by bolts directly above the system box body, and the wire on one side of the positioning server is connected to the a communication module; the bevel gear is installed on the outside of the rotating shaft, and the positive side of the bevel gear A ball screw is connected at the bottom, a b communication module is fixed by a bolt on one side of the alloy bracket, and a guide slide bar is nested and connected to the outer side of the alloy bracket.

Preferably, the system box and the alloy bracket are through-connected, and the width of the alloy bracket is three times the width of the lifting panel.

Preferably, the signal transmitter and the lifting panel form a sliding structure through an alloy bracket and a rectangular chute, and the alloy brackets are staggeredly distributed at the bottom of the system box, and the distance between the two sets of alloy brackets ranges from 5-10m.

Preferably, the positioning server and the signal transmitter are connected through a communication module and a signal data line, and the signal transmitter and the lifting panel are attached to each other.

Preferably, the rectangular chute is nestedly connected to the lifting panel, and the longitudinal section of the lifting panel is an "L"-shaped structure, and the top of the lifting panel is a groove-shaped structure.

Preferably, the electronic tag and the lifting box form a lifting structure through a vertical force arm, a ball screw and a guide slider, and the longitudinal section of the vertical force arm is a "U"-shaped structure, and the vertical force arm and The lifting box is fixed by welding.

Compared with the prior art, the beneficial effects of the present invention are: the indoor positioning system based on the deep neural network;

1. Use the vertical arm and ball screw, use the ball screw to vertically raise or lower the vertical arm, adjust the height of the vertical arm according to the height of the building and the needs of ground navigation, and lift The stability of the vertical moment arm in the process of positioning and locking is handled by hoisting the top of the lifting box through the ball screw to avoid shaking of the lifting box during the signal transmission process, and according to the length of the corridor. Lift the length of the box for replacement and switching;

2. Use the lifting panel and the rectangular chute, use the lifting panel to lift and shorten the top of the signal transmitter, adjust the distance between the signal transmitters according to the width of the signal transmitter and the width of the corridor, and use the signal The transmitter transmits the signals of the surrounding shops and entrances and exits, and uses the rectangular chute to guide and fix the bottom of the lifting panel, so as to avoid the excessive distance between the signal transmitters and affect the accuracy of the signal during transmission.

Description of drawings

Fig. 1 is the schematic diagram of the front view structure of the present invention;

Fig. 2 is a schematic diagram of the internal structure of the system box of the present invention;

Fig. 3 is a schematic diagram of the top view structure of the system box of the present invention;

Fig. 4 is a schematic view of the structure of the lifting box according to the present invention;

Fig. 5 is a schematic diagram of the internal structure of the signal box of the present invention.

In the figure: 1. System box; 2. Positioning arm; 3. Signal box; 4. Rotation shaft; 5. Lifting box; 6. Signal transmitter; 7. Lifting panel; 8. Alloy bracket; 9. a communication module; 10. positioning server; 11. signal data line; 12. rectangular chute; 13. gauze panel; 14. electronic label; 15. LED light; 16. vertical arm; gear; 18, ball screw; 19, b communication module; 20, guide slide bar.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Please refer to Figures 1-5, the present invention provides a technical solution: an indoor positioning system based on a deep neural network, a positioning arm 2 is connected directly under the system box 1, and the middle part of the system box 1 is welded and fixed There is a signal box 3, and the outer side of the signal box 3 is connected with a rotating shaft 4, including:

Lifting box 5, LED lights 15 are connected directly below it, and electronic tags 14 are arranged on the left and right sides of LED lights 15, vertical arm 16 is welded and fixed directly above lifting box 5, and the vertical force The outer side of the arm 16 is nested and connected with a guide slide bar 20, and the outer side of the vertical arm 16 is threaded with a ball screw 18;

The signal transmitter 6 is installed inside the alloy bracket 8, and one side of the signal transmitter 6 is connected with a signal data line 11. The upper surface of the alloy bracket 8 is provided with a rectangular chute 12, and the rectangular chute 12 is directly above the The nested connection has a lifting panel 7;

Positioning server 10, which is installed inside the system box 1, and a gauze panel 13 is fixed with bolts directly above the system box 1, and a communication module 9 is connected to a side wire of the positioning server 10;

The bevel gear 17 is installed on the outside of the rotating shaft 4, and the ball screw 18 is connected directly below the bevel gear 17, and the b communication module 19 is fixed on one side of the alloy bracket 8 by bolts, and the outside of the alloy bracket 8 is nested A guide slide bar 20 is connected.

The system box 1 and the alloy bracket 8 are through-connected, and the width of the alloy bracket 8 is three times the width of the lifting panel 7 .

The signal transmitter 6 and the lifting panel 7 form a sliding structure through the alloy bracket 8 and the rectangular chute 12, and the alloy brackets 8 are staggeredly distributed at the bottom of the system box 1, and the distance between the two sets of alloy brackets 8 is 5-10m .

The positioning server 10 is connected to the signal transmitter 6 through a communication module 9 and the signal data line 11, and the signal transmitter 6 and the lifting panel 7 are attached to each other.

The rectangular chute 12 is nestedly connected with the lifting panel 7, and the longitudinal section of the lifting panel 7 is an "L"-shaped structure, and the top of the lifting panel 7 is a groove-shaped structure.

The electronic tag 14 and the lifting box 5 form a lifting structure through the vertical force arm 16, the ball screw 18 and the guide slide bar 20, and the longitudinal section of the vertical force arm 16 is a "U"-shaped structure, and the vertical force arm 16 and lifting box 5 are fixed for welding.

Working principle: When using the indoor positioning system based on deep neural network, according to Figure 1, first place the device at the position where it needs to work, and the operator first places the signal transmitter according to the length of the building and the signal transmission requirements. 6 and the lifting panel 7 are fitted together, and the lifting panel 7 is pulled, so that the lifting panel 7 slides on the outside of the rectangular chute 12, the position of the signal transmitter 6 is adjusted, and the positioning force arm is aligned with the wall The tops are attached to each other, and the system box 1 and the positioning arm 2 are fixed and limited by expansion screws, and the corresponding a communication module 9 and the positioning server 10 are installed inside the system box 1, and the signal data line 11 is used to Installed at the output end of the positioning server 10, use the signal data line 11 to connect with the signal transmitter 6 respectively, and conduct the received signal through the signal data line 11;

And hold the rotating shaft 4, use the rotating shaft 4 to drive the bevel gear 17 to rotate, the bevel gear 17 drives the ball screw 18 on one side to rotate, and use the ball screw 18 to drive the vertical arm 16 on one side to perform vertical Descending, the height of the lifting box 5 is driven by the vertical arm 16 to adjust, and different specific position information is imported into the inside of the electronic tag 14, and the electronic tag 14 is installed directly below the lifting box 5, The spatial coupling of radio frequency signals is realized through the coupling element between the electronic tag 14 and the reader; in the coupling channel, energy transmission and data exchange are realized according to the timing relationship, and the operator can directly read the electronic tag 14 through the reader , to know the corresponding position. Increased overall usability.

The content not described in detail in this specification belongs to the prior art known to those skilled in the art.

Although the embodiments of the present invention have been shown and described, those skilled in the art can understand that various changes, modifications and substitutions can be made to these embodiments without departing from the principle and spirit of the present invention. and modifications, the scope of the invention is defined by the appended claims and their equivalents.

Claims (5)

1. The utility model provides an indoor positioning system based on degree of depth neural network, contains system box (1), and there is the location arm of force (2) through connection under system box (1), and the middle part welded fastening of system box (1) has signal box (3), the outside through connection of signal box (3) has rotation axis (4), its characterized in that: the method comprises the following steps:

the LED lamp lifting device comprises a lifting box body (5), wherein an LED lamp (15) is connected to the right lower portion of the lifting box body (5), electronic tags (14) are arranged on the left side and the right side of the LED lamp (15), a vertical force arm (16) is fixedly welded to the right upper portion of the lifting box body (5), a guide sliding rod (20) is connected to the outer side of the vertical force arm (16) in a nested mode, and a ball screw (18) is connected to the outer side of the vertical force arm (16) in a threaded mode;

the signal emitter (6) is installed inside the alloy support (8), an electric wire on one side of the signal emitter (6) is connected with a signal data wire (11), a rectangular sliding groove (12) is formed in the upper surface of the alloy support (8), and a lifting panel (7) is connected to the position right above the rectangular sliding groove (12) in a nested mode;

the positioning server (10) is installed inside the system box body (1), a gauze panel (13) is fixed on the right upper side of the system box body (1) through bolts, and an a communication module (9) is connected with one side of the positioning server (10) through an electric wire;

the conical gear (17) is installed on the outer side of the rotating shaft (4), a ball screw (18) is connected to the position right below the conical gear (17), a b communication module (19) is fixed to one side of the alloy support (8) through a bolt, and a guide sliding rod (20) is connected to the outer side of the alloy support (8) in a nested mode;

the signal emitter (6) and the lifting panel (7) form a sliding structure through an alloy support (8) and a rectangular sliding chute (12), the alloy supports (8) are distributed at the bottom of the system box body (1) in a staggered mode, and the distance between the 2 combinations Jin Zhijia (8) is 5-10m;

the electronic tag (14) and the lifting box body (5) form a lifting structure through a vertical force arm (16), a ball screw (18) and a guide slide rod (20), the longitudinal section of the vertical force arm (16) is of a U-shaped structure, and the vertical force arm (16) and the lifting box body (5) are fixedly welded.

2. The deep neural network-based indoor positioning system of claim 1, wherein: the system box body (1) is in through connection with the alloy support (8), and the width of the alloy support (8) is 3 times of that of the lifting panel (7).

3. The deep neural network-based indoor positioning system of claim 1, wherein: the positioning server (10) is connected with the signal emitter (6) through a communication module (9) and a signal data line (11), and the signal emitter (6) is mutually attached to the lifting panel (7).

4. The deep neural network-based indoor positioning system of claim 1, wherein: the rectangular sliding groove (12) is connected with the lifting panel (7) in a nested mode, the longitudinal section of the lifting panel (7) is of an L-shaped structure, and a groove-shaped structure is arranged right above the lifting panel (7).

5. The deep neural network-based indoor positioning system of claim 1, wherein: the working method of the system comprises the following steps: firstly, the indoor positioning system is placed at a position needing to work, an operator firstly attaches a signal transmitter (6) and a lifting panel (7) to each other according to the length of a building and the requirement of signal transmission, pulls the lifting panel (7) to enable the lifting panel (7) to slide on the outer side of a rectangular sliding groove (12), adjusts the position of the signal transmitter (6), attaches a positioning force arm to the top of a wall, fixes and limits a system box body (1) and a positioning force arm (2) by using an expansion screw, installs a corresponding communication module (a) and a corresponding positioning server (10) inside the system box body (1), installs the communication module at the output end of the positioning server (10) by using a signal data line (11), connects the signal transmitter (6) by using the signal data line (11) respectively, and conducts and processes received signals by using the signal data line (11);

the rotating shaft (4) is held, the rotating shaft (4) is utilized to drive the conical gear (17) to rotate, the conical gear (17) drives the ball screw (18) on one side to rotate, the ball screw (18) drives the vertical force arm (16) on one side to vertically descend, the vertical force arm (16) drives the lifting box body (5) to adjust the height, different specific position information is led into the electronic tag (14), the electronic tag (14) is installed under the lifting box body (5), and the electronic tag (14) and a reader are spatially coupled through a coupling element to realize radio-frequency signals; in the coupling channel, energy transfer and data exchange are realized according to a time sequence relation, and an operator can directly read the electronic tag (14) through a reader.

Images