An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles

Abstract

The present invention relates to the technical field of AI recognition and detection of defective products during the pipeline transportation of fruit vesicles, and specifically discloses an AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles. The system includes: an orange vesicle information collection module, a vesicle quality qualification analysis module, a database, a vesicle quality non-conformance processing module, and an orange vesicle quality problem feedback module; The present invention comprehensively analyzes the vesicle quality qualification of orange vesicles by analyzing three aspects: the compliance of vesicle diameter, the freshness of vesicles, and the contamination degree of vesicles. At the same time, the orange vesicle transportation section with unqualified vesicle quality is processed again, improving the comprehensiveness of the vesicle quality analysis of orange vesicles, avoiding waste of resources, reducing production costs, improving the stability of product quality and the strictness of control by comprehensively analyzing three dimensions, reducing the return rate and customer complaints, and reducing the impact on the economic benefits and reputation of the enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of AI recognition and detection of defective products during the pipeline transportation of fruit vesicles, and more specifically, to an AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles. Background Art

[0002] During the production and processing of orange vesicles, the transportation of vesicles is one of the key links. However, the traditional method for detecting defective orange vesicles mainly relies on manual visual inspection, which has problems such as low efficiency, high labor intensity, high cost, and human errors. With the continuous development of artificial intelligence technology, AI image recognition technology provides a new solution for the detection of defective orange vesicles. Therefore, in order to ensure the quality of orange vesicles and reduce the problems existing in the manual visual inspection process, it is necessary to perform AI recognition and detection on defective products during the pipeline transportation of orange vesicles.

[0003] There are also the following problems in the existing methods for AI recognition and detection of defective products during the pipeline transportation of orange vesicles: 1. Currently, only single-dimensional analysis is carried out, without comprehensively analyzing the quality of orange vesicles by combining the three aspects of vesicle diameter, vesicle freshness, and vesicle contamination. This reduces the comprehensiveness of the vesicle quality analysis of orange vesicles, and without comprehensively analyzing the three dimensions, the quality control during the production process may not be strict enough, which may lead to unstable product quality, increased return rates and customer complaints, and thus affect the economic benefits and reputation of the enterprise.

[0004] 2. After collecting orange vesicles with unqualified vesicle quality, they are not reprocessed, that is, they are directly discarded without being screened and recognized again. This may lead to waste of resources, increased production costs, and at the same time, without re-screening and recognition, the capacity of vesicles with severely unqualified quality cannot be obtained, reducing the accuracy of the quality qualification analysis of the current capacity of orange vesicles and unable to provide effective improvement measures for subsequent production and quality control. Summary of the Invention

[0005] In view of this, to solve the problems raised in the above background art, an AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles is proposed.

[0006] The object of the present invention can be achieved by the following technical solutions: The present invention provides an AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles, including: an orange vesicle information acquisition module, which is used to divide the orange vesicles of the current capacity into each orange vesicle transportation section according to a preset capacity, and sequentially transport each orange vesicle transportation section through the pipeline at a set time interval, and collect the humidity and images of each orange vesicle transportation section at each monitoring point in the transportation pipeline, so as to obtain the image information corresponding to each orange vesicle transportation section at each monitoring point.

[0007] The cyst quality qualification analysis module is used to extract the specified diameter range corresponding to the orange cysts and analyze the cyst quality qualification of each orange cyst conveying section.

[0008] The database is used to store the color set corresponding to the fresh orange cysts and store the gray value range corresponding to the clean orange cysts.

[0009] The cyst quality unqualified processing module is used to compare and analyze whether the cyst quality of each orange cyst conveying section is qualified, and reprocess the orange cyst conveying section with unqualified cyst quality.

[0010] The orange cyst quality problem feedback module is used to analyze the cyst quality qualification corresponding to the orange cysts of the current capacity, compare it with the set value. If it is less than the set value, it indicates that there are serious quality problems with the orange cysts of the current capacity and give feedback.

[0011] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention comprehensively analyzes the cyst quality qualification of orange cysts by analyzing the three aspects of cyst diameter compliance, cyst freshness, and cyst contamination degree, improving the comprehensiveness of the cyst quality analysis of orange cysts. By comprehensively analyzing the three dimensions, the strictness of quality control in the production process is improved, the stability of product quality is improved, the return rate and customer complaints are reduced, and the impact on the economic benefits and reputation of the enterprise is reduced.

[0012] (2) The present invention reprocesses the orange cyst conveying section with unqualified cyst quality, avoiding waste of resources, reducing production costs. At the same time, through re-screening and identification detection, the cyst capacity with seriously unqualified quality can be obtained, improving the accuracy of the cyst quality qualification analysis corresponding to the orange cysts of the current capacity, and providing effective improvement measures for subsequent production and quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0014] Figure 1 It is a schematic diagram of the connection of the system module structure of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] Please refer to Figure 1 As shown, the present invention provides a defective product AI identification and detection system during the pipeline transportation of fruit vesicles, including: an orange vesicle information collection module, a vesicle quality qualification analysis module, a database, a vesicle quality non-conformance processing module, and an orange vesicle quality problem feedback module.

[0017] The orange vesicle information collection module is connected to the vesicle quality qualification analysis module, the vesicle quality qualification analysis module is connected to the vesicle quality non-conformance processing module, the vesicle quality non-conformance processing module is connected to the orange vesicle quality problem feedback module, and the vesicle quality qualification analysis module is connected to the database.

[0018] The orange vesicle information collection module is used to divide the orange vesicles of the current volume into each orange vesicle transportation section according to a preset volume, and sequentially transport each orange vesicle transportation section through the pipeline at a set time interval, and collect the humidity and images of each orange vesicle transportation section at each monitoring point in the transportation pipeline, so as to obtain the image information corresponding to each orange vesicle transportation section at each monitoring point.

[0019] In a specific embodiment of the present invention, the image information includes the number of orange vesicles, the gray values of each gray area, and the diameter and color of each orange vesicle.

[0020] It should be noted that the humidity of each orange vesicle transportation section at each monitoring point in the transportation pipeline is collected by humidity sensors arranged at each monitoring point in the transportation pipeline, and the number of vesicles, the diameter and color of each orange vesicle are all located from the collected images.

[0021] It should also be noted that the acquisition method of the gray value of each gray area corresponding to each orange vesicle transportation section at each monitoring point is: import the images corresponding to each orange vesicle transportation section at each monitoring point collected into a computer, use image processing software to process and analyze it, and then obtain the gray image corresponding to each orange vesicle transportation section at each monitoring point, and locate the gray value of each gray area from the gray image.

[0022] The vesicle quality qualification analysis module is used to extract the specified diameter range corresponding to the orange vesicles and analyze the vesicle quality qualification of each orange vesicle transportation section.

[0023] It should be noted that the specified diameter range of the orange vesicles is obtained from the production requirement manual of the orange vesicles.

[0024] In a specific embodiment of the present invention, the specific process of analyzing the vesicle quality qualification degree of each orange vesicle conveying section is as follows: extracting the number of orange vesicles, the gray values of each gray area, and the diameter and color of each orange vesicle from the image information corresponding to each monitoring point of each orange vesicle conveying section, and respectively calculating the vesicle diameter compliance β i 、the vesicle freshness χ i and the vesicle contamination degree δ i of each orange vesicle conveying section, where i represents the number of the orange vesicle conveying section, and i = 1, 2,..., n.

[0025] In a specific embodiment of the present invention, the specific process of calculating the vesicle diameter compliance of each orange vesicle conveying section is: calculating the average value of the diameters of each orange vesicle corresponding to each monitoring point of each orange vesicle conveying section to obtain the vesicle diameter corresponding to each monitoring point of each orange vesicle conveying section, and denoting it as d ij , where j represents the number of the monitoring point, and j = 1, 2,..., m.

[0026] Denote the specified diameter range of the orange vesicles as [d′, d″].

[0027] Calculate the vesicle diameter compliance β ij of each orange vesicle conveying section corresponding to each monitoring point,

[0028] If the vesicle diameter compliance of a certain orange vesicle conveying section corresponding to each monitoring point is all 1, then denote the vesicle diameter compliance of this orange vesicle conveying section as φ1; if the vesicle diameter compliance of a certain orange vesicle conveying section corresponding to each monitoring point is all 0, then denote the vesicle diameter compliance of this orange vesicle conveying section as φ2; if the vesicle diameter compliance of a certain orange vesicle conveying section corresponding to a certain monitoring point is 0, then denote the vesicle diameter compliance of this orange vesicle conveying section as φ3. Thus, the vesicle diameter compliance β i of each orange vesicle conveying section is obtained, where the value of β i is φ1 or φ2 or φ3, and φ1 > φ3 > φ2.

[0029] In a specific embodiment of the present invention, the value of φ1 is 1, the value of φ2 is 0, and the value of φ3 is 0.5.

[0030] In a specific embodiment of the present invention, the specific process of calculating the vesicle freshness of each orange vesicle conveying section is: calculating the average value of the humidity corresponding to each monitoring point of each orange vesicle conveying section to obtain the humidity of each orange vesicle conveying section, and denoting it as ε i .

[0031] Compare the color of each orange segment at each monitoring point with the color set of fresh orange segments stored in the database. If the color of a certain orange segment at a certain monitoring point is within the color set of fresh orange segments, then mark this orange segment as a fresh orange segment, count the number of fresh orange segments corresponding to each orange segment at each monitoring point, and record it as

[0032] Record the number of orange segments corresponding to each orange segment at each monitoring point as μ ij 。

[0033] Calculate the freshness χ of each orange segment i , where ε′, Δε, and K represent the humidity of the set reference, the humidity deviation, and the proportion of the number of fresh orange segments respectively, a1 and a2 represent the weights of the freshness evaluation of the orange segments corresponding to the set humidity deviation and the proportion of the number of fresh orange segments respectively, and m represents the number of monitoring points.

[0034] In a specific embodiment of the present invention, the value of a1 is 0.5 and the value of a2 is 0.5.

[0035] In a specific embodiment of the present invention, the specific process of calculating the contamination degree of each orange segment is as follows: Compare the gray value of each gray region corresponding to each orange segment at each monitoring point with the gray value interval of clean orange segments stored in the database. If the gray value of a certain gray region corresponding to a certain orange segment at a certain monitoring point is not within the gray value interval of clean orange segments, then mark this gray region as a contaminated region, count the number of contaminated regions corresponding to each orange segment at each monitoring point, and accumulate them to obtain the number of contaminated regions collected by each orange segment.

[0036] If the number of contaminated regions collected by an orange segment is 0, then record the contamination degree of this orange segment as If the number of contaminated regions collected by an orange segment is not 0, then record the contamination degree of this orange segment as Thus, obtain the contamination degree δ of each orange segment i where δ i takes values of or

[0037] In a specific embodiment of the present invention takes a value of 0 takes a value of 1.

[0038] Calculate the quality qualification degree ω of each orange segment i , Among them, λ1, λ2, and λ3 respectively represent the proportion weights of the evaluation of the cyst quality qualification corresponding to the set cyst diameter compliance, cyst freshness, and cyst contamination degree.

[0039] In a specific embodiment of the present invention, the value of λ1 is 0.3, the value of λ2 is 0.35, and the value of λ3 is 0.35. Freshness is one of the important indicators to measure the quality of orange cysts. Fresh cysts contain more nutrients and flavor substances, which can provide better taste and nutritional value. At the same time, the contamination degree is directly related to the safety and hygiene of orange cysts. Cysts with a high contamination degree may contain harmful substances or microorganisms, posing a threat to human health. Therefore, during the analysis of the cyst quality qualification in each orange cyst conveying section, cyst freshness and cyst contamination degree are more important.

[0040] The embodiment of the present invention comprehensively analyzes the cyst quality qualification of orange cysts by analyzing three aspects: cyst diameter compliance, cyst freshness, and cyst contamination degree, improving the comprehensiveness of the cyst quality analysis of orange cysts. By comprehensively analyzing three dimensions, the strictness of quality control in the production process is improved, the stability of product quality is enhanced, the return rate and customer complaints are reduced, and the impact on the economic benefits and reputation of the enterprise is minimized.

[0041] The database is used to store the color set corresponding to fresh orange cysts and store the gray value range corresponding to clean orange cysts.

[0042] The data source in the database of this embodiment is shown in Table 1 below.

[0043] Table 1

[0044]

[0045] The cyst quality unqualified processing module is used to compare and analyze whether the cyst quality in each orange cyst conveying section is qualified, and reprocess the orange cyst conveying section with unqualified cyst quality.

[0046] In a specific embodiment of the present invention, the method for comparing and analyzing whether the cyst quality in each orange cyst conveying section is qualified is as follows: compare the cyst quality qualification of each orange cyst conveying section with the set reference cyst quality qualification. If the cyst quality qualification of a certain orange cyst conveying section is less than the set reference cyst quality qualification, it indicates that the cyst quality of this orange cyst conveying section is unqualified.

[0047] In a specific embodiment of the present invention, the specific process of reprocessing the orange cyst conveying section with unqualified cyst quality is as follows: Step 1: Collect each orange cyst conveying section with unqualified cyst quality to obtain the orange cyst volume with unqualified cyst quality, and record it as the initially unqualified cyst volume.

[0048] Step 2: Screen the initially unqualified cyst volumes proportionally into each conveying section, convey each conveying section through the pipeline in sequence at set time intervals, collect the humidity and images at each monitoring point in the conveying pipeline for each conveying section, so as to obtain the image information corresponding to each conveying section at each monitoring point, and analyze the cyst quality qualification degree of each conveying section in the same way as the analysis method of the cyst quality qualification degree of each orange cyst conveying section.

[0049] It should be noted that the image information includes the number of orange cysts, the gray values of each gray region, and the diameter and color of each orange cyst.

[0050] Step 3: Compare the cyst quality qualification degree of each conveying section with the set reference cyst quality qualification degree. If the cyst quality qualification degree of a certain conveying section is less than the set reference cyst quality qualification degree, then mark this conveying section as an unqualified conveying section, so as to confirm the seriously unqualified cyst volume.

[0051] In a specific embodiment of the present invention, the process of confirming the seriously unqualified cyst volume is as follows: Step 1: Extract the cyst quality qualification degree of each unqualified conveying section, and take the difference between it and the set reference cyst quality qualification degree to obtain the cyst quality qualification deviation of each unqualified conveying section.

[0052] Step 2: Compare the cyst quality qualification deviation of each unqualified conveying section with the set reference cyst quality qualification deviation. If the cyst quality qualification deviation of a certain unqualified conveying section is greater than the set reference cyst quality qualification deviation, then mark this unqualified conveying section as a seriously unqualified conveying section, collect each seriously unqualified conveying section, so as to obtain the seriously unqualified cyst volume.

[0053] The orange cyst quality problem feedback module is used to analyze the quality qualification degree corresponding to the orange cysts of the current volume, and compare it with the set value. If it is less than the set value, it indicates that there are serious quality problems with the orange cysts of the current volume, and feedback is carried out.

[0054] In a specific embodiment of the present invention, the specific process of analyzing the quality qualification degree corresponding to the orange cysts of the current volume is as follows: Denote the seriously unqualified cyst volume as τ 严 .

[0055] Denote the current volume of the orange cysts as τ 当 .

[0056] Calculate the quality qualification degree ξ corresponding to the orange cysts of the current volume, where σ represents the proportion of the set reference seriously unqualified cyst volume, and e represents the natural constant.

[0057] In the embodiments of the present invention, by reprocessing the orange cyst transport section with unqualified cyst quality, waste of resources is avoided, production costs are reduced. At the same time, through re-screening and identification detection, the cyst volume with seriously unqualified quality can be obtained, improving the accuracy of the quality compliance analysis for the orange cysts of the current volume, and providing effective improvement measures for subsequent production and quality control.

[0058] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should fall within the protection scope of the present invention.

Claims

1. An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles, characterized in that, Including: An orange cyst information acquisition module, which is used to divide the orange cysts of the current volume into each orange cyst conveying section according to a preset volume, and sequentially convey each orange cyst conveying section through a pipeline at a set time interval, and collect the humidity and images at each monitoring point in the conveying pipeline of each orange cyst conveying section, so as to obtain the image information corresponding to each orange cyst conveying section at each monitoring point; the image information includes the number of orange cysts, the gray values of each gray area, and the diameter and color of each orange cyst; A cyst quality qualification analysis module, which is used to extract the specified diameter range corresponding to the orange cysts and analyze the cyst quality qualification of each orange cyst conveying section; A database, which is used to store the color set corresponding to the fresh orange cysts and store the gray value interval corresponding to the clean orange cysts; A cyst quality unqualified processing module, which is used to compare and analyze whether the cyst quality of each orange cyst conveying section is qualified, and reprocess the orange cyst conveying section with unqualified cyst quality; An orange cyst quality problem feedback module, which is used to analyze the quality qualification corresponding to the orange cysts of the current volume, compare it with a set value, if it is less than the set value, it indicates that there are serious quality problems with the orange cysts of the current volume, and give feedback; The specific process of analyzing the cyst quality qualification of each orange cyst conveying section is: Extract the number of orange vesicles, the gray values of each gray region, the diameter and color of each orange vesicle from the image information corresponding to each monitoring point of each orange vesicle conveying section, and calculate the compliance of the vesicle diameter of each orange vesicle conveying section accordingly , vesicle freshness and vesicle contamination degree , where represents the number of the orange vesicle conveying section ; Calculate the qualified degree of the vesicle mass for each orange vesicle transport section , , where , and respectively represent the proportion weights of the qualified degree of the vesicle mass corresponding to the compliance of the set vesicle diameter, the freshness of the vesicle, and the contamination degree of the vesicle 2. The defective product AI recognition and detection system during the pipeline transportation of fruit vesicles according to claim 1, wherein: The specific process of calculating the compliance of the cyst diameter of each orange cyst conveying section is: Calculate the average value of the diameters of the orange vesicles corresponding to each monitoring point in each orange vesicle transport section, and obtain the vesicle diameter corresponding to each orange vesicle transport section at each monitoring point, which is denoted as , where represents the number of the monitoring point, ; The diameter range corresponding to the orange vesicles is denoted as ; Calculate the compliance of the cyst diameter corresponding to each orange cyst transport section at each monitoring point , ; If the compliance of the cyst diameter corresponding to each monitoring point of a certain orange cyst transportation section is 1, the compliance of the cyst diameter of this orange cyst transportation section is recorded as ; if the compliance of the cyst diameter corresponding to each monitoring point of a certain orange cyst transportation section is 0, the compliance of the cyst diameter of this orange cyst transportation section is recorded as ; if the compliance of the cyst diameter corresponding to a certain monitoring point of a certain orange cyst transportation section is 0, the compliance of the cyst diameter of this orange cyst transportation section is recorded as . Thus, the compliance of the cyst diameter of each orange cyst transportation section is obtained , where takes values of or or , .

3. The defective product AI recognition and detection system during the pipeline transportation of fruit vesicles according to claim 2, wherein: The specific process of calculating the freshness of the cysts of each orange cyst conveying section is: Calculate the average humidity corresponding to each monitoring point for each orange segment transportation section to obtain the humidity of each orange segment transportation section, and denote it as ; Compare the color of each orange segment at each monitoring point with the color set of fresh orange segments stored in the database. If the color of a certain orange segment at a certain monitoring point is within the color set of fresh orange segments, then mark this orange segment as a fresh orange segment, count the number of fresh orange segments corresponding to each orange segment at each monitoring point, and record it as ; Record the number of orange vesicles corresponding to each monitoring point in each orange vesicle transport segment as ; Calculate the freshness of each orange segment in the segment for transporting segments , , where , and respectively represent the humidity of the set reference, the humidity deviation, and the proportion of the number of fresh orange segments, and respectively represent the proportion weights of the freshness evaluation of the cyst corresponding to the set humidity deviation and the proportion of the number of fresh orange segments, represents the number of monitoring points.

4. An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles according to claim 1, characterized in that: The specific process of calculating the contamination degree of the cysts of each orange cyst conveying section is: Compare the gray values of each gray area corresponding to each orange cyst conveying section at each monitoring point with the gray value interval corresponding to the clean orange cysts stored in the database. If the gray value of a certain gray area corresponding to a certain orange cyst conveying section at a certain monitoring point is not within the gray value interval corresponding to the clean orange cysts, then mark this gray area as a contaminated area, count the number of contaminated areas corresponding to each orange cyst conveying section at each monitoring point, and accumulate them to obtain the number of contaminated areas collected by each orange cyst conveying section; If the number of contaminated areas collected in the orange cyst transportation section is 0, record the cyst contamination degree of this orange cyst transportation section as , if the number of contaminated areas collected in the orange cyst transportation section is not 0, record the cyst contamination degree of this orange cyst transportation section as , thus obtaining the cyst contamination degrees of each orange cyst transportation section , where takes values of or , .

5. An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles according to claim 1, characterized in that: The method of comparing and analyzing whether the cyst quality of each orange cyst conveying section is qualified is: compare the cyst quality qualification of each orange cyst conveying section with the set reference cyst quality qualification. If the cyst quality qualification of a certain orange cyst conveying section is less than the set reference cyst quality qualification, it indicates that the cyst quality of this orange cyst conveying section is unqualified.

6. An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles according to claim 5, characterized in that: The specific process of reprocessing the orange cyst conveying section with unqualified cyst quality is: Step 1: Collect each orange cyst conveying section with unqualified cyst quality to obtain the orange cyst volume with unqualified cyst quality, and record it as the initially unqualified cyst volume; Step 2: Screen the initially unqualified cyst volume proportionally into each conveying section, and sequentially convey each conveying section through a pipeline at a set time interval, collect the humidity and images at each monitoring point in the conveying pipeline of each conveying section, so as to obtain the image information corresponding to each conveying section at each monitoring point, and analyze the cyst quality qualification of each conveying section in the same way as the analysis method of the cyst quality qualification of each orange cyst conveying section; Step 3: Compare the cyst quality qualification degree of each conveying section with the set reference cyst quality qualification degree. If the cyst quality qualification degree of a certain conveying section is less than the set reference cyst quality qualification degree, then mark this conveying section as a non-conforming conveying section, so as to confirm the capacity of seriously non-conforming cysts.

7. An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles according to claim 6, characterized in that: The process of confirming the capacity of seriously non-conforming cysts is as follows: Step 1: Extract the cyst quality qualification degree of each non-conforming conveying section, and subtract it from the set reference cyst quality qualification degree to obtain the cyst quality qualification deviation of each non-conforming conveying section; Step 2: Compare the cyst quality qualification deviation of each non-conforming conveying section with the set reference cyst quality qualification deviation. If the cyst quality qualification deviation of a certain non-conforming conveying section is greater than the set reference cyst quality qualification deviation, then mark this non-conforming conveying section as a seriously non-conforming conveying section, collect each seriously non-conforming conveying section, so as to obtain the capacity of seriously non-conforming cysts.

8. An AI recognition and detection system for defective products during the pipeline transportation of fruit vesicles according to claim 7, characterized in that: The specific process of analyzing the quality qualification degree of the corresponding orange cysts of the current capacity is as follows: Record the severely unqualified cyst volume as ; Denote the current capacity of the orange cyst as ; Calculate the quality compliance of the orange vesicles corresponding to the current capacity , , where represents the proportion of severely non-compliant vesicle capacity set as a reference represents the natural constant

Images