CN111137602A - Garbage classification method and garbage classification system based on artificial intelligence - Google Patents
Garbage classification method and garbage classification system based on artificial intelligence Download PDFInfo
- Publication number
- CN111137602A CN111137602A CN202010110006.XA CN202010110006A CN111137602A CN 111137602 A CN111137602 A CN 111137602A CN 202010110006 A CN202010110006 A CN 202010110006A CN 111137602 A CN111137602 A CN 111137602A
- Authority
- CN
- China
- Prior art keywords
- horizontal direction
- garbage
- classification
- measuring
- along
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 230000008569 process Effects 0.000 claims description 33
- 238000009826 distribution Methods 0.000 claims description 24
- 239000002699 waste material Substances 0.000 claims description 22
- 238000005192 partition Methods 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 11
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/138—Identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/176—Sorting means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/178—Steps
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/184—Weighing means
-
- 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
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention provides a garbage classification method and a garbage classification system based on artificial intelligence. The technical scheme of the invention does not focus on trying to subdivide the garbage into accurate categories in one step, but focuses on the pretreatment stage of garbage classification, namely the rough classification stage. The coarse classification feeds back the classification control system based on each classification result, so that the classification control system is continuously trained, and the coarse classification result of the original garbage is more and more accurate; based on the coarse classification results, subsequent subdivision may be performed using other techniques according to respective finer criteria. Through the treatment of the technical scheme of the invention, at least the garbage to be treated can be distinguished more easily in physical expression form, thereby facilitating the subsequent fine identification by adopting an automatic means and further carrying out automatic classification.
Description
Technical Field
The invention belongs to the technical field of intelligent garbage treatment, and relates to a garbage classification method and a garbage classification system based on artificial intelligence.
Background
With the improvement of living standard of people, the quantity of municipal refuse is increased, according to the data of Ministry of environmental protection, the quantity of domestic refuse in the whole country is estimated to exceed 2000 ten thousand tons in 2019, the municipal refuse becomes an important pollution source of big and medium cities in the whole country, and the refuse classification is very slow. Although the existing household garbage is also provided with the recyclable garbage can and the non-recyclable garbage can, everyone can understand whether the garbage can be recycled or not differently, so that the classified garbage can is the same as the nominal garbage.
At present, more than 90% of the available wastes in China are buried or incinerated. The precondition for achieving maximum utilization is garbage classification. In Beijing, Hangzhou, Guangzhou, Shanghai and the like, the garbage classification test has been carried out for years, but no obvious practical effect is seen, and although garbage cans with different colors are placed at the doorway of a residential area, various garbage mixed and freely distributed degradable garbage bags are also used for containing other garbage.
Various front-end devices for garbage classification in the current market are all based on an artificial classification mode. The classification (two classification or four classification or six classification) of the garbage is distinguished by people throwing the garbage, then the garbage is intensively thrown into a certain classification barrel, and then different collection channels are used for transferring. However, this mode has the following drawbacks:
1) the time required by residents to cultivate the garbage classification skills is too long, and the cost is too high;
2) the classification identification and the color of each city are not uniform, which is not beneficial to the memory and the distinguishing of residents;
3) by using a reward mechanism, a great number of releasing modes depending on government subsidies cannot be continuous, and residents cannot be effectively stimulated to release the subsidies;
4) the garbage classification of public areas does not implement an effective reward incentive mechanism.
In contrast, the chinese patent application with application number CN201811000409.8 proposes a garbage collection robot based on artificial intelligence classification, which is further provided with a large database, so that not only can garbage be classified according to the existing garbage name, but also new garbage names can be automatically added, thereby realizing automatic update of garbage classification. Therefore, the invention is a garbage collection robot which is more definite based on artificial intelligence garbage classification, can open and close the garbage door at a longer distance and is more environment-friendly. However, the solution does not give a specific solution to the claimed "big database", and only refers to that "the inside of the big database is provided with a large number of garbage names, and each garbage name is classified into recyclable garbage and non-recyclable garbage; when the voice system receives the garbage name, the garbage name is stored in a large database through a control system, and the doubtful effect is achieved; the chinese patent application No. cn201810678499.x proposes an intelligent garbage recycling system based on artificial intelligence and big data technology, which uses a camera to photograph garbage, and then uses a garbage recognition module to recognize garbage photographs photographed by the camera, classifies the garbage, controls a corresponding garbage storage box to be opened, and puts the garbage into the corresponding garbage storage box. However, those skilled in the art know that the simple garbage classification method based on image recognition has low accuracy, which is why the current garbage classification requires a lot of human involvement; the Chinese patent application with the application number of CN201811546245.9 provides an automatic indoor household garbage sorting device based on artificial intelligence, a camera is controlled to shoot, an obtained picture is compared with a reference image obtained when the device is started, the obtained picture is compressed into a jpeg format, a recognition result uploaded to a cloud platform is obtained, the recognition result is still claimed to adopt an artificial intelligence classification model, the problems of inaccuracy and classification willingness of resident classification are solved, and two classification modes are rapidly realized through a turnover mechanism. But no specific classification model implementation and effect verification are given.
In summary, the garbage disposal is a complete system, and the classification collection, the classification transportation, the classification treatment and the classification utilization must be connected and matched with each other, otherwise the classification effect is greatly reduced. The prior art focuses on trying to classify garbage at one time, but if the accuracy is guaranteed, a great deal of manpower is required to be invested in the one-time classification, namely, manual cooperation is required to classify the garbage accurately, and the accuracy is low only depending on the classification result of the image recognition method and the like, so that the large-scale popularization is completely impossible.
Therefore, the inventor thinks that the intelligent garbage classification can be realized as accurately as possible by changing the technical bias of the prior art which tries one-time classification.
Disclosure of Invention
The present invention is a corresponding effective technical solution for solving the above technical problems.
Therefore, the invention provides a garbage classification method and a garbage classification system based on artificial intelligence. The technical solution of the present invention does not focus on trying to subdivide the garbage into accurate categories in one step (in fact, the detailed rules of garbage classification in each place are different), but focuses on the pre-processing stage of garbage classification, i.e. the coarse classification stage. The coarse classification feeds back the classification control system based on each classification result, so that the classification control system is continuously trained, and the coarse classification result of the original garbage is more and more accurate; based on the coarse classification results, subsequent subdivision may be performed using other techniques according to respective finer criteria. Since the subdivision is based on the coarse classification results, computerized implementations, such as image recognition techniques, may be employed to perform the subdivision.
It is noted that the garbage classification system of the present invention does not involve any process that requires image recognition.
The garbage to be classified can be classified and put by a garbage generator according to own will, and can also be original mixed garbage. Through the treatment of the technical scheme of the invention, at least the garbage to be treated can be distinguished more easily in physical expression form, thereby facilitating the subsequent fine identification by adopting an automatic means and further carrying out automatic classification.
In a first aspect of the invention, an artificial intelligence waste classification system is provided, which comprises a motion control system of a waste measuring hopper, a vertical conveyor belt system and a feedback control system connecting the motion control system and the vertical conveyor belt.
The garbage measuring hopper reciprocates along a first horizontal direction under the control of the motion control system
The vertical conveyor belt system is positioned below the first horizontal plane;
the vertical conveyor system comprises a plurality of conveyors; the conveying direction of the conveying belt is vertical to the first horizontal direction, the conveying belts are separated by a plurality of separating clapboards, and the separating clapboards are vertical to the horizontal plane of the conveying belt; and the heights of the plurality of discrete partition boards are gradually reduced from the middle to two sides;
the measuring bucket device rotates along the rotation direction along the central vertical axis of the measuring bucket device simultaneously in the reciprocating motion process along the first horizontal direction;
the vertical conveyor belt system also comprises an artificial intelligence classification and identification engine, and the rotating speed and the horizontal direction moving speed of the measuring hopper in the reciprocating motion process along the first horizontal direction are adjusted based on the identification result of the artificial intelligence classification and identification engine;
the heights of the plurality of discrete partition plates decrease from the middle to the two sides, and specifically, the height of each discrete partition plate is as follows:
the heights of the plurality of discrete baffles conform to a gaussian distribution;
in the initial state, the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction change along with the height change of the discrete partition plate below the measuring hopper.
The artificial intelligence classification and identification engine is used for identifying and classifying the garbage conveyed by the plurality of conveyor belts, and each conveyor belt is provided with a weight sensor and a humidity sensor; the weight sensor is used for detecting the weight of the garbage on the corresponding conveyor belt, and the humidity sensor is used for detecting the humidity of the garbage on the corresponding conveyor belt; if the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution.
And if the humidity values of all the wastes on the plurality of conveyor belts are uniformly distributed according to the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the humidity values of all the wastes on the plurality of conveyor belts are uniformly distributed.
The measuring bucket ware includes: a first upper frame; a second lower frame; a third chassis; a plurality of side connecting pieces connecting the first upper frame and the second lower frame; the rotating shaft is connected with the center positions of the first upper frame and the third chassis, and the plurality of cross rod pieces which are arranged on the rotating shaft and are vertical to the rotating shaft are arranged in a staggered mode.
Wherein the length values of the plurality of staggered cross-bar pieces conform to a Gaussian distribution.
And the third chassis and the second lower frame have a height difference, and the height difference is adjustable.
The area of the region surrounded by the first upper frame is larger than the area of the region surrounded by the second lower frame, and the area of the third chassis is larger than the area of the region surrounded by the second lower frame.
The measuring hopper comprises a motion control device, the motion control device is connected with the vertical conveyor belt system, and the rotation speed and the horizontal direction movement speed of the measuring hopper in the process of reciprocating in the first horizontal direction are adjusted based on the recognition result of an artificial intelligence classification recognition engine of the vertical conveyor belt system.
In a second aspect of the present invention, a method for classifying garbage by using the garbage classification system is provided, the method comprising the steps of:
s1: initializing the motion control device of the measuring funnel so that the rotation speed and the horizontal direction motion speed of the measuring funnel in the process of reciprocating along the first horizontal direction are changed along with the height change of the discrete partition plate below the measuring funnel;
s2: putting the garbage to be classified into the measuring hopper in batches until the measuring hopper is filled;
s3: the motion control device controls the measuring hopper to reciprocate along a first horizontal direction and simultaneously controls the measuring hopper to rotate along a central vertical axis of the measuring hopper along a rotating direction until the measuring hopper is in an idle state;
s4: an artificial intelligence classification recognition engine of the vertical conveyor belt system performs classification recognition on the garbage falling onto the plurality of conveyor belts;
s5: based on the classification and identification results, the vertical conveyor belt system sends feedback parameters to the motion control device, so that the motion control device adjusts the rotation speed of the measuring bucket in the reciprocating process along the first horizontal direction and the motion speed of the measuring bucket in the horizontal direction; return is made to step S2.
After the measuring hopper is in an idle state, the plurality of conveyor belts of the vertical conveyor belt system start to start, and the garbage on the conveyor belts is conveyed to a far end for classification and identification.
Wherein the height of the plurality of discrete baffles is adjustable.
Further advantages of the present invention will be further apparent from the detailed description of the preferred embodiments in conjunction with the drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is an overall framework diagram of the applicants' industrial intelligent garbage classification system;
FIG. 2 is a schematic diagram of the operation of the applicants' industrial intelligent garbage classification system;
FIG. 3 is a detailed view of a measuring hopper employed in the present application of the artificial intelligence garbage classification system;
FIG. 4 is a flowchart of an artificial intelligence garbage classification method of the present application.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
In order that the above objects, features and advantages of the present invention can be more clearly understood, the present invention will be further described with reference to the accompanying drawings and examples. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, the embodiment discloses an artificial intelligence garbage classification system, which comprises a motion control system of a garbage measuring hopper, a vertical conveyor belt system and a feedback control system connecting the motion control system and the vertical conveyor belt.
It should be noted that the present embodiment aims at coarse classification of garbage, and the garbage classification system does not include any process requiring image recognition.
Specifically, referring to fig. 2, the garbage measuring bin reciprocates in a first horizontal direction under the control of the motion control system;
the vertical conveyor belt system is positioned below the first horizontal plane;
the vertical conveyor system comprises a plurality of conveyors; the conveying direction of the conveying belt is vertical to the first horizontal direction, the conveying belts are separated by a plurality of separating clapboards, and the separating clapboards are vertical to the horizontal plane of the conveying belt; and the heights of the plurality of discrete partition boards are gradually reduced from the middle to two sides;
the measuring bucket device rotates along the rotation direction along the central vertical axis of the measuring bucket device simultaneously in the reciprocating motion process along the first horizontal direction;
the vertical conveyor belt system also comprises an artificial intelligence classification and identification engine, and the rotating speed and the horizontal direction moving speed of the measuring hopper in the reciprocating motion process along the first horizontal direction are adjusted based on the identification result of the artificial intelligence classification and identification engine;
the artificial intelligence classification and identification engine is used for identifying and classifying the garbage conveyed by the plurality of conveyor belts, and each conveyor belt is provided with a weight sensor and a humidity sensor; the weight sensor is used for detecting the weight of the garbage on the corresponding conveyor belt, and the humidity sensor is used for detecting the humidity of the garbage on the corresponding conveyor belt; if the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution.
And if the humidity values of all the wastes on the plurality of conveyor belts are uniformly distributed according to the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the humidity values of all the wastes on the plurality of conveyor belts are uniformly distributed.
For example, the vertical conveyor system of fig. 2 shows 5 vertically oriented conveyors, and the weight sensor detects the weight of the waste on the corresponding 5 conveyors, and if the weight of the waste on the 1/3/4/5 th conveyor is approximately in accordance with the gaussian distribution, and the weight of the waste on the second conveyor cannot be fitted into the distribution, it means that the weight of the waste on the second conveyor is too large or too small;
it should be noted that the number 5 is only a schematic illustration, and in fact, only 5 sample values cannot be fitted to the gaussian distribution, and the embodiment of the present invention certainly has more than 5 conveyor belts in specific operation, and the number of the conveyor belts is more, so that the embodiment of the present invention can meet the requirement of the number of the samples of the gaussian distribution.
If the weight value is too small, reducing the horizontal movement speed when the measuring hopper approaches the second conveyor belt in the horizontal direction; increasing the horizontal speed of movement, and/or increasing the rotational speed, as the hopper approaches and moves away from the second conveyor belt in the horizontal direction; preferably, the increasing value of the horizontal direction moving speed is smaller than the increasing value of the rotational speed.
Similarly, the moisture sensor detects the moisture value of the waste on the corresponding 5 conveyors, and if the moisture value of the waste on the 1/3/4/5 th conveyor is approximately consistent with a uniform distribution, and the moisture value of the waste on the second conveyor cannot be fitted into the distribution, the moisture value of the waste on the second conveyor is too large or too small;
if the weight value is too small, increasing the horizontal direction movement speed when the measuring hopper approaches the second conveyor belt in the horizontal direction; increasing the rotational speed as the bucket approaches and moves away from the second conveyor in the horizontal direction.
Of course, the garbage classification system has an initial state and cannot acquire the feedback parameters. Therefore, the initialization state needs to be set.
In the present embodiment, the inventors studied that, in the initial state, the rotation speed and the horizontal direction movement speed of the measuring funnel during the reciprocating movement in the first horizontal direction change with the height change of the discrete partition below the measuring funnel.
Specifically, the height of the discrete partition is in positive correlation with the rotation speed of the measuring funnel during reciprocating movement in a first horizontal direction, and in inverse correlation with the horizontal direction movement speed.
The heights of the plurality of discrete partition plates decrease from the middle to the two sides, and specifically, the height of each discrete partition plate is as follows:
the heights of the plurality of discrete baffles conform to a gaussian distribution.
Specifically, referring to fig. 3, a detailed view of the measuring hopper used in the intelligent garbage classification system of the present applicant is shown.
The measuring bucket ware includes:
a first upper frame (1); a second lower frame (2); a third chassis (3);
a plurality of side connecting pieces (4) connecting the first upper frame (1) and the second lower frame (2);
a rotating shaft (5) connecting the first upper frame (1) and the center of the third chassis (3);
and a plurality of cross rod pieces (6) which are arranged on the rotating shaft (5) and are vertical to the rotating shaft (5) in a staggered mode.
Wherein the length values of the plurality of staggered cross-bar pieces (6) conform to a Gaussian distribution.
The third chassis (3) and the second lower frame (2) have a height difference, and the height difference is adjustable.
The area of the area surrounded by the first upper frame (1) is larger than the area of the area surrounded by the second lower frame (2), and the area of the third chassis (3) is larger than the area of the area surrounded by the second lower frame (2).
By adopting the unique design, the distribution of the separated garbage under the influence of the motion state of the measuring hopper in the horizontal direction and the motion state in the rotating direction can conform to the expected Gaussian distribution as much as possible, so that the coarse classification of the garbage is completed.
Further referring to fig. 4, it is a flow chart of the garbage classification method of the applicant's industrial intelligence.
A method of classifying refuse using a refuse classification system, the method comprising:
s1: initializing the motion control device of the measuring funnel so that the rotation speed and the horizontal direction motion speed of the measuring funnel in the process of reciprocating along the first horizontal direction are changed along with the height change of the discrete partition plate below the measuring funnel;
preferably, in the initial state, the rotation speed and the horizontal direction movement speed of the measuring hopper during the reciprocating motion along the first horizontal direction change along with the height change of the discrete partition plate below the measuring hopper.
Specifically, the height of the discrete partition is in positive correlation with the rotation speed of the measuring funnel during reciprocating movement in a first horizontal direction, and in inverse correlation with the horizontal direction movement speed.
S2: putting the garbage to be classified into the measuring hopper in batches until the measuring hopper is filled;
the full state of the measuring bucket device in the embodiment means that the input garbage occupies the whole internal space of the measuring bucket device in volume, and the measuring bucket device comprises a space surrounded by the first upper frame (1), the second lower frame (2) and the plurality of side connecting pieces (4);
the detection of the full-filling state can be realized by a sensor component, such as an infrared sensor on the plane of the first upper frame (1);
and when filling garbage, the height difference between the third chassis (3) and the second lower frame (2) is adjusted to be minimum;
s3: the motion control device controls the measuring hopper to reciprocate along a first horizontal direction and simultaneously controls the measuring hopper to rotate along a central vertical axis of the measuring hopper along a rotating direction until the measuring hopper is in an idle state;
meanwhile, the rotating shaft (5) connecting the centers of the first upper frame (1) and the third chassis (3) is gradually lowered in the vertical direction, so that the height difference between the third chassis (3) and the second lower frame (2) is gradually increased.
The measuring hopper is in an idle state, which means that most or all of the garbage in the measuring hopper is scattered on a plurality of conveyor belts of the vertical conveyor belt system below the measuring hopper through the horizontal movement and the rotary movement; at the moment, the filled garbage is roughly classified;
the detection of said idle state can be identified by a weight sensor;
s4: an artificial intelligence classification recognition engine of the vertical conveyor belt system performs classification recognition on the garbage falling onto the plurality of conveyor belts;
specifically, the classification identification includes: each of the plurality of conveyor belts is provided with a weight sensor and a humidity sensor; the weight sensor is used for detecting the weight of the garbage on the corresponding conveyor belt, and the humidity sensor is used for detecting the humidity of the garbage on the corresponding conveyor belt;
s5: based on the classification and identification results, the vertical conveyor belt system sends feedback parameters to the motion control device, so that the motion control device adjusts the rotation speed of the measuring bucket in the reciprocating process along the first horizontal direction and the motion speed of the measuring bucket in the horizontal direction; return is made to step S2.
Specifically, the method comprises the following steps:
if the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution.
And if the humidity values of all the wastes on the plurality of conveyor belts are uniformly distributed according to the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the humidity values of all the wastes on the plurality of conveyor belts are uniformly distributed.
After the measuring hopper is in an idle state, the plurality of conveyor belts of the vertical conveyor belt system start to start, and the garbage on the conveyor belts is conveyed to a far end for classification and identification.
The far end refers to an area far away from the lower part of the measuring hopper, so that the measuring hopper cannot scatter garbage to the far end next time.
Further, the plurality of discrete baffles may be adjustable in height. In this way, the weight of waste on each conveyor can be adjusted appropriately.
As a further preference, the heights of the plurality of discrete partition plates may also be adjusted based on the classification recognition result.
In general, the technical solution of the present invention does not focus on trying to subdivide the garbage into accurate categories in one step (in fact, the detailed rules of garbage classification are different in each place), but focuses on the pre-processing stage of garbage classification, i.e. the coarse classification stage. The coarse classification feeds back the classification control system based on each classification result, so that the classification control system is continuously trained, and the coarse classification result of the original garbage is more and more accurate; based on the coarse classification results, subsequent subdivision may be performed using other techniques according to respective finer criteria. Since the subdivision is based on the coarse classification results, computerized implementations, such as image recognition techniques, may be employed to perform the subdivision.
Practice shows that after the garbage is roughly separated by the technical scheme of the invention, the accuracy of the subsequent automatic computer identification process is greatly improved, the manpower is effectively reduced, and the garbage classification efficiency is improved.
The garbage to be classified can be classified and put by a garbage generator according to own will, and can also be original mixed garbage. Through the treatment of the technical scheme of the invention, at least the garbage to be treated can be distinguished more easily in physical expression form, thereby facilitating the subsequent fine identification by adopting an automatic means and further carrying out automatic classification.
The present invention can be easily implemented by those skilled in the art from the above detailed description. It should be understood, however, that the intention is not to limit the invention to the particular embodiments described. On the basis of the disclosed embodiments, a person skilled in the art can combine different technical features at will, thereby implementing different technical solutions.
Claims (10)
1. An artificial intelligence waste classification system, the classification system comprising at least one measuring bucket reciprocating in a first horizontal direction, a vertical conveyor system located below the first horizontal direction;
the vertical conveyor system comprises a plurality of conveyors; the conveying direction of the conveying belt is vertical to the first horizontal direction, the conveying belts are separated by a plurality of discrete partition plates, and the discrete partition plates are vertical to the horizontal plane of the conveying belt; and the heights of the plurality of discrete partition boards are gradually reduced from the middle to two sides;
the method is characterized in that:
the measuring bucket device rotates along the rotation direction along the central vertical axis of the measuring bucket device simultaneously in the reciprocating motion process along the first horizontal direction;
the vertical conveyor belt system also comprises an artificial intelligence classification and identification engine, and the rotating speed and the horizontal direction moving speed of the measuring hopper in the reciprocating motion process along the first horizontal direction are adjusted based on the identification result of the artificial intelligence classification and identification engine;
the heights of the plurality of discrete partition plates decrease from the middle to the two sides, and specifically, the height of each discrete partition plate is as follows:
the heights of the plurality of discrete baffles conform to a gaussian distribution;
in an initial state, the rotating speed and the horizontal direction moving speed of the measuring hopper device in the process of reciprocating along the first horizontal direction change along with the height change of the discrete partition plate below the measuring hopper device;
the artificial intelligence classification and identification engine is used for identifying and classifying the garbage conveyed by the plurality of conveyor belts, and each conveyor belt is provided with a weight sensor and a humidity sensor; the weight sensor is used for detecting the weight of the garbage on the corresponding conveyor belt, and the humidity sensor is used for detecting the humidity of the garbage on the corresponding conveyor belt; if the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution, keeping the rotating speed and the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction unchanged, and otherwise, adjusting the rotating speed and/or the horizontal direction moving speed of the measuring hopper in the process of reciprocating along the first horizontal direction, so that the weight values of all the garbage on the plurality of conveyor belts accord with the Gaussian distribution.
2. The system of claim 1, wherein if the moisture values of all the waste on the plurality of conveyors are in accordance with uniform distribution, the rotation speed and the horizontal direction movement speed of the hopper during the reciprocating movement in the first horizontal direction are maintained constant, otherwise, the rotation speed and/or the horizontal direction movement speed of the hopper during the reciprocating movement in the first horizontal direction are adjusted so that the moisture values of all the waste on the plurality of conveyors are in accordance with uniform distribution.
3. The system of claim 1, wherein the measuring hopper comprises:
a first upper frame (1); a second lower frame (2); a third chassis (3);
a plurality of side connecting pieces (4) connecting the first upper frame (1) and the second lower frame (2); the rotating shaft (5) is connected with the center positions of the first upper frame (1) and the third chassis (3), and a plurality of cross rod pieces (6) which are arranged on the rotating shaft (5) and are vertical to the rotating shaft (5) and arranged in a staggered mode.
4. The system according to claim 3, wherein the plurality of staggered crosspiece sheets (6) have length values conforming to a Gaussian distribution.
5. A system according to claim 3 or 4, wherein the third chassis (3) has a height difference with the second lower frame (2), and the height difference is adjustable.
6. The system of claim 3 or 4, wherein the area enclosed by the first upper frame (1) is larger than the area enclosed by the second lower frame (2), and the area of the third chassis (3) is larger than the area enclosed by the second lower frame (2).
7. The system of claim 1, wherein the measuring device comprises a motion control device, the motion control device is connected with the vertical conveyor belt system, and the rotation speed and the horizontal direction movement speed of the measuring device in the process of reciprocating along the first horizontal direction are adjusted based on the recognition result of the artificial intelligence classification recognition engine of the vertical conveyor belt system.
8. A method of sorting refuse using the refuse sorting system of any one of claims 1-7, the method comprising:
s1: initializing the motion control device of the measuring funnel so that the rotation speed and the horizontal direction motion speed of the measuring funnel in the process of reciprocating along the first horizontal direction are changed along with the height change of the discrete partition plate below the measuring funnel;
s2: putting the garbage to be classified into the measuring hopper in batches until the measuring hopper is filled;
s3: the motion control device controls the measuring hopper to reciprocate along a first horizontal direction and simultaneously controls the measuring hopper to rotate along a central vertical axis of the measuring hopper along a rotating direction until the measuring hopper is in an idle state;
s4: an artificial intelligence classification recognition engine of the vertical conveyor belt system performs classification recognition on the garbage falling onto the plurality of conveyor belts;
s5: based on the classification and identification results, the vertical conveyor belt system sends feedback parameters to the motion control device, so that the motion control device adjusts the rotation speed of the measuring bucket in the reciprocating process along the first horizontal direction and the motion speed of the measuring bucket in the horizontal direction; return is made to step S2.
9. The method of claim 8, wherein after the hopper is in an idle state, the plurality of conveyors of the vertical conveyor system begin to start up to convey waste on the conveyors to a remote location for the sorting identification.
10. The method of claim 8, wherein the height of the plurality of discrete baffles is adjustable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010110006.XA CN111137602B (en) | 2020-02-23 | 2020-02-23 | Garbage classification method and garbage classification system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010110006.XA CN111137602B (en) | 2020-02-23 | 2020-02-23 | Garbage classification method and garbage classification system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111137602A true CN111137602A (en) | 2020-05-12 |
| CN111137602B CN111137602B (en) | 2020-12-11 |
Family
ID=70527830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010110006.XA Expired - Fee Related CN111137602B (en) | 2020-02-23 | 2020-02-23 | Garbage classification method and garbage classification system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111137602B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931597A (en) * | 2020-07-20 | 2020-11-13 | 苏州富鑫林光电科技有限公司 | Garbage sorting method and system based on artificial intelligence, storage medium and equipment |
| CN113182194A (en) * | 2021-04-28 | 2021-07-30 | 上海翠麟科技有限公司 | Intelligent automatic garbage classification system and classification method based on AI (Artificial Intelligence) recognition technology |
| WO2024152847A1 (en) * | 2023-01-19 | 2024-07-25 | 北京极智嘉科技股份有限公司 | Three-dimensional re-binning management method and system, storage medium and management device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04347404A (en) * | 1991-05-23 | 1992-12-02 | Inshinaa Kogyo Kk | Refuse incinerator according to weight classification of refuse |
| CN108994043A (en) * | 2018-07-01 | 2018-12-14 | 派腾奥普科技服务（北京）有限公司 | A kind of rubbish preliminary classification processing environmental protecting device |
| CN109127679A (en) * | 2018-10-24 | 2019-01-04 | 王钰洁 | A kind of municipal refuse automatic sorting processing system and method for separating |
| CN110586629A (en) * | 2019-10-28 | 2019-12-20 | 安徽清蓝环保工程有限公司 | Garbage rough treatment method |
| CN110803409A (en) * | 2019-12-02 | 2020-02-18 | 苏州毫厘文化传媒科技有限公司 | Working method of indoor intelligent classification dustbin |
-
2020
- 2020-02-23 CN CN202010110006.XA patent/CN111137602B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04347404A (en) * | 1991-05-23 | 1992-12-02 | Inshinaa Kogyo Kk | Refuse incinerator according to weight classification of refuse |
| CN108994043A (en) * | 2018-07-01 | 2018-12-14 | 派腾奥普科技服务（北京）有限公司 | A kind of rubbish preliminary classification processing environmental protecting device |
| CN109127679A (en) * | 2018-10-24 | 2019-01-04 | 王钰洁 | A kind of municipal refuse automatic sorting processing system and method for separating |
| CN110586629A (en) * | 2019-10-28 | 2019-12-20 | 安徽清蓝环保工程有限公司 | Garbage rough treatment method |
| CN110803409A (en) * | 2019-12-02 | 2020-02-18 | 苏州毫厘文化传媒科技有限公司 | Working method of indoor intelligent classification dustbin |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931597A (en) * | 2020-07-20 | 2020-11-13 | 苏州富鑫林光电科技有限公司 | Garbage sorting method and system based on artificial intelligence, storage medium and equipment |
| CN111931597B (en) * | 2020-07-20 | 2024-06-04 | 苏州富鑫林光电科技有限公司 | Garbage sorting method and system based on artificial intelligence, storage medium and equipment |
| CN113182194A (en) * | 2021-04-28 | 2021-07-30 | 上海翠麟科技有限公司 | Intelligent automatic garbage classification system and classification method based on AI (Artificial Intelligence) recognition technology |
| WO2024152847A1 (en) * | 2023-01-19 | 2024-07-25 | 北京极智嘉科技股份有限公司 | Three-dimensional re-binning management method and system, storage medium and management device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111137602B (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111137602B (en) | Garbage classification method and garbage classification system based on artificial intelligence | |
| CN111439500B (en) | Automatic garbage classification method and automatic garbage classification device | |
| CN110210635A (en) | A kind of intelligent classification recovery system that can identify waste | |
| CN110884791A (en) | Vision garbage classification system and classification method based on TensorFlow | |
| CN110371534A (en) | It is a kind of can intelligent classification recycling dustbin and sort management method | |
| CN110053903A (en) | Categorized consumer waste retrieval management system and method | |
| CN110355188B (en) | Smart garbage classification in-situ reduction recycling system based on multiple land utilization | |
| CN110589282A (en) | Intelligent garbage classification method based on machine learning and automatic garbage sorting device | |
| CN111301886B (en) | Garbage classification and recovery system based on RBF neural network and control method | |
| CN111559588A (en) | Intelligent garbage can for classified garbage throwing and classified garbage throwing method | |
| CN111619992A (en) | Intelligent garbage classification system and method based on machine vision | |
| CN109622390A (en) | A kind of intelligent garbage recovery system and its method | |
| CN111056191A (en) | Intelligent garbage collection system capable of classifying and delivering multiple garbage | |
| CN113859803A (en) | Intelligent identification trash can and intelligent identification method thereof | |
| CN113291666A (en) | Novel intelligent classification dustbin and working method thereof | |
| CN215708916U (en) | Intelligent recognition garbage can | |
| CN112849814A (en) | Garbage identification and throwing device and control method thereof | |
| CN113083705A (en) | Garbage classification and delivery system and method | |
| CN115744308B (en) | Intelligent conveying system for classifying and collecting dirt | |
| CN116620744A (en) | Intelligent classification system based on deep learning and implementation method thereof | |
| CN113428525A (en) | Garbage classification system based on computer vision | |
| CN214191135U (en) | Garbage throwing device | |
| CN113148477B (en) | Intelligent garbage can device | |
| CN109675823A (en) | A kind of waste sorting equipment and method for sorting | |
| CN112620165B (en) | Garbage classification method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201124 Address after: L3130, 3 / F, Chuangye building, No. 1009, Tianyuan East Road, Jiangning District, Nanjing City, Jiangsu Province Applicant after: Jiangsu Shien Ecological Technology Co., Ltd Address before: 650031 Kunming University of technology, 727 Jingming South Road, Chenggong District, Kunming City, Yunnan Province Applicant before: Liang Riquan |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201211 Termination date: 20210223 |