Automatic grading device for fresh cut flowers

Abstract

The utility model belongs to the field of fresh cut flower grading, and provides a fresh cut flower automatic grading device which comprises a conveying mechanism, the conveying mechanism is used for conveying fresh flowers, a visual detection mechanism is arranged in the moving direction of the conveying mechanism, and the visual detection mechanism is used for capturing and shooting the fresh flowers passing through the conveying mechanism and transmitting the fresh flowers to an external computer system; according to the invention, based on the convolutional neural network technology, the computer camera has a self-learning ability, the data of each camera is maximized to be visual and digitized by imitating artificial experience, and the grading precision and the grading speed are improved.

Description

Technical Field

[0001] The invention belongs to the field of fresh cut flower grading, in particular to an automatic fresh cut flower grading device. Background Art

[0002] Grading fresh cut flowers helps determine the market price of roses. Roses can be priced according to their grade, ensuring that flowers of different qualities have different prices in the market, thus meeting the needs of different consumers. Grading also helps to distinguish roses of different qualities during distribution and sales, so that flower shops, flower markets and flower supply chains can choose suitable roses for sale and distribution according to the grading of roses, ensuring that customers get the quality they expect and evaluate the quality of roses.

[0003] Most of the existing cut rose grading machines use visual recognition technology, and the flowers are suspended on a vertical clamp and dropped by compressed air through a slide rail. There is no grading of flower head size, stem thickness, or flower head or leaf defect.

[0004] The above-mentioned cut rose grader has the following disadvantages:

[0005] The grading accuracy is low (below 85%), the grading speed is low (<1000 pieces / person / hour), the yield is low (flower loss>15%), the equipment is large (length>20 meters, height>2.5 meters), and the selling price is high (>1 million yuan / unit).

[0006] The main factors causing the above shortcomings are:

[0007] (1) The visual algorithm software lacks intelligent self-learning function, resulting in low classification accuracy;

[0008] (2) Incomplete understanding of the cut rose grading standards resulted in missing grading parameters;

[0009] (3) The equipment transmission process and structural design technology are backward, resulting in low grading efficiency, large equipment size and low yield rate. Summary of the invention

[0010] In order to solve the above technical problems, the present invention provides an automatic fresh cut flower grading device to solve the problems in the prior art such as low grading accuracy, incomplete understanding of the cut rose grading standards, low grading efficiency, large equipment volume, and low yield rate.

[0011] An automatic grading device for fresh cut flowers comprises a conveying mechanism, the conveying mechanism is used to convey fresh flowers, a visual detection mechanism is arranged along the moving direction of the conveying mechanism, the visual detection mechanism is used to capture and photograph the fresh flowers passing on the conveying mechanism, and transmit them to an external computer system;

[0012] The flipping mechanism is arranged downstream of the conveying mechanism, and receives the processing result of the photos by the external computer system, and automatically puts the flowers into the corresponding flower storage bins.

[0013] Preferably, the conveying mechanism is a conveyor belt.

[0014] Preferably, a plurality of flower pillows are fixedly mounted on the conveyor belt.

[0015] Preferably, the flower pillows are evenly distributed on the conveyor belt.

[0016] Preferably, the visual detection mechanism includes a plurality of cameras.

[0017] Preferably, the flipping mechanism includes a chain and a plurality of evenly arranged flower storage bins, the chain is provided with a plurality of evenly arranged flower slots, each of the flower slots is provided with an electromagnetic mechanism, the electromagnetic mechanism is connected to two rotating shafts, swing arms are fixedly installed on the circumferential sides of the two rotating shafts, a rack is installed on the circumferential sides of the two swing arms, and the rack meshes with a local gear fixedly installed on the flower slot.

[0018] Preferably, a warning light is installed in the flower storage bin.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] 1. The present invention adopts a horizontal placement of flowers and a free-falling flower trough storage structure to avoid flower damage caused by the impact of clamps and pneumatic components, thereby improving the yield rate; reducing the size of the equipment, reducing the manufacturing cost and selling price; reducing the process action time and improving the grading efficiency.

[0021] 2. The present invention improves the grading standards of cut roses by perfecting the grading parameters of cut roses.

[0022] 3. The present invention is based on convolutional neural network technology, which enables the computer camera to have self-learning ability, and imitates manual experience to maximize the "visualization" and "digitalization" of the data of each flower, thereby improving the grading accuracy and grading speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0024] Figure 2 For the present invention Figure 1 Schematic diagram of the conveyor belt structure;

[0025] Figure 3 For the present invention Figure 1 Schematic diagram of the structure of the conveyor belt and the turning mechanism;

[0026] Figure 4For the present invention Figure 1 Schematic diagram of the camera structure;

[0027] Figure 5 For the present invention Figure 1 Schematic diagram of the flip mechanism structure;

[0028] Figure 6 For the present invention Figure 5 Schematic diagram of the specific structure of the middle flip mechanism;

[0029] Figure 7 The external computer system of the present invention shows the flower classification structure. Figure 1 ;

[0030] Figure 8 The external computer system of the present invention shows the flower classification structure. Figure 2 .

[0031] In the figure:

[0032] 1. Conveyor belt; 2. Visual inspection mechanism; 3. Flipping mechanism; 4. Flower pillow; 5. Camera; 6. Flower trough; 7. Rack; 8. Gear; 9. Flower storage bin; 10. Rotating shaft; 11. Swing arm. DETAILED DESCRIPTION

[0033] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0034] Embodiment 1: As shown in the attached Figure 1 To Attachment Figure 8 As shown: The present invention provides an automatic grading device for fresh cut flowers, comprising a conveying mechanism, the conveying mechanism is used to convey flowers, a visual detection mechanism 2 is arranged along the moving direction of the conveying mechanism, the visual detection mechanism 2 is used to capture and photograph the flowers passing through the conveying mechanism, and transmit them to an external computer system;

[0035] The flowers to be graded are divided into 6 evaluation indicators, and the grading standards are:

[0036] (1) Flower stem length, ≤5 levels;

[0037] (2) flower stem thickness, ≤3 levels;

[0038] (3) flower head size, ≤3 grades;

[0039] (4) flower color, ≤ 4 levels;

[0040] (5) openness, ≤3 levels;

[0041] (6) Flower and leaf defects, ≤3 grades.

[0042] These six indicators change with many factors such as temperature, humidity, light, water, fertilizer, pests and diseases, and origin.

[0043] The external computer system grades each flower to be graded according to the above six indicators based on the pictures taken by the visual detection mechanism 2, and controls the subsequent movement of the turning mechanism 3 to place the flowers into the corresponding flower storage bins 9 respectively.

[0044] The visual inspection mechanism 2 is based on the convolutional neural network technology, which enables the computer camera 5 to have self-learning ability, and imitates artificial experience to maximize the "visualization" and "digitalization" of the data of each flower, thereby improving the grading accuracy and grading speed.

[0045] The turning mechanism 3 is arranged downstream of the conveying mechanism. The turning mechanism 3 receives the processing result of the photos by the external computer system and automatically puts the flowers into the corresponding flower storage bins 9 respectively.

[0046] The conveying mechanism is a conveyor belt 1, on which a plurality of flower pillows 4 are fixedly installed. The flower pillows 4 are evenly distributed on the conveyor belt 1. The flower pillows 4 are used to place fresh flowers, and the fresh flowers can be placed horizontally, which is not only convenient for the visual detection mechanism 2 to capture and shoot, but also avoids flower damage caused by the impact of clamps and pneumatic components when the fresh flowers fall into the corresponding flower storage bin 9, thereby improving the yield of the finished products.

[0047] The visual inspection mechanism 2 includes a plurality of cameras 5 .

[0048] The flipping mechanism 3 includes a chain and a plurality of evenly arranged flower storage bins 9, a plurality of evenly arranged flower slots 6 are installed on the chain, and an electromagnetic mechanism is correspondingly arranged on each flower slot 6, and the electromagnetic mechanism is connected to two rotating shafts 10, and swing arms 11 are fixedly installed on the sides of the two rotating shafts 10, and a rack 7 is installed on the sides of the two swing arms 11, and the rack 7 meshes with a local gear 8 fixedly installed on the flower slot 6.

[0049] A warning light is installed in the flower storage bin 9. When the flowers in the flower storage bin 9 reach a certain number, the warning light prompts the workers to take out the flowers.

[0050] A method for automatic grading of fresh cut flowers comprises the following steps:

[0051] S11: placing the flowers to be graded in the flower pillow 4 above the conveyor belt 1;

[0052] S12: According to the distribution of flowers to be graded, the conveying speed of the conveyor belt 1 is adjusted adaptively;

[0053] S13: When the flowers pass through the visual inspection mechanism 2, the multiple cameras 5 of the visual inspection mechanism 2 capture and take pictures of the flowers to be graded, and transmit the captured pictures to the external computer system;

[0054] S14: the external computer system processes the image captured in step S3 to determine the grade of the flowers to be graded;

[0055] S15: the flowers to be graded continue to move forward on the conveyor belt 1 and fall into the flower trough 6;

[0056] S16: The external computer system controls the corresponding flower trough 6 to flip according to the transmission speed of the chain, so that the flowers to be graded fall into the flower storage bin 9 of the corresponding grade.

[0057] After step S16, the method further includes step S17, in which a warning light is turned on to give an alarm when the flowers in the flower storage bin 9 reach the maximum capacity.

[0058] The flowers to be graded are placed on the flower pillows 4 of the conveyor belt 1 respectively. The flowers are transported by the conveyor belt 1 to the position of the visual detection mechanism 2. At this time, the visual detection mechanism 2 automatically triggers the collection of photos, and the external computer system analyzes the flowers according to the photo data to make a grade judgment; the flowers continue to move and enter the turning mechanism 3; when the flowers run to the corresponding grade flower storage bin 9, the corresponding electromagnetic mechanism is actuated to drive the rack 7 to press down, and mesh with the gear 8 connected to the end of the flower storage bin 9, driving the flower storage bin 9 to flip forward, and the flowers automatically fall into the lower flower storage bin 9 due to gravity to complete the flower grade classification.

[0059] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A fresh cut flower automatic grading device, characterized in that: include: A conveying mechanism, the conveying mechanism is used to convey flowers, a visual detection mechanism (2) is arranged along the moving direction of the conveying mechanism, the visual detection mechanism (2) is used to capture and photograph the flowers passing on the conveying mechanism, and transmit them to an external computer system; The visual detection mechanism (2) is based on convolutional neural network technology; A turning mechanism (3) is arranged downstream of the conveying mechanism, and the turning mechanism (3) receives the processing result of the photos by the external computer system and automatically puts the flowers into the corresponding flower storage bins (9).

2. The automatic grading device for fresh cut flowers as claimed in claim 1, characterized in that: The conveying mechanism is a conveyor belt (1).

3. The automatic grading device for fresh cut flowers as claimed in claim 2, characterized in that: A plurality of flower pillows (4) are fixedly mounted on the conveyor belt (1).

4. The automatic grading device for fresh cut flowers as claimed in claim 3, characterized in that: The flower pillows (4) are evenly distributed on the conveyor belt (1).

5. The automatic grading device for fresh cut flowers as claimed in claim 1, characterized in that: The visual detection mechanism (2) comprises a plurality of cameras.

6. The automatic grading device for fresh cut flowers according to claim 1, characterized in that: The turning mechanism (3) comprises a chain and a plurality of evenly arranged flower storage bins (9); a plurality of evenly arranged flower troughs (6) are mounted on the chain; each of the flower troughs (6) is provided with an electromagnetic mechanism; the electromagnetic mechanism is connected to two rotating shafts (10); swing arms (11) are fixedly mounted on the circumferential sides of the two rotating shafts (10); a rack (7) is mounted on the circumferential sides of the two swing arms (11); the rack (7) meshes with a local gear fixedly mounted on the flower trough (6).

7. The automatic fresh cut flower grading device according to claim 1, characterized in that: A warning light is installed in the flower storage bin (9).

Images