A method, device and storage medium for controlling air volume of tobacco wind separator

Abstract

The present application provides an air volume control method, device and storage medium of a tobacco winnowing machine. A first camera assembly is provided at the waste material outlet of the tobacco winnowing machine. The method comprises: obtaining a waste material image of the waste material discharged by the tobacco winnowing machine captured by the first camera assembly from the first camera assembly; identifying the waste material image to determine whether there are foreign objects in the waste material discharged by the tobacco winnowing machine; if there are foreign objects, generating a shutdown control instruction, and sending the shutdown control instruction to the tobacco winnowing machine to control the tobacco winnowing machine to stop; if there are no foreign objects, determining the type of material contained in the waste material; and adjusting the air volume of the tobacco winnowing machine according to the type of material contained in the waste material. It is used to automatically adjust the negative pressure air volume according to the composition of the discharge material from the waste material outlet.

Description

Technical Field

[0001] The present application relates to the technical field of tobacco processing, and in particular to an air volume control method, device and storage medium of a tobacco winnowing machine. Background Art

[0002] In the prior art, an air classifier is used to screen the impurities in the dried material, thereby separating the tobacco from the impurities. At present, the frequency adjustment of the leaf air classifier in the tobacco production line of the cigarette factory is mostly adjusted according to the relationship between the material flow rate and the wind pressure input to the air classifier. However, since the tobacco contains materials that affect the product quality, such as stems and wet tobacco, it also contains impurities such as plastic, paper, rubber, and feather slices. The weight of each impurity is different, and the negative pressure air volume required to remove each impurity is also different. Therefore, the method of adjusting the negative pressure air volume using the corresponding relationship between material flow and wind pressure has low accuracy. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide an air volume control method, device and storage medium for a tobacco air separator, which are used to automatically adjust the negative pressure air volume according to the composition of the discharge from the waste discharge port.

[0004] In a first aspect, an embodiment of the present application provides an air volume control method for a tobacco winnowing machine, wherein a first camera assembly is provided at a waste material outlet of the tobacco winnowing machine, and the method comprises: obtaining, from the first camera assembly, a waste material image of the waste material discharged from the tobacco winnowing machine captured by the first camera assembly; identifying the waste material image to determine whether there are foreign objects in the waste material discharged from the tobacco winnowing machine; if there are foreign objects, generating a shutdown control instruction, and sending the shutdown control instruction to the tobacco winnowing machine to control the tobacco winnowing machine to shut down; if there are no foreign objects, determining the type of material contained in the waste material; and adjusting the air volume of the tobacco winnowing machine according to the type of material contained in the waste material.

[0005] Preferably, the step of identifying the waste image and determining whether there are debris in the waste discharged by the tobacco winnowing machine includes: inputting the waste image into a debris recognition model to output the debris recognition result of the waste image, and the debris recognition result is used to indicate whether there are debris in the waste discharged by the tobacco winnowing machine.

[0006] Preferably, the step of determining the material type contained in the waste includes: inputting the waste image into a material recognition model to output a material recognition result of the waste image, the material recognition result including preset material types of multiple material objects and credibility values ​​of the material types; for each material object, comparing the credibility value corresponding to the material object with a preset threshold; and determining the preset material type greater than the preset threshold as the material type contained in the waste.

[0007] Preferably, the first camera assembly includes multiple cameras, each camera capturing waste images of the waste discharged by the tobacco winnowing machine at different shooting angles; wherein the step of determining the types of materials contained in the waste includes: for each camera, determining the types of candidate materials contained in the waste based on the waste images captured by the camera; and determining the sum of the candidate material types corresponding to all cameras as the types of materials contained in the waste.

[0008] Preferably, the material types include at least one of wet tobacco, dry tobacco and stems, wherein the step of adjusting the air volume of the tobacco air separator according to the material types contained in the waste material specifically includes: determining whether the material types contained in the waste material include wet tobacco; if it is determined that the material types contained in the waste material include wet tobacco, generating a first frequency reduction instruction, and sending the first frequency reduction instruction to the tobacco air separator to control the frequency of the tobacco air separator to reduce the set frequency value.

[0009] Preferably, a second camera assembly is provided at the material discharge port of the tobacco air separator, wherein after the frequency of the tobacco air separator is controlled to reduce the set frequency value, it also includes: obtaining from the second camera assembly a material image of the material discharged by the tobacco air separator after the frequency is adjusted, which is captured by the second camera assembly; identifying the material image to determine whether there are wet clumps of tobacco in the material discharged by the tobacco air separator after the frequency is adjusted; if there are wet clumps of tobacco, generating a shutdown control instruction, and sending the shutdown control instruction to the tobacco air separator to control the tobacco air separator to shut down; if there are no wet clumps of tobacco, keeping the frequency of the tobacco air separator unchanged.

[0010] Preferably, the step of adjusting the air volume of the tobacco winnowing machine according to the types of materials contained in the waste material specifically further includes: if it is determined that the types of materials contained in the waste material do not include wet tobacco, determining the amount of dry tobacco and the number of stems contained in the waste material discharged by the tobacco winnowing machine; determining the stem ratio value according to the number of stems and the amount of dry tobacco; and adjusting the air volume of the tobacco winnowing machine according to the stem ratio value and a preset ratio range.

[0011] Preferably, the step of adjusting the air volume of the tobacco air separator according to the stem pick ratio and the preset ratio range specifically includes: determining whether the stem pick ratio is greater than the upper limit of the preset ratio range; if it is greater than the upper limit of the preset ratio range, generating a frequency increase instruction, and sending the frequency increase instruction to the tobacco air separator to control the tobacco air separator to increase the frequency; determining whether the stem pick ratio is less than the lower limit of the preset ratio range; if it is less than the lower limit of the preset ratio range, generating a second frequency reduction instruction, and sending the second frequency reduction instruction to the tobacco air separator to control the tobacco air separator to reduce the frequency; if the stem pick ratio is not less than the lower limit of the preset ratio range and not greater than the upper limit of the preset ratio range, keeping the frequency of the tobacco air separator unchanged.

[0012] In a second aspect, the embodiment of the present application further provides an air volume control device for a tobacco winnowing machine, wherein a first camera assembly is provided at a waste material outlet of the tobacco winnowing machine, and the device comprises:

[0013] An acquisition module, used for acquiring, from the first camera assembly, a waste material image of waste material discharged from the tobacco winnowing machine captured by the first camera assembly;

[0014] The recognition module is used to recognize the waste image and determine whether there are foreign objects in the waste discharged by the tobacco winnowing machine;

[0015] An execution module, for generating a shutdown control instruction if there are foreign objects, and sending the shutdown control instruction to the tobacco winnowing machine to control the tobacco winnowing machine to shut down;

[0016] A judgment module, for determining the type of material contained in the waste material if there is no debris;

[0017] The regulating module is used to adjust the air volume of the tobacco winnowing machine according to the types of materials contained in the waste.

[0018] In a third aspect, an embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the air volume control method of the tobacco air separation machine as described above.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the air volume control method of the tobacco air selection machine are executed.

[0020] The embodiments of the present application provide an air volume control method, device and storage medium for a tobacco winnowing machine, wherein a first camera assembly is provided at a waste material outlet of the tobacco winnowing machine, and an image of waste material discharged by the tobacco winnowing machine is acquired through the first camera assembly, and the waste material image is identified. First, it is determined whether there are foreign objects in the waste material image. If there are foreign objects, a shutdown control instruction is generated to control the tobacco winnowing machine to shut down. If there are no foreign objects, the type of material in the waste is determined, and the air volume of the tobacco winnowing machine is adjusted according to the type of material, thereby controlling the air volume of the tobacco winnowing machine according to the composition of the discharge from the waste material outlet of the tobacco winnowing machine, thereby improving the accuracy of air volume adjustment of the tobacco winnowing machine.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A schematic diagram of the structure of a control system of a tobacco winnowing machine provided in an embodiment of the present application;

[0024] Figure 2 A flow chart of the air volume control method of the tobacco air separator provided in the embodiment of the present application;

[0025] Figure 3 A flow chart of the steps of adjusting the air volume of a tobacco blower according to the type of material provided in an embodiment of the present application;

[0026] Figure 4 A flow chart of a method for adjusting air volume according to the ratio of stems provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of the structure of an air volume control device for a tobacco air separator provided in an embodiment of the present application;

[0028] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0030] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0031] In the prior art, an air classifier is used to screen the impurities in the dried material, thereby separating the tobacco from the impurities. At present, the frequency adjustment of the leaf air classifier in the tobacco production line of the cigarette factory is mostly adjusted according to the relationship between the material flow rate and the wind pressure input to the air classifier. However, since the tobacco contains materials that affect the product quality, such as stems and wet tobacco, it also contains impurities such as plastic, paper, rubber, and feather slices. The weight of each impurity is different, and the negative pressure air volume required to remove each impurity is also different. Therefore, the method of adjusting the negative pressure air volume using the corresponding relationship between material flow and wind pressure has low accuracy.

[0032] In response to the above problems, the embodiments of the present application provide an air volume control method, device and storage medium for a tobacco air separator, which are described below through embodiments.

[0033] To facilitate the understanding of the present application, the technical solution provided by the present application is described in detail below in conjunction with specific embodiments.

[0034] It is understandable that in the tobacco making process of cigarette factories, wind separators are usually used to select tobacco leaves. The wind separation of tobacco leaves here is a process to remove tobacco impurities (such as stems and wet tobacco) and non-tobacco impurities (such as plastic, paper, feathers, rubber slices, etc.) from tobacco. It is the last process in the tobacco making process to improve the purity of the finished tobacco, so it plays an important role in ensuring product quality.

[0035] In actual production, the materials after the drying process enter from the material inlet through the feed conveyor. Under the action of a certain negative pressure, the tobacco is discharged from the material outlet of the air separator, while the sundries, stems, wet tobacco, etc. are discharged from the waste outlet. The tobacco discharged from the material outlet is sent to the next process through the discharge conveyor.

[0036] like Figure 1 , which is a schematic diagram of the structure of a control system of a tobacco winnowing machine provided in an embodiment of the present application. The control system of the tobacco winnowing machine includes an image monitoring device, a tobacco winnowing machine and a server (not shown in the figure).

[0037] The tobacco winnowing machine comprises a material outlet 110 and a waste outlet 120 , and the material discharged from the material outlet 110 is transported by a conveying device 210 . The image monitoring device comprises a first camera assembly 310 and a second camera assembly 320 .

[0038] The first camera assembly 310 is disposed below the waste material outlet 120, and is used to capture waste images of waste materials discharged from the waste material outlet 120. The second camera assembly 320 is disposed above the conveying device 210, and is used to capture material images of materials discharged from the material outlet 110. The first camera assembly 310 and the second camera assembly 320 can be installed through a connecting structure, which is not shown in the figure.

[0039] The tobacco winnowing machine 10 is provided with a material outlet 110, a waste outlet 120 and a material inlet. The tobacco winnowing machine is connected with a negative pressure pipe 140, and the negative pressure pipe 140 is connected with a negative pressure fan 150. The negative pressure air volume of the negative pressure fan 150 can be changed by adjusting the frequency of the negative pressure fan.

[0040] The waste discharge port 120 of the tobacco winnowing machine is generally arranged at the bottom of the machine body, and the first camera assembly 310 can be arranged below the waste discharge port 120 to capture the waste image of the waste discharged from the waste discharge port 120. The waste image here can be an image of the waste falling process or an image of the surface of the waste that has already fallen.

[0041] The material discharge port 110 of the tobacco winnowing machine is generally arranged on one side of the machine body, one end of the conveying device 210 is arranged directly below the material discharge port 110, and the other end of the conveying device 210 can be arranged above the feed port of the processing equipment of the next process, so as to convey the dry tobacco that meets the standards screened by the tobacco winnowing machine to the processing equipment of the next process. The conveying device 210 here can be a conveyor belt. The second camera assembly 320 can be arranged above the conveying device 210. The second camera assembly 320 is used to capture the material image of the material discharged from the material discharge port 110. The material image here can be an image of the upper surface of the material at any section of the conveying device 210, or it can be an image of the process of the material being discharged from the material discharge port 110 and falling to the conveying device 210.

[0042] The image monitoring device here monitors the waste discharge port 120 and uploads the captured waste image to the server. The server can identify the waste image and control the air volume of the tobacco winnowing machine according to the identification result to meet the process standard requirements of the tobacco winnowing process.

[0043] Specifically, the first camera component 310 can take pictures at a preset frequency or at a preset time point and upload them to the server.

[0044] Specifically, the server can Figure 2 A method for controlling the air volume of a tobacco air separator is shown, and the method includes:

[0045] S201. Acquire, from a first camera assembly, a waste material image of waste material discharged from a tobacco winnowing machine captured by the first camera assembly.

[0046] S202: Identify the waste material image to determine whether there are foreign objects in the waste material discharged from the tobacco winnowing machine.

[0047] After receiving the waste image taken by the first camera assembly, the server can input the waste image into a debris recognition model to output a debris recognition result of the waste image, which is used to indicate whether there is debris in the waste discharged by the tobacco winnowing machine.

[0048] The input of the debris recognition model here is the waste image, and the output can be whether there is debris in the waste image. The debris here can include but is not limited to plastic, paper, rubber, feather slices, etc.

[0049] In another embodiment of the present application, the debris recognition model may further output the predicted debris type and the corresponding confidence value of each recognized object in the waste image.

[0050] If any kind of debris exists in the debris identification results output by the debris identification model, it is determined that the waste discharged by the tobacco winnowing machine contains debris.

[0051] S203. If there are foreign objects, a shutdown control instruction is generated and sent to the tobacco winnowing machine to control the tobacco winnowing machine to shut down.

[0052] If it is determined that there are impurities in the waste discharged by the tobacco winnowing machine, a shutdown control command is generated and sent to the tobacco winnowing machine. After receiving the shutdown control command, the tobacco winnowing machine adjusts the frequency of the negative pressure fan to zero, and the tobacco winnowing machine stops working. At the same time, the processing equipment before this process also stops working and empties the current material of the winnowing machine. It is understandable that if there are impurities in the waste, it means that the previous screening or impurity removal process is not thorough, and the current material cannot be used as the material for the next process. Therefore, it is necessary to adjust the previous screening or impurity removal process at the same time.

[0053] S204: If there is no debris, determine the type of material contained in the waste.

[0054] If it is determined that there are no impurities in the waste discharged by the tobacco winnowing machine, it is necessary to determine the material types contained in the waste. The waste image is input into the material recognition model to output the material recognition result of the waste image, and the material recognition result includes the preset material types of multiple material objects and the credibility value of the material type.

[0055] The input of the material recognition model here is the waste image, and the output material recognition result is the preset material type of each material object in the waste image and the credibility value of the material type. For example, for a material object in the waste image, the corresponding material recognition result can be: 1-(wet shredded tobacco, 0.98), where 1 is the serial number used to represent the material object, the wet shredded tobacco is the preset material type of the material object, that is, the material type recognized by the model, and 0.98 is the corresponding credibility value, and the credibility value range is {0, 1}.

[0056] For each material object, the credibility value corresponding to the material object is compared with a preset threshold value, and the preset material types greater than the preset threshold value are determined as the material types included in the waste.

[0057] The preset threshold here can be preset according to the recognition effect of the material recognition model on different types of materials. Different types of materials have different corresponding preset thresholds. Exemplarily, if the material recognition model has a good recognition effect on wet tobacco, the preset threshold corresponding to the wet tobacco can be set to 0.8, and if the material recognition effect on stems is average, the preset threshold corresponding to the stems can be set to 0.6. If the confidence value of the material object with serial number 1 being wet tobacco is 0.98, which is greater than 0.6, then it can be determined that the material object with serial number 1 is wet tobacco. Finally, based on the comparison of the credibility value of each material object with the preset threshold, the result can be that the waste image contains 3 wet tobacco, 4 stems, and 10 tobacco.

[0058] Specifically, the first camera assembly includes multiple cameras, each camera captures the waste image of the waste discharged by the tobacco winnowing machine at different shooting angles; wherein, the step of determining the type of material contained in the waste includes: for each camera, determining the candidate material type contained in the waste based on the waste image captured by the camera, and determining the sum of the candidate material types corresponding to all cameras as the material type contained in the waste.

[0059] It is understandable that, whether it is a debris recognition model or a material recognition model, the input waste material images are multiple sub-images obtained from multiple cameras at different angles, each sub-image covers a part of the surface of the entire material, and the coverage areas of multiple sub-images are not repeated. Therefore, it is necessary to aggregate the recognition results of multiple sub-images into a total debris recognition result or material recognition result.

[0060] S205. Adjust the air volume of the tobacco winnowing machine according to the types of materials contained in the waste.

[0061] The material types here include at least one of wet shredded tobacco, dry shredded tobacco, and stemmed tobacco. Figure 3 As shown, according to the type of materials contained in the waste, the steps of adjusting the air volume of the tobacco blower specifically include:

[0062] S301, determining whether the types of materials contained in the waste include wet shredded tobacco.

[0063] If there is a problem in the previous drying process, there will be wet tobacco clumps in the waste discharged from the waste discharge port. At this time, there must be wet tobacco clumps in the material discharged from the material discharge port, which does not meet the process standards. In step S301, the result that the waste contains wet tobacco clumps will also be obtained.

[0064] S302: If it is determined that the material types included in the waste include wet tobacco, a first frequency reduction instruction is generated, and the first frequency reduction instruction is sent to the tobacco air separator to control the frequency of the tobacco air separator to reduce the set frequency value.

[0065] If it is determined that the waste contains wet tobacco, a first frequency reduction instruction is generated and sent to the tobacco air classifier. The tobacco air classifier reduces the frequency to a set frequency value according to the first frequency reduction instruction to blow the wet tobacco apart and dry it. The set frequency value here is a preset value, which can be set by workshop production personnel based on experience or experimental results, in order to make the wet tobacco become dry tobacco that meets the process standards under the action of negative pressure.

[0066] Furthermore, in order to determine the effectiveness of the above adjustment steps and verify whether the set frequency value can solve the problem of wet clumps of tobacco in the material discharged from the material outlet, it is necessary to set a second camera component at the material outlet of the tobacco air separator. The second camera component here is used to capture the material image of the material discharged from the material outlet. And determine whether the tobacco air separator adjusted to the set frequency value solves the problem of wet clumps of tobacco in the material through the following steps:

[0067] S303. Acquire, from the second camera assembly, a material image of the material discharged by the tobacco winnowing machine after the frequency is adjusted, which is captured by the second camera assembly.

[0068] Specifically, after the tobacco winnowing machine is adjusted to the set frequency value for a period of time, an image of the material out of the material outlet captured by the second camera assembly is obtained.

[0069] S304, identifying the material image to determine whether there are wet clumps of tobacco in the material discharged by the tobacco winnowing machine after adjusting the frequency.

[0070] Specifically, the same material recognition model can be used to recognize the material image. Similar to the step of determining the material type contained in the waste material in step S204, the material type contained in the material image can be determined, and it can be determined whether the material type still includes wet shredded tobacco.

[0071] S305. If there are wet clumps of tobacco, a shutdown control instruction is generated and sent to the tobacco winnowing machine to control the tobacco winnowing machine to shut down.

[0072] If there are still wet clumps of tobacco in the recognition result of the material image, it means that the tobacco air classifier cannot solve the problem of wet clumps of tobacco in the material after adjusting to the set frequency value. At this time, a shutdown control command is generated and sent to the tobacco air classifier. The tobacco air classifier adjusts the frequency to zero according to the shutdown control command, and the tobacco air classifier stops working. At the same time, the processing equipment before and after this process also stops working, and the current material of the air classifier is emptied.

[0073] S306. If there is no wet tobacco mass, the frequency of the tobacco air separator is kept unchanged.

[0074] If there is no wet clump of tobacco in the recognition result of the material image, it means that the tobacco winnowing machine adjusted to the set frequency value has solved the problem of wet clumps of tobacco in the material. At this time, there is no need to adjust the tobacco winnowing machine.

[0075] The embodiment of the present application provides an air volume control method for a tobacco air classifier, wherein a first camera component is provided at the waste material outlet of the tobacco air classifier, and an image of the waste material discharged by the tobacco air classifier is obtained by the first camera group, and the waste material image is identified. First, it is determined whether there are foreign objects in the waste material image. If there are foreign objects, a shutdown control instruction is generated to control the tobacco air classifier to shut down. If there are no foreign objects, the type of material in the waste is determined, and the air volume of the tobacco air classifier is adjusted according to the type of material, so that the air volume of the tobacco air classifier is adjusted according to the composition of the discharge from the waste material outlet of the tobacco air classifier, so that the material outlet of the tobacco air classifier is pure and free of foreign objects, thereby improving the accuracy and timeliness of the air volume adjustment of the tobacco air classifier.

[0076] Furthermore, if it is determined that the types of materials contained in the waste do not include wet tobacco, the amount of dry tobacco and the number of stems contained in the waste discharged by the tobacco winnowing machine are determined, and the stem ratio is determined based on the number of stems and the amount of dry tobacco. The air volume of the tobacco winnowing machine is adjusted based on the stem ratio and the preset ratio range.

[0077] Specifically, the number of dry tobacco shreds and the number of stems can be determined according to the material identification results output by the material identification model. In actual production, the process standards of each brand of tobacco shreds are different, and the stem ratio values ​​of the materials discharged from the waste material outlet are also different. The preset ratio value range here can be set to different preset ratio value ranges according to the production of different brands of tobacco shreds.

[0078] Specifically, when there is no debris and wet tobacco shreds in the material discharged from the waste material outlet, the material discharged from the waste material outlet only contains dry tobacco shreds and stems. At this time, in order to make the material at the material outlet meet the process standards and reduce the waste of materials, the following method can be used: Figure 4 A method for adjusting air volume according to the ratio of stems and sticks, and adjusting the air volume of a tobacco wind separator, the method comprising:

[0079] S401: Determine whether the stem signature ratio value is greater than an upper limit value of a preset ratio value range.

[0080] Here, it is necessary to determine whether the current stem ratio meets the process standard. If the stem ratio is not within the preset ratio range, the frequency of the current tobacco winnowing machine needs to be adjusted. Therefore, it can be first determined whether the stem ratio is greater than the upper limit of the preset ratio range.

[0081] S402, if it is greater than the upper limit of the preset ratio value range, a frequency increase instruction is generated, and the frequency increase instruction is sent to the tobacco winnowing machine to control the tobacco winnowing machine to increase the frequency;

[0082] If the stem ratio is greater than the upper limit of the preset ratio range, it means that the current stem ratio is too large and there are too many stems in the waste, and the negative pressure air volume needs to be increased. Therefore, a frequency increase instruction is generated and sent to the tobacco winnowing machine, and the tobacco winnowing machine increases the frequency according to the frequency increase instruction. Here, the frequency can be increased to a specified frequency value.

[0083] S403: Determine whether the stem signature ratio value is less than a lower limit value of a preset ratio value range.

[0084] If the stem-sign ratio is not greater than the upper limit of the preset ratio value range, it is determined whether the stem-sign ratio is less than the lower limit of the preset ratio value range.

[0085] S404: If the value is less than the lower limit of the preset ratio value range, a second frequency reduction instruction is generated, and the second frequency reduction instruction is sent to the tobacco winnowing machine to control the tobacco winnowing machine to reduce the frequency.

[0086] If the stem ratio is less than the lower limit of the preset ratio range, it means that the current stem ratio is too small and there are too few stems in the waste, and the negative pressure air volume needs to be reduced. Therefore, a second frequency reduction instruction is generated and sent to the tobacco air separator. The tobacco air separator reduces the frequency according to the second frequency reduction instruction.

[0087] S405: If the stem-to-stalk ratio is not less than the lower limit of the preset ratio range and not greater than the upper limit of the preset ratio range, the frequency of the tobacco winnowing machine is kept unchanged.

[0088] If the stem-stick ratio is not less than the lower limit of the preset ratio and not greater than the upper limit of the preset ratio, the stem-stick ratio is within the preset ratio range, indicating that the stem-stick ratio meets the process standard, and the frequency of the tobacco air classifier does not need to be adjusted. This ensures that the material discharged from the material outlet of the tobacco air classifier meets the process standard and improves the accuracy of adjusting the negative pressure air volume.

[0089] The debris recognition model and material recognition model provided in the embodiment of the present application can be trained in the following way:

[0090] Developers can collect a large number of waste images or material images captured by the first camera component and the second camera component at a preset frequency or time.

[0091] Developers use model training software to first perform instance segmentation and image enhancement on the collected image data to form a data set.

[0092] The deep learning algorithm is then used to train the data set. By adjusting parameters including but not limited to epoch, learning rate, batch size, save interval, warm up initial learning rate, warm up steps, learning attenuation rounds, etc., an AI model is generated and the algorithm parameters are continuously adjusted. The pre-trained model can also be imported for transfer learning to accelerate the convergence of the model. Finally, through model evaluation, the fit and generalization of the model meet the recognition accuracy requirements, and the final debris recognition model and material recognition model are obtained.

[0093] Among them, the debris recognition model only recognizes non-tobacco debris and has high accuracy requirements, so FastRcnn, YOLO and other target detection neural networks can be used to train the data set. The material recognition model can recognize the types and quantities of materials such as tobacco, stems and wet tobacco, and can use instance segmentation neural networks including but not limited to MaskRcnn.

[0094] Based on the same inventive concept, an air volume control device for a tobacco air classifier corresponding to the air volume control method for the tobacco air classifier is also provided in the embodiment of the present application. Since the principle of solving the problem by the air volume control device for the tobacco air classifier in the embodiment of the present application is similar to the air volume control method for the tobacco air classifier in the embodiment of the present application, the implementation of the air volume control device for the tobacco air classifier can refer to the implementation of the method, and the repeated parts will not be repeated.

[0095] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of an air volume control device for a tobacco wind separator provided in an embodiment of the present application. Figure 5 As shown in FIG. , the air volume control device 500 includes:

[0096] In a preferred embodiment, it includes:

[0097] An acquisition module 510 is used to acquire, from the first camera assembly, a waste material image of waste material discharged from the tobacco winnowing machine captured by the first camera assembly;

[0098] The identification module 520 is used to identify the waste material image and determine whether there are foreign objects in the waste material discharged by the tobacco winnowing machine;

[0099] The execution module 530 is used to generate a shutdown control instruction if there are foreign objects, and send the shutdown control instruction to the tobacco winnowing machine to control the tobacco winnowing machine to shut down;

[0100] A determination module 540 is used to determine the type of material contained in the waste if there is no debris;

[0101] The regulating module 550 is used to adjust the air volume of the tobacco winnowing machine according to the types of materials contained in the waste.

[0102] In a preferred embodiment, the recognition module 520 is specifically used to: input the waste image into the debris recognition model to output the debris recognition result of the waste image, and the debris recognition result is used to indicate whether there are debris in the waste discharged by the tobacco winnowing machine.

[0103] In a preferred embodiment, the judgment module 540 is specifically used to: input the waste image into a material recognition model to output a material recognition result of the waste image, wherein the material recognition result includes preset material types of multiple material objects and credibility values ​​of the material types; for each material object, compare the credibility value corresponding to the material object with a preset threshold; and determine the preset material type that is greater than the preset threshold as the material type contained in the waste.

[0104] In a preferred embodiment, the first camera assembly includes multiple cameras, each camera capturing waste images of the waste discharged by the tobacco winnowing machine at different shooting angles; wherein the judgment module 540 is also used to: for each camera, determine the candidate material types contained in the waste based on the waste image captured by the camera; and determine the sum of the candidate material types corresponding to all cameras as the material types contained in the waste.

[0105] In a preferred embodiment, the material types include at least one of wet tobacco, dry tobacco and stems, wherein the adjustment module 550 is specifically used to: determine whether the material types contained in the waste include wet tobacco; if it is determined that the material types contained in the waste include wet tobacco, generate a first frequency reduction instruction, and send the first frequency reduction instruction to the tobacco air separator to control the frequency of the tobacco air separator to reduce the set frequency value.

[0106] In a preferred embodiment, the adjustment module 550 is also used to: obtain from the second camera component a material image of the material discharged by the tobacco winnowing machine after the frequency is adjusted, which is captured by the second camera component; identify the material image to determine whether there are wet clumps of tobacco in the material discharged by the tobacco winnowing machine after the frequency is adjusted; if there are wet clumps of tobacco, generate a shutdown control command, and send the shutdown control command to the tobacco winnowing machine to control the shutdown of the tobacco winnowing machine; if there are no wet clumps of tobacco, keep the frequency of the tobacco winnowing machine unchanged.

[0107] In a preferred embodiment, the adjustment module 550 is also used for: if it is determined that the type of material contained in the waste does not include wet tobacco, then determining the amount of dry tobacco and the number of stems contained in the waste discharged by the tobacco winnowing machine; determining the stem ratio value based on the number of stems and the amount of dry tobacco; and adjusting the air volume of the tobacco winnowing machine based on the stem ratio value and a preset ratio range.

[0108] In a preferred embodiment, the adjustment module 550 is also used to: determine whether the stem pick ratio value is greater than the upper limit value of the preset ratio value range; if it is greater than the upper limit value of the preset ratio value range, generate a frequency increase instruction, and send the frequency increase instruction to the tobacco winnowing machine to control the tobacco winnowing machine to increase the frequency; determine whether the stem pick ratio value is less than the lower limit value of the preset ratio value range; if it is less than the lower limit value of the preset ratio value range, generate a second frequency reduction instruction, and send the second frequency reduction instruction to the tobacco winnowing machine to control the tobacco winnowing machine to reduce the frequency; if the stem pick ratio value is not less than the lower limit value of the preset ratio value range and not greater than the upper limit value of the preset ratio value range, keep the frequency of the tobacco winnowing machine unchanged.

[0109] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown in , the electronic device 600 includes a processor 610 , a memory 620 , and a bus 630 .

[0110] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is running, the processor 610 communicates with the memory 620 through the bus 630. When the machine-readable instructions are executed by the processor 610, the steps of the air volume control method of the tobacco air sorting machine in the above-mentioned method embodiment can be executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0111] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the air volume control method of the tobacco air sorting machine mentioned above can be executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0116] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable memory that can be executed by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0117] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for controlling the air volume of a tobacco air separator, characterized in that: A first camera assembly is provided at the waste material outlet of the tobacco winnowing machine, and the method comprises: Acquire, from the first camera assembly, a waste material image of the waste material discharged from the tobacco winnowing machine captured by the first camera assembly; Identifying the waste material image to determine whether there are foreign objects in the waste material discharged by the tobacco winnowing machine; If there are foreign objects, a shutdown control instruction is generated, and the shutdown control instruction is sent to the tobacco winnowing machine to control the tobacco winnowing machine to shut down; If there is no debris, the material type contained in the waste is determined, and the step of determining the material type contained in the waste includes: inputting the waste image into a material recognition model to output a material recognition result of the waste image, wherein the material recognition result includes preset material types of multiple material objects and a credibility value of the material type; for each material object, comparing the credibility value corresponding to the material object with a preset threshold value; and determining the preset material type greater than the preset threshold value as the material type contained in the waste; According to the types of materials contained in the waste materials, the air volume of the tobacco winnowing machine is adjusted; The material type includes at least one of wet shredded tobacco, dry shredded tobacco and stems, wherein the step of adjusting the air volume of the shredded tobacco air separator according to the material type contained in the waste material specifically includes: Determining whether the types of materials contained in the waste include wet shredded tobacco; If it is determined that the type of material contained in the waste material includes wet shredded tobacco, a first frequency reduction instruction is generated, and the first frequency reduction instruction is sent to the shredded tobacco air separator to control the frequency of the shredded tobacco air separator to reduce the set frequency value; If it is determined that the type of material contained in the waste does not include wet tobacco, then determine the number of dry tobacco and the number of stems contained in the waste discharged by the tobacco air classifier; determine the stem ratio according to the number of stems and the number of dry tobacco; determine whether the stem ratio is greater than the upper limit of the preset ratio range; if it is greater than the upper limit of the preset ratio range, generate a frequency increase instruction, and send the frequency increase instruction to the tobacco air classifier to control the tobacco air classifier to increase the frequency; determine whether the stem ratio is less than the lower limit of the preset ratio range; if it is less than the lower limit of the preset ratio range, generate a second frequency reduction instruction, and send the second frequency reduction instruction to the tobacco air classifier to control the tobacco air classifier to reduce the frequency; if the stem ratio is not less than the lower limit of the preset ratio range and not greater than the upper limit of the preset ratio range, keep the frequency of the tobacco air classifier unchanged; A second camera assembly is provided at the material outlet of the tobacco wind separator, wherein after the frequency of the tobacco wind separator is controlled to be reduced to a set frequency value, the method further comprises: Acquire, from the second camera assembly, a material image of the material discharged by the tobacco winnowing machine after the frequency is adjusted, which is captured by the second camera assembly; Identify the material image to determine whether wet shredded tobacco exists in the material discharged by the shredded tobacco winnowing machine after adjusting the frequency; If there is wet clumps of tobacco, a shutdown control instruction is generated, and the shutdown control instruction is sent to the tobacco winnowing machine to control the tobacco winnowing machine to shut down; If there is no wet clump of tobacco, the frequency of the tobacco air classifier is kept unchanged.

2. The method according to claim 1, characterized in that The step of identifying the waste material image and determining whether there are impurities in the waste material discharged by the tobacco winnowing machine includes: The waste material image is input into a debris recognition model to output a debris recognition result of the waste material image, wherein the debris recognition result is used to indicate whether debris exists in the waste material discharged by the tobacco winnowing machine.

3. The method according to claim 1, characterized in that The first camera assembly includes a plurality of cameras, each of which captures waste images of the waste discharged by the tobacco winnowing machine at different shooting angles; The step of determining the type of material contained in the waste material comprises: For each camera, determining the candidate material types contained in the waste based on the waste image captured by the camera; The sum of the candidate material types corresponding to all cameras is determined as the material types contained in the waste.

4. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the air volume control method of the tobacco winnowing machine as claimed in any one of claims 1 to 3 are executed.

Images