A vision-based online parameter adjustment method for atomization effect of tobacco flavoring nozzle

Abstract

The invention discloses a method for adjusting the atomization effect of a tobacco flavoring nozzle based on vision, which relates to the technical field of tobacco flavoring, and comprises the steps of establishing a standard library of atomization effects under different parameter conditions of a flavoring nozzle, establishing an evaluation standard for the atomization effect of a flavoring nozzle, and adjusting the parameters of a production process online, collecting nozzle atomization images under different process parameter conditions such as pressure and flow rate through an industrial camera, constructing a standard library of nozzle atomization and an evaluation standard for atomization effect of different brands after processing based on a machine vision algorithm, performing effect analysis on the nozzle atomization images of a flavoring process in the production process, and adjusting the liquid flow rate and the compressed air pressure online to ensure that the nozzle atomization effect meets the batch atomization standard of the atomization brand, thereby improving the uniformity of tobacco flavoring application in the flavoring process and reducing the waste of flavoring.

Description

Technical Field

[0001] The invention relates to the technical field of tobacco flavoring, and in particular to a vision-based online parameter adjustment method for atomization effect of a tobacco flavoring nozzle. Background Art

[0002] The flavoring process is a key process in the cigarette making process. The tobacco leaves or tobacco shreds are evenly loosened by the rotation of the drum. The flavors and spices are evenly sprayed on the surface of the tobacco leaves or tobacco shreds after being atomized by compressed air through the atomizing nozzle, thereby realizing the watering and flavoring process in this process. Since the working area of ​​the nozzle is generally in a basically closed drum-type equipment, the atomization effect of the nozzle can only be observed in the first few seconds of spraying. After a few seconds, the cylinder is filled with water vapor, and the atomization effect cannot be clearly viewed. People cannot enter the cylinder for inspection. Even if the nozzle atomization is not good or there are drops of liquid falling, it cannot be observed and eliminated. The atomization effect of the liquid sprayed on the leaves is difficult to determine. There are no qualitative or quantitative standards for the atomization effect and atomization angle, and it is difficult to ensure the quality of verification. It will also cause the material to adhere to the wall of the flavoring cylinder, increasing consumption. The uneven mist combined with the tobacco shreds will easily make the tobacco shreds wet, forming wet clumps of tobacco shreds, and the humidity of these wet clumps of tobacco shreds is obviously higher than the standard. The appearance of wet tobacco can easily lead to yellow spots in cigarette products, thus affecting the quality and taste of the entire batch of tobacco.

[0003] Currently, there is a lack of equipment to calibrate the nozzles. The only way to infer whether the nozzle atomization effect is sufficient is to observe the amount and shape of the smoke sticking to the furnace. This is a post-facto judgment and cannot effectively guarantee the stability of the process quality. During the flavoring production process, it is impossible to monitor the nozzle atomization effect in real time and achieve precise control of the flavoring process. Summary of the invention

[0004] The embodiment of the present invention provides a vision-based online parameter adjustment method for the atomization effect of a tobacco flavoring nozzle. Based on a machine vision algorithm, it can analyze the effect of the nozzle atomization image of the flavoring process, adjust the liquid flow rate and the compressed air pressure online, and ensure that the nozzle atomization effect meets the batch atomization standard of the atomization brand, thereby improving the uniformity of the application of tobacco flavoring in the flavoring process and reducing the waste of flavoring.

[0005] A vision-based online parameter adjustment method for atomization effect of a tobacco flavoring nozzle comprises the following steps:

[0006] Step 1, establishing a standard library of atomization effects of a fragrance nozzle under different parameter conditions: obtaining images of liquid droplets atomized by a fragrance nozzle under different liquid flow rates and different compressed air pressures, and performing digital image analysis on the obtained liquid droplets images to obtain a standard library of nozzle atomization under different brands, different compressed air pressures, and liquid flow rates;

[0007] Step 2, establishing an evaluation standard for the atomization effect of a fragrance adding nozzle: determining an evaluation standard for the atomization effect of a fragrance adding nozzle by analyzing the data in the nozzle atomization standard library obtained in step 1;

[0008] Step 3, online parameter adjustment of the production process: the atomization image of the flavoring nozzle is obtained online by an industrial camera installed on the inner wall of the flavoring drum, and the current atomization effect of the flavoring nozzle is evaluated according to the flavoring nozzle atomization effect evaluation standard obtained in the step 2. If the atomization effect does not meet the batch process requirements, it is compared with the data in the nozzle atomization standard library, and the current compressed air pressure and liquid flow rate are adjusted according to the comparison results.

[0009] Furthermore, the step 1 specifically includes the following steps:

[0010] Step 11, obtaining images of liquid droplets atomized by the fragrance nozzle under different liquid flow rates and compressed air pressures: optimizing the light source, using an industrial camera to collect photos of the atomization of the fragrance nozzle under different combinations of compressed air pressure and liquid flow rates, filtering out fine mist in the imaging, and obtaining images of liquid droplets;

[0011] Step 12, digital image analysis: use image morphological analysis method to analyze and process the number, area and position parameters of liquid droplets in the liquid droplet image to obtain image analysis results, use regression algorithm to obtain the parameter correlation relationship between different compressed air pressures, liquid flow rates and the number, area and position of water droplets, and construct a nozzle atomization standard library under different brands, different compressed air pressures and liquid flow rates. The nozzle atomization standard library includes liquid droplet images, image analysis results and corresponding compressed air pressures and liquid flow rates.

[0012] Furthermore, the step 2 specifically includes the following steps:

[0013] Step 21, digital quantification of standards: according to the image analysis results and parameter correlation relationship in step 12, the nozzle atomization effect evaluation standard is obtained, and the standard is digitally quantified;

[0014] Step 22, determining the parameter range for unqualified atomization quality: based on the image analysis results in step 12, the corresponding relationship between the number, area and position parameters of abnormal particles in the atomized liquid droplets and the nozzle atomization effect evaluation in step 21 is analyzed through a correlation analysis algorithm to determine the parameter range for unqualified atomization quality.

[0015] Furthermore, the step 3 specifically includes the following steps:

[0016] Step 31, online acquisition of the fragrance nozzle atomization image analysis during the production process: an industrial camera installed on the inner wall of the fragrance drum is used to acquire the fragrance nozzle atomization image online, and the edge water droplets in the image are extracted by a machine vision deep learning algorithm. The number, area and position of the liquid water droplets in the acquired fragrance nozzle atomization image are analyzed and calculated;

[0017] Step 32, spray effect evaluation: the number, area and position of liquid droplets in the atomization image of the fragrance nozzle in step 31 are evaluated according to the parameter intervals of unqualified atomization quality obtained in step 21 and step 22 to obtain an evaluation result;

[0018] Step 33, parameter comparison: if the evaluation result obtained in step 32 is that the batch process requirements are not met, the number, area and position of the liquid droplets analyzed and calculated in step 31 are compared with the number, area and position of the liquid droplet images in the nozzle atomization standard library;

[0019] Step 34, nozzle atomization effect adjustment: After the comparison is completed, the optimal atomization effect parameters of the same brand in the standard library are automatically obtained. The system overwrites the compressed air controller and the liquid flow control valve according to the parameter values, changes the current compressed air pressure and liquid flow, and makes the current nozzle atomization effect within the optimal range.

[0020] Furthermore, the light source optimization in step 11 refers to using light sources of different wavelengths to perform fog penetration processing in an environment simulating the darkness inside the fragrance drum to obtain the best fog penetration light source.

[0021] Furthermore, the process of filtering out fine mist in the image in step 11 is to pre-process the image based on a filtering algorithm.

[0022] Furthermore, the image morphological analysis method in step 12 is a Blob analysis algorithm based on deep learning.

[0023] The beneficial effects of the above-mentioned technical solution provided by the embodiment of the present invention include at least: this is a vision-based online parameter adjustment method for the atomization effect of tobacco flavoring nozzles, which uses an industrial camera to collect nozzle atomization images under different process parameter conditions such as pressure and flow, and based on a machine vision algorithm, can analyze the effect of the nozzle atomization image of the flavoring process, adjust the liquid flow rate and compressed air pressure online, and ensure that the nozzle atomization effect meets the batch atomization standard of the atomization brand, thereby improving the uniformity of tobacco flavoring application in the flavoring process and reducing the waste of flavors.

[0024] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0025] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0027] Figure 1 It is a flow chart of a method for adjusting online parameters of atomization effect of a tobacco flavoring nozzle based on vision disclosed in an embodiment of the present invention;

[0028] Figure 2 A flowchart of step 1 disclosed in an embodiment of the present invention;

[0029] Figure 3 This is a flow chart of step 2 disclosed in an embodiment of the present invention;

[0030] Figure 4 This is a flowchart of step 3 disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0032] like Figure 1-4 As shown, an embodiment of the present invention provides a method for adjusting online parameters of atomization effect of a tobacco flavoring nozzle based on vision, comprising the following steps:

[0033] Step 1, establishing a standard library of atomization effects of a fragrance nozzle under different parameter conditions: obtaining images of liquid droplets atomized by a fragrance nozzle under different liquid flow rates and different compressed air pressures, and performing digital image analysis on the obtained liquid droplets images to obtain a standard library of nozzle atomization under different brands, different compressed air pressures, and liquid flow rates;

[0034] Step 1 specifically includes the following steps:

[0035] Step 11, obtaining images of liquid droplets atomized by the fragrance nozzle under different liquid flow rates and compressed air pressures: optimizing the light source, using an industrial camera to collect photos of the atomization of the fragrance nozzle under different combinations of compressed air pressure and liquid flow rates, filtering out fine mist in the imaging, and obtaining images of liquid droplets;

[0036] It should be noted that the light source optimization in step 11 refers to using light sources of different wavelengths to perform fog penetration processing in a simulated dark environment inside the fragrance drum to obtain the best fog penetration light source. Specifically, according to design requirements, ring lights of different wavelengths such as red, blue, and green are used to test in a simulated fragrance drum test environment, and a surveillance video recorder is used to test. The best image acquisition effect solution is obtained, that is, using long-wavelength light sources such as blue and red for illumination;

[0037] The specific process of using industrial cameras to collect photos of the atomization of the flavoring nozzle under different combinations of compressed air pressure and liquid flow rate is as follows: in the test environment, simulate the atomization conditions of different brands of the flavoring process under different combinations of liquid flow rate and compressed air pressure parameters, and use industrial cameras to record the atomization images of the flavoring nozzle under different combinations of parameters;

[0038] The process of filtering out fine mist in the image in step 11 is to pre-process the image based on a filtering algorithm.

[0039] Step 12, image digital analysis: using image morphological analysis method to analyze and process the number, area and position parameters of the liquid droplets in the liquid droplet image, and obtain image analysis results, and using regression algorithm to obtain the parameter correlation relationship between different compressed air pressures, liquid flow rates and the number, area and position of water droplets, and construct a nozzle atomization standard library under different brands, different compressed air pressures and liquid flow rates, and the nozzle atomization standard library includes liquid droplet images, image analysis results and corresponding compressed air pressures and liquid flow rates;

[0040] The image morphological analysis method in step 12 is a Blob analysis algorithm based on deep learning.

[0041] Step 2, establishing the evaluation standard of the atomization effect of the fragrance adding nozzle: by analyzing the data in the nozzle atomization standard library obtained in step 1, determining the evaluation standard of the atomization effect of the fragrance adding nozzle;

[0042] Step 2 specifically includes the following steps:

[0043] Step 21, digital quantification of standards: according to the image analysis results and parameter correlation relationship in step 12, the nozzle atomization effect evaluation standard is obtained, and the standard is digitally quantified;

[0044] Step 22, determine the parameter range for unqualified atomization quality: According to the image analysis results in step 12, the corresponding relationship between the number, area and position parameters of abnormal particles in the atomized liquid droplets and the nozzle atomization effect evaluation in step 21 is analyzed through a correlation analysis algorithm to determine the parameter range for unqualified atomization quality.

[0045] Step 3, online parameter adjustment of the production process: the atomization image of the flavoring nozzle is obtained online through the industrial camera installed on the inner wall of the flavoring drum, and the current atomization effect of the flavoring nozzle is evaluated according to the flavoring nozzle atomization effect evaluation standard obtained in step 2. If the atomization effect does not meet the batch process requirements, it is compared with the data in the nozzle atomization standard library, and the current compressed air pressure and liquid flow rate are adjusted according to the comparison results;

[0046] Step 3 specifically includes the following steps:

[0047] Step 31, online acquisition of the fragrance nozzle atomization image analysis during the production process: the fragrance nozzle atomization image is acquired online through an industrial camera installed on the inner wall of the fragrance drum, and the nozzle spray image is preprocessed through image processing algorithms such as image format shaping, histogram processing, grayscale processing, image filtering, etc., to improve the image clarity and avoid the image being too bright or too dark. The extracted image is subjected to a machine vision deep learning algorithm to extract edge water droplets in the image, and the number, area and position of liquid water droplets in the obtained fragrance nozzle atomization image are analyzed and calculated;

[0048] Step 32, spray effect evaluation: the number, area and position of liquid droplets in the atomization image of the fragrance nozzle in step 31 are evaluated according to the parameter intervals of unqualified atomization quality obtained in step 21 and step 22 to obtain an evaluation result;

[0049] Step 33, parameter comparison: if the evaluation result obtained in step 32 is that the batch process requirements are not met, the number, area and position of the liquid droplets analyzed and calculated in step 31 are compared with the number, area and position of the liquid droplet images in the nozzle atomization standard library;

[0050] Step 34, nozzle atomization effect adjustment: after the comparison is completed, the best atomization effect parameters of the same brand in the standard library are automatically obtained. The parameters include compressed air pressure and liquid flow rate. The system overwrites the compressed air controller and liquid flow control valve according to the parameter values, changes the current compressed air pressure and liquid flow rate, and makes the current nozzle atomization effect within the optimal range.

[0051] Specifically, the present invention collects nozzle atomization images under different process parameter conditions such as pressure and flow rate through an industrial camera, constructs a nozzle atomization standard library of different brands and an atomization effect evaluation standard after processing based on a machine vision algorithm, performs effect analysis on the nozzle atomization image of the flavoring process during the production process, and adjusts the liquid flow rate and compressed air pressure online to ensure that the nozzle atomization effect meets the batch atomization standard of the atomization brand, thereby improving the uniformity of tobacco flavoring application in the flavoring process and reducing the waste of flavors.

[0052] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0053] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0054] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0055] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0056] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0057] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A vision-based online parameter adjustment method for atomization effect of a tobacco flavoring nozzle, characterized in that: The following steps are involved: Step 1, establishing a standard library of atomization effects of a fragrance nozzle under different parameter conditions: obtaining images of liquid droplets atomized by a fragrance nozzle under different liquid flow rates and different compressed air pressures, and performing digital image analysis on the obtained liquid droplets images to obtain a standard library of nozzle atomization under different brands, different compressed air pressures, and liquid flow rates; The step 1 comprises the following steps: Step 11, obtaining images of liquid droplets atomized by the fragrance nozzle under different liquid flow rates and compressed air pressures: optimizing the light source, using an industrial camera to collect photos of the atomization of the fragrance nozzle under different combinations of compressed air pressure and liquid flow rates, filtering out fine mist in the imaging, and obtaining images of liquid droplets; Step 12, image digital analysis: using image morphological analysis method to analyze and process the number, area and position parameters of the liquid droplets in the liquid droplet image, and obtain image analysis results, and using regression algorithm to obtain the parameter correlation relationship between different compressed air pressures, liquid flow rates and the number, area and position of water droplets, and construct a nozzle atomization standard library under different brands, different compressed air pressures and liquid flow rates, and the nozzle atomization standard library includes liquid droplet images, image analysis results and corresponding compressed air pressures and liquid flow rates; Step 2, establishing an evaluation standard for the atomization effect of a fragrance adding nozzle: by analyzing the data in the nozzle atomization standard library obtained in the step 1, determining the evaluation standard for the atomization effect of a fragrance adding nozzle; The step 2 comprises the following steps: Step 21, digital quantification of standards: according to the image analysis results and parameter correlation relationship in step 12, the nozzle atomization effect evaluation standard is obtained, and the standard is digitally quantified; Step 22, determining the parameter interval for unqualified atomization quality: according to the image analysis result in step 12, the corresponding relationship between the number, area and position parameters of abnormal particles of atomized liquid droplets and the nozzle atomization effect evaluation in step 21 is analyzed by a correlation analysis algorithm to determine the parameter interval for unqualified atomization quality; Step 3, online parameter adjustment of the production process: an industrial camera installed on the inner wall of the aroma drum is used to obtain an image of the aroma nozzle atomization online, and the aroma nozzle atomization effect evaluation standard obtained in step 2 is used to evaluate the current aroma nozzle atomization effect. If the atomization effect does not meet the batch process requirements, it is compared with the data in the nozzle atomization standard library, and the current compressed air pressure and liquid flow rate are adjusted according to the comparison results; The step 3 comprises the following steps: Step 31, online acquisition of the fragrance nozzle atomization image analysis during the production process: an industrial camera installed on the inner wall of the fragrance drum is used to acquire the fragrance nozzle atomization image online, and the edge water droplets in the image are extracted by a machine vision deep learning algorithm. The number, area and position of the liquid water droplets in the acquired fragrance nozzle atomization image are analyzed and calculated; Step 32, spray effect evaluation: the number, area and position of liquid droplets in the atomization image of the fragrance nozzle in step 31 are evaluated according to the parameter intervals of unqualified atomization quality obtained in step 21 and step 22 to obtain an evaluation result; Step 33, parameter comparison: if the evaluation result obtained in step 32 is that the batch process requirements are not met, the number, area and position of the liquid droplets analyzed and calculated in step 31 are compared with the number, area and position of the liquid droplet images in the nozzle atomization standard library; Step 34, nozzle atomization effect adjustment: After the comparison is completed, the optimal atomization effect parameters of the same brand in the standard library are automatically obtained. The system overwrites the compressed air controller and the liquid flow control valve according to the parameter values, changes the current compressed air pressure and liquid flow, and makes the current nozzle atomization effect within the optimal range.

2. The method for adjusting the online parameters of the atomization effect of a tobacco flavoring nozzle based on vision according to claim 1, characterized in that: The light source optimization in step 11 refers to using light sources of different wavelengths to perform fog penetration processing in an environment simulating the darkness inside the fragrance drum to obtain the best fog penetration light source.

3. The method for adjusting the online parameters of the atomization effect of a tobacco flavoring nozzle based on vision according to claim 1, characterized in that: The process of filtering out fine mist in the image in step 11 is to pre-process the image based on a filtering algorithm.

4. The method for adjusting the online parameters of the atomization effect of a tobacco flavoring nozzle based on vision according to claim 1, characterized in that: The image morphological analysis method in step 12 is a Blob analysis algorithm based on deep learning.

Images