Walnut material conveying and automatic sorting device

Abstract

The utility model belongs to the technical field of sorting machinery, and particularly relates to a walnut material conveying and automatic sorting device which comprises a rack and a conveying belt arranged on the rack. An identification control box and a sorting mechanism are sequentially installed on the conveying belt from the position close to the feeding end. A processor applying a convolutional neural network is installed in the recognition control box, the processor is connected with a recognition lens arranged downwards at the bottom of the recognition control box, and a split type annular light source is arranged around the recognition lens; the sorting mechanism comprises a plurality of pneumatic throttle valves installed on the conveying belt at equal intervals, the pneumatic throttle valves are connected with pneumatic electromagnetic valves installed on the recognition control box through air pipes, and photoelectric sensors are further arranged on the pneumatic throttle valves. And a sorting box mounted on the rack is correspondingly arranged opposite to each pneumatic throttle valve. A split type annular light source and a three-dimensional camera obscura with a fixed lens, a fixed light source and a fixed distance between the lens and a material are adopted, so that the consistency of a photographing environment is ensured, and the accuracy and the stability are effectively improved.

Description

Technical Field

[0001] The utility model belongs to the technical field of sorting machinery, and in particular relates to an automatic walnut material conveying and sorting device. Background Art

[0002] Walnut material sorting is an important link in the fields of food processing and agricultural product processing. The main purpose is to quickly and accurately classify the walnuts according to the completeness of the materials after the walnuts are shelled. The sorting process plays a vital role in improving product quality and overall production efficiency. The traditional kernel sorting method mainly relies on manual labor, which is inefficient and easily affected by personal subjectivity, resulting in unstable sorting results.

[0003] The development of computer vision provides a new method for non-destructive testing of agricultural products. It is a technology that uses computers to simulate human visual functions to extract, process and understand information from images of objective objects. Generally, material images are obtained through intelligent scanning equipment, and then the required information is extracted through digital image processing technology, and the materials are automatically classified and screened based on this information. This can not only greatly improve agricultural production efficiency, but also reduce interference from human factors, improve sorting accuracy, and provide favorable support for the development of the walnut industry.

[0004] With the rapid development of deep learning and parallel processing technology of image processors (GPUs), image recognition methods based on convolutional neural networks (CNNs) have shown greater superiority. Deep learning is based on a neural network model. By simulating the learning process of the human brain, it allows computers to automatically extract useful features from large amounts of data and perform tasks such as classification and regression. Deep learning has been widely used in various fields, and has even surpassed humans in some fields. Convolutional neural networks, by simulating the way the human brain's visual cortex processes information, can learn grid-structured data and acquire abilities similar to "intelligent thinking", and have excellent performance in the field of image recognition. However, when it is currently configured for use in sorting devices, there are still problems such as a large impact of the lighting environment on image recognition, low consistency in the sample photography environment, and low recognition accuracy. Utility Model Content

[0005] In order to solve the above technical problems, the utility model designs an automatic walnut material conveying and sorting device, which adopts a split reflective diode ring light as a light source, and a stereo dark box with a fixed distance between the lens, the light source, and the lens and the material, to ensure the consistency of the photographing environment of the collected samples and effectively improve the accuracy and stability.

[0006] In order to achieve the above technical purpose, the utility model is realized by the following technical scheme: a walnut material transmission automatic sorting device, including a frame and a conveyor belt arranged on the frame;

[0007] The conveyor belt is provided with an identification control box and a sorting mechanism in sequence from the position close to the feeding end;

[0008] A processor using a convolutional neural network is installed in the recognition control box, and the processor is connected to a recognition lens arranged downward at the bottom of the recognition control box, and a split ring light source is arranged around the recognition lens;

[0009] The sorting mechanism includes a plurality of pneumatic throttle valves equidistantly installed on the conveyor belt, the pneumatic throttle valves are connected to the pneumatic solenoid valves installed on the identification control box through air pipes, and the pneumatic throttle valves are also provided with photoelectric sensors;

[0010] Opposite to each pneumatic throttle valve is a sorting box installed on the frame.

[0011] Preferably, a speed regulating motor is provided at the lower part of the feeding end of the conveyor belt, the speed regulating motor is fixed on the frame through a motor bracket, the output end of the speed regulating motor drives the conveyor belt shaft to rotate through a synchronous belt, and a material carrying box is also provided at the unloading end of the conveyor belt.

[0012] Preferably, a mounting frame at the bottom of the identification control box is also provided with fasteners connected to the frame.

[0013] The beneficial effects of the utility model are:

[0014] (1) The identification control box of the device uses a split ring light as the light source, and a stereo dark box with a fixed distance between the lens, light source, and lens and material to ensure the consistency of the photographic environment of the collected samples, effectively improving the accuracy and stability of sorting;

[0015] (2) The conveyor belt delivers the crushed walnut material into the identification control box. When the lens under the identification control box recognizes the image information of the material, the processor analyzes and classifies the image through a deep learning target detection algorithm. According to the preset classification standard, when the corresponding photoelectric sensor senses the material on the conveyor belt, the corresponding pneumatic solenoid valve will open, thereby spraying the material into different sorting boxes. Some walnut materials that have not been successfully identified will be transported to the material carrying box at the end of the conveyor belt. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present utility model, the following briefly introduces the drawings required for describing the embodiments.

[0017] Figure 1 It is a schematic diagram of the overall axonometric structure of the utility model;

[0018] Figure 2 It is a schematic diagram of the local structure of the identification control box of the utility model;

[0019] Figure 3 It is a schematic diagram of the structure of the identification control box of the utility model when viewed from above.

[0020] In the accompanying drawings, the structural names represented by the reference numerals are:

[0021] 1- identification control box, 101- processor, 102- lens, 103- ring light source, 2- conveyor belt, 3- speed regulating motor, 4- frame, 5- pneumatic solenoid valve, 6- photoelectric sensor, 7- pneumatic throttle valve, 8- air pipe, 9- material carrying box, 10- synchronous belt, 11- motor bracket, 12- fastener. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. In addition, the technical features involved in the various embodiments described below can be combined with each other as long as they do not conflict with each other.

[0023] Example

[0024] See also Figures 1 to 3 As shown, first, the main structure of the device includes a frame 4 and a conveyor belt 2 arranged on the frame 4. The frame 4 serves as a supporting structure for the entire device, ensuring that the conveyor belt 2 and the components subsequently installed can work stably. The conveyor belt 2 is responsible for conveying the walnut material from the feeding end of the device to the unloading end.

[0025] On the conveyor belt 2, an identification control box 1 and a sorting mechanism are installed in sequence from the feed end. A processor 101 using a convolutional neural network is installed inside the identification control box 1, and the processor 101 is connected to an identification lens 102 set downward at the bottom of the identification control box 1. The identification lens 102 is responsible for capturing the image information of the walnut material and passing it to the processor 101 for analysis and processing. In order to ensure the clarity and accuracy of image acquisition, a split ring light source 103 is arranged around the identification lens 102 to provide uniform and sufficient lighting conditions.

[0026] The sorting mechanism includes a plurality of pneumatic throttle valves 7 equidistantly installed on the conveyor belt 2, and these pneumatic throttle valves 7 are connected to the pneumatic solenoid valves 5 installed on the identification control box 1 through air pipes 8. When the processor 101 recognizes the specific features of the walnut material according to the image information, it controls the corresponding pneumatic throttle valve 7 to operate through the pneumatic solenoid valve 5. The pneumatic throttle valve 7 is also provided with a photoelectric sensor 6 for real-time monitoring of the position of the walnut material to ensure the accuracy of sorting.

[0027] In addition, each pneumatic throttle valve 7 is provided with a sorting box installed on the frame 4. When the pneumatic throttle valve 7 is actuated, the walnut material will be pushed into the corresponding sorting box to realize automatic sorting of the material.

[0028] In order to further optimize the performance of the device, a speed regulating motor 3 is also provided at the lower part of the feeding end of the conveyor belt 2. The speed regulating motor 3 is fixed to the frame 4 through the motor bracket 11, and its output end drives the conveyor belt 2 shaft to rotate through the synchronous belt 10, thereby adjusting the speed of the conveyor belt 2. This design can adjust the conveying speed of the walnut material according to actual needs and improve the sorting efficiency.

[0029] At the unloading end of the conveyor belt 2, a material carrying box 9 is also provided for collecting unsorted walnut materials.

[0030] In order to ensure the stable installation of the identification control box 1, a fastener 12 is also provided on the mounting frame at the bottom thereof to connect with the frame 4. Through the fastener 12, the identification control box 1 can be firmly fixed on the frame 4 to prevent displacement or shaking during operation.

[0031] In summary, the present invention realizes automatic identification and sorting of walnut materials by combining convolutional neural network and pneumatic sorting technology. The whole device has compact structure, simple operation, high sorting accuracy, and is suitable for the material sorting link in the walnut material processing production line.

[0032] The preferred embodiments of the utility model disclosed above are only used to help explain the utility model. The preferred embodiments do not describe all details in detail, nor do they limit the utility model to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification.

Claims

1. A walnut material conveying and automatic sorting device, comprising a frame (4) and a conveyor belt (2) arranged on the frame (4); characterized in that: The conveyor belt (2) is provided with an identification control box (1) and a sorting mechanism in sequence from the position close to the feeding end; The recognition control box (1) is equipped with a processor (101) using a convolutional neural network, the processor (101) is connected to a recognition lens (102) arranged downward at the bottom of the recognition control box (1), and a split ring light source (103) is arranged around the recognition lens (102); The sorting mechanism comprises a plurality of pneumatic throttle valves (7) equidistantly installed on the conveyor belt (2), the pneumatic throttle valves (7) being connected to a pneumatic solenoid valve (5) installed on the identification control box (1) via an air pipe (8), and a photoelectric sensor (6) is also provided on the pneumatic throttle valve (7); Opposite each of the pneumatic throttle valves (7) is a corresponding sorting box installed on the frame (4).

2. The walnut material conveying and automatic sorting device according to claim 1 is characterized in that: A speed regulating motor (3) is arranged at the lower part of the feeding end of the conveyor belt (2); the speed regulating motor (3) is fixed to the frame (4) via a motor bracket (11); the output end of the speed regulating motor (3) drives the conveyor belt (2) to rotate via a synchronous belt (10); and a material carrying box (9) is also arranged at the unloading end of the conveyor belt (2).

3. The walnut material conveying and automatic sorting device according to claim 2 is characterized in that: A fastener (12) is also provided on the mounting frame at the bottom of the identification control box (1) and is connected to the frame (4).

Images