Tobacco slicing apparatus control method and device, tobacco slicing apparatus, and storage medium

Abstract

The present disclosure provides a tobacco slicing device control method and device, a tobacco slicing device and a storage medium. The tobacco slicing device control method comprises: collecting quality information of sliced tobacco; obtaining a device key parameter value corresponding to the quality information according to a preset first mapping relationship; and adjusting the parameters of the tobacco slicing device by using the device key parameter value.

Description

Technical Field

[0001] This disclosure relates to the field of tobacco processing, and in particular to a method and apparatus for controlling a tobacco slicing device, a tobacco slicing device, and a storage medium. Background Technology

[0002] In cigarette manufacturing lines, after the raw materials such as re-dried tobacco leaves and flakes are opened, the first process is generally slicing. The slicing machine cuts the tobacco blocks into multiple flakes through several steps, including measuring and conveying the tobacco bales, compacting the tobacco blocks, lowering the cutting blade, and placing the flakes. These flakes are then sent to the next process for further loosening and rehydration, resulting in loose tobacco flakes with the required temperature and moisture content. Therefore, the quality of the slicing determines the overall quality of the entire production line and the entire batch, directly affecting the overall quality of the material throughout the entire process.

[0003] The quality of the finished product is primarily based on the quality of the tobacco flakes. Currently, the industry mainly relies on workers visually assessing the quality of tobacco flake slices, and then adjusting the slicing machine based on their experience. Summary of the Invention

[0004] The inventors noted that in related technologies, the current industry standard for slicing tobacco sheets mainly relies on visual inspection by workers, who then adjust the slicing machine based on their experience. Therefore, it is impossible to effectively guarantee the slicing quality of tobacco sheets.

[0005] Accordingly, this disclosure provides a control scheme for a tobacco slicing equipment, which can automatically adjust the parameters of the tobacco slicing equipment based on the quality information of the sliced ​​tobacco, thereby effectively ensuring the slicing quality of the tobacco.

[0006] In a first aspect of this disclosure, a method for controlling a tobacco slicing device is provided, comprising: collecting quality information of sliced ​​tobacco sheets; obtaining key parameter values ​​of the device corresponding to the quality information according to a preset first mapping relationship; and adjusting the parameters of the tobacco slicing device using the key parameter values ​​of the device.

[0007] In some embodiments, collecting quality information of the cut tobacco sheets includes: collecting the quality information using at least one of image recognition method, microwave detection method, laser detection method, hyperspectral detection method, and ion diffusion method.

[0008] In some embodiments, acquiring the quality information using an image recognition method includes: acquiring an image of the tobacco sheet; and performing recognition processing on the image of the tobacco sheet to obtain the quality information.

[0009] In some embodiments, acquiring images of the smoke sheet includes acquiring images of the smoke sheet using at least one of an industrial camera, an industrial video camera, an infrared camera, an infrared thermal imager, a spectrometer, and a scanner.

[0010] In some embodiments, the image recognition processing of the tobacco sheet includes: performing image segmentation processing on the image of the tobacco sheet to obtain a segmented image; extracting features from the segmented image; and processing the features of the segmented image using a trained machine learning model to obtain the quality information.

[0011] In some embodiments, image segmentation processing of the tobacco sheet image includes: performing image segmentation processing on the tobacco sheet image using at least one of a threshold segmentation algorithm, a geometric feature-based segmentation algorithm, a template matching algorithm, and a compressed sensing-based segmentation algorithm.

[0012] In some embodiments, extracting features from the segmented image includes: extracting features from the segmented image using at least one of a region feature extraction algorithm, a grayscale feature extraction algorithm, a contour feature extraction algorithm, and a phase consistency-based feature extraction algorithm.

[0013] In some embodiments, the quality information includes the slice thickness information of the tobacco sheet; the first mapping relationship includes the interaction between the slice thickness information of the tobacco sheet and key equipment parameters.

[0014] In some embodiments, obtaining the key equipment parameter values ​​associated with the quality information includes: obtaining the corresponding key equipment parameter values ​​through the first mapping relationship based on the slice thickness information of the tobacco sheet.

[0015] In some embodiments, it is determined whether the slice thickness information of the tobacco sheet is within a preset range; if the slice thickness information of the tobacco sheet is not within the preset range, an alarm is triggered.

[0016] In some embodiments, the quality information includes information about foreign objects in the tobacco sheet; the method further includes: identifying the location of the foreign object; and grasping and removing the foreign object.

[0017] In some embodiments, an alarm is triggered based on the foreign object information; and auxiliary handling information associated with handling the foreign object is presented.

[0018] In some embodiments, before slicing the tobacco pack to obtain tobacco slices, tobacco pack information is collected; according to a preset second mapping relationship, a set of slicing equipment control parameters corresponding to the tobacco pack information is obtained; and the tobacco slicing equipment is configured with parameters using the set of slicing equipment control parameters.

[0019] In some embodiments, collecting cigarette pack information includes: reading barcode information set on the cigarette pack to obtain the cigarette pack information.

[0020] In some embodiments, monitoring information of a target component in the tobacco slicing equipment is acquired; the monitoring information of the target component is processed to determine whether the target component is faulty; if the target component is faulty, a maintenance strategy corresponding to the fault is acquired according to a preset third mapping relationship; and the tobacco slicing equipment is automatically maintained online using the maintenance strategy.

[0021] In some embodiments, obtaining monitoring information of a target component in the tobacco slicing device includes: obtaining monitoring information of the target component through image monitoring or target component status monitoring.

[0022] In some embodiments, target component status monitoring includes at least one of vibration monitoring, noise monitoring, and current monitoring of the target component.

[0023] In some embodiments, auxiliary maintenance information associated with the maintenance strategy is presented.

[0024] In a second aspect of this disclosure, a tobacco slicing equipment control device is provided, comprising: a first processing module configured to collect quality information of sliced ​​tobacco sheets; a second processing module configured to obtain key equipment parameter values ​​corresponding to the quality information according to a preset first mapping relationship; and a third processing module configured to adjust the parameters of the tobacco slicing equipment using the key equipment parameter values.

[0025] In a third aspect of this disclosure, a tobacco slicing equipment control device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute instructions stored in the memory to implement the method as described in any of the above embodiments.

[0026] In a fourth aspect of this disclosure, a tobacco slicing apparatus is provided, including a tobacco slicing apparatus control device as described in any of the above embodiments.

[0027] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method as described in any of the above embodiments.

[0028] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic flowchart of a tobacco slicing equipment control method according to an embodiment of the present disclosure;

[0031] Figure 2 This is a schematic flowchart of a tobacco slicing equipment control method according to another embodiment of the present disclosure;

[0032] Figure 3 This is a schematic flowchart illustrating a tobacco slicing equipment control method according to yet another embodiment of the present disclosure;

[0033] Figure 4 This is a schematic diagram of the structure of a tobacco slicing equipment control device according to an embodiment of the present disclosure;

[0034] Figure 5 This is a schematic diagram of the structure of a tobacco slicing equipment control device according to another embodiment of the present disclosure;

[0035] Figure 6 This is a schematic diagram of the structure of a tobacco slicing apparatus according to an embodiment of the present disclosure. Detailed Implementation

[0036] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0037] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0038] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0039] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0040] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0041] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0042] Figure 1 This is a schematic flowchart illustrating a tobacco slicing equipment control method according to an embodiment of the present disclosure. In some embodiments, the following tobacco slicing equipment control method is executed by a tobacco slicing equipment control device.

[0043] In step 101, the quality information of the cut tobacco sheets is collected.

[0044] For example, the quality information of tobacco sheets includes slice thickness information. Slice thickness information is used to determine whether the slice thickness is uneven, whether there are trapezoidal tobacco sheets, whether the tobacco sheets are not in blocks or are stacked, etc. Another example is that the quality information of tobacco sheets also includes information on foreign objects, such as non-tobacco debris, tobacco insects, and Penicillium mold.

[0045] In some embodiments, quality information is acquired using at least one of image recognition methods, microwave detection methods, laser detection methods, hyperspectral detection methods, and ion diffusion methods.

[0046] In some embodiments, images of tobacco sheets are acquired and processed for identification to obtain quality information.

[0047] In some embodiments, images of the smoke sheet are acquired using at least one of an industrial camera, an industrial video camera, an infrared camera, an infrared thermal imager, a spectrometer, and a scanner.

[0048] In some embodiments, the image recognition processing of tobacco sheets includes the following steps:

[0049] 1) Perform image segmentation processing on the image of the tobacco sheet to obtain a segmented image.

[0050] For example, image segmentation processing of tobacco flake images can be performed using at least one of threshold segmentation algorithms, geometric feature-based segmentation algorithms, template matching algorithms, and compressed sensing-based segmentation algorithms.

[0051] 2) Extract features from the segmented image.

[0052] For example, features of the segmented image can be extracted using at least one of the following: region feature extraction algorithm, grayscale feature extraction algorithm, contour feature extraction algorithm, and phase consistency-based feature extraction algorithm.

[0053] 3) Use a trained machine learning model to process the features of the segmented image to obtain quality information.

[0054] For example, image segmentation is performed on the sample image to obtain segmented images. Features are extracted from the segmented images to obtain a sample feature set. The sample feature set is then used to train a machine learning model so that the trained machine learning model can identify quality defects in tobacco sheets.

[0055] In step 102, the key parameter values ​​of the equipment corresponding to the quality information are obtained according to the preset first mapping relationship.

[0056] It should be noted that, based on historical data obtained from online detection technology, preliminary analysis was conducted using scatter plots, regression analysis, and correlation analysis to analyze the interaction between slice thickness anomalies and various key parameters. This establishes a mapping relationship between the post-slicing quality database and the equipment's key parameter experience base.

[0057] For example, the post-cutting quality database includes issues related to slice thickness: the thickness difference between different tobacco slices is greater than 7cm, the thickness difference between the two ends of a single tobacco slice in the feeding and discharging directions exceeds 5%, and the thickness of a single tobacco slice is less than the benchmark value of 3cm.

[0058] In step 103, the parameters of the tobacco slicing equipment are adjusted using the key parameter values ​​of the equipment.

[0059] For example, key parameters include at least one of the following: pusher plate pushing speed, bottom belt speed, compaction block pressure, compaction time, cutting speed, pallet unloading delay time, baffle plate retraction distance during cutting, baffle plate retraction distance during unloading, and unloading smoke block gap.

[0060] For example, when the quality information includes the slice thickness of the tobacco sheet, the first mapping relationship includes the interaction between the slice thickness information and the key equipment parameters. In this case, the corresponding key equipment parameter values ​​are obtained based on the slice thickness information of the tobacco sheet through the first mapping relationship.

[0061] In other words, when the slice thickness of the tobacco sheet does not meet the preset conditions, fine-tuning parameters for the relevant parameters of the slicing equipment are obtained through the first mapping relationship. These fine-tuning parameters are then used to adjust the slicing equipment so that the slice thickness of the tobacco sheet meets the preset conditions.

[0062] In some embodiments, the thickness information of the tobacco slices is determined to be within a preset range. If the thickness information of the tobacco slices is not within the preset range, an alarm is triggered to promptly remind the staff.

[0063] In some embodiments, where the quality information includes information about foreign objects in the tobacco sheet, the tobacco slicing equipment control method further identifies the location of the foreign object in order to grasp and remove it.

[0064] For example, the grasping and removal of foreign objects includes grasping non-smoking debris and removing tobacco insects and Penicillium tobacco leaves.

[0065] For example, the location of foreign objects can be determined by using photocells at the position of the smoke sheet and information such as the speed of the conveyor belt.

[0066] In some embodiments, an alarm is triggered based on foreign object information, and auxiliary handling information associated with handling the foreign object is presented to provide staff with supplementary suggestions. Staff can then use this auxiliary handling information to perform a series of actions such as reporting, cutting off material, intercepting, suspending operations, cleaning, and restoring the system.

[0067] In the tobacco slicing equipment control method provided in the above embodiments of this disclosure, by collecting the quality information of the sliced ​​tobacco sheets, obtaining the key equipment parameter values ​​corresponding to the quality information according to the mapping relationship, and using the key equipment parameter values ​​to adjust the parameters of the tobacco slicing equipment, the slicing quality of the tobacco sheets can be effectively guaranteed.

[0068] Figure 2 This is a schematic flowchart illustrating a tobacco slicing equipment control method according to an embodiment of the present disclosure. In some embodiments, the following tobacco slicing equipment control method is executed by a tobacco slicing equipment control device.

[0069] In step 201, before slicing the tobacco pack to obtain tobacco slices, the tobacco pack information is collected.

[0070] It should be noted that raw material information includes raw material type and tobacco leaf characteristics. Raw material types include tobacco leaves, flakes, etc. Tobacco leaf characteristics include origin, year, grade, etc. During the slicing process, because the type and characteristics of the raw material are strongly correlated with its friction, viscosity, and looseness, the slicing equipment needs to be configured accordingly based on the raw material.

[0071] In some embodiments, information about the cigarette pack is obtained by reading barcode information, such as barcodes or QR codes, set on the pack.

[0072] In step 202, according to the preset second mapping relationship, the set of control parameters of the slicing equipment corresponding to the tobacco package information is obtained.

[0073] It should be noted that by analyzing the interaction between the information of each tobacco pack and the slice thickness anomaly, an experience library of pre-configured characteristic parameter benchmark ranges most suitable for the slicing equipment is established, thereby obtaining the mapping relationship between each tobacco pack and the optimal auxiliary pre-configured control parameter set.

[0074] For example, the information obtained from the scan includes details about Yunnan and Guizhou tobacco leaves, upper tobacco leaves, and tobacco leaves aged for 3 years. Since these tobacco leaves have characteristics such as high viscosity and strong elasticity, the control parameters of the tobacco bale are adjusted appropriately based on experience, including adjusting the cutting speed and compaction pressure, to achieve optimal slice quality per bale.

[0075] In some embodiments, the control parameter set of each tobacco pack slicing equipment includes at least one of the following: pusher plate pushing speed, bottom belt speed, compaction block pressure, compaction time, cutting speed, tray unloading delay time, baffle plate retraction distance during cutting, baffle plate retraction distance during unloading, and unloading tobacco block gap, etc.

[0076] In step 203, the parameters of the tobacco slicing equipment are configured using the slicing equipment control parameter set.

[0077] For example, by combining the position indication of the photoelectric tube on the tobacco pack on the preparation conveyor belt, the parameter set of each formula tobacco pack is integrated according to the position order and running progress to form a total parameter pre-configuration sheet, which is then pushed to the system or directly sent to the slicing equipment.

[0078] In some embodiments, the relevant parameters are corrected online based on the thickness detection results of the cut tobacco sheets to obtain tobacco sheets that meet the thickness requirements. For example, if the thickness difference between different tobacco sheets is greater than 7 cm, the thickness difference between the two ends of a single tobacco sheet in the feeding and discharging direction exceeds 5%, or the thickness of a single tobacco sheet is less than the reference value of 3 cm, then the parameters are corrected online to obtain tobacco sheets that meet the thickness requirements.

[0079] In some embodiments, historical tobacco sheet quality data is analyzed using tools such as scatter plots, regression analysis, and correlation analysis, so as to continuously update and iterate the pre-configured experience base of characteristic parameter benchmark ranges in order to obtain high-quality tobacco sheets.

[0080] Figure 3 This is a schematic flowchart illustrating a tobacco slicing equipment control method according to another embodiment of the present disclosure. In some embodiments, the following tobacco slicing equipment control method is executed by a tobacco slicing equipment control device.

[0081] In step 301, monitoring information of the target component in the tobacco slicing equipment is obtained.

[0082] It should be noted that the condition of key components of the slicing equipment, such as the cutter assembly, pusher assembly, tray assembly, and encoder, directly affects the slicing quality and ensures the effectiveness of the equipment's operation. Therefore, monitoring the condition of these core components ensures the quality of the tobacco sheets.

[0083] For example, core components include at least one of the following: cutter (blade edge), pusher plate, bottom belt, baffle plate, pallet plate, compaction block, rotary encoder, etc.

[0084] In some embodiments, monitoring information of the target component is obtained through image monitoring or target component status monitoring.

[0085] For example, target component condition monitoring includes at least one of vibration monitoring, noise monitoring, and current monitoring of the target component.

[0086] In step 302, the monitoring information of the target component is identified and processed to determine whether the target component has a fault.

[0087] For example, image monitoring can be performed by using at least one of an industrial camera, an industrial video camera, an infrared camera, an infrared thermal imager, a spectrometer, or a scanner.

[0088] Next, at least one of the following algorithms is used to segment the surveillance image: threshold segmentation algorithm, geometric feature-based segmentation algorithm, template matching algorithm, or compressed sensing-based segmentation algorithm.

[0089] Then, at least one of the following algorithms—region feature extraction algorithm, grayscale feature extraction algorithm, contour feature extraction algorithm, and phase consistency-based feature extraction algorithm—is used to extract features from the segmented image to obtain a feature set. A trained machine learning model is then used to process the feature set to identify whether the target component has a fault.

[0090] For example, image segmentation is performed on the sample image to obtain segmented images. Features are extracted from the segmented images to obtain a sample feature set. The sample feature set is then used to train a machine learning model so that the trained machine learning model can identify defects in the target component.

[0091] In step 303, if the target component is faulty, a maintenance strategy corresponding to the fault is obtained according to a preset third mapping relationship.

[0092] For example, the faults include at least one of the following: the cutter is not sharp, the cutter is tilted, the compaction pressure is too high or too low, the pusher plate is tilted, the pusher plate is out of sync, the encoder of the baffle plate is drifting at zero point, the baffle plate is tilted, the unloading gap is too small, the unloading time is too short, etc.

[0093] For example, the third mapping relationship includes the relationship between fault information and maintenance strategies. The maintenance strategy corresponding to a specified fault can be obtained through the third mapping relationship.

[0094] In some embodiments, historical data are analyzed using scatter plots, regression analysis, correlation analysis, and other methods to analyze the interaction between slice thickness anomalies and various faults. That is, a mapping relationship is established between post-slicing quality data and faults.

[0095] In step 304, the tobacco slicing equipment is automatically maintained online using a maintenance strategy to obtain tobacco slices that meet quality requirements.

[0096] For example, online automatic maintenance includes at least one of the following: online initiation of the belt sander's blade sharpening and dust collection process, initiation of an action process to increase the pressure of the automatic pressure regulating valve in the compaction air circuit by 5%, initiation of an action process to extend the unloading time by 5%, and an action process to accelerate or reduce the speed of the single-sided pusher plate by 5%, etc.

[0097] In some embodiments, auxiliary maintenance information associated with maintenance strategies is presented to provide staff with helpful tips and prompts.

[0098] For example, auxiliary maintenance information includes at least one of the following: prompts for sharpening the blade and its maintenance steps, prompts for cutting blade tilt and its maintenance steps, prompts for excessive or insufficient compaction pressure and its maintenance steps, prompts for adjusting the pusher plate tilt and its maintenance steps, prompts for adjusting pusher plate asynchrony and its maintenance steps, prompts for zero-point drift of the baffle plate encoder and its maintenance steps, prompts for adjusting the unloading gap and its maintenance steps, etc.

[0099] Figure 4 This is a schematic diagram of the structure of a tobacco slicing equipment control device according to an embodiment of this disclosure. Figure 4 As shown, the tobacco slicing equipment control device includes a first processing module 41, a second processing module 42, and a third processing module 43.

[0100] The first processing module 41 is configured to collect quality information of the cut tobacco sheets.

[0101] In some embodiments, the first processing module 41 uses at least one of image recognition method, microwave detection method, laser detection method, hyperspectral detection method and ion diffusion method to collect quality information.

[0102] In some embodiments, the first processing module 41 acquires images of tobacco sheets and performs recognition processing on the images to obtain quality information.

[0103] In some embodiments, the first processing module 41 acquires images of the smoke sheet using at least one of an industrial camera, an industrial video camera, an infrared camera, an infrared thermal imager, a spectrometer, and a scanner.

[0104] In some embodiments, the first processing module 41 performs image recognition processing on the tobacco sheet, including the following steps:

[0105] 1) Perform image segmentation processing on the image of the tobacco sheet to obtain a segmented image.

[0106] For example, image segmentation processing of tobacco flake images can be performed using at least one of threshold segmentation algorithms, geometric feature-based segmentation algorithms, template matching algorithms, and compressed sensing-based segmentation algorithms.

[0107] 2) Extract features from the segmented image.

[0108] For example, features of the segmented image can be extracted using at least one of the following: region feature extraction algorithm, grayscale feature extraction algorithm, contour feature extraction algorithm, and phase consistency-based feature extraction algorithm.

[0109] 3) Use a trained machine learning model to process the features of the segmented image to obtain quality information.

[0110] The second processing module 42 is configured to obtain the key parameter values ​​of the equipment corresponding to the quality information according to the preset first mapping relationship.

[0111] The third processing module 43 is configured to adjust the parameters of the tobacco slicing equipment using key parameter values.

[0112] In some embodiments, the third processing module 43 determines whether the slice thickness information of the tobacco sheet is within a preset range. If the slice thickness information of the tobacco sheet is not within the preset range, an alarm is triggered to promptly remind the staff.

[0113] In some embodiments, where the quality information includes information about foreign objects in the tobacco sheet, the third processing module 43 identifies the location of the foreign object in order to capture and remove it.

[0114] In some embodiments, the third processing module 43 performs alarm processing based on foreign object information and presents auxiliary handling information associated with handling the foreign object in order to provide staff with auxiliary suggestions.

[0115] In some embodiments, before slicing the tobacco pack to obtain tobacco slices, the first processing module 41 collects tobacco pack information.

[0116] In some embodiments, the first processing module 41 obtains cigarette pack information by reading barcode information, such as barcode or QR code information, set on the cigarette pack.

[0117] The second processing module 42 obtains the set of slicing equipment control parameters corresponding to the tobacco package information according to the preset second mapping relationship.

[0118] The third processing module 43 configures the parameters of the tobacco slicing equipment using the slicing equipment control parameter set.

[0119] In some embodiments, the first processing module 41 acquires monitoring information of the target component in the tobacco slicing device.

[0120] In some embodiments, monitoring information of the target component is obtained through image monitoring or target component status monitoring.

[0121] For example, target component condition monitoring includes at least one of vibration monitoring, noise monitoring, and current monitoring of the target component.

[0122] The second processing module 42 identifies and processes the monitoring information of the target component to determine whether the target component has a fault.

[0123] For example, the second processing module 42 performs image monitoring by using at least one of an industrial camera, an industrial video camera, an infrared camera, an infrared thermal imager, a spectrometer, and a scanner.

[0124] Next, the second processing module 42 uses at least one of the following: threshold segmentation algorithm, geometric feature-based segmentation algorithm, template matching algorithm, or compressed sensing-based segmentation algorithm to perform image segmentation processing on the monitoring image.

[0125] Then, the second processing module 42 uses at least one of the following algorithms to extract features from the segmented image: region feature extraction algorithm, grayscale feature extraction algorithm, contour feature extraction algorithm, and phase consistency-based feature extraction algorithm, to obtain a feature set. The trained machine learning model is then used to process the feature set to identify whether the target component has a fault.

[0126] When a target component malfunctions, the third processing module 43 obtains a maintenance strategy corresponding to the malfunction based on a preset third mapping relationship, and uses the maintenance strategy to perform online automatic maintenance on the tobacco slicing equipment in order to obtain tobacco slices that meet quality requirements.

[0127] In some embodiments, the third processing module 43 presents auxiliary maintenance information associated with the maintenance strategy in order to provide staff with auxiliary prompts.

[0128] Figure 5 This is a schematic diagram of the structure of a tobacco slicing equipment control device according to another embodiment of this disclosure. Figure 5 As shown, the tobacco slicing equipment control device includes a memory 51 and a processor 52.

[0129] Memory 51 is used to store instructions, and processor 52 is coupled to memory 51. Processor 52 is configured to execute instructions based on memory storage, as shown in the example below. Figure 1-3 The method involved in any of the embodiments.

[0130] like Figure 5As shown, the tobacco slicing equipment control device also includes a communication interface 53 for information exchange with other devices. Additionally, the tobacco slicing equipment control device includes a bus 54, through which the processor 52, communication interface 53, and memory 51 communicate with each other.

[0131] The memory 51 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive. The memory 51 may also be a memory array. The memory 51 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0132] Furthermore, processor 52 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present disclosure.

[0133] This disclosure also relates to a computer-readable storage medium storing computer instructions that, when executed by a processor, implement... Figure 1-3 The method involved in any of the embodiments.

[0134] Figure 6 This is a schematic diagram of the structure of a tobacco slicing apparatus according to an embodiment of this disclosure. Figure 6 As shown, the tobacco slicing equipment 61 includes a tobacco slicing equipment control device 62. The tobacco slicing equipment control device 62 is... Figure 4 or Figure 5 The tobacco slicing equipment control device involved in any of the embodiments.

[0135] In some embodiments, this disclosure also provides an intelligent equipment adjustment scheme targeting slice quality, namely an intelligent equipment adjustment scheme based on the coupling of post-slice tobacco slice quality, incoming material information, and equipment fault detection information.

[0136] For example, the mass A of the cut tobacco sheets is shown in the following formula.

[0137]

[0138] Where i represents the quality category number of the cut tobacco sheet, j represents the cause category number of the cause of the cut tobacco sheet quality, ψ represents the weight of the cause of the cause of the cut tobacco sheet quality, f represents the cause of the cause of the cut tobacco sheet quality, x represents the parameter cause, y represents the foreign object removal cause, and z represents the equipment failure cause, where x = u + v, u represents the key parameter, and v represents the pre-configured parameter.

[0139] For example, the weights of each cause can be determined based on historical data.

[0140] In some embodiments, the corresponding treatment measure B satisfies the following formula.

[0141]

[0142] Where u represents key parameter adjustment, v represents pre-configured parameter adjustment, w represents foreign object rejection number, and r represents equipment fault repair.

[0143] In some embodiments, the key parameter u is adjusted to satisfy:

[0144]

[0145] Where h represents the key parameter category number, and based on the key parameter experience base, for non-key parameter reasons, u = 0.

[0146] In some embodiments, the pre-configured parameter adjustment v satisfies:

[0147]

[0148] Where m represents the parameter type number. Based on the pre-configured parameter experience base, for non-pre-configured parameter reasons, v = 0.

[0149] In some embodiments, the foreign object removal number w satisfies:

[0150]

[0151] Where k represents the foreign object removal category number.

[0152] k takes values ​​of 1, 2, and 3, corresponding to non-smoke debris, smoke insects, and Penicillium smoke. This follows the foreign matter handling procedure based on process quality control requirements.

[0153] W1 indicates that the rejection device has been activated to remove non-smoke debris, triggering an alarm and providing auxiliary handling information. Shift leaders, process engineers, section chiefs, operators, and other personnel at all levels can then perform a series of actions based on the auxiliary handling information, including reporting, cutting off material, intercepting, suspending operations, cleaning, and restoring.

[0154] W2 and W3—When tobacco insects or Penicillium mold are detected, an alarm is triggered, and auxiliary process handling information is displayed. Shift leaders, process engineers, section chiefs, operators, and other personnel at all levels follow the auxiliary handling information to perform a series of actions, including reporting, cutting off material, intercepting, suspending operations, cleaning, and restoring.

[0155] In some embodiments, equipment fault repair r satisfies:

[0156]

[0157] Where l represents the parameter type number.

[0158] For example, based on the fault database and maintenance database, auxiliary maintenance methods and operating standards can be pushed out separately, or online automatic adjustments can be triggered. If the cause is not equipment failure, then r = 0.

[0159] By implementing the above embodiments of this disclosure, the following beneficial effects can be obtained:

[0160] 1. Achieve intelligent online feedback and parameter-assisted adjustment for stand-alone machines based on physical quantities;

[0161] 2. Implement equipment fault monitoring, feedback, and online maintenance based on physical quality;

[0162] 3. Implement an experience base of pre-configured parameters based on incoming material status information, with each cigarette pack as the granularity;

[0163] 4. Implement an online detection method that couples post-cut tobacco sheet quality inspection with fault monitoring of core equipment components;

[0164] 5. Online parameter adjustment and online component maintenance provide dual assistance, improving the real-time nature of quality control, the systematic nature of operation and maintenance, and reducing the risk of foreign objects.

[0165] In some embodiments, the functional units described above may be implemented as general-purpose processors, programmable logic controllers (PLCs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any suitable combination thereof for performing the functions described herein.

[0166] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0167] The description in this disclosure is provided for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the disclosure to its forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of this disclosure and to enable those skilled in the art to understand this disclosure and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A method for controlling a tobacco slicing device, comprising: Collect quality information of the cut tobacco sheets, wherein the quality information includes the slice thickness information of the tobacco sheets and the information of foreign objects in the tobacco sheets; According to a preset first mapping relationship, the key equipment parameter values ​​corresponding to the quality information are obtained. The first mapping relationship includes the mutual influence relationship between the slice thickness information of the tobacco sheet and the key equipment parameters. According to the slice thickness information of the tobacco sheet, the corresponding key equipment parameter values ​​are obtained through the first mapping relationship. The parameters of the tobacco slicing equipment are adjusted using the key parameter values ​​of the equipment. Determine whether the slice thickness information of the tobacco sheet is within a preset range; If the slice thickness information of the tobacco sheet is not within the preset range, an alarm will be triggered. Identify the location of the foreign object; Grasp and remove the foreign objects; An alarm will be triggered based on the foreign object information. Present auxiliary handling information associated with the handling of the foreign object.

2. The method according to claim 1, wherein, The quality information collected after slicing the tobacco leaves includes: The quality information is acquired using at least one of the following methods: image recognition, microwave detection, laser detection, hyperspectral detection, and ion diffusion.

3. The method according to claim 2, wherein, The quality information acquired using image recognition methods includes: Acquire images of the tobacco sheet; The image of the tobacco sheet is processed for recognition to obtain the quality information.

4. The method according to claim 3, wherein, The images of the tobacco sheet were acquired including: Images of the smoke sheet are acquired using at least one of an industrial camera, an industrial video camera, an infrared camera, an infrared thermal imager, a spectrometer, and a scanner.

5. The method according to claim 3, wherein, Image recognition processing of the tobacco sheet includes: The image of the tobacco sheet is subjected to image segmentation processing to obtain a segmented image; Extract features from the segmented image; The features of the segmented image are processed using a trained machine learning model to obtain the quality information.

6. The method according to claim 5, wherein, Image segmentation processing of the image of the tobacco sheet includes: The image of the tobacco sheet is segmented using at least one of the following algorithms: threshold segmentation algorithm, geometric feature-based segmentation algorithm, template matching algorithm, and compressed sensing-based segmentation algorithm.

7. The method according to claim 5, wherein, Extracting features from the segmented image includes: The features of the segmented image are extracted using at least one of the following algorithms: region feature extraction algorithm, grayscale feature extraction algorithm, contour feature extraction algorithm, and phase consistency-based feature extraction algorithm.

8. The method according to claim 1, further comprising: Before slicing the tobacco pack to obtain tobacco slices, the tobacco pack information is collected. According to the preset second mapping relationship, obtain the set of slicing equipment control parameters corresponding to the tobacco package information; The tobacco slicing equipment is configured with parameters using the control parameter set of the slicing equipment.

9. The method according to claim 8, wherein, The information collected from the cigarette packs includes: Read the barcode information set on the cigarette pack to obtain the cigarette pack information.

10. The method according to any one of claims 1-9, further comprising: Acquire monitoring information of the target components in the tobacco slicing equipment; The monitoring information of the target component is identified and processed to determine whether the target component is faulty; If the target component is faulty, a maintenance strategy corresponding to the fault is obtained according to a preset third mapping relationship; The aforementioned maintenance strategy is used to perform online automatic maintenance on the tobacco slicing equipment.

11. The method according to claim 10, wherein, Acquiring monitoring information of the target components in the tobacco slicing equipment includes: Monitoring information of the target component is obtained through image monitoring or target component status monitoring.

12. The method according to claim 11, wherein, Target component status monitoring includes at least one of vibration monitoring, noise monitoring, and current monitoring of the target component.

13. The method of claim 10, further comprising: Present auxiliary maintenance information associated with the maintenance strategy.

14. A control device for a tobacco slicing machine, comprising: The first processing module is configured to collect quality information of the cut tobacco sheets, wherein the quality information includes the slice thickness information of the tobacco sheets and the information of foreign objects in the tobacco sheets; The second processing module is configured to obtain the equipment key parameter values ​​corresponding to the quality information according to a preset first mapping relationship, wherein the first mapping relationship includes the mutual influence relationship between the slice thickness information of the tobacco sheet and the equipment key parameters, and obtain the corresponding equipment key parameter values ​​according to the slice thickness information of the tobacco sheet through the first mapping relationship. The third processing module is configured to adjust the parameters of the tobacco slicing equipment using the key parameter values ​​of the equipment. The fourth processing module is configured to determine whether the slice thickness information of the tobacco sheet is within a preset range. If the slice thickness information of the tobacco sheet is not within the preset range, an alarm is triggered. The fifth processing module is configured to identify the location of the foreign object, grasp and remove the foreign object, perform alarm processing based on the foreign object information, and present auxiliary handling information related to the processing of the foreign object.

15. A control device for tobacco slicing equipment, comprising: Memory; A processor, coupled to a memory, configured to implement the method as described in any one of claims 1-13 based on memory-stored instruction execution.

16. A tobacco slicing apparatus, comprising the tobacco slicing apparatus control device as described in claim 14 or 15.

17. A computer-readable storage medium, wherein, A computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method as described in any one of claims 1-13.

Images