Automatic waste plastic sorting device and method with intelligent recognition function
The automated waste plastic sorting device with intelligent identification utilizes multimodal sensing and feature fusion technology to achieve rapid and accurate classification of waste plastics, improving recycling efficiency and solving the problem of classification difficulties caused by the wide variety of waste plastics.
Patent Information
- Application Number
- CN202511066527.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-31
- Publication Date
- 2025-11-14
AI Technical Summary
Due to the complexity and variety of waste plastic sources, existing sorting methods are unable to quickly and accurately classify and process waste plastics, resulting in low recycling efficiency.
An automated waste plastic sorting device employing intelligent identification includes a transmission module, a multimodal perception layer, a feature fusion module, a control decision layer, a communication module, a sorting execution module, and a human-machine interaction module. The multimodal perception layer acquires various feature information of waste plastics, the feature fusion module performs information fusion processing, the control decision layer analyzes and judges the type according to preset rules and algorithms, and the sorting execution module achieves fast and accurate classification.
It enables rapid and accurate classification of waste plastics, improves recycling efficiency, and solves the problem of difficult classification and processing in existing technologies.
Smart Images
Figure CN120940249A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of plastic processing technology, and in particular to an automated waste plastic sorting device and method with intelligent identification. Background Technology
[0002] With the acceleration of global industrialization and the transformation of consumption patterns, plastic products are widely used in various fields such as packaging, construction, electronics, and automobiles due to their lightweight, durability, and low cost. However, this has led to a continuous and rapid increase in the amount of waste plastics generated. The total amount of waste plastics generated globally each year is showing an increasing trend. If these waste plastics are not effectively recycled and treated, they will not only cause resource waste, but also cause serious pollution to the soil, water bodies, and atmospheric environment due to long-term accumulation or incineration.
[0003] When recycling waste plastics, they need to be sorted and processed. However, due to the complex sources and variety of waste plastics, existing sorting methods are difficult to classify and process waste plastics quickly and accurately, resulting in low recycling efficiency. Summary of the Invention
[0004] The purpose of this invention is to provide an intelligent identification automated waste plastic sorting device and method, which aims to solve the technical problem that existing sorting methods are difficult to quickly and accurately classify and process waste plastics due to the complex sources and diverse types of waste plastics, resulting in low recycling efficiency.
[0005] To achieve the above objectives, the present invention employs an intelligent identification automated waste plastic sorting device, comprising a transmission module, a multimodal perception layer, a feature fusion module, a control decision layer, a communication module, a sorting execution module, and a human-machine interaction module. The multimodal perception layer is connected to the transmission module, the control decision layer is connected to the multimodal perception layer through the feature fusion module, the communication module is connected to the control decision layer, the sorting execution module is connected to the communication module, and the human-machine interaction module is connected to the control decision layer.
[0006] The sorting execution module includes two waste boxes, a mounting assembly, a bracket, a dual-axis motor, two sets of abutment assemblies, and two sets of pusher assemblies. The mounting assembly is used to install the bracket at a designated position. The bracket has two sliding grooves. The dual-axis motor is mounted on the bracket. The two sets of pusher assemblies are slidably connected to the corresponding sliding grooves. The two output ends of the dual-axis motor are connected to the corresponding pusher assemblies through the corresponding abutment assemblies. The two waste boxes are arranged on both sides of the transmission module.
[0007] The feeding assembly includes a slider, an L-plate, a cylinder, and a push plate. The slider is slidably connected to the corresponding groove, the L-plate is fixedly connected to the slider, the cylinder is mounted on the L-plate, and the output end of the cylinder is fixedly connected to the push plate.
[0008] The supporting assembly includes a disc, a supporting rod, and a force-receiving block. The force-receiving block is fixedly connected to the L-plate and has a force-receiving groove. The disc is fixedly connected to the corresponding output end of the dual-axis motor. One end of the supporting rod is fixedly connected to the disc, and the other end of the supporting rod is inserted into the force-receiving groove.
[0009] The mounting assembly includes two U-shaped parts and two fasteners. Both U-shaped parts are fixedly connected to the bracket, and the two fasteners are respectively set on the corresponding U-shaped parts.
[0010] The intelligent identification automated waste plastic sorting device further includes a spatiotemporal alignment module and a weight adjustment module, which are respectively connected to the multimodal perception layer and the feature fusion module.
[0011] The intelligent identification automated waste plastic sorting device further includes a decision engine optimization module and an environmental monitoring module, which are respectively connected to the control decision layer and the sorting execution module.
[0012] The intelligent identification automated waste plastic sorting device further includes a full material detection module and a multi-language support module, which are respectively connected to the sorting execution module and the human-machine interaction module.
[0013] This invention also provides an intelligent identification-based automated waste plastic sorting method, applicable to the intelligent identification-based automated waste plastic sorting device described above.
[0014] Includes the following steps:
[0015] The waste plastics to be sorted are transported to the detection area of the multimodal sensing layer through the transmission module;
[0016] The multimodal sensing layer is used to acquire various feature information of waste plastics and transmits it to the feature fusion module;
[0017] The feature fusion module fuses multiple feature information to obtain comprehensive feature information, which is then transmitted to the control decision layer. The control decision layer analyzes and judges the comprehensive feature information according to preset sorting rules and algorithms to determine the type of waste plastic and generate corresponding sorting control instructions.
[0018] The communication module transmits the sorting control command to the sorting execution module. The dual-axis motor starts according to the sorting control command and drives the slider of the corresponding pusher component to slide in the groove of the bracket through the corresponding abutment component, so that the corresponding pusher component moves to the appropriate position.
[0019] The cylinder is activated according to the sorting control command, pushing the pusher plate to push the corresponding type of waste plastic on the transmission module into the corresponding waste box.
[0020] This invention discloses an automated waste plastic sorting device and method with intelligent identification. In practical use, the waste plastic to be sorted is transported to the detection area of the multimodal sensing layer via the transmission module; the multimodal sensing layer acquires various feature information of the waste plastic and transmits it to the feature fusion module; the feature fusion module fuses the various feature information to obtain comprehensive feature information, which is then transmitted to the control decision layer; the control decision layer analyzes and judges the comprehensive feature information according to preset sorting rules and algorithms to determine the type of waste plastic and generates corresponding sorting control commands; the communication module connects the sorting... The control command is transmitted to the sorting execution module, which then determines which pushing component should push the waste plastic. The dual-axis motor is then started, and one of its outputs drives the corresponding pushing component downwards via the corresponding abutment component. This pushing component then pushes the waste plastic out. Meanwhile, the other pushing component moves upwards without obstructing the pushing of the waste plastic. This method solves the technical problem in the prior art where the complex sources and diverse types of waste plastic make it difficult to quickly and accurately classify and process them, resulting in low recycling efficiency. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a schematic diagram of the intelligent identification automated waste plastic sorting device according to the first embodiment of the present invention.
[0023] Figure 2 This is a schematic diagram of the intelligent identification automated waste plastic sorting device of the present invention.
[0024] Figure 3 This is the invention Figure 2 Enlarged view of the local structure at point A.
[0025] Figure 4 This is a schematic diagram of the intelligent identification automated waste plastic sorting device according to the second embodiment of the present invention.
[0026] Figure 5 This is a schematic diagram of the intelligent identification automated waste plastic sorting device according to the third embodiment of the present invention.
[0027] 101-Transmission Module, 102-Multimodal Perception Layer, 103-Feature Fusion Module, 104-Control Decision Layer, 105-Communication Module, 106-Sorting Execution Module, 107-Human-Machine Interaction Module, 108-Waste Frame, 109-Support, 110-Dual-Axis Motor, 111-Slider, 112-L-Plate, 113-Cylinder, 114-Push Plate, 115-Disc, 116-Holding Rod, 117-Force Block, 118-U-Shaped Part, 119-Fastener, 120-Groove, 201-Spatiotemporal Alignment Module, 202-Weight Adjustment Module, 203-Decision Engine Optimization Module, 204-Environmental Monitoring Module, 205-Full Material Detection Module, 206-Multilingual Support Module, 301-Blockchain Storage Module, 302-Data Mining Module, 303-Strategy Generation Module. Detailed Implementation
[0028] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, but should not be construed as limiting the present invention.
[0029] For the first embodiment, please refer to... Figures 1 to 3 , Figure 1 This is a schematic diagram of the intelligent identification automated waste plastic sorting device according to the first embodiment of the present invention. Figure 2 This is a schematic diagram of the intelligent identification automated waste plastic sorting device of the present invention. Figure 3 This is the invention Figure 2 Enlarged view of the local structure at point A.
[0030] This invention provides an intelligent identification automated waste plastic sorting device, including a transmission module 101, a multimodal perception layer 102, a feature fusion module 103, a control decision layer 104, a communication module 105, a sorting execution module 106, and a human-machine interaction module 107. The sorting execution module 106 includes two waste boxes 108, an installation assembly, a bracket 109, a dual-axis motor 110, two sets of abutment assemblies, and two sets of pushing assemblies. The pushing assembly includes a slider 111, an L-plate 112, a cylinder 113, and a push plate 114. The abutment assembly includes a disc 115, an abutment rod 116, and a force-bearing block 117. The installation assembly includes two U-shaped parts 118 and two fasteners 119. The aforementioned technical solution solves the technical problem in the prior art that due to the complex sources and diverse types of waste plastics, existing sorting methods are difficult to quickly and accurately classify and process waste plastics, resulting in low recycling efficiency.
[0031] In this specific embodiment, the multimodal perception layer 102 is connected to the transmission module 101, the control decision layer 104 is connected to the multimodal perception layer 102 through the feature fusion module 103, the communication module 105 is connected to the control decision layer 104, the sorting execution module 106 is connected to the communication module 105, the human-computer interaction module 107 is connected to the control decision layer 104, and the installation component is used to install the bracket 109 in a designated position. The bracket 109 has two... A chute 120 is provided, and the dual-axis motor 110 is mounted on the bracket 109. Two sets of pushing components are slidably connected to the corresponding chute 120. The two output ends of the dual-axis motor 110 are connected to the corresponding pushing components through the corresponding abutment components. Two waste boxes 108 are arranged on both sides of the transmission module 101. In actual use, the waste plastic to be sorted is transported to the detection area of the multimodal sensing layer 102 through the transmission module 101; the multimodal sensing layer 102 is used to obtain waste... Multiple characteristic information of plastics is collected and transmitted to the feature fusion module 103. The feature fusion module 103 fuses the multiple characteristic information to obtain comprehensive characteristic information, which is then transmitted to the control decision layer 104. The control decision layer 104 analyzes and judges the comprehensive characteristic information according to preset sorting rules and algorithms to determine the type of waste plastic and generate corresponding sorting control instructions. The communication module 105 transmits the sorting control instructions to the sorting execution module 106. At this time, it can be determined which of the pushing components should push the waste plastic. Therefore, the dual-axis motor 110 is started. One of the output terminals of the dual-axis motor 110 drives the pushing component that should push the plastic to move down through the corresponding abutment component. Then, this pushing component is started to push the waste plastic. At this time, the other pushing component moves up and does not block the pushing of the waste plastic. In this way, the technical problem of low recycling efficiency caused by the complexity and variety of waste plastic sources in the prior art makes it difficult to quickly and accurately classify and process waste plastics.
[0032] The slider 111 is slidably connected to the corresponding groove 120, the L-plate 112 is fixedly connected to the slider 111, the cylinder 113 is mounted on the L-plate 112, the output end of the cylinder 113 is fixedly connected to the push plate 114, the output end of the dual-axis motor 110 drives the L-plate 112 to move through the corresponding abutment component, the L-plate 112 drives the slider 111 to slide in the corresponding groove 120, and the L-plate 112 drives the cylinder 113 to move, and the cylinder 113 can push out the waste plastic through the push plate 114.
[0033] Secondly, the force-bearing block 117 is fixedly connected to the L-plate 112. The force-bearing block 117 has a force-bearing groove. The disc 115 is fixedly connected to the corresponding output end of the dual-axis motor 110. One end of the abutment rod 116 is fixedly connected to the disc 115, and the other end of the abutment rod 116 is inserted into the force-bearing groove. The output end of the dual-axis motor 110 drives the disc 115 to rotate. The disc 115 drives the corresponding abutment rod 116 to slide in the corresponding force-bearing groove, thereby driving the force-bearing block 117 to move, and thus driving the corresponding L-plate 112 to move.
[0034] Furthermore, both U-shaped parts 118 are fixedly connected to the bracket 109, and two fasteners 119 are respectively set on the corresponding U-shaped parts 118. The two U-shaped parts 118 can be fixed in the designated position by the two fasteners 119, thereby installing the bracket 109.
[0035] In this embodiment, an automated waste plastic sorting device with intelligent identification is used. In practical application, the waste plastic to be sorted is transported to the detection area of the multimodal sensing layer 102 via the transmission module 101. The multimodal sensing layer 102 acquires various feature information of the waste plastic and transmits it to the feature fusion module 103. The feature fusion module 103 fuses the various feature information to obtain comprehensive feature information, which is then transmitted to the control decision layer 104. The control decision layer 104 analyzes and judges the comprehensive feature information according to preset sorting rules and algorithms to determine the type of waste plastic and generate corresponding sorting control commands. The communication module... Block 105 transmits the sorting control command to the sorting execution module 106. At this time, it can be determined which of the pushing components should push the waste plastic. Therefore, the dual-axis motor 110 is started. One of the output terminals of the dual-axis motor 110 drives the pushing component that should push the waste plastic to move down through the corresponding abutment component. Then, this pushing component is started to push the waste plastic out. At this time, the other pushing component moves up and does not block the pushing out of the waste plastic. In this way, the technical problem of low recycling efficiency caused by the complexity and variety of waste plastic sources in the prior art makes it difficult to quickly and accurately classify and process waste plastic.
[0036] Second embodiment, please refer to Figure 4 , Figure 4 This is a schematic diagram of the intelligent identification automated waste plastic sorting device according to the second embodiment of the present invention.
[0037] In the first embodiment, the present invention provides an intelligent identification automated waste plastic sorting device, which also includes a spatiotemporal alignment module 201, a weight adjustment module 202, a decision engine optimization module 203, an environmental monitoring module 204, a full material detection module 205, and a multilingual support module 206.
[0038] In this specific embodiment, the spatiotemporal alignment module 201 and the weight adjustment module 202 are respectively connected to the multimodal perception layer 102 and the feature fusion module 103. The spatiotemporal alignment module 201 is used to perform precise time synchronization and spatial registration of the feature information of different modalities collected by the multimodal perception layer 102, ensuring that various feature information can accurately correspond when the feature fusion module 103 performs fusion processing, avoiding information misalignment caused by spatiotemporal differences. The weight adjustment module 202 can dynamically adjust the weight coefficients of various feature information acquired by the multimodal perception layer 102 in the feature fusion process according to the actual sorting situation and a large amount of experimental data.
[0039] The decision engine optimization module 203 and the environmental monitoring module 204 are connected to the control decision layer 104 and the sorting execution module 106, respectively. The decision engine optimization module 203 can continuously collect actual data and feedback information during the sorting process, and optimize and improve the decision engine of the control decision layer 104 through machine learning, data analysis and other technologies. The environmental monitoring module 204 can monitor the pollutant emissions generated during the operation of the sorting device in real time, such as dust concentration and the content of harmful substances in the exhaust gas, and transmit the monitoring data to the control decision layer 104.
[0040] Secondly, the full material detection module 205 and the multi-language support module 206 are respectively connected to the sorting execution module 106 and the human-machine interaction module 107. The full material detection module 205 can monitor the accumulation of waste plastic in the waste bin 108 in real time. When the waste bin 108 is about to be full or has been full, it promptly sends a signal to the sorting execution module 106 and the control decision layer 104. The multi-language support module 206 can provide operators with multiple language options, enabling the human-machine interaction module 107 to display sorting status information, operation prompts, alarm information, etc., in a language familiar to the operator, while also supporting operators to input operation commands in the corresponding language.
[0041] Using an automated waste plastic sorting device with intelligent identification according to this embodiment, the spatiotemporal alignment module 201 is used to perform precise time synchronization and spatial registration of the feature information of different modes collected by the multimodal perception layer 102, so as to ensure that various feature information can be accurately matched when the feature fusion module 103 performs fusion processing, and avoid information misalignment caused by spatiotemporal differences; the weight adjustment module 202 can dynamically adjust the weight coefficients of various feature information acquired by the multimodal perception layer 102 in the feature fusion process according to the actual sorting situation and a large amount of experimental data.
[0042] Third embodiment, please refer to Figure 5 , Figure 5 This is a schematic diagram of the intelligent identification automated waste plastic sorting device according to the third embodiment of the present invention.
[0043] In terms of the technology of the first embodiment, the present invention provides an automated waste plastic sorting device with intelligent identification, which also includes a blockchain storage module 301, a data mining module 302 and a strategy generation module 303.
[0044] In this specific embodiment, the blockchain storage module 301 is connected to the control decision layer 104. The blockchain storage module 301 is directly connected to the control decision layer 104 to store key data in the waste plastic sorting process (such as plastic type identification results, sorting time, equipment status, operator information, etc.) on the blockchain, forming an immutable distributed ledger.
[0045] The data mining module 302 is connected to the blockchain storage module 301, and the strategy generation module 303 is connected to the data mining module 302. The data mining module 302 extracts massive amounts of sorting data from the blockchain storage module 301 and uses machine learning (such as cluster analysis and association rule mining) or deep learning (such as time series prediction models) techniques to mine hidden patterns in the data. The strategy generation module 303, based on the output of the data mining module 302 and combined with real-time sorting data (such as the current waste plastic flow composition ratio), dynamically generates optimization strategies through a rule engine or reinforcement learning algorithm and feeds them back to the control decision layer 104 to adjust the sorting parameters.
[0046] Using an automated waste plastic sorting device with intelligent identification in this embodiment, the blockchain storage module 301 is connected to the control decision layer 104. The blockchain storage module 301 is directly connected to the control decision layer 104 to store key data in the waste plastic sorting process (such as plastic type identification results, sorting time, equipment status, operator information, etc.) on the blockchain to form an immutable distributed ledger.
[0047] The data mining module 302 is connected to the blockchain storage module 301, and the strategy generation module 303 is connected to the data mining module 302. The data mining module 302 extracts massive amounts of sorting data from the blockchain storage module 301 and uses machine learning (such as cluster analysis and association rule mining) or deep learning (such as time series prediction models) techniques to mine hidden patterns in the data. Based on the output results of the data mining module 302 and combined with real-time sorting data (such as the current waste plastic flow composition ratio), the strategy generation module 303 dynamically generates optimization strategies through a rule engine or reinforcement learning algorithm and feeds them back to the control decision layer 104 to adjust the sorting parameters.
[0048] This invention also provides an intelligent identification-based automated waste plastic sorting method, applicable to the intelligent identification-based automated waste plastic sorting device described above.
[0049] Includes the following steps:
[0050] The waste plastic to be sorted is transported to the detection area of the multimodal sensing layer 102 through the transmission module 101;
[0051] The multimodal sensing layer 102 is used to acquire various feature information of waste plastics and transmits it to the feature fusion module 103;
[0052] The feature fusion module 103 fuses multiple feature information to obtain comprehensive feature information, which is then transmitted to the control decision layer 104. The control decision layer 104 analyzes and judges the comprehensive feature information according to preset sorting rules and algorithms to determine the type of waste plastic and generate corresponding sorting control instructions.
[0053] The communication module 105 transmits the sorting control command to the sorting execution module 106. The dual-axis motor 110 starts according to the sorting control command and drives the slider 111 of the corresponding pusher component to slide in the groove 120 of the bracket 109 through the corresponding abutment component, so that the corresponding pusher component moves to a suitable position.
[0054] The cylinder 113 is activated according to the sorting control command, pushing the pusher plate 114 to push the waste plastic of the corresponding type on the transmission module 101 into the corresponding waste box 108.
[0055] The above description discloses only one preferred embodiment of the present invention, and should not be construed as limiting the scope of the present invention. Those skilled in the art will understand that all or part of the processes of the above embodiments can be implemented, and equivalent changes made in accordance with the claims of the present invention are still within the scope of the invention.
Claims
1. An automated waste plastic sorting device with intelligent identification, characterized in that, It includes a transmission module, a multimodal perception layer, a feature fusion module, a control decision layer, a communication module, a sorting execution module, and a human-computer interaction module. The multimodal perception layer is connected to the transmission module, the control decision layer is connected to the multimodal perception layer through the feature fusion module, the communication module is connected to the control decision layer, the sorting execution module is connected to the communication module, and the human-computer interaction module is connected to the control decision layer. The sorting execution module includes two waste boxes, a mounting assembly, a bracket, a dual-axis motor, two sets of abutment assemblies, and two sets of pusher assemblies. The mounting assembly is used to install the bracket at a designated position. The bracket has two sliding grooves. The dual-axis motor is mounted on the bracket. The two sets of pusher assemblies are slidably connected to the corresponding sliding grooves. The two output ends of the dual-axis motor are connected to the corresponding pusher assemblies through the corresponding abutment assemblies. The two waste boxes are arranged on both sides of the transmission module.
2. The automated waste plastic sorting device with intelligent identification as described in claim 1, characterized in that, The feeding assembly includes a slider, an L-plate, a cylinder, and a push plate. The slider is slidably connected to the corresponding groove, the L-plate is fixedly connected to the slider, the cylinder is mounted on the L-plate, and the output end of the cylinder is fixedly connected to the push plate.
3. The automated waste plastic sorting device with intelligent identification as described in claim 2, characterized in that, The supporting assembly includes a disc, a supporting rod, and a force-receiving block. The force-receiving block is fixedly connected to the L-plate and has a force-receiving groove. The disc is fixedly connected to the corresponding output end of the dual-axis motor. One end of the supporting rod is fixedly connected to the disc, and the other end of the supporting rod is inserted into the force-receiving groove.
4. The automated waste plastic sorting device with intelligent identification as described in claim 3, characterized in that, The mounting assembly includes two U-shaped parts and two fasteners. Both U-shaped parts are fixedly connected to the bracket, and the two fasteners are respectively set on the corresponding U-shaped parts.
5. The automated waste plastic sorting device with intelligent identification as described in claim 4, characterized in that, The intelligent identification automated waste plastic sorting device also includes a spatiotemporal alignment module and a weight adjustment module, which are respectively connected to the multimodal perception layer and the feature fusion module.
6. The automated waste plastic sorting device with intelligent identification as described in claim 5, characterized in that, The intelligent identification automated waste plastic sorting device also includes a decision engine optimization module and an environmental monitoring module, which are respectively connected to the control decision layer and the sorting execution module.
7. The automated waste plastic sorting device with intelligent identification as described in claim 6, characterized in that, The intelligent identification automated waste plastic sorting device also includes a full material detection module and a multi-language support module, which are respectively connected to the sorting execution module and the human-machine interaction module.
8. A method for intelligent identification and automated waste plastic sorting, applied to the intelligent identification and automated waste plastic sorting device as described in claim 7, characterized in that, Includes the following steps: The waste plastics to be sorted are transported to the detection area of the multimodal sensing layer through the transmission module; The multimodal sensing layer is used to acquire various feature information of waste plastics and transmits it to the feature fusion module; The feature fusion module fuses multiple feature information to obtain comprehensive feature information, which is then transmitted to the control decision layer. The control decision layer analyzes and judges the comprehensive feature information according to preset sorting rules and algorithms to determine the type of waste plastic and generate corresponding sorting control instructions. The communication module transmits the sorting control command to the sorting execution module. The dual-axis motor starts according to the sorting control command and drives the slider of the corresponding pusher component to slide in the groove of the bracket through the corresponding abutment component, so that the corresponding pusher component moves to the appropriate position. The cylinder is activated according to the sorting control command, pushing the pusher plate to push the corresponding type of waste plastic on the transmission module into the corresponding waste box.