Real-time monitoring and early warning method and system for key impurities based on photoelectric impurity removal of tobacco lamina

Abstract

The invention relates to the field of tobacco impurity removal, and provides a key impurity real-time monitoring and early warning method and system based on tobacco strip photoelectric impurity removal. Firstly, tobacco leaves are scanned, images are collected, and high-quality tobacco leaf images are obtained. Secondly, whether sundries exist in the tobacco leaf image or not is judged, and if yes, the tobacco leaf image serves as a sundry image; and thirdly, caching continuous multi-segment sundry images, splicing the continuous multi-segment sundry images into a complete sundry image through timestamps, and uploading the complete sundry image to an upper industrial personal computer. Fourthly, the upper industrial personal computer monitors the complete sundry image in real time, the image is displayed on a statistical billboard, key sundry is recognized based on an AI classification algorithm, whether the sundry belongs to the key sundry or not is judged, and if the sundry belongs to the key sundry, a sound-light alarm is given out. According to the invention, real-time monitoring and early warning of key impurities are realized, and the technical problem that in the prior art, tobacco leaf impurity removal is in a black box state and impurity information cannot be visually processed is solved.

Description

Technical Field

[0001] The invention relates to the field of tobacco impurity removal, and in particular to a real-time monitoring and early warning method and system for key impurities based on photoelectric impurity removal of tobacco sheets. Background Art

[0002] In the field of tobacco impurity removal, the presence of key impurities in tobacco has always been the most concerned issue for cigarette companies. Frequent quality incidents of key impurities in the manufacturing process of cigarette companies have caused huge losses. The presence of key impurities in tobacco not only means that the purity of tobacco will be greatly affected, but also may mean that major failures may occur in tobacco production equipment (for example, when there is serious misalignment and friction between the belt and the connecting parts of the production line, the rubber particles generated by the friction of the belt and the paint of the connecting parts will be wiped off, and the rubber particles and paint blocks will fall directly into the normal tobacco materials and enter the subsequent processes, as well as plastics and rubber that are accidentally added in the previous process. These impurities will have a significant impact on the taste of cigarettes, so rubber particles, paint blocks, plastics, rubber, etc. that produce abnormal odors are key impurities, and some of these key impurities will appear continuously as long as they appear).

[0003] If a key debris is found on the production line, the tobacco manufacturer will stop the entire production line and then arrange a large number of personnel to conduct centralized inspections in the preceding and following sections where the key debris was found. On the one hand, this is to prevent the key debris from entering the subsequent normal production line and causing a decline in the quality of cigarette products. On the other hand, it is to check whether there is a major failure in the production equipment that has led to the appearance of the key debris. This manual inspection is time-consuming and labor-intensive, seriously affecting the production efficiency of tobacco manufacturers, and also causing a large amount of material waste.

[0004] At present, the impurity removal machines at home and abroad are unable to alarm when they find key impurities. The working principle is that after the image collected by the linear array / area array camera is transmitted to the image processing unit, it will be cached in the internal storage first (only a small amount of data can be cached each time), and then the image processing function of the image processing unit will be used to identify the impurities in the tobacco leaves, and then the impurity signal will be transmitted to the rejection mechanism. After the rejection mechanism performs the rejection action, the FPGA will clear the previously cached data and receive the subsequent collected pictures. For example, patent CN116965581A proposes an intelligent photoelectric impurity removal method based on broken tobacco processing. Because the tobacco leaves are transmitted at a fast speed, the images collected by the linear array / area array camera can only capture part of the impurities, and cannot capture the complete impurities. At the same time, the photoelectric debris removal system completes the process from debris detection and identification to removal in a very short time (<4ms), and the whole process is in a black box state. During the whole process, we only know that the system has identified the debris and completed the removal action. We do not know the specific information of the debris (size, category, whether it is a key debris), and there is no way to visualize the debris information, including the real-time image, size, category, and quantity of the debris. There is no way to achieve real-time warning of key debris and subsequent mining of debris data. Summary of the invention

[0005] In order to solve the technical problems that the prior art cannot visualize the information of key debris and realize real-time early warning of debris, the present invention proposes a real-time monitoring and early warning method and system for key debris based on photoelectric debris removal of cigarette sheets, so as to realize real-time monitoring and alarm of key debris and provide early warning of possible equipment failures.

[0006] The specific plan is as follows: A real-time monitoring and early warning method for key debris based on smoke sheet photoelectric debris removal comprises the following steps: Step 1: Scan tobacco leaves and collect images: In the tobacco leaf photoelectric impurity removal system, a linear array or area array camera is used to scan tobacco leaves and collect tobacco leaf image information; Step 2: Identify debris: determine whether there is debris in the tobacco leaf image, and if so, use it as a debris image; Step 3: Miscellaneous image stitching: Cache multiple consecutive segments of miscellaneous images and record timestamps until the next image does not contain any miscellaneous objects, stitch the multiple consecutive segments of miscellaneous images into a complete miscellaneous image by using timestamps, and upload the complete miscellaneous image to the upper industrial computer using a switch and a gigabit network; Step 4: Real-time monitoring and early warning of key debris: The upper industrial computer monitors the complete debris image in real time, and the image is displayed on the statistical dashboard. Based on the AI ​​classification algorithm, key debris is identified and it is determined whether the debris is a key debris. If it is a key debris, an audible and visual alarm is issued.

[0007] Preferably, the step 2 of identifying debris and the step 3 of stitching the debris images are integrated and implemented in an image processing unit, the image processing unit identifies the image information and determines whether it is a debris image, and caches a plurality of continuous segments of debris images, stitches them into a complete debris image through image stitching technology, and then transmits the debris image to a gigabit network switch, and the gigabit network switch transmits the debris image to a host industrial computer using the gigabit network.

[0008] Preferably, the method for splicing the debris images in step 3 is: Step 3.1: Construct two image buffers, one is a defect image buffer and the other is a complete image buffer; Step 3.2: After the image detection starts, the first identified debris image is first stored in the defect image buffer. If the debris appears in at least one debris image, all debris images with the debris are stored in the defect image buffer in sequence. The complete continuous images of the debris are stored until the last image is not a debris image, which is considered as a stitching task. Step 3.3: According to the timestamp recorded in the debris image, all debris images in the defect image buffer are stitched into a complete debris image and copied to the complete image buffer, and the complete debris image is uploaded to the host computer through the complete image buffer; and the defect image buffer is cleared until the next debris image enters and step 3.2 is repeated.

[0009] Preferably, the method for identifying key debris in step 4 is: The YOLOv5 model in AI technology is used to build a model; the YOLOv5 model is used to identify and classify debris and determine whether the debris is a key debris. If it is a key debris, the warning module controls the sound and light alarm to issue a warning. If the same type of key debris appears continuously in the same period of time, the warning module will issue a key debris warning prompt, that is, the decibel of the sound emitted by the sound and light alarm will increase, and the frequency of flashing red light will increase; At the same time, the category, size and quantity of the debris are displayed in real time on the key debris statistics dashboard, and it is determined whether the debris is caused by production equipment failure.

[0010] Preferably, the step of analyzing and warning the key sundries may further include: determining whether the key sundries appear continuously within a period of time; if the sundries appear continuously, the system will issue a key sundries warning prompt.

[0011] A key debris early warning system based on smoke sheet photoelectric debris removal, It includes: a smoke sheet photoelectric impurity removal system for identifying and obtaining impurity images and a host industrial control computer for classifying, warning and displaying impurity images; The tobacco leaf photoelectric impurity removal system comprises: an optical imaging module for photographing tobacco leaf images, an image acquisition module for acquiring tobacco leaf images, an image processing unit for identifying impurities in tobacco leaf images and splicing impurity images, and a rejection actuator for rejecting impurities based on a solenoid valve; The upper industrial control computer includes: a key sundries analysis and processing module for identifying key sundries based on an AI classification algorithm, and a key sundries statistics dashboard for displaying images of key sundries.

[0012] Preferably, the optical imaging module is composed of at least one linear array or area array camera, a lens, and a light source; The image acquisition module includes an image acquisition card, which acquires tobacco leaf image information to generate tobacco leaf images, and further transmits the tobacco leaf images to the image recognition submodule of the image processing module; The image recognition submodule processes the collected image information, identifies whether there are foreign objects in the tobacco leaf image, and if there are foreign objects, uses the tobacco leaf image as a foreign object image; generates foreign object information, and then transmits the foreign object information to the rejection execution mechanism; The image processing module further includes: an image stitching submodule; the image stitching submodule continuously receives a plurality of consecutive segments of debris images from the image recognition submodule until the next image is detected to have no debris as a task completion mark; The rejection execution mechanism includes a rejection program and a rejection mechanism. After receiving the debris information, the rejection program controls the rejection mechanism to reject the debris.

[0013] Preferably, the image processing module is integrated in an image processing unit, which identifies the image information and determines whether it is a debris image, and caches a plurality of continuous segments of debris images, stitches them into a complete debris image through image stitching technology, and then transmits the debris image to a gigabit network switch, which transmits the debris image to a host industrial computer using the gigabit network.

[0014] Beneficial effects: The present invention proposes a real-time monitoring and early warning method and system for key debris based on the photoelectric impurity removal of tobacco leaves. First, scan tobacco leaves and collect images: in the photoelectric impurity removal system of tobacco leaves, use a linear array or area array camera to scan tobacco leaves and collect tobacco leaf image information; obtain high-quality tobacco leaf images. Secondly, identify debris: and determine whether there are debris in the tobacco leaf image, if so, use it as a debris image. Third, splicing debris images: cache multiple consecutive segments of debris images, splice multiple consecutive segments of debris images into a complete debris image through timestamps, and upload the complete debris image to the upper industrial computer using a switch and a gigabit network. Fourth, real-time monitoring and early warning of key debris: the upper industrial computer monitors the complete debris image in real time, and the image is displayed on the statistical dashboard. Based on the AI ​​classification algorithm, the key debris is identified, and it is determined whether the debris belongs to the key debris. If it belongs to the key debris, an audible and visual alarm is issued, and then it is further determined whether the key debris appears continuously. If it appears continuously, the system will issue a unique early warning prompt. Therefore, the present invention realizes real-time monitoring and early warning of key debris, and solves the technical problem that the existing technology is in a black box state for tobacco leaf debris removal and cannot visualize the debris information. Through the tobacco leaf photoelectric debris removal system combined with the AI ​​classification algorithm of the host computer, debris can be discovered in real time for monitoring and early warning.

[0015] In the photoelectric impurity removal system of cigarette sheets, due to the high speed of material movement, no matter whether a line scanning or surface scanning digital camera is used, only a small segment of material image within the camera field of view can be collected at a certain moment for analysis and processing, and some key debris cannot be seen in this small segment of image at all, and it is impossible to judge whether it is a key debris and what kind of key debris it is based on this small segment of image. Therefore, the present invention first proposes an image splicing method based on the photoelectric impurity removal result. In step 3, the continuous multiple segments of debris images collected by the camera are spliced ​​together to obtain a complete debris image with a large height for subsequent key debris analysis and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette sheets according to the present invention; Figure 2 It is a schematic diagram of the structure of the photoelectric impurity removal system based on the present invention; Figure 3 This is a diagram of the image processing architecture of the present invention; Figure 4 A schematic diagram of the workflow of a method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette pieces in an embodiment; Figure 5 This is a schematic diagram of an image stitching method proposed by the present invention.

[0017] Among them, 1- linear array or area array camera, 2- foreign object removal host computer software, 3- Gigabit network switch, 4- FPGA image processing box, 5- photoelectric signal processing box, 6- solenoid valve driver board, 7- solenoid valve. DETAILED DESCRIPTION

[0018] The specific implementation methods of the present invention are further described below in conjunction with the accompanying drawings.

[0019] like Figure 1 As shown, a real-time monitoring and early warning method for key debris based on smoke sheet photoelectric debris removal includes the following steps: Step 1: Scan tobacco leaves and collect images: In the tobacco leaf photoelectric impurity removal system, a linear array or area array camera is used to scan tobacco leaves and collect tobacco leaf image information; Step 2: Identify debris: determine whether there is debris in the tobacco leaf image, and if so, use it as a debris image; Step 3: Miscellaneous image stitching: Cache multiple consecutive segments of miscellaneous images and record timestamps until the next image does not contain any miscellaneous objects, stitch the multiple consecutive segments of miscellaneous images into a complete miscellaneous image by using timestamps, and upload the complete miscellaneous image to the upper industrial computer using a switch and a gigabit network; Step 4: Real-time monitoring and early warning of key debris: The upper industrial computer monitors the complete debris image in real time, and the image is displayed on the statistical dashboard. Based on the AI ​​classification algorithm, key debris is identified and it is determined whether the debris is a key debris. If it is a key debris, an audible and visual alarm is issued.

[0020] Preferably, the step 2 of identifying debris and the step 3 of stitching the debris images are integrated and implemented in an image processing unit, the image processing unit identifies the image information and determines whether it is a debris image, and caches a plurality of continuous segments of debris images, stitches them into a complete debris image through image stitching technology, and then transmits the debris image to a gigabit network switch, and the gigabit network switch transmits the debris image to a host industrial computer using the gigabit network.

[0021] Preferably, the method for splicing the debris images in step 3 is: Step 3.1: Construct two image buffers, one is a defect image buffer and the other is a complete image buffer; Step 3.2: After the image detection starts, the first identified debris image is first stored in the defect image buffer. If the debris appears in at least one debris image, all debris images with the debris are stored in the defect image buffer in sequence. The complete continuous images of the debris are stored until the last image is not a debris image, which is considered as a stitching task. Step 3.3: According to the timestamp recorded in the debris image, all debris images in the defect image buffer are stitched into a complete debris image and copied to the complete image buffer, and the complete debris image is uploaded to the host computer through the complete image buffer; and the defect image buffer is cleared until the next debris image enters and step 3.2 is repeated.

[0022] Preferably, the method for identifying key debris in step 4 is: The YOLOv5 model in AI technology is used to build a model; the YOLOv5 model is used to identify and classify debris and determine whether the debris is a key debris. If it is a key debris, the warning module controls the sound and light alarm to issue a warning. If the same type of key debris appears continuously in the same period of time, the warning module will issue a key debris warning prompt, that is, the decibel of the sound emitted by the sound and light alarm will increase, and the frequency of flashing red light will increase; At the same time, the category, size and quantity of the debris are displayed in real time on the key debris statistics dashboard, and it is determined whether the debris may be caused by production equipment failure.

[0023] Preferably, the step of analyzing and warning the key sundries may further include: determining whether the key sundries appear continuously within a period of time; if the sundries appear continuously, the system will issue a key sundries warning prompt.

[0024] A key debris early warning system based on smoke sheet photoelectric debris removal, It includes: a smoke sheet photoelectric impurity removal system for identifying and obtaining impurity images and a host industrial control computer for classifying, warning and displaying impurity images; The tobacco leaf photoelectric impurity removal system comprises: an optical imaging module for photographing tobacco leaf images, an image acquisition module for acquiring tobacco leaf images, an image processing unit for identifying impurities in tobacco leaf images and splicing impurity images, and a rejection actuator for rejecting impurities based on a solenoid valve; The upper industrial control computer includes: a key sundries analysis and processing module for identifying key sundries based on an AI classification algorithm, and a key sundries statistics dashboard for displaying images of key sundries.

[0025] Preferably, the optical imaging module is composed of at least one linear array or area array camera, a lens, a light source and a background; The image acquisition module includes an image acquisition card, which acquires tobacco leaf image information to generate tobacco leaf images, and further transmits the tobacco leaf images to the image recognition submodule of the image processing module; The image recognition submodule processes the collected image information, identifies whether there are foreign objects in the tobacco leaf image, and if there are foreign objects, uses the tobacco leaf image as a foreign object image; generates foreign object information, and then transmits the foreign object information to the rejection execution mechanism; The image processing module further includes: an image stitching submodule; the image stitching submodule continuously receives a plurality of consecutive segments of debris images from the image recognition submodule until the next image is detected to have no debris as a task completion mark; The rejection execution mechanism includes a rejection program and a rejection mechanism. After receiving the debris information, the rejection program controls the rejection mechanism to reject the debris.

[0026] Preferably, the image processing module is integrated in an image processing unit, which identifies the image information and determines whether it is a debris image, and caches a plurality of continuous segments of debris images, stitches them into a complete debris image through image stitching technology, and then transmits the debris image to a gigabit network switch, which transmits the debris image to a host industrial computer using the gigabit network.

[0027] The system structure of a real-time monitoring and early warning method for key debris based on smoke sheet photoelectric impurity removal is as follows: Figure 1 , mainly including photoelectric impurity removal system, upper software, sound and light alarm, statistical dashboard and other units.

[0028] The structure of the photoelectric impurity removal system is as follows: Figure 2 , mainly including optical imaging module, image acquisition module, image processing module, and rejection actuator; The optical imaging module is mainly composed of a camera, a lens, and a light source background, which creates imaging conditions for image acquisition; The image acquisition module mainly includes an image acquisition card, which collects image information and further transmits the collected information to the image processing module; The image processing module mainly includes an image processing algorithm, which processes the collected image information, identifies the debris information in the tobacco leaves, and then transmits the debris information to the rejection actuator; The rejection actuator includes a rejection program and a rejection mechanism. After receiving the debris information, the rejection program will control the rejection mechanism to reject the debris.

[0029] The image processing architecture of the present invention is as follows Figure 3As shown, a linear array / area array camera 1 is used to acquire images of tobacco leaves and debris, and the collected image data is transmitted to an image processing unit, namely, an FPGA image processing box 4, through interfaces such as Camera Link, GigE Vision, USB, etc., and will first be stored in an internal memory (so that it can be quickly read and written in the subsequent processing process), FPGA dual-channel transmission (different from the traditional single-channel transmission), FPGA image processing box 4 recognizes the debris image in the tobacco leaves through a graphics processing function (FPGA K7 UN), wherein the debris image recognition includes recognizing the debris in the image based on a color recognition algorithm and an AI classification learning algorithm, and outputting a debris signal; the debris signal is transmitted to the photoelectric signal processing box 5 of the rejection mechanism through one of the channels (24-way IO control interface), and the photoelectric signal processing box 5 then converts the optical signal into an electrical signal and transmits it to the solenoid valve drive board 6, and the solenoid valve drive board 6 controls the solenoid valve 7 to reject the debris in the tobacco leaves; On the other hand, the FPGA image processing box 4 stitches the cached continuous multiple segments of debris image information into a complete image through image stitching technology, and then transmits the debris picture to the Gigabit network switch 3 through another channel. The Gigabit network switch 3 transmits the picture to the foreign object removal host computer software 2 of the photoelectric debris removal system using the Gigabit network.

[0030] The image stitching method is to construct two image buffers inside the image processing unit of the photoelectric impurity removal system, one is the defect image buffer and the other is the complete image buffer; after the image detection starts, the first debris image of the photoelectric impurity removal system is first stored in the defect image buffer, if the impurity appears on multiple images, then the multiple debris images are stored in the buffer in sequence; all the debris images are stored until a certain image is not a debris image, at which time all the debris images in the buffer are stitched into a complete debris image and copied to the complete image buffer, and the defect image buffer is cleared to wait for the arrival of the next debris image.

[0031] The present invention uses artificial intelligence technology to analyze and process the key debris images, uses the mature YOLOv5 to build a model based on AI technology, uses the AI ​​model to identify the debris, obtains the classification of the debris, and determines whether the debris belongs to the key debris. If it belongs to the key debris, the size and attributes of the debris are obtained, and it is determined whether the debris may be caused by the failure of the production equipment. If the key debris analysis and processing module determines that the debris image is a key debris, the early warning module controls the sound and light alarm to issue an early warning. If the same type of key debris appears continuously in the same period, the early warning module issues a key debris early warning prompt, that is, the sound decibel emitted by the sound and light alarm increases, and the frequency of flashing red light increases. The statistical dashboard displays the key debris information including size, category, and quantity in real time.

[0032] The workflow of the method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette sheets of the present invention is as follows: Figure 4 As shown, firstly, a plurality of continuous debris images are obtained by scanning with a camera of an optoelectronic debris removal system, and then the plurality of continuous debris images are stitched into a complete debris image by an image stitching method; Image stitching methods such as Figure 5 ,Two image buffers are constructed inside the image processing module of the photoelectric impurity removal system, one is the defect image buffer and the other is the complete image buffer; After the image detection starts, the first debris image of the photoelectric de-dusting system is first stored in the defect image buffer. If the next image of the debris image is also a debris image, the next debris image will continue to be stored in the buffer in sequence; all consecutive debris images are stored until a certain image is not a debris image. At this time, all the debris images in the buffer are spliced ​​into a complete debris image and copied to the complete image buffer, and the defect image buffer is cleared to wait for the arrival of the next debris image.

[0033] After the photoelectric debris removal system obtains a complete debris image, it will be uploaded to the upper software via the Gigabit network through the image processing module in the photoelectric debris removal system. The key debris analysis and processing module in the upper software will determine whether the debris is a key debris. If it is a key debris, the system will issue an audible and visual alarm, and then further determine whether the key debris appears continuously. If it appears continuously, the system will issue a unique early warning prompt.

[0034] The statistical dashboard in the upper software will count the size, category, quantity, etc. of key sundries.

[0035] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present invention.

Claims

1. A real-time monitoring and early warning method for key debris based on photoelectric impurity removal of cigarette pieces, characterized in that: The steps include: Step 1: Scan tobacco leaves and collect images: In the tobacco leaf photoelectric impurity removal system, a linear array or area array camera is used to scan tobacco leaves and collect tobacco leaf image information; Step 2: Identify debris: determine whether there is debris in the tobacco leaf image, and if so, use it as a debris image; Step 3: Miscellaneous image stitching: Cache multiple consecutive segments of miscellaneous images and record timestamps until the next image does not contain any miscellaneous objects, stitch the multiple consecutive segments of miscellaneous images into a complete miscellaneous image by using timestamps, and upload the complete miscellaneous image to the upper industrial computer using a switch and a gigabit network; Step 4: Real-time monitoring and early warning of key debris: The upper industrial computer monitors the complete debris image in real time, and the image is displayed on the statistical dashboard. Based on the AI ​​classification algorithm, key debris is identified and it is determined whether the debris is a key debris. If it is a key debris, an audible and visual alarm is issued.

2. According to claim 1, a method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette pieces is characterized by: The step 2 of identifying debris and the step 3 of splicing the debris images are integrated and implemented in an image processing unit. The image processing unit identifies the image information and determines whether it is a debris image, and caches a plurality of continuous segments of debris images, splices them into a complete debris image through image splicing technology, and then transmits the debris image to a gigabit network switch. The gigabit network switch transmits the debris image to a host industrial computer using the gigabit network.

3. The method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette pieces according to claim 1 is characterized by: The method for splicing the debris images in step 3 is: Step 3.1: Construct two image buffers, one is a defect image buffer and the other is a complete image buffer; Step 3.2: After the image detection starts, the first identified debris image is first stored in the defect image buffer. If the debris appears in at least one debris image, all debris images with the debris are stored in the defect image buffer in sequence. The complete continuous images of the debris are stored until the last image is not a debris image, which is considered as a stitching task. Step 3.3: According to the timestamp recorded in the debris image, all debris images in the defect image buffer are stitched into a complete debris image and copied to the complete image buffer, and the complete debris image is uploaded to the host computer through the complete image buffer; and the defect image buffer is cleared until the next debris image enters and step 3.2 is repeated.

4. The method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette pieces according to claim 1 is characterized by: The method for identifying key debris in step 4 is: The model is constructed by using YOLOv5 in AI technology; the model identifies and classifies the debris and determines whether the debris is a key debris. If it is a key debris, the early warning module controls the sound and light alarm to issue an early warning. If the same type of key debris appears continuously in the same period, the early warning module issues a key debris early warning prompt, that is, the decibel of the sound emitted by the sound and light alarm increases, and the frequency of flashing red light increases; At the same time, the category, size and quantity of the debris are displayed in real time on the key debris statistics dashboard, and it is determined whether the debris is caused by production equipment failure.

5. The method for real-time monitoring and early warning of key debris based on photoelectric impurity removal of cigarette pieces according to claim 1 is characterized by: The key debris analysis and warning steps may also include: determining whether the key debris appears continuously within a period of time. If the debris appears continuously, the system will issue a key debris warning prompt.

6. A real-time monitoring and early warning system for key debris based on photoelectric impurity removal of cigarette pieces constructed according to the method described in claims 1-5, characterized in that: include: The photoelectric impurity removal system for cigarette pieces that identifies the impurity image and the upper industrial control computer that monitors the impurity image in real time and issues early warning for key impurities; The tobacco leaf photoelectric impurity removal system comprises: an optical imaging module for photographing tobacco leaf images, an image acquisition module for acquiring tobacco leaf images, an image processing unit for identifying impurities in tobacco leaf images and splicing impurity images, and a rejection actuator for rejecting impurities based on a solenoid valve; The upper industrial control computer includes: a key sundries analysis and processing module for identifying whether key sundries appear in an image based on an AI classification algorithm, and a key sundries statistics dashboard for real-time monitoring of key sundries images.

7. The key debris early warning system based on smoke sheet photoelectric debris removal according to claim 6 is characterized by: The optical imaging module is composed of at least one linear array or area array camera, a lens and a light source; The image acquisition module includes an image acquisition card, which acquires tobacco leaf image information to generate tobacco leaf images, and further transmits the tobacco leaf images to the image recognition submodule of the image processing module; The image recognition submodule processes the collected image information to identify whether there are foreign objects in the tobacco leaf image, and if there are foreign objects, the tobacco leaf image is used as a foreign object image; and generate debris information, which is then transmitted to a rejection actuator; The image processing module also includes: an image stitching submodule; The image stitching submodule continues to receive the continuous multiple segments of debris images from the image recognition submodule until the next image is detected to have no debris as a task completion mark; The rejection execution mechanism includes a rejection program and a rejection mechanism. After receiving the debris information, the rejection program controls the rejection mechanism to reject the debris.

8. The key debris early warning system based on smoke sheet photoelectric debris removal according to claim 7 is characterized in that: The image processing module is integrated in the image processing unit, which identifies the image information and determines whether it is a debris image, and caches multiple consecutive segments of debris images, splices them into a complete debris image through image splicing technology, and then transmits the debris image to the Gigabit network switch. The Gigabit network switch transmits the debris image to the upper industrial computer using the Gigabit network.

Images