CN114313683A - Intelligent household garbage classification method - Google Patents
Intelligent household garbage classification method Download PDFInfo
- Publication number
- CN114313683A CN114313683A CN202210016832.7A CN202210016832A CN114313683A CN 114313683 A CN114313683 A CN 114313683A CN 202210016832 A CN202210016832 A CN 202210016832A CN 114313683 A CN114313683 A CN 114313683A
- Authority
- CN
- China
- Prior art keywords
- garbage
- steering engine
- classification
- box body
- detection device
- 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
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 136
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001514 detection method Methods 0.000 claims abstract description 59
- 230000006870 function Effects 0.000 claims description 16
- 239000010410 layer Substances 0.000 claims description 13
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 239000002344 surface layer Substances 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000011161 development Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 7
- 238000013461 design Methods 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004064 recycling Methods 0.000 description 3
- 239000010791 domestic waste Substances 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- RSWGJHLUYNHPMX-UHFFFAOYSA-N Abietic-Saeure Natural products C12CCC(C(C)C)=CC2=CCC2C1(C)CCCC2(C)C(O)=O RSWGJHLUYNHPMX-UHFFFAOYSA-N 0.000 description 1
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- KHPCPRHQVVSZAH-HUOMCSJISA-N Rosin Natural products O(C/C=C/c1ccccc1)[C@H]1[C@H](O)[C@@H](O)[C@@H](O)[C@@H](CO)O1 KHPCPRHQVVSZAH-HUOMCSJISA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010992 reflux Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- KHPCPRHQVVSZAH-UHFFFAOYSA-N trans-cinnamyl beta-D-glucopyranoside Natural products OC1C(O)C(O)C(CO)OC1OCC=CC1=CC=CC=C1 KHPCPRHQVVSZAH-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/10—Waste collection, transportation, transfer or storage, e.g. segregated refuse collecting, electric or hybrid propulsion
Landscapes
- Processing Of Solid Wastes (AREA)
Abstract
The invention provides an intelligent household garbage classification method, which comprises the following steps: the method comprises the following steps that (1), garbage types are obtained through a recognition detection device in a classification box body, and signals are sent through an upper computer; step (2), the recognition detection device controls a garbage throwing device in the classification box body to throw garbage into different types of garbage cans; step (3), the recognition and detection device in the classification box body performs multiple times of garbage height detection and averages the garbage height to realize overflow detection; and (4) when the height data of the garbage obtained by the identification and detection device reaches a set value, giving an overflow alarm, and taking out and replacing the garbage can from the opening at the lower end of the classification box body. The invention improves the classification efficiency by continuously detecting the signal of the upper computer and has the advantages of stable operation, high putting efficiency, low maintenance cost and good development prospect.
Description
Technical Field
The invention relates to the technical field of garbage classification, in particular to an intelligent household garbage classification method.
Background
The garbage recycling is a huge industry, the recycling of garbage can bring huge profits to waste-utilizing enterprises, and the price of the garbage can be doubled. The average gross profit rate of waste recovery can reach more than 50% according to incomplete statistics. The garbage recycling industry has huge development prospect.
Since 2018, garbage classification is promoted in a plurality of cities in China, but the complex classification standards make correct garbage putting and treatment difficult for the public, and great demands are made on an intelligent classification system of domestic garbage.
Current rubbish intelligent classification system, from the categorised object, can divide into industry waste product intelligent classification and domestic waste classification, this patent is mainly towards domestic waste classification. Due to the fact that the properties of the household garbage are greatly different from each other, the classification system is often high in price, high in error rate, low in recognition speed, ineffective in overflow detection and the like, and is difficult to apply on a large scale.
In the process of visual identification, due to various inefficacy forces such as external light change and the like, an identification system can be out of order, so that a classification process is in failure or even is blocked, and the required manpower maintenance cost is extremely high.
Disclosure of Invention
The invention aims to provide an intelligent household garbage classification method to solve the problems in the background technology.
The technical problem solved by the invention is realized by adopting the following technical scheme: an intelligent household garbage classification method comprises the following steps:
the method comprises the following steps that (1), garbage types are obtained through a recognition detection device in a classification box body, and signals are sent through an upper computer;
step (2), the recognition detection device controls a garbage throwing device in the classification box body to throw garbage into different types of garbage cans;
step (3), the recognition and detection device in the classification box body performs multiple times of garbage height detection and averages the garbage height to realize overflow detection;
and (4) when the height data of the garbage obtained by the identification and detection device reaches a set value, giving an overflow alarm, and taking out and replacing the garbage can from the opening at the lower end of the classification box body.
The garbage type identification of the identification detection device is as follows: the upper computer of the recognition and detection device uses jetson nano to realize image processing, an algorithm is built by a deep learning YOLO3 framework, the garbage throwing device continuously receives data transmitted by the upper computer, different garbage types are distinguished, and a two-dimensional holder is controlled to throw garbage into corresponding small garbage cans.
The overflow detection of the identification detection device places the laser ranging module at the top of the garbage can, after the garbage classification is completed by the two-dimensional cradle head, the laser ranging module is rotated to the position above the corresponding small garbage can through a rocker at the top, and the full load condition of the current garbage can is determined through the feedback distance.
The garbage bin is characterized in that four garbage cans are arranged in the classification box body, an identification and detection device is arranged at the upper end of the classification box body, a throwing port is arranged at the front end of the classification box body, and a garbage throwing device is arranged in the throwing port.
The YOLO3 framework includes surface layer functions for performing classification operations, hidden layer functions for performing learning, and output layer functions for processing learning results and feeding back to the surface layer functions.
The identification detection device comprises a UI interface, and the more vivid trash can capacity display is carried out through the UI interface.
The identification and detection device comprises a camera, the camera is installed on a camera fixing support, a laser range finder is arranged on one side of the camera and installed on the laser range finder support, the laser range finder support and the camera fixing support are installed on a steering engine flange through a bolt M3X 8, the steering engine flange is installed on a steering engine, the steering engine is connected to an upper computer, the upper computer is connected with a power module, a control template, a power supply and a display screen, and the upper computer, the power module, the control template, the power supply and the display screen are installed in a control room on a control room partition plate.
The garbage throwing device comprises a tray, the tray is installed on a tray support, the tray support is installed on an upper steering engine through an upper steering engine flange, the upper steering engine is installed on a lower steering engine flange through an upper steering engine support, the lower steering engine flange is installed on a lower steering engine, and the lower steering engine is installed on a classification box body through a lower steering engine support.
The classification box body comprises a frame consisting of a plurality of upright column profiles and cross rod profiles, the upright column profiles and the cross rod profiles are fixedly connected through corner blocks, nuts M5 and bolts M5 x 10, a bottom plate, a left side plate, a front side plate, a right side plate, a rear side plate and a cover plate are arranged on the outer side of the frame, and the bottom plate, the left side plate, the front side plate, the right side plate, the rear side plate and the cover plate are arranged on the frame through nuts M5 and bolts M5 x 10.
Compared with the prior art, the invention has the beneficial effects that: the invention continuously detects the signal of the upper computer to improve the classification efficiency. The full load of the garbage is measured through the laser sensor, the garbage is detected for multiple times above the barrel, and the average value of the height of the garbage is obtained to reflect the overflow condition. The serial port communication protocol is self-defined, so that the packet loss condition in the transmission process is avoided, and the whole system is more stable to operate. The circuit adopts a physical isolation unit design mode to distinguish a digital area from an analog area, the digital area and the analog area are not mutually coherent, and mutual influence between the digital area and the analog area is reduced. And the PCB is subjected to modular design, and mutual structural consistency is realized.
AI discernment is based on the deep learning design, and the algorithm is built by YOLO3 frame, divide into the three-layer with the main program, is the top layer function of carrying out the waste classification order respectively, carries out the hidden function of deep learning through the waste classification result to and feed back the output function of top layer function with the learning result, make the discernment of rubbish more accurate stable, and make the duration of garbage bin visual identification logic stronger, can adapt to the categorised demand of epoch development to novel rubbish. Compared with the existing intelligent classification system, the implementation scheme has the advantages of stable operation, high putting efficiency, low maintenance cost and good development prospect.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a flowchart illustrating a main procedure of the method of the present invention.
FIG. 3 is a flow chart of a communication subroutine of the present invention.
Fig. 4 is a schematic flow chart of the two-dimensional pan-tilt classification subroutine of the present invention.
FIG. 5 is a flowchart illustrating an overflow detection procedure according to the present invention.
FIG. 6 is a schematic diagram of a voltage step-down circuit according to the present invention.
Fig. 7 is a circuit schematic diagram of the minimum system of the single chip microcomputer.
FIG. 8 is a schematic view of a steering engine interface according to the present invention.
Fig. 9 is an exploded view of the sorting cabinet of the present invention.
Fig. 10 is a schematic structural diagram of YOLOv 3416 model according to the present invention.
Fig. 11 is a front view schematic of the present invention.
Fig. 12 is a cross-sectional view along AA of fig. 11.
Fig. 13 is a cross-sectional view taken along line BB of fig. 11.
In the figure: 1. a column section bar; 2. a cross bar section; 3. a corner block; 4. a nut M5; 5. bolt M5 × 10; 6. a base plate; 7. a trash can; 8. a lower steering engine; 9. a lower steering engine bracket; 10. a lower steering engine flange; 11. an upper steering engine; 12. an upper steering engine bracket; 13. an upper steering engine flange; 14. a tray support; 15. a tray; 16. a left side plate; 17. a front side plate; 18. a right side plate; 19. a rear side plate; 20. a camera; 21. a camera fixing bracket; 22. bolt M3 × 8; 23. a steering engine flange; 24. a laser rangefinder support; 25. a laser range finder; 26. a steering engine; 27. a control room partition; 28. an upper computer; 29. a power supply module; 30. a control template; 31. a power source; 32. a cover plate; 33. a display screen.
Detailed Description
In the description of the present invention, it should be noted that unless otherwise specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected, mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements.
Example 1
As shown in fig. 1 to 8, an intelligent classification method for household garbage includes the following steps:
the method comprises the following steps that (1), garbage types are obtained through a recognition detection device in a classification box body, and signals are sent through an upper computer;
step (2), the recognition detection device controls a garbage throwing device in the classification box body to throw garbage into different types of garbage cans;
step (3), the recognition and detection device in the classification box body performs multiple times of garbage height detection and averages the garbage height to realize overflow detection;
and (4) when the height data of the garbage obtained by the identification and detection device reaches a set value, giving an overflow alarm, and taking out and replacing the garbage can from the opening at the lower end of the classification box body.
The garbage type identification of the identification detection device is as follows: the upper computer of the recognition and detection device uses jetson nano to realize image processing, an algorithm is built by a deep learning YOLO3 framework, the garbage throwing device continuously receives data transmitted by the upper computer, different garbage types are distinguished, and a two-dimensional holder is controlled to throw garbage into corresponding small garbage cans. The overflow detection of the identification detection device places the laser ranging module at the top of the garbage can, after the garbage classification is completed by the two-dimensional cradle head, the laser ranging module is rotated to the position above the corresponding small garbage can through a rocker at the top, and the full load condition of the current garbage can is determined through the feedback distance. The YOLO3 framework includes surface layer functions for performing classification operations, hidden layer functions for performing learning, and output layer functions for processing learning results and feeding back to the surface layer functions. The identification detection device comprises a UI interface, and the more vivid trash can capacity display is carried out through the UI interface.
The main control selects an STM32F103C8T6 block, and the operation speed is high, the peripheral equipment is abundant, the price is moderate, and the encapsulation is small. In order to accurately put rubbish into the corresponding garbage can, the scheme adopts two 1501 digital steering engines to form a two-dimensional cradle head, the controllable angle of the two-dimensional cradle head is 180 degrees, the linearity is good, and the two-dimensional cradle head is accurately controlled. In order to meet the requirement of measuring the full load condition of the garbage can, a TF-Luna laser radar ranging sensor is selected, so that the resolution is high, the detection range is large, and the detection precision is high. Simultaneously, the 3115 digital steering wheel of 270 degrees has been selected and has been regarded as the rotary power of rocker, and controllable scope can cover 4 garbage bins, and accurate help range finding goes. The power supply selects a 3S model airplane battery with 11.1V, a 25C battery with strong discharging capacity is selected for preventing voltage drop in the working process of the motor, LM2596S and 1AMS1117 are used for voltage stabilization, the steering engine and the control circuit are separately powered, and the control circuit is prevented from being influenced to supply power when the steering engine rotates.
Wherein:
(1) the main procedure is as follows: the main program is basic business logic for classifying the garbage can, waiting for garbage input, obtaining garbage types through communication,
And the tasks of garbage classification and overflow detection can be completed by sequentially executing two-dimensional cradle head classification, overflow detection and two-position cradle head reset.
(2) A communication main program: the lower computer STM32 and the upper computer JETSON NANO exchange data through serial ports, and the upper computer transmits and recognizes
The garbage type is that the lower computer transmits the full load condition of the garbage can by setting a flag bit; type to decide whether the receiving or transmitting state is currently present.
(3) Two-dimensional pan-tilt classification subprogram: the garbage can is classified and thrown in through the steering gears of the horizontal shaft and the pitching shaft.
(4) And (3) overflow detection program: the laser sensor at the top of the garbage can is changed by controlling the rocker mechanism at the top of the garbage can, and the overflow condition of each garbage can is detected by the sensor.
The main control unit is composed of a DC/DC voltage reduction circuit, a singlechip minimum system circuit, a steering engine interface, a laser ranging module interface, a key interface, a serial interface, an SWD interface and an OLED interface. The following is a functional introduction of each module:
(1) DC/DC step-down circuit: the power supply is 12V input, an 11.1V lithium battery interface is arranged at the power supply, the IC1 is LM2596-5.0, 5V (for steering engine, infrared distance measurement, serial communication and OLED) AMS1117-3.3 is output, and 3.3V (for MCU and ADC) is output; (2) the minimum system of the single chip microcomputer: the single chip microcomputer control minimum system takes STM32F103C8T6 as a core; (3) and 2, serial port 2: the communication module is used for communication between the upper computer and the lower computer; (4) and (3) serial port: the device is used for detecting the overflow condition of the garbage can; (5) the steering engine interface: the steering engine is connected with the two-dimensional pan-tilt and is connected with the 270-degree steering engine for controlling the rocker; (6) an SWD interface: the device is used for debugging and downloading the program of the single chip microcomputer; (7) an OLED interface: is convenient for observation and debugging. (8) Pressing a key: user self-defining; (9) power indicator, LED lamp: power-on prompt, load (10) extension IO: and adding other peripheral equipment.
The circuit is designed according to the principle of high reliability, low cost and benefit to mass production. On the premise of ensuring stable work, the chip is made of a commonly-used domestic model, so that the cost and the purchasing difficulty are greatly reduced. The position and the angle that components and parts were put on the circuit board all do benefit to the chip mounter and paste the dress, do not go up the via hole during the wiring on the pad, and solder paste flows into the via hole and causes the rosin joint when preventing the excessive reflux to improve production quality, integrate all components and parts on a PCB bottom plate.
The digital ground and the analog ground are separated by adopting a physical isolation unit design mode and are not interfered with each other, so that the mutual influence between a digital circuit and an analog circuit is reduced. Meanwhile, the power circuit and the signal circuit are separated, and the interference on the circuit signal can be reduced. A plurality of filter capacitors are used in the power supply, and the direct current power supply used by people is guaranteed.
The interface is designed according to the shortest wiring principle, so that the cost of the electric wire is reduced; the PCB is designed in a modularized way, and the structures are mutually consistent. Full load detection: full-load device is used for detecting whether the rubbish in the garbage bin exceeds whole volumetric 75%, need have stronger accuracy and last working capacity, consequently adopts cantilever structure, and it is rotatory in the garbage bin top to drive the cantilever by 270 degrees steering engines, carries out the omnidirectional scanning, detects each corner of garbage bin. AI identification: the garbage is identified based on deep learning. The camera data are processed through the edge computing terminal, so that the effect is more obvious, and the identification is more accurate.
Example 2
As shown in fig. 1 and 9, an intelligent classification method for household garbage includes the following steps:
the method comprises the following steps that (1), garbage types are obtained through a recognition detection device in a classification box body, and signals are sent through an upper computer;
step (2), the recognition detection device controls a garbage throwing device in the classification box body to throw garbage into different types of garbage cans;
step (3), the recognition and detection device in the classification box body performs multiple times of garbage height detection and averages the garbage height to realize overflow detection;
and (4) when the height data of the garbage obtained by the identification and detection device reaches a set value, giving an overflow alarm, and taking out and replacing the garbage can from the opening at the lower end of the classification box body.
The garbage bin is characterized in that four garbage bins 7 are arranged in the classification box body, an identification and detection device is arranged at the upper end of the classification box body, a throwing port is arranged at the front end of the classification box body, and a garbage throwing device is arranged in the throwing port.
The identification and detection device comprises a camera 20, the camera 20 is installed on a camera fixing support 21, a laser range finder 25 is arranged on one side of the camera 20, the laser range finder 25 is installed on the laser range finder support 24, the laser range finder support 24 and the camera fixing support 21 are installed on a steering engine flange 23 through a bolt M3X 822, the steering engine flange 23 is installed on a steering engine 26, the steering engine 26 is connected to an upper computer 28, the upper computer 28 is connected with a power module 29, a control template 30, a power supply 31 and a display screen 33, and the upper computer 28, the power module 29, the control template 30, the power supply 31 and the display screen 33 are installed in a control chamber on a control chamber partition plate 27.
The garbage throwing device comprises a tray 15, wherein the tray 15 is installed on a tray support 14, the tray support 14 is installed on an upper steering engine 11 through an upper steering engine flange 13, the upper steering engine 11 is installed on a lower steering engine flange 10 through an upper steering engine support 12, the lower steering engine flange 10 is installed on a lower steering engine 8, and the lower steering engine 8 is installed on a classification box body through a lower steering engine support 9.
The classification box body comprises a frame consisting of a plurality of upright column profiles 1 and cross rod profiles 2, the upright column profiles 1 and the cross rod profiles 2 are fixedly connected through corner blocks 3, nuts M54 and bolts M5X 105, a bottom plate 6, a left side plate 16, a front side plate 17, a right side plate 18, a rear side plate 19 and a cover plate 32 are arranged on the outer side of the frame, and the bottom plate 6, the left side plate 16, the front side plate 17, the right side plate 18, the rear side plate 19 and the cover plate 32 are arranged on the frame through nuts M54 and bolts M5X 105.
The operation characteristic of the Yolov3 structure is that firstly, an FPN feature pyramid is constructed from a data set for reinforced feature extraction: detecting a detection target, extracting three characteristic layers, and constructing an FPN layer by using the three characteristic layers; secondly, obtaining a prediction result by using a Yolo Head, obtaining three reinforced features by using the FPN feature pyramid, and obtaining the prediction result by using the three feature layers and transmitting the Yolo Head; and after a final prediction result is obtained, performing score sorting and non-maximum inhibition screening to obtain a result.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. An intelligent household garbage classification method is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps that (1), garbage types are obtained through a recognition detection device in a classification box body, and signals are sent through an upper computer;
step (2), the recognition detection device controls a garbage throwing device in the classification box body to throw garbage into different types of garbage cans;
step (3), the recognition and detection device in the classification box body performs multiple times of garbage height detection and averages the garbage height to realize overflow detection;
and (4) when the height data of the garbage obtained by the identification and detection device reaches a set value, giving an overflow alarm, and taking out and replacing the garbage can from the opening at the lower end of the classification box body.
2. The intelligent household garbage classification method according to claim 1, characterized in that: the garbage type identification of the identification detection device is as follows: the upper computer of the recognition and detection device uses jetson nano to realize image processing, an algorithm is built by a deep learning YOLO3 framework, the garbage throwing device continuously receives data transmitted by the upper computer, different garbage types are distinguished, and a two-dimensional holder is controlled to throw garbage into corresponding small garbage cans.
3. The intelligent household garbage classification method according to claim 2, characterized in that: the overflow detection of the identification detection device places the laser ranging module at the top of the garbage can, after the garbage classification is completed by the two-dimensional cradle head, the laser ranging module is rotated to the position above the corresponding small garbage can through a rocker at the top, and the full load condition of the current garbage can is determined through the feedback distance.
4. The intelligent household garbage classification method according to claim 1, characterized in that: the garbage can is characterized in that four garbage cans (7) are arranged in the classification box body, an identification and detection device is arranged at the upper end of the classification box body, a throwing port is arranged at the front end of the classification box body, and a garbage throwing device is arranged in the throwing port.
5. The intelligent household garbage classification method according to claim 2, characterized in that: the YOLO3 framework includes surface layer functions for performing classification operations, hidden layer functions for performing learning, and output layer functions for processing learning results and feeding back to the surface layer functions.
6. The intelligent household garbage classification method according to claim 1, characterized in that: the identification detection device comprises a UI interface, and the more vivid trash can capacity display is carried out through the UI interface.
7. The intelligent household garbage classification method according to claim 4, characterized in that: the identification detection device comprises a camera (20), the camera (20) is arranged on a camera fixing support (21), a laser range finder (25) is arranged on one side of the camera (20), the laser range finder (25) is arranged on a laser range finder bracket (24), the laser range finder bracket (24) and the camera fixing bracket (21) are arranged on the steering engine flange (23) through bolts M3 multiplied by 8(22), the steering engine flange (23) is arranged on a steering engine (26), the steering engine (26) is connected with an upper computer (28), the control room is characterized in that the upper computer (28) is connected with a power module (29), a control template (30), a power supply (31) and a display screen (33), and the upper computer (28), the power module (29), the control template (30), the power supply (31) and the display screen (33) are installed in the control room on the control room partition plate (27).
8. The intelligent household garbage classification method according to claim 4, characterized in that: the garbage throwing device comprises a tray (15), wherein the tray (15) is installed on a tray support (14), the tray support (14) is installed on an upper steering engine (11) through an upper steering engine flange (13), the upper steering engine (11) is installed on a lower steering engine flange (10) through an upper steering engine support (12), the lower steering engine flange (10) is installed on a lower steering engine (8), and the lower steering engine (8) is installed on a classification box body through a lower steering engine support (9).
9. The intelligent household garbage classification method according to claim 4, characterized in that: the classification box body comprises a frame consisting of a plurality of upright column profiles (1) and cross rod profiles (2), the upright column profiles (1) and the cross rod profiles (2) are fixedly connected through corner blocks (3), nuts M5(4) and bolts M5 x 10(5), a bottom plate (6), a left side plate (16), a front side plate (17), a right side plate (18), a rear side plate (19) and a cover plate (32) are arranged on the outer side of the frame, the bottom plate (6), the left side plate (16), the front side plate (17), the right side plate (18), the rear side plate (19) and the cover plate (32) are arranged on the frame through the nuts M5(4) and the bolts M5 x 10 (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210016832.7A CN114313683A (en) | 2022-01-07 | 2022-01-07 | Intelligent household garbage classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210016832.7A CN114313683A (en) | 2022-01-07 | 2022-01-07 | Intelligent household garbage classification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114313683A true CN114313683A (en) | 2022-04-12 |
Family
ID=81024885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210016832.7A Pending CN114313683A (en) | 2022-01-07 | 2022-01-07 | Intelligent household garbage classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114313683A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152521A (en) * | 2023-09-04 | 2023-12-01 | 长江大学 | Garbage can device based on convolutional neural network and embedded technology and use method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730741B1 (en) * | 2015-12-30 | 2017-05-11 | 배응준 | Separating and Collecting Apparatus with Easy Loading of Recycled Product |
| CN107352297A (en) * | 2016-04-26 | 2017-11-17 | 京瓷办公信息系统株式会社 | Sheet material loading device and the sheet post-processing apparatus and image processing system for possessing it |
| CN109230096A (en) * | 2018-10-31 | 2019-01-18 | 徐州徐工环境技术有限公司 | A kind of kitchen waste cart weighing detection system and detection method |
| CN110076782A (en) * | 2019-06-11 | 2019-08-02 | 长春财经学院 | A kind of intelligence control garbage classification machine people of computer vision target identification |
| CN210534039U (en) * | 2019-07-12 | 2020-05-15 | 江苏丰创新材料有限公司 | Heat conduction effect detection device of heat dissipation film |
| CN111924386A (en) * | 2020-07-31 | 2020-11-13 | 长沙普惠环保机械有限公司 | Automatic garbage can carrying control system and method of garbage compression equipment |
| CN112009899A (en) * | 2020-07-13 | 2020-12-01 | 西安建筑科技大学 | Garbage classification box constructed based on convolutional neural network |
| CN113401533A (en) * | 2021-07-29 | 2021-09-17 | 浙江金实乐环境工程有限公司 | Image recognition-based garbage classification putting system and method |
-
2022
- 2022-01-07 CN CN202210016832.7A patent/CN114313683A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730741B1 (en) * | 2015-12-30 | 2017-05-11 | 배응준 | Separating and Collecting Apparatus with Easy Loading of Recycled Product |
| CN107352297A (en) * | 2016-04-26 | 2017-11-17 | 京瓷办公信息系统株式会社 | Sheet material loading device and the sheet post-processing apparatus and image processing system for possessing it |
| CN109230096A (en) * | 2018-10-31 | 2019-01-18 | 徐州徐工环境技术有限公司 | A kind of kitchen waste cart weighing detection system and detection method |
| CN110076782A (en) * | 2019-06-11 | 2019-08-02 | 长春财经学院 | A kind of intelligence control garbage classification machine people of computer vision target identification |
| CN210534039U (en) * | 2019-07-12 | 2020-05-15 | 江苏丰创新材料有限公司 | Heat conduction effect detection device of heat dissipation film |
| CN112009899A (en) * | 2020-07-13 | 2020-12-01 | 西安建筑科技大学 | Garbage classification box constructed based on convolutional neural network |
| CN111924386A (en) * | 2020-07-31 | 2020-11-13 | 长沙普惠环保机械有限公司 | Automatic garbage can carrying control system and method of garbage compression equipment |
| CN113401533A (en) * | 2021-07-29 | 2021-09-17 | 浙江金实乐环境工程有限公司 | Image recognition-based garbage classification putting system and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152521A (en) * | 2023-09-04 | 2023-12-01 | 长江大学 | Garbage can device based on convolutional neural network and embedded technology and use method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114313683A (en) | Intelligent household garbage classification method | |
| CN107138503B (en) | A kind of garbage classification, recycling, the processing integral intelligent circulatory system | |
| CN103991660A (en) | Intelligent weighing sorting dustbin | |
| CN109305490B (en) | Intelligent classification dustbin based on image recognition technology | |
| CN201532310U (en) | Complete automobile road-test testing device | |
| CN111717560A (en) | Intelligent classification garbage bin based on computer vision technique | |
| CN109809060A (en) | A kind of automatic sorting garbage bin and its management system | |
| CN112849814A (en) | Garbage identification and throwing device and control method thereof | |
| CN210392358U (en) | Garbage can for detecting garbage weight and overflow condition | |
| CN110539989A (en) | Pronunciation intelligent classification garbage bin | |
| CN203076217U (en) | Bean color sorter | |
| CN113800146A (en) | Independent power supply intelligent classification dustbin | |
| CN112793954A (en) | Intelligent paid garbage recycling bin and method | |
| CN203903214U (en) | Intelligent weighing and classifying dustbin | |
| CN218143550U (en) | Automatic garbage classification device | |
| CN208333597U (en) | Oil-measuring apparatus for metering separator | |
| CN208636680U (en) | A kind of agricultural collection system of Internet of things | |
| CN113562355A (en) | Intelligent garbage sorting device and method based on deep learning technology | |
| CN203438651U (en) | 2D solder paste detection printing device | |
| CN112642170B (en) | Garbage classification toy | |
| CN201327415Y (en) | Embedded-type image detecting device | |
| CN214191135U (en) | Garbage throwing device | |
| CN212654886U (en) | Rubbish automatic classification bucket based on raspberry group control | |
| CN2663984Y (en) | An embedded real-time image processing unit based on DSP | |
| Zeng et al. | Design of intelligent classified trash can based on STM32 |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220412 |
|
| RJ01 | Rejection of invention patent application after publication |