A tobacco stem sorting control method, device, medium and product

Abstract

The application discloses a tobacco stem sorting control method and device, medium and product, relates to the technical field of tobacco manufacturing and cigarette production automation, and the method comprises the following steps: obtaining tobacco stem material to be sorted, uniformly distributing and defibrating the material, and then conveying the material to a first sorting area through a first conveying belt; collecting a first tobacco stem image of the tobacco stem material to be sorted, and identifying unqualified material; according to a first identification result, controlling a first high-speed air valve to blow the identified first unqualified material to a second conveying belt, continuously collecting pictures in the blowing process of the unqualified material, and fitting to obtain an actual motion trajectory; collecting a second tobacco stem image of the first unqualified material, and identifying unqualified material; and according to the actual motion trajectory and a second identification result, adjusting the operation parameters of a second high-speed air valve, and blowing the second unqualified material to a target recycling device, so that the problem of misblowing and missed blowing generated in the first-stage sorting is reduced, and the stability and working condition adaptability of the sorting process are enhanced.

Description

Technical Field

[0001] This invention relates to the field of tobacco manufacturing and cigarette production automation technology, and in particular to a tobacco stem sorting control method, equipment, medium and product. Background Technology

[0002] In the cigarette processing industry, the sorting of tobacco stems generally adopts image recognition combined with high-speed air valve blowing to remove unqualified materials. In order to further optimize the sorting effect, the industry is also gradually applying multi-level screening mode to improve the overall performance of material sorting.

[0003] Current mainstream tobacco stem sorting solutions employ fixed operating parameters for image recognition and high-speed air valve blowing throughout the entire process. Multi-stage sorting relies solely on the image recognition results of the current stage to control the air valves and complete the blowing action, with each stage operating relatively independently. However, in actual production conditions, due to differences in the type, size, weight, and shape of the unqualified materials, the actual blowing trajectory of the materials after each stage of sorting deviates from the preset ideal trajectory. Existing multi-stage sorting solutions cannot compensate for this trajectory deviation, causing the blowing position and force parameters of subsequent sorting to fail to adapt to the actual movement of the materials. This frequently results in unqualified materials being missed or mistakenly blown, significantly reducing sorting accuracy and material rejection efficiency. It also easily leads to the accidental recycling of qualified tobacco stems, increasing raw material loss. Furthermore, the overall adaptability and operational stability of the equipment to complex operating conditions are difficult to guarantee. Summary of the Invention

[0004] This invention provides a tobacco stem sorting control method, equipment, medium, and product to solve the technical problems of insufficient tobacco stem sorting accuracy, easy occurrence of missed blowing and misblowing, resulting in low sorting efficiency, large raw material loss, and poor equipment adaptability.

[0005] According to one aspect of the present invention, a tobacco stem sorting control method is provided, comprising:

[0006] After obtaining the tobacco stem material to be sorted and performing homogenization and loosening treatment, the material is conveyed to the first sorting area via the first conveyor belt.

[0007] The first tobacco stem image of the tobacco stem material to be sorted arriving at the first sorting area is acquired, and the unqualified material is identified based on the first tobacco stem image to obtain the first identification result;

[0008] Based on the first identification result, the first high-speed air valve is controlled to blow the identified first non-conforming material to the second conveyor belt. At the same time, the images of the non-conforming material blowing process are continuously collected, and the actual movement trajectory of the first non-conforming material is obtained by fitting.

[0009] A second tobacco stem image of the first non-conforming material is acquired by the second conveyor belt and transported to the second sorting area. The non-conforming material is identified based on the second tobacco stem image to obtain a second identification result.

[0010] Based on the actual motion trajectory and the second identification result, the operating parameters of the second high-speed air valve are adjusted, and the second unqualified material in the first unqualified material is blown to the target recovery device through the second high-speed air valve.

[0011] According to another aspect of the present invention, a tobacco stem sorting control device is provided, comprising:

[0012] The material homogenization and unpacking module is used to acquire the tobacco stem material to be sorted and perform material homogenization and unpacking treatment on the material, and then transport it to the first sorting area via the first conveyor belt.

[0013] The first identification module is used to acquire the first tobacco stem image of the tobacco stem material to be sorted arriving at the first sorting area, and to identify unqualified materials based on the first tobacco stem image to obtain the first identification result;

[0014] The motion trajectory module is used to control the first high-speed air valve to blow the identified first non-conforming material to the second conveyor belt based on the first recognition result, and at the same time continuously collect the images of the non-conforming material during the blowing process, and fit the actual motion trajectory of the first non-conforming material.

[0015] The second identification module is used to acquire a second tobacco stem image of the first unqualified material conveyed to the second sorting area by the second conveyor belt, and to identify the unqualified material based on the second tobacco stem image to obtain a second identification result;

[0016] The recycling device module is used to adjust the operating parameters of the second high-speed air valve according to the actual motion trajectory and the second identification result, and to blow the second unqualified material in the first unqualified material to the target recycling device through the second high-speed air valve.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the tobacco stem sorting control method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the tobacco stem sorting control method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the method as described in any embodiment of the present invention.

[0021] The technical solution of this invention pre-treats the tobacco stem material to be sorted by uniform material dispersing, which can effectively avoid material stacking and adhesion, creating favorable conditions for subsequent image acquisition and recognition, and improving the accuracy of image recognition. Image acquisition and material recognition are completed by two-stage sorting zones respectively. The operating parameters of the second high-speed air valve are dynamically adjusted by combining the actual movement trajectory of the first unqualified material with the secondary recognition results. Compared with the traditional sorting method that uses fixed parameter blowing, it can effectively offset the movement trajectory deviation caused by material shape and airflow disturbance, accurately distinguish and remove the real second unqualified material in the first unqualified material. This reduces the problems of false blowing and missed blowing caused by the first-stage sorting, improves the overall sorting accuracy and the efficiency of unqualified material removal, and reduces the raw material loss caused by the wrong recycling of qualified tobacco stems. At the same time, the two-stage sorting architecture combined with the linkage of trajectory fitting and parameter adaptive adjustment also enhances the stability and adaptability of the entire sorting process.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0024] Figure 1 This is a flowchart of a tobacco stem sorting and control method provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of another tobacco stem sorting and control method provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a flowchart of another tobacco stem sorting and control method provided in Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of a tobacco stem sorting control method applicable to an embodiment of the present invention;

[0028] Figure 5This is a schematic diagram of the structure of a tobacco stem sorting and control device according to Embodiment 4 of the present invention;

[0029] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the tobacco stem sorting and control method of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a tobacco stem sorting control method provided in Embodiment 1 of the present invention. This embodiment is applicable to the sorting of tobacco stem materials. The method can be executed by a tobacco stem sorting control device, which can be implemented in hardware and / or software and is generally configured in an electronic device. Figure 1 As shown, the method includes:

[0034] S110. After obtaining the tobacco stem material to be sorted and performing uniform material dispersing treatment, the material is conveyed to the first sorting area via the first conveyor belt.

[0035] In this embodiment of the invention, the tobacco stem material to be sorted can be specifically understood as: raw tobacco stem material that has not yet undergone quality screening and is mixed with various defective products. The homogenization and loosening process can be specifically understood as: performing a pre-treatment operation of breaking up and layering, and spreading out the tobacco stems that are piled up and stuck together. The first conveyor belt can be specifically understood as: a conveying device used for transferring and conveying the tobacco stems after homogenization to the primary sorting station. The first sorting area can be specifically understood as: the first sorting station where image acquisition and material quality identification are carried out.

[0036] Specifically, after obtaining the tobacco stems to be sorted, a pre-treatment process of material dispersion and thinning is carried out, which has the effect of dispersing, layering, and spreading. For example, the tobacco stems to be sorted are fed into a material dispersing vibrating trough that operates according to the preset material dispersing mode and matching parameters. The initial material dispersion is completed by the guide structure of the vibrating trough. The material slides towards the sliding plate by inertia and gravity and is dispersed a second time by relying on the sliding speed difference. After the material falls to the material drop area of ​​the first conveyor belt, the third sorting and thinning is completed by the speed difference formed between the material and the conveyor belt. The entire structure of vibrating trough, sliding plate, and conveyor belt speed adjustment eliminates the problem of tobacco stem stacking and adhesion layer by layer throughout the process. Alternatively, by setting the material screening particle size threshold and the spreading uniformity threshold, the material to be sorted can be rolled and screened by the roller screening structure to initially break the stacking and adhesion of the material. Then, the vibrating spreading plate continuously vibrates and sorts the falling material according to the preset vibration frequency level, further widening the material spacing and spreading the material evenly, so as to achieve the effect of material dispersion and thinning and regularization of tobacco stem material.

[0037] The first conveyor belt is used to transport the neatly spread tobacco stems to the first sorting area, completing the pre-transportation preparation work.

[0038] S120. Acquire the first tobacco stem image of the tobacco stem material to be sorted in the first sorting area, and identify unqualified materials based on the first tobacco stem image to obtain the first identification result.

[0039] In this embodiment of the invention, the first tobacco stem image can be specifically understood as: an image of the tobacco stem captured by the first image acquisition device. The first recognition result can be specifically understood as: initial determination information regarding whether the material has defects. The first image acquisition device can be specifically understood as: a camera device used for primary imaging, such as an industrial camera.

[0040] Specifically, after the tobacco stem material to be sorted arrives at the designated throwing point in the first sorting area, the first image acquisition device captures the image of the material being thrown off the conveyor belt, generates the first tobacco stem image, and completes the first round of recognition and judgment to obtain the first recognition result.

[0041] For example, an image feature library can be pre-built to store the image features of various defective materials, and a feature matching threshold can be set. Acquisition and recognition methods can be adopted, such as double-sided shooting, fixed-point single-sided capture, and segmented continuous scanning.

[0042] When performing dual-sided shooting and recognition, two sets of acquisition devices are simultaneously deployed in the material throwing area to capture complete images of both sides of the tobacco stem. The images are compared with the feature library and the defective materials are determined by referring to the matching degree threshold.

[0043] When using fixed-point single-sided capture, a single-sided image is captured when the material is thrown past the fixed-point acquisition position. The image is then compared with the feature library and the defective material is determined by referring to the matching degree threshold.

[0044] When using segmented continuous scanning, multiple sets of acquisition units are deployed along the material throwing path to continuously capture material images segment by segment. All images are matched with the image feature library to obtain the matching value corresponding to each frame. A threshold for the effective judgment ratio of multiple frames is set. When the proportion of image frames that reach the matching degree threshold to the total number of acquired frames is higher than the threshold, the material is uniformly marked as unqualified material; otherwise, it is judged as qualified material.

[0045] S130. Based on the first identification result, control the first high-speed air valve to blow the identified first non-conforming material to the second conveyor belt, and at the same time continuously collect the images of the non-conforming material during the blowing process, and fit the actual movement trajectory of the first non-conforming material.

[0046] In this embodiment of the invention, the first high-speed air valve can be specifically understood as an airflow control component that performs the first-stage blowing action. The first unqualified material can be specifically understood as a mixture that is blown and transferred after being identified and marked in the first stage.

[0047] The second conveyor belt can be specifically understood as the component used to receive and transport the first non-conforming material. The actual motion trajectory can be specifically understood as the actual flight path of the first non-conforming material after it is blown away from the conveyor carrier by the airflow.

[0048] Specifically, based on the initial identification result, the location of the material marked as unqualified is determined. The first high-speed air valve is triggered to open and spray air according to the preset valve opening delay and airflow pressure settings. The directional airflow impacts the target unqualified material, causing it to detach from the first conveyor belt and fall onto the second conveyor belt. For materials identified as qualified, the air valve remains closed, allowing the qualified material to travel normally along its original trajectory without airflow interference. The entire process, with the spraying action starting and stopping according to the identification marks, achieves the directional transfer of the unqualified material.

[0049] The first non-conforming material is transported to the second sorting area by the second conveyor belt.

[0050] Throughout the entire process of transferring the first non-conforming material via jet blowing, a trajectory acquisition process can be initiated simultaneously. This can be achieved by using a frame-by-frame extraction and point-fitting method, capturing material flight images according to a preset sampling level, extracting material coordinates frame by frame to generate a position sequence, and then calculating and fitting a complete actual flight trajectory. Alternatively, a laser ranging and tracking method can be used, relying on a ranging module to collect continuous distance coordinate information and using a trajectory fitting algorithm to construct a complete actual flight trajectory of the material against a trajectory smoothing threshold. Another method can be infrared displacement detection, using an infrared sensing unit to capture material displacement change signals, collecting continuous displacement data, and using a trajectory fitting algorithm to construct a complete actual flight trajectory of the material against a trajectory smoothing threshold.

[0051] S140. Acquire a second tobacco stem image of the first non-conforming material conveyed to the second sorting area via the second conveyor belt, and identify the non-conforming material based on the second tobacco stem image to obtain a second identification result.

[0052] In this embodiment of the invention, the second sorting area can be specifically understood as: a workstation for secondary image recognition and sorting. The second tobacco stem image can be specifically understood as: a material imaging image captured by the second image acquisition device. The second recognition result can be specifically understood as: a judgment conclusion obtained by further identifying genuine defective products within the mixed material. The second image acquisition device can be specifically understood as: an image acquisition and shooting device used for the secondary workstation, such as an industrial camera.

[0053] Specifically, when the first unqualified material is transported to the designated throwing and emptying point in the second sorting area by the second conveyor belt, the position sensing signal is triggered to activate the second image acquisition device. The acquisition mode can be selected as double-sided shooting, fixed-point single-sided capture or segmented continuous scanning shooting. The material image is captured according to the preset shooting sampling level as the second tobacco stem image.

[0054] A unified image feature library is constructed by pre-storing the appearance characteristics of various defective tobacco stems and setting the feature matching degree threshold. When using double-sided shooting, two sets of acquisition devices are deployed in the material throwing section to capture images of both sides. When using fixed-point single-sided shooting, a single-sided image is captured when the material passes through the sensing fixed point. Segmented continuous scanning and shooting are performed by arranging multiple sets of acquisition units along the conveying path.

[0055] The acquired second tobacco stem images are compared one by one with the pre-stored defect feature library to obtain image matching values. These values ​​are then compared with a preset feature matching threshold. Materials whose matching values ​​meet the threshold criteria are identified as genuine defective products, while materials whose matching values ​​do not meet the threshold criteria are identified as qualified tobacco stems that were mistakenly blown during the first-level sorting. This process is used to distinguish and screen the two types of materials, resulting in the second identification result.

[0056] S150. Based on the actual motion trajectory and the second identification result, adjust the operating parameters of the second high-speed air valve, and blow the second unqualified material in the first unqualified material to the target recovery device through the second high-speed air valve.

[0057] In this embodiment of the invention, the second high-speed air valve can be specifically understood as an airflow control component for performing the secondary sorting and blowing. The second non-conforming material can be specifically understood as the confirmed defective material remaining after the first non-conforming material has been removed from the first non-conforming material after the mistakenly blown-conforming material has been removed. The target recovery device can be specifically understood as a device for collecting and storing the second non-conforming defective material. Here, "first" and "second" are only used to distinguish different components or concepts and have no meaning of priority or sequence.

[0058] Specifically, the standard ideal motion trajectory is obtained by matching and generating it in advance according to information such as valve operating conditions and material categories. The actual motion trajectory obtained by the acquisition and fitting is compared with it to calculate the trajectory deviation. Combined with the location and category information of the second unqualified material marked by the second identification result, at least one of the following operating parameters of the second high-speed air valve is adjusted according to the trajectory deviation compensation level: blowing angle, blowing speed, blowing duration, airflow trigger response delay, airflow nozzle opening, multi-channel air valve opening and closing combination mode, airflow pressure stabilization compensation level, pulse jet interval, etc. Only the second unqualified material marked by identification is triggered to perform the jet action after parameter adjustment. The defective material is blown into the pre-deployed target recovery device by relying on directional airflow. The qualified tobacco stems that are mistakenly blown into the mixed material do not have the effect of airflow and proceed normally along the original conveying path for diversion.

[0059] Understandably, the first-stage sorting process is affected by material adhesion and airflow disturbance, which may produce a first-stage unqualified mixture of qualified materials. If all of them are recycled directly, it will waste good raw materials and reduce the output rate of finished products. Relying solely on fixed-parameter blowing will result in blowing inaccuracy due to the actual flight trajectory of each batch of materials deviating from the theoretical trajectory.

[0060] Tobacco stems are thin and light, making them prone to shifting and dragging adjacent stems together under the impact of the primary airflow, resulting in a mixed first layer of substandard material. Furthermore, the thin material's trajectory is prone to irregular deviations. By collecting and measuring actual motion trajectories, the operating parameters of the air valve are dynamically corrected to offset trajectory deviations caused by airflow disturbances. Secondary image recognition then precisely separates the adhered good and substandard stems. Only confirmed substandard stems are recycled using adjustable parameters, while mistakenly blown-through qualified stems are naturally diverted. This approach not only solves the industry-wide common defect of insufficient accuracy in single-stage sorting and identification but also adapts to the specific working conditions of thin, easily disturbed, and easily adhered tobacco stems, achieving the dual effect of accurate substandard product collection and lossless reuse of good products.

[0061] Optionally, based on the above embodiments, the first conveyor belt and the second conveyor belt are arranged vertically. The first unqualified material blown off by the first high-speed air valve falls to the second conveyor belt by gravity. The second conveyor belt transports the first unqualified material to the second sorting area in the opposite conveying direction to the first conveyor belt.

[0062] In this embodiment of the invention, the upper and lower arrangement structure can be specifically understood as a hierarchical arrangement in which two conveyor belts have a height difference.

[0063] Specifically, the first and second conveyor belts are arranged in a high-low layered layout. After the first high-speed air valve blows the first unqualified material away from the upper first conveyor belt, the material falls vertically to the lower second conveyor belt by its own weight. The second conveyor belt is set to operate in the opposite direction to the material conveying direction of the first conveyor belt, carrying all the first unqualified mixed materials in the reverse direction and stably transferring them to the second sorting area for secondary identification and sorting. The reverse layout saves the horizontal space occupied by the equipment and also leaves enough space for imaging and capture of the falling material.

[0064] By adopting a structure with a first and second conveyor belt arranged vertically, the first unqualified material blown off by the first high-speed air valve falls naturally to the lower second conveyor belt by gravity. The second conveyor belt then transports the material in the opposite direction to the second sorting area. From a spatial layout perspective, this reduces the horizontal footprint of the entire sorting equipment. The vertical drop creates a material airspace, facilitating the collection of material flight trajectories and the capture of imaging images. The reverse conveying path allows the two-stage identification and sorting stations to be located at opposite ends of the equipment, preventing interference and collision between the qualified material conveyed in the first stage and the mixed material awaiting re-inspection in the second stage. The gravity-feeding material transfer method eliminates the need for an additional pushing mechanism to complete the material transfer, reducing the number of supporting transmission components and thus lowering the equipment failure rate and power consumption.

[0065] Furthermore, based on the above embodiments, before the second non-conforming material in the first non-conforming material is blown to the target recycling device through the second high-speed air valve, the following may also be included:

[0066] Determine the blowing position of the first non-conforming material on the first conveyor belt and its landing position on the second conveyor belt, and calculate the relative position formed by the blowing position and the landing position; based on the relative position, deploy the target recovery device.

[0067] In this embodiment of the invention, the blowing position can be specifically understood as: the point where the first high-speed air valve blows the first defective material away from the first conveyor belt. The landing position can be specifically understood as: the point where the material falls and contacts the second conveyor belt. The relative position can be specifically understood as: the spatial coordinate distance between the blowing position and the landing position.

[0068] Specifically, before the second high-speed air valve sprays the second unqualified material to the target recovery device, the first unqualified material is positioned at the blowing position on the first conveyor belt and the landing position on the second conveyor belt to obtain the first relative positional relationship between the two. The target recovery device is arranged according to this spatial correspondence, so that the secondary blowing point of the material on the second conveyor belt and the target recovery device form a matching second relative positional relationship. Relying on the vertical integration layout of the upper and lower double-layer conveyor belts, the space occupied by the equipment is reduced and the axial length of the whole machine is shortened. The mixed material after the first-stage sorting falls naturally into the reverse-running lower conveyor belt by gravity. The intermediate transmission components are eliminated to achieve seamless automatic connection of the two-stage sorting process. The stable geometric correspondence between the upper and lower points can be used as a reference benchmark. The operating parameters of the second high-speed air valve are calibrated in conjunction with the actual motion trajectory collected in the first stage. On the basis of simplifying the equipment structure and reducing the energy consumption of operation and maintenance, the continuous processing rate of materials and the accuracy of secondary sorting and blowing are improved.

[0069] Specifically, the first relative positional relationship can be understood as the spatial matching state between the primary blowing point and the lower landing point. The second relative positional relationship can be understood as the spatial matching and alignment state between the secondary blowing point and the recovery device.

[0070] By first calculating the spatial relative relationship between the primary blowing position and the lower landing position and then deploying the target recovery device, the unified spatial matching logic between the two-stage blowing points and the receiving structure can be replicated. Relying on the stable geometric reference formed by the primary points, a reference coordinate is provided for the secondary blowing, reducing the installation and debugging deviation caused by the flight deviation of different materials. There is no need to repeatedly test and adjust the placement of the recovery device, reducing the difficulty of on-site assembly and debugging of the equipment. The unified relative position matching logic also allows the second high-speed air valve to quickly correct its own operating parameters based on the primary trajectory data, improving the positioning accuracy of the second unqualified material spraying and collection, avoiding the scattering of defective products and mixing into the conveying path of qualified materials. At the same time, the standardized position layout method is compatible with the compact layout of the upper and lower double-layer conveyor belts, without occupying additional horizontal and vertical installation space of the equipment, maintaining the structural advantages of the compact and efficient whole machine.

[0071] The technical solution of this invention pre-treats the tobacco stem material to be sorted by uniform material dispersing, which can effectively avoid material stacking and adhesion, creating favorable conditions for subsequent image acquisition and recognition, and improving the accuracy of image recognition. Image acquisition and material recognition are completed by two-stage sorting zones respectively. The operating parameters of the second high-speed air valve are dynamically adjusted by combining the actual movement trajectory of the first unqualified material with the secondary recognition results. Compared with the traditional sorting method that uses fixed parameter blowing, it can effectively offset the movement trajectory deviation caused by material shape and airflow disturbance, accurately distinguish and remove the real second unqualified material in the first unqualified material. This reduces the problems of false blowing and missed blowing caused by the first-stage sorting, improves the overall sorting accuracy and the efficiency of unqualified material removal, and reduces the raw material loss caused by the wrong recycling of qualified tobacco stems. At the same time, the two-stage sorting architecture combined with the linkage of trajectory fitting and parameter adaptive adjustment also enhances the stability and adaptability of the entire sorting process.

[0072] Example 2

[0073] Figure 2 This is a flowchart of another tobacco stem sorting control method provided in Embodiment 2 of the present invention. This embodiment is a refinement of the step in the above embodiment of "continuously collecting images of the blowing process of unqualified materials and fitting the actual movement trajectory of the first unqualified material". Figure 2 As shown, the method includes:

[0074] S210. After obtaining the tobacco stem material to be sorted and performing uniform material dispersing treatment, the material is conveyed to the first sorting area via the first conveyor belt.

[0075] Optionally, based on the above embodiments, the material homogenization and dispersing process may include:

[0076] Based on the preset material distribution mode, the corresponding material distribution parameters are determined, and the tobacco stems to be sorted are fed into the material distribution vibrating trough. The material is dispersed to both sides by the guide structure of the vibrating trough. After dispersion, the tobacco stems slide down to the sliding plate under the action of inertia and gravity. After a second dispersion is completed by the sliding difference, the material continuously falls onto the first conveyor belt. The horizontal movement speed of the tobacco stems sliding down the sliding plate and the actual flatness of the tobacco stems in the material falling area of ​​the first conveyor belt are collected and compared with the preset standard flatness. The running speed of the first conveyor belt is adjusted according to the horizontal movement speed of the tobacco stems and the comparison results. By using the speed difference between the material and the conveyor belt, the continuously falling tobacco stems are dispersed for the third time, so that the tobacco stems on the first conveyor belt reach the preset standard flatness.

[0077] In this embodiment of the invention, the uniform material distribution mode can be specifically understood as: a pre-set operating plan corresponding to different material working conditions. The actual flat laying state can be specifically understood as: the actual situation of the thickness and density of the tobacco stems stacked on the conveyor belt. The preset standard flat laying state can be specifically understood as: the ideal thinning and spreading arrangement that meets the requirements of image recognition and shooting.

[0078] Specifically, the material uniforming and spreading process can be divided into three steps. The first step is to set the matching material uniforming parameters (such as vibration amplitude and vibration frequency of the vibrating trough) according to the preset material uniforming mode suitable for the material working conditions. The tobacco stems to be sorted are sent into the material uniforming vibrating trough, and the tobacco stems are dispersed to both sides by the guide structure of the vibrating trough (such as herringbone guide strip) to complete the first dispersion.

[0079] After the second step of diversion, the tobacco stems slide down the sliding plate under the combined action of inertia and gravity. The stacked and sticky tobacco stems separate from each other by the difference in sliding speed, completing the secondary dispersion and falling onto the first conveyor belt (such as the material buffer zone of the first conveyor belt).

[0080] The third step involves real-time synchronous acquisition of the horizontal speed of the tobacco stems sliding down the slide and the actual spreading and arrangement of the tobacco stems within the first conveyor belt (such as in the buffer zone). For example, a speed sensor is used to continuously capture the horizontal speed signal of the tobacco stems sliding down the slide, and a visual imaging acquisition device is used to continuously capture images of the material in the material buffer zone of the first conveyor belt. Based on image analysis algorithms, features such as the thickness of the tobacco stem stack and the density of the material gaps are extracted to obtain the actual spreading and arrangement. The two types of acquisition signals are synchronously transmitted to the main control computing unit to achieve real-time synchronous acquisition of speed data and spreading state images. Two sets of monitoring information are acquired according to the preset sampling period, providing the original monitoring basis for synchronous matching for subsequent conveyor belt speed adjustment.

[0081] The actual flat-laying state is compared and verified with the preset standard flat-laying state. The running speed of the first conveyor belt is dynamically adjusted by combining the difference between the horizontal movement speed of the tobacco stems and the flat-laying comparison. The material gap is widened by the speed difference between the falling material and the conveyor belt to complete the third thinning and spreading. The arrangement density is continuously corrected until all tobacco stems on the first conveyor belt stably maintain the target thinning and flat-laying state that is adapted to the shooting and recognition.

[0082] For example, the main control unit uses an image segmentation algorithm to distinguish between the solid area of ​​the tobacco stem and the blank background area, and counts various characterization parameters such as the percentage of material pixels, the thickness range of a single stack, and the size of the horizontal and vertical gaps of the material. These parameters are then integrated and converted into density feature values ​​that represent the density of the arrangement. This allows for the complete analysis and extraction of the density features corresponding to the actual flat state of the material on the first conveyor belt.

[0083] The actual density feature value obtained from the analysis is calculated by subtracting the standard flat feature template value stored in the system to obtain the flat deviation difference value. The system synchronously reads the horizontal movement speed signal of the tobacco stems transmitted back in real time by the sensing components, and retrieves the preset speed matching gear reference table corresponding to different speed ranges and different deviation ranges stored in the internal storage. The main control unit combines the flat deviation level and the downward speed condition level for comprehensive weighted calculation, and matches and outputs speed adjustment commands to increase, decrease or maintain the rotation speed and sends them to the conveyor belt drive actuator to complete the linkage speed adjustment, so that a controllable travel speed difference is formed between the falling tobacco stems and the conveyor belt. The speed difference is used to increase the spacing between adjacent tobacco stems to achieve the third thinning. The closed-loop control process of cyclic comparison, speed adjustment and thinning continuously corrects the material distribution density on the conveyor belt, and finally allows the tobacco stems to maintain a stable target flat shape that is suitable for clear image acquisition and recognition in the long term.

[0084] Specifically, the material buffer zone can be understood as the area where the first conveyor belt receives the falling tobacco stems. The horizontal movement speed can be understood as the lateral movement rate of the tobacco stems as they slide down the slide plate.

[0085] The first round of material distribution is achieved by guiding the material through a vibrating trough. A second round of material distribution is then achieved using the sliding speed difference of the slide plate. Finally, a third round of thinning is achieved through a closed-loop speed control system that integrates speed acquisition and visual inspection of the spread material. This process breaks up the layers of tobacco stems that are stuck together, preventing material stacking and obstruction from causing missed detections or misjudgments in image recognition. The phased dispersion method is gentle and suitable for thin and fragile tobacco stems, avoiding excessive material loss due to forceful dispersal. Combined with a closed-loop control mode that coordinates the horizontal speed of the slide plate and the spread deviation, it can adapt to changes in material sliding characteristics caused by varying amounts of material and different levels of dryness and hardness. This maintains a stable, standard spread state on the conveyor line, suitable for imaging, eliminating the need for frequent manual adjustments to the vibrating trough and conveyor belt conditions, reducing manual intervention costs. The evenly spread material also allows for more precise positioning by the two-stage high-speed air valves, improving the overall recognition accuracy and yield of the intelligent tobacco stem sorting equipment.

[0086] S220. Acquire the first tobacco stem image of the tobacco stem material to be sorted in the first sorting area, and identify unqualified materials based on the first tobacco stem image to obtain the first identification result.

[0087] S230. Based on the first identification result, control the first high-speed air valve to blow the identified first non-conforming material to the second conveyor belt. At the same time, continuously collect the flight image of the first non-conforming material after it leaves the first conveyor belt according to the preset shooting frequency, and extract the outline edge or center point information of the first non-conforming material in the image frame by frame.

[0088] In this embodiment of the invention, the preset shooting frequency can be specifically understood as: the fixed frame rate of image capture by the image acquisition device. The flight image can be specifically understood as: the image captured during the airborne phase when the first defective material leaves the first conveyor belt.

[0089] S240. Generate a continuous position sequence based on the extracted point information, and obtain the actual movement trajectory of the first unqualified material by fitting the continuous position sequence.

[0090] In this embodiment of the invention, the continuous position sequence can be specifically understood as: a set of coordinate data of multiple frames arranged in chronological order, and the trajectory fitting relies on the time-series coordinate calculation to restore the complete airborne movement path of the material.

[0091] Specifically, the first image acquisition device is activated to continuously capture a complete sequence of flight images of the material after it leaves the first conveyor belt at a preset fixed frame rate; the unqualified tobacco stem material in the image is identified frame by frame, and the outline edge coordinates or center point (centroid center) coordinates of the material in each frame are extracted, and all time-series coordinates are arranged in an orderly manner to construct a continuous position sequence.

[0092] By performing trajectory fitting calculations based on the time-series coordinate values ​​in the continuous position sequence, the actual aerial movement trajectory of the first non-conforming material in this batch during the entire blowing process is reconstructed, providing a precise displacement reference for subsequent adjustment of the secondary air valve parameters.

[0093] Specifically, the first image acquisition device can be understood as a device used to capture the flight images of materials after the first stage of blowing, such as an industrial camera.

[0094] S250: Collect a second tobacco stem image of the first non-conforming material that is conveyed to the second sorting area via the second conveyor belt, and identify the non-conforming material based on the second tobacco stem image to obtain a second identification result.

[0095] S260. Based on the actual motion trajectory and the second identification result, adjust the operating parameters of the second high-speed air valve, and blow the second unqualified material in the first unqualified material to the target recovery device through the second high-speed air valve.

[0096] Optionally, based on the above embodiments, adjusting the operating parameters of the second high-speed air valve according to the actual motion trajectory and the second recognition result may include:

[0097] The first operating parameters of the first high-speed air valve and the type information of the first non-conforming material are obtained, and the corresponding standard ideal motion trajectory is matched; the actual motion trajectory is compared with the standard ideal motion trajectory, and the trajectory deviation is calculated; the operating parameters of the second high-speed air valve are adjusted according to the trajectory deviation; wherein, the operating parameters of the second high-speed air valve include at least one of the following: blowing angle, blowing speed and blowing duration.

[0098] In this embodiment of the invention, the first operating parameter can be specifically understood as: the current jetting condition data of the first high-speed air valve in the primary sorting stage. The standard ideal motion trajectory can be specifically understood as: the theoretical flight path of the material under the corresponding operating condition when there is no disturbance. The trajectory deviation can be specifically understood as: the difference in spatial position and travel attitude between the actual trajectory and the ideal trajectory.

[0099] Specifically, the real-time operating parameters of the first high-speed air valve and the information of the first unqualified material category are collected, and the mapping relationship table built from historical data is matched with the corresponding preset standard ideal motion trajectory.

[0100] The actual motion trajectory of the material obtained by fitting is compared with the standard ideal motion trajectory to obtain the trajectory deviation. Based on the magnitude of the deviation, at least one of the following operating parameters of the second high-speed air valve is adjusted in a targeted manner: blowing angle, blowing speed, and blowing duration, so as to adapt to the material flight deviation and complete the compensation jet.

[0101] For example, the standard ideal motion trajectory coordinate dataset generated by the matching working condition is retrieved and compared with the actual motion trajectory coordinate dataset obtained by fitting the image points, and the spatial offset difference throughout the entire process is calculated to form the trajectory deviation amount and the deviation level range is divided. The main control unit retrieves the preset parameters to correct the matching rules according to the deviation level range, and applies compensation adjustment to any one or more of the operating conditions of the second high-speed air valve, such as the blowing angle, blowing speed, and blowing duration. If the deviation is biased towards the front of the movement, the jet duration is extended or the jet speed is increased. If the deviation is biased towards the lateral side, the jet angle is adjusted simultaneously to offset the positioning error caused by the flight deviation.

[0102] By extracting the centroid and contour coordinates of the image frame by frame to fit the real trajectory, the system accurately quantifies the material's own shape and weight, as well as the flight deviation caused by airflow disturbance. The system uses the trajectory perception data from the first stage to adaptively compensate for the secondary jetting conditions, forming a closed-loop self-control system that links the first stage trajectory monitoring with the second stage air valve parameter adjustment. Compared with the traditional fixed parameter jetting mode, this system effectively counteracts various external and material-related interferences, significantly improving the overall accuracy of the two-stage sorting system in accurately removing defective products.

[0103] Specifically, the mapping table can be understood as a matching table between the valve parameters, material type, and ideal trajectory of the first high-speed gas valve, built based on long-term historical operating data. Material category information can be specifically understood as information such as the thickness, weight, and grade of the tobacco stems.

[0104] By matching the operating conditions of the primary air valve with the standard ideal motion trajectory of the material category, and comparing the actual trajectory to calculate the deviation, the blowing angle, speed, and duration of the secondary air valve are dynamically fine-tuned. This can accurately offset the flight deviation caused by differences in the material's self-weight and shape, as well as environmental airflow disturbances. Combined with the result of secondary identification to lock in the real defective products, the blowing is only accurately compensated for the target material. This prevents defective products from being missed due to trajectory deviation, and also prevents the loss of good products due to accidental impact on qualified tobacco stems mixed in. The two-stage air valve forms a sensing and control closed loop, which is suitable for the material characteristics of tobacco stems that are thin, easy to deviate, and sticky and mixed. This continuously and stably improves the accuracy of defective product rejection, reduces raw material waste and energy consumption caused by ineffective air blowing, and reduces the frequency of equipment debugging. It is also suitable for continuous automated sorting operations of tobacco stems of different batches and different grades.

[0105] The technical solution of this invention pre-processes the tobacco stem material to be sorted by uniform material dispersing, which effectively avoids material stacking and adhesion, creating favorable conditions for subsequent image acquisition and recognition, and improving the accuracy of image recognition. By continuously acquiring the flight images of the first unqualified material after it leaves the first conveyor belt at a preset shooting frequency, extracting the material outline edge or center point information frame by frame and generating a continuous position sequence, and then fitting the actual movement trajectory of the material based on the position sequence, it can completely and realistically restore the dynamic movement state of the unqualified material during the blowing process, accurately capture the trajectory deviation caused by the material's own shape, weight and external airflow, etc., and provide reliable and detailed data basis for targeted adjustment of the high-speed air valve operating parameters in the subsequent secondary sorting stage. This avoids the blowing position deviation caused by the inability to grasp the actual movement trajectory from the source, thereby effectively improving the accuracy of secondary blowing and reducing missed blowing and misblowing. Image acquisition and material identification are completed in two-stage sorting zones. The operating parameters of the second high-speed air valve are dynamically adjusted by combining the actual movement trajectory of the first unqualified material with the secondary identification results. Compared with the traditional sorting method that uses fixed parameter blowing, this method can effectively offset the movement trajectory deviation caused by material shape and airflow disturbance. It can accurately distinguish and remove the real second unqualified material from the first unqualified material. This reduces the problems of false blowing and missed blowing caused by the first-stage sorting, improves the overall sorting accuracy and the efficiency of unqualified material removal, and reduces the raw material loss caused by the wrong recycling of qualified tobacco stems. At the same time, the two-stage sorting architecture, combined with the linkage of trajectory fitting and parameter adaptive adjustment, also enhances the stability and adaptability of the entire sorting process.

[0106] Example 3

[0107] Figure 3 This is a flowchart of another tobacco stem sorting control method provided in Embodiment 3 of the present invention. This embodiment is a refinement of the above embodiment's step of "collecting a first tobacco stem image of the tobacco stem material to be sorted arriving at the first sorting area, and identifying unqualified materials based on the first tobacco stem image to obtain a first identification result." Figure 3As shown, the method includes:

[0108] S310. After obtaining the tobacco stem material to be sorted and performing uniform material dispersing treatment, the material is conveyed to the first sorting area via the first conveyor belt.

[0109] S320. During the process of transporting the tobacco stem material to be sorted to the first sorting area and throwing the material on the first conveyor belt, a double-sided image of the tobacco stem material is collected.

[0110] In this embodiment of the invention, the double-sided image can be specifically understood as: the front and back images captured simultaneously when the material is airborne.

[0111] S330. Based on the preset image feature library of various types of non-conforming materials and the collected double-sided images of tobacco stem materials, identify non-conforming materials and obtain the first identification result.

[0112] Among them, unqualified materials include at least one of the following: tobacco stems, discolored tobacco stems, and miscellaneous materials.

[0113] In this embodiment of the invention, the image feature library can be specifically understood as a pre-stored set of standard visual samples such as tobacco stem crooks, discolored tobacco stems, and debris. Specifically, a tobacco stem crook can be understood as a defective tobacco stem with a bent or distorted shape. A discolored tobacco stem can be understood as a tobacco stem whose color deviates from the acceptable standard. Debris can be understood as foreign impurities with a density similar to that of the tobacco stem.

[0114] Specifically, the first conveyor belt transports the tobacco stems, which have been uniformly dispersed and thinned, to the first sorting area and completes the material throwing. Simultaneously, the imaging equipment acquires images of both sides of the airborne tobacco stems, calls up the image feature library of various unqualified materials to compare the image information, identifies stem bends, discolored tobacco stems, and debris, and outputs the first identification result.

[0115] In addition, alternative implementation methods such as multi-dimensional feature decomposition and extraction can be adopted to match exclusive feature dimensions for different types of materials to complete classification and identification, and simultaneously integrate multi-dimensional features to verify qualified tobacco stems.

[0116] Non-conforming materials may include tobacco stems, similarly dense impurities, and tobacco stems of different colors. The tobacco stems are identified by shape features, the tobacco stems of different colors are identified by color features, the similarly dense impurities are identified by texture features, and the qualified tobacco stems are identified by a combination of the shape features, the color features, and the texture features.

[0117] Color features are among the most intuitive visual characteristics of an image. They can be improved by converting the RGB (Red, Green, Blue) color space to HSV (Hue, Saturation, Brightness) or Lab (Lightness ab, Red-Green axis, Yellow-Blue axis) color spaces suitable for color difference identification, thus enhancing the accuracy of color characteristic description. Alternatively, color histograms can be used to statistically analyze the frequency of various colors within an image to characterize the overall color tone distribution. Color statistical features can also be used, relying on low-order moments such as mean, variance, and color intensity frequency to quantify the color distribution. Through sample channel intensity comparison verification, qualified tobacco stems show significant differentiation from darker tobacco stems and impurities in the G (Green) and B (Blue) channels. Qualified tobacco stems and darker tobacco stems show outstanding differentiation from impurities in the S (Saturation) channel, which can be used as the core color difference criterion for determining dissimilar tobacco stems and impurities.

[0118] Shape features primarily focus on the overall outline and shape of the material. Outline features characterize the outer boundary shape of the material, and continuous outline curves can be extracted from binary images as a shape benchmark. Stems, qualified tobacco stems, and debris are distinguished by outline features and region features. Outline features can be quantitatively represented using parameters such as area, perimeter, centroid, convex hull, and minimum bounding rectangle. This can be achieved through geometric parameter methods, i.e., characterizing the shape using quantitative geometric parameters such as moment values, area, and perimeter; or through the shape-invariant moment method, which uses moment parameters with translation, scaling, and rotation invariance properties to complete shape matching. Hu moments (Hu's invariant moments) are typical and commonly used shape-invariant moments, relying on the stable values ​​of multiple moment orders such as zero-order moments and first-order moments to describe the material's shape.

[0119] The first non-conforming material is transported by the second conveyor belt to the second sorting area for double-sided image acquisition. Based on the same image feature library, a multi-dimensional feature decomposition and identification process is performed to obtain the second identification result.

[0120] Understandably, as an extended alternative implementation structure, it can be connected in series with three, four, or other multi-level gradient sorting stations. Each level is equipped with an independent conveyor belt, a double-sided imaging acquisition unit, and a high-speed air valve. Suspected unqualified mixed materials screened in the previous level are conveyed to the next level and the feature judgment threshold is tightened for fine verification. The high-speed air valves at each level dynamically adjust the blowing angle, blowing speed, blowing duration, and other operating parameters based on the actual motion trajectory of the material. Only the truly defective products identified and confirmed at this level are accurately sprayed into the recovery device. Qualified tobacco stems that are mistakenly carried continue to the next level station for re-inspection, realizing multi-level gradient precision sorting of coarse screening, fine screening, and fine inspection.

[0121] S340. Based on the first identification result, control the first high-speed air valve to blow the identified first non-conforming material to the second conveyor belt, and at the same time continuously collect the images of the non-conforming material during the blowing process, and fit the actual movement trajectory of the first non-conforming material.

[0122] S350: Collect a second tobacco stem image of the first non-conforming material that is conveyed to the second sorting area via the second conveyor belt, and identify the non-conforming material based on the second tobacco stem image to obtain a second identification result.

[0123] S360. Based on the actual motion trajectory and the second identification result, adjust the operating parameters of the second high-speed air valve, and blow the second unqualified material in the first unqualified material to the target recovery device through the second high-speed air valve.

[0124] In a specific example Figure 4 This is a schematic diagram of a tobacco stem sorting control applicable to an embodiment of the present invention. As shown in the figure, the overall structure adopts a double-layer conveyor belt arrangement in opposite directions. A thinning and leveling station is set at the starting point on the right side for pre-thinning and loosening the raw material. The material is fed into the upper conveyor belt from the thinning and leveling station and is horizontally conveyed in the leftward flow direction shown in the figure. A double-sided image acquisition component consisting of a light source and a camera, as well as a high-speed air valve, is equipped at the left end of the upper conveyor belt. When the material is conveyed to the end of the upper conveyor belt and thrown into the air, the light source and the camera complete the material imaging acquisition and recognition. After recognition, the high-speed air valve performs a sorting and blowing action. The qualified material is directly dropped into the qualified material collection area on the left, while the unqualified material blown out is limited by the background plate. Under the influence of gravity, the material falls to the surface of the lower track under the obstruction of the upper track. The lower track transports the first-stage unqualified mixed material in the opposite direction to the upper track, to the right as shown in the diagram. The right end of the lower track is also equipped with a light source, camera imaging and acquisition components, and a high-speed air valve. The first-stage unqualified material is transported to the end of the lower track and is then imaged and identified again during the air-throwing stage. After the second identification, it is sorted by the corresponding high-speed air valve. The actual defective material is assigned to the second-stage unqualified material collection area, while the good material that was mistakenly carried is returned to the front-end process for re-sorting as second-stage return material. Throughout the process, the upper and lower tracks are each equipped with an independent imaging light source, camera, high-speed air valve, and background plate, forming a two-stage gradient tobacco stem sorting structure with primary coarse sorting and secondary fine re-inspection.

[0125] The method proposed in this invention pre-processes the tobacco stem material by spreading and homogenizing it. It then establishes a sorting system with two stages of reverse conveyor belts, consisting of a coarse screening and a secondary inspection. The primary sorting zone collects images of the tobacco stems to identify defective materials and blows them to the secondary sorting zone. Simultaneously, it captures the actual flight trajectory of the defective materials during the primary blowing process. The secondary sorting zone then re-images and verifies the material's condition. Based on the measured trajectory from the primary sorting zone, it dynamically and adaptively adjusts the blowing angle, blowing speed, and blowing duration of the secondary high-speed air valve. This compensates for flight deviations caused by differences in the weight and shape of the tobacco stems and environmental airflow disturbances, avoiding the crude sorting mode of traditional fixed jet parameters. The closed-loop linkage of trajectory perception and air valve control between the two stages of sorting improves the accurate removal rate of defective tobacco stems, impurities, and other defective materials, enhancing the tobacco stem selection quality and operational stability of the entire system during long-term continuous operation.

[0126] The technical solution of this invention pre-processes the tobacco stem material to be sorted by uniformly dispersing it, which effectively avoids material stacking and adhesion, creating favorable conditions for subsequent image acquisition and recognition, and improving the accuracy of image recognition. The tobacco stem material to be sorted is conveyed to the first sorting area via a first conveyor belt, and images of both sides of the material are captured during the throwing process. Compared to capturing only a single-sided image, this method can completely capture the appearance, color, and texture details of both sides of the tobacco stem. Then, by comparing the images with a stored image feature library of various defective material characteristics, different colored tobacco stems, and other impurities, different defects such as stem crooks, discolored tobacco stems, and foreign matter can be identified. This comprehensively eliminates the problems of feature occlusion and recognition omissions caused by single-sided shooting, significantly improving the accuracy of the initial image recognition, accurately screening out the first batch of defective materials, and reducing the risk of misblowing and missed blowing caused by recognition errors at the sorting front end. This lays a reliable foundation for subsequent trajectory acquisition and secondary precise sorting. Image acquisition and material identification are completed in two-stage sorting zones. The operating parameters of the second high-speed air valve are dynamically adjusted by combining the actual movement trajectory of the first unqualified material with the secondary identification results. Compared with the traditional sorting method that uses fixed parameter blowing, this method can effectively offset the movement trajectory deviation caused by material shape and airflow disturbance. It can accurately distinguish and remove the real second unqualified material from the first unqualified material. This reduces the problems of false blowing and missed blowing caused by the first-stage sorting, improves the overall sorting accuracy and the efficiency of unqualified material removal, and reduces the raw material loss caused by the wrong recycling of qualified tobacco stems. At the same time, the two-stage sorting architecture, combined with the linkage of trajectory fitting and parameter adaptive adjustment, also enhances the stability and adaptability of the entire sorting process.

[0127] Example 4

[0128] Figure 5 This is a schematic diagram of a tobacco stem sorting and control device provided in Embodiment 4 of the present invention. Figure 5As shown, the device includes: a material equalization and dispersing module 510, a first identification module 520, a motion trajectory module 530, a second identification module 540, and a recycling device module 550, wherein:

[0129] The material homogenization and unpacking module 510 is used to acquire the tobacco stem material to be sorted and perform material homogenization and unpacking treatment on the material, and then transport it to the first sorting area via the first conveyor belt.

[0130] The first identification module 520 is used to acquire the first tobacco stem image of the tobacco stem material to be sorted arriving at the first sorting area, and to identify unqualified materials based on the first tobacco stem image to obtain the first identification result;

[0131] The motion trajectory module 530 is used to control the first high-speed air valve to blow the identified first non-conforming material to the second conveyor belt according to the first recognition result, and at the same time continuously collect the picture of the non-conforming material during the blowing process, and fit the actual motion trajectory of the first non-conforming material.

[0132] The second identification module 540 is used to acquire a second tobacco stem image of the first unqualified material conveyed to the second sorting area by the second conveyor belt, and to identify the unqualified material based on the second tobacco stem image to obtain a second identification result;

[0133] The recycling module 550 is used to adjust the operating parameters of the second high-speed air valve according to the actual motion trajectory and the second identification result, and to blow the second unqualified material in the first unqualified material to the target recycling device through the second high-speed air valve.

[0134] The technical solution of this invention pre-treats the tobacco stem material to be sorted by uniform material dispersing, which can effectively avoid material stacking and adhesion, creating favorable conditions for subsequent image acquisition and recognition, and improving the accuracy of image recognition. Image acquisition and material recognition are completed by two-stage sorting zones respectively. The operating parameters of the second high-speed air valve are dynamically adjusted by combining the actual movement trajectory of the first unqualified material with the secondary recognition results. Compared with the traditional sorting method that uses fixed parameter blowing, it can effectively offset the movement trajectory deviation caused by material shape and airflow disturbance, accurately distinguish and remove the real second unqualified material in the first unqualified material. This reduces the problems of false blowing and missed blowing caused by the first-stage sorting, improves the overall sorting accuracy and the efficiency of unqualified material removal, and reduces the raw material loss caused by the wrong recycling of qualified tobacco stems. At the same time, the two-stage sorting architecture combined with the linkage of trajectory fitting and parameter adaptive adjustment also enhances the stability and adaptability of the entire sorting process.

[0135] Based on the above embodiments, the first conveyor belt and the second conveyor belt are arranged vertically. The first defective material blown off by the first high-speed air valve falls to the second conveyor belt by gravity. The second conveyor belt transports the first defective material to the second sorting area in the opposite conveying direction to the first conveyor belt.

[0136] Furthermore, based on the above embodiments, the tobacco stem sorting control device may further include: a position calculation module and a placement device module, wherein:

[0137] The position calculation module is used to determine the blowing position of the first non-conforming material on the first conveyor belt and the landing position on the second conveyor belt before the second non-conforming material in the first non-conforming material is blown to the target recycling device through the second high-speed air valve, and to calculate the relative position formed by the blowing position and the landing position.

[0138] The deployment module is used to deploy the target recovery device according to its relative location.

[0139] Based on the above embodiments, the motion trajectory module 530 is specifically used for:

[0140] The system continuously captures images of the first defective material after it leaves the first conveyor belt at a preset shooting frequency, extracting the outline edge or center point information of the first defective material frame by frame; a continuous position sequence is generated based on the extracted point information, and the actual movement trajectory of the first defective material is obtained by fitting the continuous position sequence.

[0141] Based on the above embodiments, the recycling device module 550 is specifically used for:

[0142] The first operating parameters of the first high-speed air valve and the type information of the first non-conforming material are obtained, and the corresponding standard ideal motion trajectory is matched; the actual motion trajectory is compared with the standard ideal motion trajectory, and the trajectory deviation is calculated; the operating parameters of the second high-speed air valve are adjusted according to the trajectory deviation; wherein, the operating parameters of the second high-speed air valve include at least one of the following: blowing angle, blowing speed and blowing duration.

[0143] Based on the above embodiments, the material homogenization and dispersing module 510 is specifically used for:

[0144] Based on the preset material distribution mode, the corresponding material distribution parameters are determined, and the tobacco stems to be sorted are fed into the material distribution vibrating trough. The material is dispersed to both sides by the guide structure of the vibrating trough. After dispersion, the tobacco stems slide down to the sliding plate under the action of inertia and gravity. After a second dispersion is completed by the sliding difference, the material continuously falls onto the first conveyor belt. The horizontal movement speed of the tobacco stems sliding down the sliding plate and the actual flatness of the tobacco stems in the material falling area of ​​the first conveyor belt are collected and compared with the preset standard flatness. The running speed of the first conveyor belt is adjusted according to the horizontal movement speed of the tobacco stems and the comparison results. By using the speed difference between the material and the conveyor belt, the continuously falling tobacco stems are dispersed for the third time, so that the tobacco stems on the first conveyor belt reach the preset standard flatness.

[0145] Based on the above embodiments, the first identification module 520 is specifically used for:

[0146] During the process of transporting the tobacco stem material to be sorted to the first sorting area and throwing the material on the first conveyor belt, double-sided images of the tobacco stem material are collected; based on the preset image feature library of multiple types of unqualified materials and the collected double-sided images of the tobacco stem material, unqualified materials are identified to obtain the first identification result; wherein, unqualified materials include at least one of the following: stem twigs, discolored tobacco stems, and foreign matter.

[0147] The tobacco stem sorting and control device provided in the embodiments of the present invention can execute the tobacco stem sorting and control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0148] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0149] Example 5

[0150] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0151] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0152] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0153] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the tobacco stem sorting control method, namely:

[0154] After obtaining the tobacco stem material to be sorted and performing homogenization and loosening treatment, the material is conveyed to the first sorting area via the first conveyor belt.

[0155] The first tobacco stem image of the tobacco stem material to be sorted arriving at the first sorting area is acquired, and the unqualified material is identified based on the first tobacco stem image to obtain the first identification result;

[0156] Based on the first identification result, the first high-speed air valve is controlled to blow the identified first non-conforming material to the second conveyor belt. At the same time, the images of the non-conforming material blowing process are continuously collected, and the actual movement trajectory of the first non-conforming material is obtained by fitting.

[0157] A second tobacco stem image of the first non-conforming material is acquired by the second conveyor belt and transported to the second sorting area. The non-conforming material is identified based on the second tobacco stem image to obtain a second identification result.

[0158] Based on the actual motion trajectory and the second identification result, the operating parameters of the second high-speed air valve are adjusted, and the second unqualified material in the first unqualified material is blown to the target recovery device through the second high-speed air valve.

[0159] In some embodiments, the tobacco stem sorting control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the tobacco stem sorting control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the tobacco stem sorting control method by any other suitable means (e.g., by means of firmware).

[0160] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0162] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0163] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0164] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0165] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0166] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0167] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for controlling the sorting of tobacco stems, characterized in that, include: After obtaining the tobacco stem material to be sorted and performing homogenization and loosening treatment, the material is conveyed to the first sorting area via the first conveyor belt. The first tobacco stem image of the tobacco stem material to be sorted arriving at the first sorting area is acquired, and the unqualified material is identified based on the first tobacco stem image to obtain the first identification result; Based on the first identification result, the first high-speed air valve is controlled to blow the identified first non-conforming material to the second conveyor belt. At the same time, the images of the non-conforming material blowing process are continuously collected, and the actual movement trajectory of the first non-conforming material is obtained by fitting. A second tobacco stem image of the first non-conforming material is acquired by the second conveyor belt and transported to the second sorting area. The non-conforming material is identified based on the second tobacco stem image to obtain a second identification result. Based on the actual motion trajectory and the second identification result, the operating parameters of the second high-speed air valve are adjusted, and the second unqualified material in the first unqualified material is blown to the target recovery device through the second high-speed air valve.

2. The method according to claim 1, characterized in that, The first conveyor belt and the second conveyor belt are arranged vertically. The first defective material blown off by the first high-speed air valve falls to the second conveyor belt by gravity. The second conveyor belt transports the first defective material to the second sorting area in the opposite conveying direction to the first conveyor belt.

3. The method according to claim 2, characterized in that, Before the second non-conforming material in the first non-conforming material is blown to the target recovery device through the second high-speed air valve, the process also includes: Determine the blowing position of the first non-conforming material on the first conveyor belt and the landing position on the second conveyor belt, and calculate the relative position formed by the blowing position and the landing position; Deploy target recovery devices based on their relative locations.

4. The method according to claim 1, characterized in that, Continuously capture images of the non-conforming material being blown through the system, and fit these images to obtain the actual trajectory of the first non-conforming material, including: The first defective material is continuously captured in flight footage after leaving the first conveyor belt at a preset shooting frequency, and the outline edge or center point information of the first defective material is extracted frame by frame. A continuous position sequence is generated based on the extracted location information, and the actual movement trajectory of the first non-conforming material is obtained by fitting the continuous position sequence.

5. The method according to claim 1, characterized in that, Based on the actual motion trajectory and the second recognition result, the operating parameters of the second high-speed air valve are adjusted, including: The first operating parameters of the first high-speed air valve and the type information of the first unqualified material are obtained, and the corresponding standard ideal motion trajectory is matched. The actual motion trajectory is compared with the standard ideal motion trajectory, and the trajectory deviation is calculated. The operating parameters of the second high-speed air valve are adjusted according to the trajectory deviation; wherein the operating parameters of the second high-speed air valve include at least one of the following: blowing angle, blowing speed and blowing duration.

6. The method according to claim 1, characterized in that, The material undergoes homogenization and dispersion treatment, including: Based on the preset material uniformization mode, the corresponding material uniformization parameters are determined, and the tobacco stem material to be sorted is fed into the material uniformization vibrating trough. The material uniformizing material is then dispersed to both sides by the vibrating trough guiding structure. After being dispersed, the tobacco stem material slides down onto the sliding plate under the action of inertia and gravity. After being dispersed a second time through the sliding difference, it continuously falls onto the first conveyor belt. The horizontal speed of the tobacco stem material sliding down the slide plate and the actual flatness of the tobacco stem material in the first conveyor belt drop area are collected, and the actual flatness is compared with the preset standard flatness. The running speed of the first conveyor belt is adjusted according to the horizontal movement speed of the tobacco stem material and the comparison results. By utilizing the speed difference between the material and the conveyor belt, the continuously falling tobacco stem material is dispersed for the third time, so that the tobacco stem material on the first conveyor belt reaches the preset standard flat state.

7. The method according to claim 1, characterized in that, The system acquires images of the first tobacco stems arriving at the first sorting zone, identifies defective materials based on these images, and obtains a first identification result, including: During the process of transporting the tobacco stem material to be sorted to the first sorting area on the first conveyor belt and throwing the material, double-sided images of the tobacco stem material are captured. Based on a pre-set image feature library of various types of non-conforming materials and double-sided images of collected tobacco stem materials, non-conforming materials are identified, and a first identification result is obtained. Among them, unqualified materials include at least one of the following: tobacco stems, discolored tobacco stems, and miscellaneous materials.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the tobacco stem sorting control method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the tobacco stem sorting control method according to any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the tobacco stem sorting control method according to any one of claims 1-7.

Images