Intelligent control method and system for grain drying process based on image recognition

Abstract

The invention provides a grain drying process intelligent control method and system based on image recognition, and belongs to the technical field of image recognition, and the method specifically comprises the steps: employing a determination method to determine an attention diameter group, employing the attention diameter group and the distribution deviation condition of the attention diameter group in different monitoring image frames, and carrying out the intelligent control of the grain drying process. Determining a drying control strategy, determining a matched temperature interval in the drying temperature interval based on the drying control strategy, and determining the drying temperature interval according to the consistency degree between the change condition of the moisture content in different diameter intervals in the matched temperature interval and the concerned diameter group and the deviation condition of the consistency degree in different drying temperature intervals. And the adjustment control strategy matched with the temperature interval is determined, so that the reliability of drying treatment is improved.

Description

Technical Field

[0001] This invention belongs to the field of image recognition technology, and in particular relates to an intelligent control method and system for grain drying process based on image recognition. Background Technology

[0002] Existing grain drying processes often employ fixed drying control strategies. However, due to variations in grain varieties and adulteration, these fixed strategies are insufficient to effectively dry all grain varieties.

[0003] To address the aforementioned technical problems, the existing technical solution, as described in invention patent application CN202510422563.8 "Grain Drying Parameter Control System Based on Correlation Analysis," obtains image information and physical properties of grains and uses machine learning algorithms to accurately identify grain types, thereby improving drying efficiency and quality. Furthermore, it dynamically adjusts drying parameters based on real-time data and external environmental information, further ensuring the drying process remains in an optimized state. However, it suffers from the following technical issues: During the drying process, the diameter distribution of the drying target may be biased. Grain particles of different diameters have different moisture content variation characteristics. Deviation in diameter distribution will lead to uneven moisture content during the drying process, thus affecting the overall drying quality. Therefore, it may be difficult to effectively achieve reliable drying of the drying target by adopting a fixed temperature control strategy. This makes it an urgent technical problem to determine how to identify the optimal drying temperature range based on the distribution deviation of diameter groups between different image frames, so as to ensure the reliability of the drying process.

[0004] Specifically, this application provides an intelligent control method and system for grain drying process based on image recognition. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides an intelligent control method for grain drying process based on image recognition, which includes: S1 uses image recognition data to identify particles of the drying target, divides diameter groups according to the particle identification results, determines the image monitoring and processing strategy of the drying target based on the distribution data of different diameter groups, determines the composition deviation of diameter groups between different monitoring image frames based on the image monitoring and processing strategy, and determines the diameter group of interest in the diameter group based on the composition deviation and the image monitoring and processing strategy. S2 uses the determination method to determine the group of diameters of interest, and uses the group of diameters of interest and the distribution deviation of the group of diameters of interest in different monitoring image frames to determine the drying control strategy. S3 determines the matching temperature range within the drying temperature range based on the drying control strategy. Then, based on the variation in moisture content within different diameter ranges within the matching temperature range, the degree of consistency with the target diameter group, and the deviation from the degree of consistency within different drying temperature ranges, an adjustment control strategy for the matching temperature range is determined.

[0006] The beneficial effects of this invention are as follows: Based on the distribution data of different diameter groups, the image monitoring and processing strategy for the drying target is determined. The particle diameter of the drying target is analyzed in detail to identify the matching diameter groups that consistently occupy a large proportion during the drying process. Based on the number of matching diameter groups and their average proportion, the drastic change in the current diameter is determined. The image monitoring and processing strategy is dynamically formulated, transforming massive image recognition data into meaningful decision indicators. The drastic change in the current diameter is determined, and based on this, the frequency of image monitoring and abnormal triggering conditions are determined, realizing the adaptive matching of monitoring resources and diameter distribution characteristics.

[0007] Based on the variation of moisture content in different diameter intervals within the matched temperature range and its consistency with the target diameter group, as well as the deviation from the consistency with different drying temperature ranges, an adjustment control strategy for the matched temperature range is determined. This strategy is dynamically formulated based on the consistency of moisture content variation in different diameter intervals within the matched temperature range and the target diameter group to determine whether a switch to a new matched temperature range is necessary. When the number of diameter intervals with consistent deviations is large, it indicates that the current temperature range can no longer meet the requirements for uniform drying, and a new matched temperature range is directly acquired. When the number of diameter intervals with consistent deviations is moderate, the performance of these intervals in other temperature ranges is further analyzed. If their control difficulty is high, a comprehensive judgment is made; otherwise, a new matched temperature range is acquired. This mechanism ensures that the temperature range adjustment strategy can adaptively match the control difficulty of the drying process, achieving a balance between drying uniformity and process stability, and improving the efficiency of identifying and processing the optimal temperature control range.

[0008] Furthermore, the image recognition data is determined based on the recognition results of different monitoring image frames during the process of the drying target entering the drying tower.

[0009] Furthermore, the particle identification of the drying target includes the diameter of the drying target in different monitoring image frames.

[0010] Furthermore, the diameter groups are further divided, specifically including: Drying targets within the same diameter range are grouped into the same diameter group.

[0011] Furthermore, the method for determining the image monitoring and processing strategy for the drying target is as follows: S11 determines the proportion of drying targets in different diameter groups in the monitoring image frame based on the distribution data of different diameter groups; S12 uses the proportion of drying targets in different diameter groups in different monitoring image frames to determine the matching diameter group in the diameter group; S13 determines the image monitoring and processing strategy for the drying target based on the matching diameter group and the average proportion of the drying target in different monitoring image frames for different matching diameter groups.

[0012] Furthermore, the method for determining the adjustment control strategy for the matching temperature range is as follows: S41 determines the diameter range whose deviation rate from the moisture content variation curves of different diameter ranges within the matching temperature range is not less than a preset deviation rate threshold, based on the consistency between the variation of moisture content in different diameter ranges within the matching temperature range and the diameter group of interest, and uses this as the consistent deviation diameter range. S42 determines the drying temperature range to which the consistent deviation diameter range belongs based on the degree of consistency of the consistent deviation diameter range in different drying temperature ranges, and uses it as the deviation matching temperature range. S43 determines the adjustment control strategy for the matching temperature range based on the consistent deviation diameter range data within the matching temperature range and the deviation matching temperature ranges for different consistent deviation diameter ranges.

[0013] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described intelligent control method for grain drying process based on image recognition when running the computer program.

[0014] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0015] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0017] Figure 1 This is a flowchart of an intelligent control method for grain drying process based on image recognition; Figure 2 This is a flowchart illustrating the method for determining the image monitoring and processing strategy for the drying target; Figure 3 This is a flowchart illustrating the method for determining the diameter group of interest within the diameter group. Detailed Implementation

[0018] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0019] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0020] Example 1 To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, an intelligent control method for grain drying process based on image recognition is provided, specifically including: S1 uses image recognition data to identify particles of the drying target, divides diameter groups according to the particle identification results, determines the image monitoring and processing strategy of the drying target based on the distribution data of different diameter groups, determines the composition deviation of diameter groups between different monitoring image frames based on the image monitoring and processing strategy, and determines the diameter group of interest in the diameter group based on the composition deviation and the image monitoring and processing strategy. S2 uses the determination method to determine the group of diameters of interest, and uses the group of diameters of interest and the distribution deviation of the group of diameters of interest in different monitoring image frames to determine the drying control strategy. S3 determines the matching temperature range within the drying temperature range based on the drying control strategy. Then, based on the variation in moisture content within different diameter ranges within the matching temperature range, the degree of consistency with the target diameter group, and the deviation from the degree of consistency within different drying temperature ranges, an adjustment control strategy for the matching temperature range is determined.

[0021] Furthermore, the image recognition data is determined based on the recognition results of different monitoring image frames during the process of the drying target entering the drying tower.

[0022] Furthermore, the particle identification of the drying target includes the diameter of the drying target in different monitoring image frames.

[0023] Furthermore, the diameter groups are further divided, specifically including: Drying targets within the same diameter range are grouped into the same diameter group.

[0024] Furthermore, the method for determining the image monitoring and processing strategy for the drying target is as follows: This embodiment identifies matching diameter groups that consistently occupy a large proportion during the drying process through refined analysis of the diameter of the target particles. Based on the number of matching diameter groups and their average proportion, it determines the drastic degree of diameter variation and dynamically formulates image monitoring and processing strategies. The core function of this module is to transform massive amounts of image recognition data into meaningful decision indicators, determine the drastic degree of diameter variation, and based on this, determine the frequency of image monitoring and anomaly triggering conditions, achieving adaptive matching between monitoring resources and diameter distribution characteristics.

[0025] First, by identifying matching diameter groups, the system can focus on truly representative diameter groups, avoiding the scattered waste of image analysis resources. Second, through hierarchical judgment in three scenarios, the system can employ a basic monitoring strategy to reduce resource consumption when diameter distribution is concentrated, and an optimized monitoring strategy to ensure that key changes are not missed when diameter distribution is dispersed. Finally, the introduction of a matching reliability coefficient allows the system to comprehensively evaluate the overall representativeness of multiple matching diameter groups, improving the scientific nature and accuracy of monitoring strategy formulation.

[0026] S11 determines the proportion of drying targets in different diameter groups in the monitoring image frame based on the distribution data of different diameter groups; The image recognition data refers to the monitoring image frames captured by industrial cameras during the process of the drying target entering the drying tower, and the particle diameter information of the drying target extracted from them using image recognition algorithms. The drying target refers to the grain crop that needs to be dried. Particle identification refers to the measurement and classification of the diameter of each drying target particle in the monitoring image frame. The diameter group refers to several continuous intervals divided according to the particle diameter range of the drying target, with each interval corresponding to a diameter group. The distribution data refers to the proportion of the number of drying targets in each diameter group to the total number of drying targets in that frame across different monitoring image frames. The proportion refers to the ratio of the number of drying targets in a specific diameter group to the total number of all drying targets in that monitoring image frame.

[0027] This step involves preliminary statistical processing of the raw image recognition data. By calculating the proportion of each diameter group, the raw particle count data can be transformed into a standardized index reflecting the diameter distribution characteristics, facilitating comparison and analysis between different image frames. Without this step, it is impossible to quantify the relative importance of different diameter groups during the drying process.

[0028] The significance of this step lies in realizing the quantitative expression of the diameter distribution characteristics of the drying targets, eliminating the influence of the difference in the total number of drying targets between different image frames, and making the comparison of distribution characteristics consistent and comparable.

[0029] In an intelligent control system for a corn drying tower, the system uses industrial cameras to capture monitoring image frames of corn entering the drying tower, collecting a total of 20 monitoring image frames. The image recognition module measures the diameter of the corn kernels in each frame, classifying them into five diameter groups: Group 1 (2-4 mm), Group 2 (4-6 mm), Group 3 (6-8 mm), Group 4 (8-10 mm), and Group 5 (10-12 mm). The system counts the number of corn kernels in each diameter group within each monitoring image frame and calculates its proportion of the total number of corn kernels in that frame. The statistics show that across the 20 monitoring image frames, the average proportion for diameter group 1 is 10%, for diameter group 2 it is 45%, for diameter group 3 it is 35%, for diameter group 4 it is 8%, and for diameter group 5 it is 2%.

[0030] S12 uses the proportion of drying targets in different diameter groups in different monitoring image frames to determine the matching diameter group in the diameter group; The matched diameter group refers to a diameter group in which the average proportion of the drying target in different monitoring image frames is greater than a preset proportion threshold, reflecting a diameter group that consistently occupies a large proportion during the drying process. The preset proportion threshold is a pre-set critical value used to determine whether a certain diameter group has consistent representativeness during the drying process.

[0031] By calculating the average proportion of each diameter group across multiple monitoring image frames, representative diameter groups that persist throughout the drying process can be identified. These matching diameter groups are the core focus of subsequent image monitoring strategies, as their variations best reflect the overall state of the drying process. Relying solely on single-frame data may lead to misjudgments of key groups due to random fluctuations.

[0032] The significance of this step lies in selecting key groups with sustained representativeness from numerous diameter groups, providing a focused target for the formulation of image monitoring strategies, and avoiding the waste of resources caused by monitoring all diameter groups with equal intensity.

[0033] Continuing with the above embodiment, the system reads a preset ratio threshold of 30%. Diameter groups with an average ratio greater than 30% are identified as matching diameter groups. Upon comparison, the average ratio of diameter group 2 (45%) is greater than 30%, and the average ratio of diameter group 3 (35%) is greater than 30%. Therefore, diameter groups 2 and 3 are identified as matching diameter groups.

[0034] S13 determines the image monitoring and processing strategy for the drying target based on the matching diameter group and the average proportion of the drying target in different monitoring image frames for different matching diameter groups.

[0035] It should be noted that the matching diameter group is the diameter group in which the average proportion of the drying target in different monitoring image frames is greater than a preset proportion threshold.

[0036] It is understood that, based on the matching diameter group, the image monitoring and processing strategy for determining the drying target specifically includes: Case 1: If the number of matching diameter groups is less than the preset group number threshold, then the image monitoring and processing strategy for the drying target is determined to be the basic monitoring and processing strategy. That is, if there are newly added matching diameter groups and the proportion of drying targets is not greater than the preset proportion threshold, then the image monitoring and analysis processing of the monitoring image frames will be performed according to the basic extraction cycle after a preset number of monitoring image frames are extracted in the future unit time period; otherwise, the image monitoring and analysis processing of the monitoring image frames will be performed according to the basic extraction cycle. Case 2: If the number of matching diameter groups is not less than the preset group number threshold, or if the number of matching diameter groups is greater than the preset diameter group number threshold, then the image monitoring and processing strategy for the drying target is determined to be an optimized monitoring and processing strategy. That is, if there are monitoring image frames where the proportion of newly added matching diameter groups of drying targets is not greater than the preset proportion threshold, or if there are monitoring image frames where the deviation rate of the proportion of drying targets in the previous monitoring image frames is greater than the preset deviation rate threshold, then after extracting a preset number of monitoring image frames in the future unit time period, the image monitoring and analysis processing of the monitoring image frames is performed according to the basic extraction cycle; otherwise, the image monitoring and analysis processing of the monitoring image frames is performed according to the basic extraction cycle. Case 3: If the number of matching diameter groups is not greater than a preset threshold for the number of diameter groups, the sum of the average proportions of the drying targets in different monitoring image frames of the matching diameter groups is used as the matching reliability coefficient. It is then determined whether the matching reliability coefficient is greater than a preset reliability coefficient threshold. If so, the image monitoring and processing strategy for the drying targets is determined to be an optimized monitoring and processing strategy. That is, if there are newly added monitoring image frames where the proportion of drying targets in a matching diameter group is not greater than a preset proportion threshold, or if there are monitoring image frames where the deviation rate of the proportion of drying targets in a matching diameter group from the previous monitoring image frames is greater than a preset deviation rate threshold, then within a future unit of time, a pre-selected image frame is extracted. If a predetermined number of monitoring image frames are extracted, the image monitoring and analysis processing of the monitoring image frames will be performed according to the basic extraction cycle. Otherwise, the image monitoring and analysis processing of the monitoring image frames will be performed according to the basic extraction cycle. If there are newly added monitoring image frames with a matching diameter group whose proportion of drying targets is not greater than a preset proportion threshold, or if there are monitoring image frames with diameter groups whose deviation rate from the proportion of drying targets in previous monitoring image frames is greater than a preset deviation rate threshold, then a predetermined number of monitoring image frames will be extracted within the future unit time period, and the image monitoring and analysis processing of the monitoring image frames will be performed according to the basic extraction cycle. Otherwise, the image monitoring and analysis processing of the monitoring image frames will be performed according to the basic extraction cycle.

[0037] It should be noted that the preset number is greater than the number of monitoring image frames extracted within a unit time period in the basic extraction cycle.

[0038] The image monitoring and processing strategy refers to the strategy of determining the monitoring image frame acquisition frequency and abnormal monitoring trigger conditions based on the number of matching diameter groups and their average proportions. The basic monitoring and processing strategy refers to a relatively conventional monitoring method that increases the monitoring frequency only when specific conditions are triggered. The optimized monitoring and processing strategy refers to a more proactive monitoring method that increases the monitoring frequency when multiple abnormal conditions are triggered. The matching reliability coefficient refers to the sum of the average proportions of dried targets in different monitoring image frames of the matching diameter groups, used to evaluate the overall representativeness of the matching diameter groups.

[0039] The number and average proportion of matching diameter groups reflect the concentration and stability of the diameter distribution of the drying target. When the number of matching diameter groups is small, it indicates that the diameter distribution is highly concentrated, and the basic monitoring strategy can effectively monitor key changes. When the number of matching diameter groups is large or the matching reliability coefficient is high, it indicates that the diameter distribution is relatively dispersed or that there are multiple representative groups, requiring an optimized monitoring strategy to capture richer change information. Through hierarchical judgment of these three cases, the monitoring strategy can adaptively match the diameter distribution characteristics.

[0040] The significance of this step lies in achieving adaptive matching between the image monitoring strategy and the diameter distribution characteristics of the drying target, which ensures the effective capture of key changes while avoiding the waste of computing resources caused by over-monitoring.

[0041] Continuing with the above embodiment, the number of matching diameter groups is 2, and the preset group number threshold is set to 2, meaning the number of matching diameter groups is not less than the preset group number threshold. The system further determines whether the number of matching diameter groups is greater than the preset diameter group number threshold, which is set to 3, since 2 is not greater than 3. The system then enters state 3, using the sum of the average proportions of the drying targets in different monitoring image frames for each matching diameter group as the matching reliability coefficient, i.e., 45% + 35% = 80%, resulting in a matching reliability coefficient of 0.8. The preset reliability coefficient threshold is set to 0.7, and since 0.8 is greater than 0.7, the system determines the image monitoring processing strategy to be the optimized monitoring processing strategy. The optimized monitoring and processing strategy is as follows: During subsequent monitoring, if there are newly added matching diameter groups (i.e., new diameter groups with an average proportion greater than 30%) whose proportion of drying targets is not greater than a preset proportion threshold (30%), or if there are monitoring image frames with diameter groups whose deviation rate from the proportion of drying targets in previous monitoring image frames is greater than a preset deviation rate threshold (10%), then a preset number of monitoring image frames will be extracted within a future unit of time, and then image monitoring and analysis processing will be performed according to the basic extraction cycle. In this embodiment, the preset number is set to 20 frames, and the basic extraction cycle is set to 1 frame every 5 minutes.

[0042] Furthermore, the deviation of the diameter groups between the monitored image frames is determined based on the deviation of the associated groups between the monitored image frames.

[0043] It should be noted that the associated group of the monitoring image frames is the diameter group in which the proportion of drying targets in the monitoring image frames is greater than a preset proportion threshold.

[0044] Furthermore, the method for determining the diameter group of interest within the diameter group is as follows: By analyzing the diameter composition deviations between monitored image frames, image frames with consistent correlation groups are grouped together. Through multi-level conditional judgments, an adaptive method for determining the diameter groups of interest is selected. The core function of this module is to comprehensively characterize the changing features of diameter distribution from both temporal and compositional dimensions, determine the degree of drastic change in diameter groups between different image frames, thereby determining the strategy for identifying diameter groups of interest, and accurately identifying key diameter groups that have a significant impact on the drying process.

[0045] First, by dividing image frames into groups, the system can distinguish the diameter composition characteristics at different stages, avoiding misjudging random fluctuations as trend changes. Second, through quantitative analysis of the number of deviations and the compositional deviation values, the system can comprehensively grasp the changing characteristics of diameter composition from both overall and individual dimensions. Finally, through adaptive selection of basic determination methods, rigorous determination methods, and general determination methods, the system can accurately identify key diameter groups under different operating conditions, avoiding missed or false detections caused by fixed identification conditions, and also laying the foundation for further determination of the optimal temperature control range.

[0046] S21, based on the deviation in the diameter groups between the monitored image frames, divides the monitored image frames with consistent related groups into the same image frame group; In the above steps, the number of the image frame groups is obtained, and it is determined whether the number of the image frame groups is greater than the preset threshold for the number of image frame groups. If so, the method for determining the diameter group of interest in the diameter group is the basic method. That is, if the proportion of the number of monitored image frames belonging to the associated group of the diameter group is greater than the target proportion threshold, the diameter group is regarded as the diameter group of interest. If not, proceed to step S22. The associated group refers to the diameter group in the monitored image frame where the proportion of drying targets is greater than a preset proportion threshold, reflecting the main diameter composition of that image frame. The image frame group refers to the set of monitored image frames whose associated group compositions are completely consistent. The composition deviation refers to the degree of consistency in the diameter group composition between different monitored image frames.

[0047] By grouping monitoring image frames with consistent correlation into the same group, time periods with similar diameter composition characteristics during the drying process can be identified, providing a basis for analyzing compositional deviations. Without this clustering, it would be difficult to identify compositional change trends across different time periods.

[0048] The significance of this step lies in realizing cluster analysis of the monitored image frames, grouping image frames with the same diameter compositional characteristics into one category, which facilitates subsequent analysis of compositional changes between different time periods.

[0049] Continuing with the above embodiments, the system determines the associated group for each monitored image frame. The associated group is defined as the diameter group in that frame where the proportion of dried targets is greater than a preset threshold (30%). Statistically, among the 20 monitored image frames, the associated groups for the first 10 frames are both diameter group 2 and diameter group 3, and the associated groups for the last 10 frames are also both diameter group 2 and diameter group 3. Therefore, all 20 frames belong to the same image frame group. The number of image frame groups is 1.

[0050] S22 determines the number of deviations in the associated groups between image frame groups based on the compositional deviations of the associated groups between image frame groups; The aforementioned compositional deviation refers to the degree of difference in the composition of associated groups between different image frame groups. The number of deviations refers to the number of different diameter groups in the associated group sets of two image frame groups.

[0051] By calculating the number of deviations between groups of image frames, the degree of change in diameter composition over different time periods can be quantified. The larger the number of deviations, the more drastic the change in diameter composition.

[0052] Continuing with the above embodiments, since there is only one image frame group, the number of deviations between the associated groups of image frame groups is 0.

[0053] It should be noted that the above steps include the following: S221 determines the average number of deviations between different monitoring image frame groups based on the number of deviations between the associated groups of image frame groups, and determines whether the average number of deviations between different monitoring image frame groups is greater than a preset diameter group number threshold. If so, the method for determining the diameter group of interest in the diameter group is determined as the basic method. That is, if the proportion of monitoring image frames belonging to the associated group in the diameter group is greater than the target proportion threshold, the diameter group is regarded as the diameter group of interest. If not, proceed to step S222. The average number of deviations refers to the arithmetic mean of the number of deviations among all image frame group pairs, used to assess the severity of the overall compositional change. The preset diameter group number threshold is a pre-set critical value used to determine whether the compositional change has reached a level requiring the use of basic determination methods.

[0054] By calculating the average number of deviations, the degree of variation in diameter composition can be assessed as a whole. A high average indicates drastic changes in composition, in which case a more lenient basic determination method can be used to broaden the identification scope of the diameter group of interest.

[0055] Specific example: Continuing from the above embodiment, the average number of deviations between different monitoring image frame groups is 0. The preset diameter group number threshold is set to 2, where 0 is not greater than 2, and the system proceeds to step S222.

[0056] S222 determines the compositional deviation value between the image frame group and other monitoring image frame groups by the ratio of the number of deviations between the image frame group and other monitoring image frame groups to the number of associated groups of the image frame group. It then determines whether there is a monitoring image frame group whose average compositional deviation value with other monitoring image frame groups is greater than a preset deviation threshold. If yes, proceed to step S23. If no, determine that the method for determining the diameter group of interest in the diameter group is a strict determination method. That is, if the proportion of monitoring image frames belonging to the associated groups of the diameter group is greater than the target proportion threshold, and the average proportion of the drying target in different monitoring image frames of the diameter group is greater than the target proportion threshold, then the diameter group is regarded as the diameter group of interest. The compositional deviation value refers to the ratio of the deviation between a certain image frame group and other image frame groups to the number of its own associated groups, used to measure the particularity of the group in the overall composition. The preset deviation threshold is a pre-set critical value used to determine whether there are image frame groups that significantly deviate from the overall composition.

[0057] By calculating the compositional deviation value for each image frame group, special groups that differ significantly from other groups in diameter composition can be identified. If such groups exist, it indicates that the diameter composition has changed significantly over certain time periods, requiring further refined analysis (step S23).

[0058] Specific example: Continuing from the above embodiment, since there is only one image frame group, there is no situation where the average value of the constituent deviation value between it and other monitored image frame groups is greater than the preset deviation threshold (0.5), so the system proceeds to step S23.

[0059] S23 uses the number of image frame groups and the number of deviations between related groups of image frame groups, and combines the image monitoring and processing strategy to determine the method for determining the diameter group of interest in the diameter group.

[0060] In the above steps, it is determined whether the image monitoring and processing strategy belongs to the basic monitoring and processing strategy. If so, the method for determining the diameter group of interest in the diameter group is determined as the basic determination method. If not, the method for determining the diameter group of interest in the diameter group is determined as the general determination method. That is, if the proportion of the number of monitoring image frames belonging to the associated group of the diameter group is greater than the target proportion threshold, and the average proportion of the drying target in different monitoring image frames of the diameter group is greater than the preset target proportion threshold, then the diameter group is regarded as the diameter group of interest.

[0061] The method for determining the diameter group of interest refers to the specific rules used to identify the diameter group of interest, determined based on the image frame group analysis results and image monitoring processing strategy. These rules include a basic determination method, a strict determination method, and a general determination method. The basic determination method uses relatively lenient identification rules; that is, a diameter group is considered a diameter group of interest only when the proportion of monitoring image frames belonging to the associated group is greater than a target proportion threshold. The strict determination method uses relatively strict identification rules; that is, a diameter group is considered a diameter group of interest only when the proportion of monitoring image frames belonging to the associated group is greater than a target proportion threshold, and the average proportion of this diameter group across different monitoring image frames is greater than a target proportion threshold. The general determination method uses identification rules with conditions between the two; that is, a diameter group is considered a diameter group of interest only when the proportion of monitoring image frames belonging to the associated group is greater than a target proportion threshold, and the average proportion of this diameter group across different monitoring image frames is greater than a preset target proportion threshold (but less than the target proportion threshold).

[0062] The number of image frame groups and the number of deviations reflect the diversity and variability of diameter composition during the drying process. Combining image monitoring and processing strategies allows for a more comprehensive assessment of the stability of the current drying process, thus enabling the selection of the most suitable method for identifying the diameter group of interest. Basic determination methods have relatively lenient conditions and are suitable for scenarios with unstable and highly variable compositions; rigorous determination methods have stricter conditions and are suitable for scenarios with stable compositions; general determination methods fall between the two.

[0063] The significance of this step lies in achieving an adaptive match between the method for determining the diameter group and the stability of the drying process, ensuring that the key diameter group can be accurately identified under different operating conditions.

[0064] Continuing with the above embodiments, the image monitoring and processing strategy is an optimized monitoring and processing strategy, not a basic monitoring and processing strategy. The reliability of image frame acquisition is high in this case, therefore the system determines the diameter group of interest using a general method. Specifically, the general method is as follows: if the proportion of monitoring image frames belonging to the associated group of a diameter group is greater than the target proportion threshold (30%), and the average proportion of drying targets in different monitoring image frames of this diameter group is greater than the preset target proportion threshold (25%), then this diameter group is designated as the diameter group of interest. Statistically, diameter group 2 has 100% of monitoring image frames belonging to the associated group, with an average proportion of 45%, which is greater than 25%; diameter group 3 also has 100% of monitoring image frames belonging to the associated group, with an average proportion of 35%, which is greater than 25%. Therefore, the system determines diameter groups 2 and 3 as diameter groups of interest.

[0065] It should be noted that the preset target ratio threshold is less than the target ratio threshold.

[0066] Furthermore, the method for determining the drying control strategy is as follows: Based on the identified groups of diameters of interest, the module calculates group matching deviation values ​​by analyzing their quantity and distribution deviations in the monitored image frames, and selects either a preset drying control strategy or a strict drying control strategy accordingly. The core function of this module is to transform the image analysis results into executable temperature range switching commands, achieving a crucial leap from monitoring to control.

[0067] Overall beneficial effects: First, by statistically analyzing the number of diameter groups, the system can quickly determine the complexity of the diameter distribution, providing a concise and effective decision-making indicator for the selection of control strategies. Second, through quantitative analysis of indicators such as the matching deviation ratio and the number of image frames showing the focus deviation, the system can comprehensively evaluate the representativeness of the diameter groups of focus, providing a basis for the refined selection of control strategies. Finally, through the comprehensive calculation of group matching deviation values, the system can employ a preset strategy to ensure timely response when the matching degree is low, i.e., when the diameter changes significantly, and employ a strict strategy to avoid frequent switching when the matching degree is high, thus achieving a balance between timely response and process stability.

[0068] S31 uses the data of the diameter of interest groups to determine the number of the diameter of interest groups; It is understandable that if the number of diameter groups of interest in the above steps is greater than the preset threshold for the number of diameter groups of interest, then the number of diameter groups of interest is large. Therefore, the drying control strategy is a preset drying control strategy, that is, as long as the proportion of the number of variable deviation groups in the diameter groups of interest within the temperature range is greater than the deviation group proportion threshold in the most recent preset time period, it is determined that the temperature range does not belong to the matching temperature range, and the system switches to the next temperature range to identify the matching temperature range, thereby significantly improving the efficiency of the matching temperature range identification and processing of the drying target.

[0069] It should be noted that the variation deviation group is a group of diameters of interest that, within the most recent preset time period, have a moisture content variation curve that is inconsistent with that of the diameter of interest group. Whether they are consistent is determined based on whether the deviation rate of the variation curve is less than a preset deviation rate threshold.

[0070] The data on diameter groups of interest refers to the set of diameter groups identified by the aforementioned method that require key monitoring during the drying process. The number of diameter groups of interest refers to the number of diameter groups contained in this set.

[0071] The number of diameter groups to monitor reflects the concentration of the diameter distribution of the drying target. A larger number indicates a more dispersed diameter distribution, requiring more groups to be monitored simultaneously, and increasing sensitivity to temperature range switching.

[0072] The significance of this step is that it provides the first layer of decision-making basis for the selection of drying control strategies. When there are many items, a preset drying control strategy is used to improve switching efficiency, while when there are few items, a more refined analysis is performed.

[0073] Continuing with the above embodiment, the number of diameter groups of interest is 2. The preset threshold for the number of interest groups is set to 2. Since 2 is not greater than 2, the system proceeds to step S32.

[0074] Furthermore, if the number of the attention diameter groups is not greater than the preset attention group number threshold, then proceed to step S32.

[0075] S32 determines the proportion of related groups that do not belong to the diameter of interest group in the related groups of the monitoring image frame based on the distribution deviation of the diameter of interest group in different monitoring image frames, and uses it as the matching deviation proportion. The distribution deviation refers to the stability of the diameter group of interest in different monitoring image frames. The matching deviation ratio refers to the proportion of diameters in the associated group that do not belong to the diameter group of interest in a certain monitoring image frame, reflecting the proportion of diameters not covered by the diameter group of interest in that frame.

[0076] By calculating the matching deviation ratio, the extent to which the diameter group of interest covers the current diameter composition can be quantified. A higher matching deviation ratio indicates that the diameter group of interest is less able to fully reflect the current diameter distribution characteristics.

[0077] The significance of this step is that it provides a quantitative indicator for judging the comprehensiveness of the diameter group of concern. When the proportion of image frames with concern deviation is high, it indicates that a preset drying control strategy needs to be adopted to switch the temperature range more frequently.

[0078] Continuing with the above embodiments, if the associated groups of all subsequent monitoring image frames are diameter group 2 and diameter group 3, and both of these groups are diameter groups of interest, then the matching deviation ratio of all monitoring image frames is 0.

[0079] The above steps include the following: S321 Based on the matching deviation ratio of the diameter group of interest, it is determined that there are monitoring image frames in the associated group that do not belong to the diameter group of interest. These monitoring image frames in the associated group that do not belong to the diameter group of interest are taken as the deviation image frames of interest. It is determined whether the proportion of the deviation image frames of interest in the monitoring image frames is greater than a preset image frame proportion threshold. If so, the diameter group of interest may not be comprehensive enough, that is, it does not fully reflect the distribution data of the drying target in different diameter groups. Therefore, in order to ensure the efficiency of the matching temperature range selection process and the consistency of the drying process, the drying control strategy is determined to be the preset drying control strategy. If not, proceed to step S322.

[0080] The "focused deviation image frame" refers to a monitoring image frame in the associated group that does not belong to the focus diameter group, reflecting an abnormal frame that the focus diameter group has not fully covered. The preset image frame ratio threshold is a pre-set critical value used to determine whether the ratio of focus deviation image frames has reached a level that requires the use of a preset drying control strategy.

[0081] When the proportion of biased image frames is high, it indicates that the diameter group in question fails to fully reflect the diameter distribution characteristics. In this case, a preset drying control strategy can be used to switch temperature ranges more frequently to cope with the diversity of distribution changes.

[0082] The significance of this step is that it determines the comprehensiveness of the diameter group of concern by focusing on the proportion of the biased image frames, and prioritizes the use of the preset strategy when the comprehensiveness is insufficient.

[0083] Continuing with the above embodiments, there are no monitoring image frames in the associated groups that do not belong to the diameter of interest group. Therefore, the proportion of image frames with attention deviation is 0, which is not greater than the preset image frame proportion threshold (20%). The system then proceeds to step S322.

[0084] S322 determines whether there are monitoring image frames with a matching deviation ratio greater than a preset value based on the matching deviation ratio of different monitoring image frames. If so, the drying control strategy is determined to be a strict drying control strategy. That is, as long as the proportion of the number of variable deviation groups in the diameter group within the temperature range is greater than the deviation group proportion threshold within the most recent preset time, and the duration proportion of multiple variable deviation groups within the temperature range is greater than the preset time proportion threshold, the temperature range is determined not to belong to the matching temperature range. If not, proceed to step S33.

[0085] The preset value for the matching deviation ratio is a pre-set threshold value used to determine whether there are monitoring image frames with an abnormally high matching deviation ratio.

[0086] When there is a monitoring image frame with an abnormally high matching deviation ratio, it indicates that the diameter composition of the frame is significantly different from the whole, and a strict drying control strategy is required to more accurately determine the switching timing.

[0087] Specific example: Continuing from the above embodiment, all matching deviation ratios are 0 and are not greater than the preset value of matching deviation ratio (10%). The system then proceeds to step S33.

[0088] S33 determines the drying control strategy based on the number of the diameter groups of interest and the matching deviation ratio in different monitoring image frames.

[0089] In the above steps, the average of the matching deviation ratios of different monitoring image frames and the proportion of the image frames with the focus deviation in the monitoring image frames are used to determine the group matching deviation value of the focus diameter group. It is then determined whether the group matching deviation value is greater than a preset group matching deviation threshold. If it is, the drying control strategy is determined to be a preset drying control strategy; otherwise, the drying control strategy is determined to be a strict drying control strategy.

[0090] The group matching deviation value is a comprehensive quantitative index calculated using the average of the matching deviation ratios of different monitoring image frames and the proportion of the biased image frames in the monitoring image frames. It is used to evaluate the degree of matching between the current diameter group of interest and the diameter distribution characteristics. The preset group matching deviation threshold is a pre-set critical value used to determine whether the group matching deviation value has reached a level that requires the adoption of a preset drying control strategy.

[0091] By comprehensively considering the number of diameter groups and the proportion of matching deviations, the complexity of the current diameter composition and the representativeness of the diameter groups can be fully assessed, thereby selecting the most suitable drying control strategy. When the group matching deviation value is large, a preset strategy is adopted to improve switching efficiency; when the group matching deviation value is small, a strict strategy is adopted to avoid frequent switching.

[0092] The significance of this step lies in achieving adaptive matching between the drying control strategy and the diameter distribution characteristics, which ensures timely switching while avoiding unnecessary frequent switching.

[0093] Continuing with the above embodiments, the average matching deviation ratio is 0, the proportion of image frames with focus deviation is 0, and the group matching deviation value is calculated to be 0. The preset group matching deviation threshold is set to 0.3, and 0 is not greater than 0.3. Therefore, the system determines the drying control strategy as a strict drying control strategy. The strict drying control strategy is as follows: within a temperature range, if the proportion of variable deviation groups in the focus diameter group is greater than the deviation group proportion threshold (20%) within the most recent preset duration (30 minutes), and the duration proportion of multiple variable deviation groups within the temperature range is greater than the preset duration proportion threshold (10%), then the temperature range is determined not to belong to the matching temperature range. Among them, the variable deviation group refers to the diameter group that has a different moisture content variation curve than the focus diameter group within the most recent preset duration. Whether they are consistent is determined by whether the deviation rate of the variation curve is less than the preset deviation rate threshold (5%).

[0094] Furthermore, the method for determining the adjustment control strategy for the matching temperature range is as follows: Based on the consistency between the moisture content variations of different diameter intervals within the matched temperature range and the group of diameters of interest, a dynamic adjustment control strategy for the temperature range is formulated to determine whether a switch to a new matched temperature range is necessary. The core logic lies in using a hierarchical, multi-condition judgment mechanism to comprehensively evaluate indicators such as the number of diameter intervals with consistent deviations, the distribution of the matched temperature intervals with deviations, and the weight value of control difficulty, thereby determining which adjustment strategy to adopt. When the number of diameter intervals with consistent deviations is large, it indicates that the current temperature range can no longer meet the requirements for uniform drying, and a new matched temperature range is directly acquired. When the number of diameter intervals with consistent deviations is moderate, the performance of these intervals in other temperature ranges is further analyzed. If their control difficulty is high, a comprehensive judgment is made; otherwise, a new matched temperature range is acquired. Finally, by calculating the temperature control requirement value and considering the number of diameter intervals with consistent deviations and the degree of control difficulty, a decision is made whether to acquire a new matched temperature range or not. This mechanism ensures that the temperature range adjustment strategy can adaptively match the control difficulty of the drying process, achieving a balanced optimization of drying uniformity and process stability.

[0095] S41 determines the diameter range whose deviation rate from the moisture content variation curves of different diameter ranges within the matching temperature range is not less than a preset deviation rate threshold, based on the consistency between the variation of moisture content in different diameter ranges within the matching temperature range and the diameter group of interest, and uses this as the consistent deviation diameter range. The consistent deviation diameter range refers to the diameter range within the matched temperature range where the moisture content variation curve deviates significantly from the moisture content variation curves of all diameter groups of interest. The deviation rate refers to the relative degree of difference between the moisture content variation curves of different diameter ranges and the moisture content variation curves of the diameter groups of interest. The preset deviation rate threshold is a pre-set critical value used to determine whether the deviation has reached a significant level.

[0096] By identifying the consistent deviation diameter ranges, it is possible to pinpoint which diameter ranges exhibit significant differences in drying progress compared to the diameter group of interest within the current temperature range. These ranges are the main factors causing uneven drying.

[0097] Specific example: Continuing from the above embodiment, the current matching temperature range is temperature range B. The system acquires the moisture content variation curves of different diameter ranges (diameter groups 1-5) and compares them with the moisture content variation curves of the diameter groups of interest (diameter groups 2 and 3). The preset deviation rate threshold is set to 5%. Statistically, the deviation rate of the moisture content variation curve of diameter group 1 from diameter group 2 is 8%, and the deviation rate from diameter group 3 is 7%, both not less than 5%; the deviation rates of diameter group 4 are 4% and 3%, both less than 5%; the deviation rates of diameter group 5 are 3% and 4%, both less than 5%. Therefore, the diameter range with consistent deviation is diameter group 1.

[0098] Specifically, if the number of consistent deviation diameter intervals within the matched temperature range is greater than a preset threshold for the number of deviation diameter intervals, the adjustment control strategy for the matched temperature range is determined to be to acquire a new matched temperature range. During the acquisition of a new matched temperature range, if no new matched temperature range is found within a specified time period, the current matched temperature range is converted for control processing.

[0099] Additionally, it can be understood that if the number of consistent deviation diameter intervals within the matched temperature range is not greater than a preset threshold for the number of deviation diameter intervals, then it is determined whether the number of consistent deviation diameter intervals is less than the preset threshold for the number of deviation intervals. If so, the adjustment control strategy for the matched temperature range is determined to be no adjustment required; otherwise, the process proceeds to step S42.

[0100] The preset threshold for the number of deviation diameter intervals is a pre-set critical value used to determine whether the number of consistent deviation diameter intervals has reached a level requiring immediate temperature interval switching. The specified duration (e.g., 15 minutes) refers to the maximum allowed search time during the acquisition of a new matching temperature interval. If no new matching temperature interval is found within this duration, the process reverts to the current temperature interval for control processing.

[0101] When the number of diameter ranges with consistent deviations exceeds a preset threshold, it indicates that the current temperature range can no longer meet the uniform drying requirements of most diameter ranges, and adjustment is highly necessary. Therefore, a new matching temperature range should be obtained directly. When the number does not exceed the threshold, further analysis of the specific number is needed to determine the subsequent processing method.

[0102] The significance of this judgment lies in the establishment of a mechanism of "prioritizing adjustment of high deviation quantity". When there are a large number of diameter ranges that are inconsistent with the focus group, the temperature range switching is immediately initiated to improve the uneven drying situation as quickly as possible.

[0103] Continuing with the above embodiment, the number of consistent deviation diameter intervals is 1. The preset threshold for the number of deviation diameter intervals is set to 2, where 1 is not greater than 2, so the system proceeds to the next step. The system determines whether the number of consistent deviation diameter intervals is less than the preset threshold for the number of deviation intervals. The preset threshold for the number of deviation intervals is set to 1, where 1 is not less than 1, so the system proceeds to step S42.

[0104] S42 determines the drying temperature range to which the consistent deviation diameter range belongs based on the degree of consistency of the consistent deviation diameter range in different drying temperature ranges, and uses it as the deviation matching temperature range. The aforementioned deviation matching temperature range refers to the set of temperature ranges in which a certain consistent deviation diameter range also exhibits inconsistency with the diameter group of interest in other drying temperature ranges. The aforementioned consistency refers to the universality with which the consistent deviation diameter range consistently exhibits inconsistency across different temperature ranges.

[0105] By analyzing the performance of the consistent deviation diameter range in other temperature ranges, we can assess the sensitivity of this range to temperature changes and the difficulty of control. If it exhibits inconsistency in multiple temperature ranges, it indicates that the diameter range is difficult to control.

[0106] Continuing with the above embodiments, the system determines its deviation matching temperature range based on the degree of consistency of the consistent deviation diameter range (diameter group 1) within different drying temperature ranges. Historical data analysis shows that diameter group 1 exhibits deviation rates of 6% and 5% from the moisture content variation curve of the diameter group of interest in temperature range A (75℃-85℃), both not less than 5%; in temperature range B (85℃-95℃), the deviation rates are 8% and 7%, both not less than 5%; and in temperature range C (95℃-105℃), the deviation rates are 2% and 3%, both less than 5%. Therefore, diameter group 1 exhibits a consistent deviation diameter range in both temperature ranges A and B, and its deviation matching temperature range includes both temperature ranges A and B.

[0107] The above steps include the following: Case 1: If there is no deviation matching temperature range other than the matching temperature range in the consistent deviation diameter range, then the adjustment control strategy for the matching temperature range is determined to be to obtain a new matching temperature range. If no new matching temperature range is found within a specified time, then the current matching temperature range is converted for control processing.

[0108] The phrase "no deviation matching temperature range except for the matching temperature range" means that the consistent deviation diameter range is inconsistent only in the current matching temperature range, and is consistent with the diameter group of interest in all other temperature ranges.

[0109] When the consistency deviation diameter range exhibits anomalies only within the current temperature range, it indicates that this range is highly sensitive to temperature changes, but can be effectively controlled in other temperature ranges. In this case, the deviation problem in this range can be resolved by switching to another temperature range, so a new matching temperature range can be directly obtained.

[0110] For example: If diameter group 1 exhibits a consistent deviation diameter range in temperature range B, but remains consistent with the diameter group of interest in temperature ranges A, C, D, and E, then the system determines to adjust the control strategy to obtain a new matching temperature range.

[0111] Case 2: If there is a deviation matching temperature interval other than the matching temperature interval in the consistent deviation diameter interval, the control difficulty weight value of the consistent deviation diameter curve is determined according to the number of deviation matching temperature intervals in the consistent deviation diameter interval. It is then determined whether there is a consistent deviation diameter interval whose control difficulty weight value is greater than a preset weight threshold. If yes, proceed to step S43. If no, the adjustment control strategy for the matching temperature interval is determined to be to obtain a new matching temperature interval. If no new matching temperature interval is found within a specified time, it is converted to the current matching temperature interval for control processing.

[0112] It should be noted that the specified target duration is less than the specified duration.

[0113] The control difficulty weight value refers to a weight index determined based on the number of deviation matching temperature ranges within the consistent deviation diameter range, used to quantify the control difficulty of that diameter range. The preset weight threshold is a pre-set critical value used to determine whether the control difficulty weight value has reached a high level.

[0114] When the consistent deviation diameter range is inconsistent across multiple temperature ranges, it indicates that this range is insensitive to temperature changes, and the deviation problem cannot be resolved regardless of which temperature range is switched to, making it difficult to control. In this case, it is necessary to perform a quantitative evaluation by using a control difficulty weight value. If the weight value exceeds a preset threshold, a comprehensive judgment is initiated (step S43); otherwise, a new matching temperature range is obtained.

[0115] Continuing with the above embodiments, diameter group 1, excluding the matching temperature range (range B), has a deviation matching temperature range (range A). The system determines the control difficulty weight value based on the number of deviation matching temperature ranges within the consistent deviation diameter range. The total number of temperature ranges is set to 5, and the control difficulty weight value = number of deviation matching temperature ranges / total number of temperature ranges = 2 / 5 = 0.4. The preset weight threshold is set to 0.3. Since 0.4 is greater than 0.3, there exists a consistent deviation diameter range with a control difficulty weight value greater than the preset weight threshold, and the system proceeds to step S43.

[0116] S43 determines the adjustment control strategy for the matching temperature range based on the consistent deviation diameter range data within the matching temperature range and the deviation matching temperature ranges for different consistent deviation diameter ranges.

[0117] Furthermore, based on the number of consistent deviation diameter intervals and the average of the control difficulty weight values ​​of different consistent deviation diameter curves, the temperature control requirement value of the consistent deviation diameter curve within the matching temperature interval is determined. It is then determined whether the temperature control requirement value of the matching temperature interval is greater than a preset requirement threshold. If so, the adjustment control strategy for the matching temperature interval is determined to be to acquire a new matching temperature interval. If no new matching temperature interval is found within a specified target time period, the current matching temperature interval is converted for control processing. Otherwise, the adjustment control strategy for the matching temperature interval is determined to be that no adjustment processing is required.

[0118] It should be noted that the more consistent deviation diameter intervals there are, the smaller the average weight value of the control difficulty of different consistent deviation diameter curves, and the greater the temperature control requirement value of the matching temperature interval.

[0119] The temperature control demand value is a comprehensive quantitative index calculated by combining the number of consistent deviation diameter intervals and the average of the control difficulty weight values ​​of different consistent deviation diameter curves. It is used to reflect the necessity of adjusting the current matching temperature interval. The preset demand threshold is a pre-set critical value used to determine whether the temperature control demand value has reached the level where a new matching temperature interval needs to be acquired. The specified target duration refers to the short search time allowed during the acquisition of a new matching temperature interval. If no new matching temperature interval is found within this duration, the system will switch back to the current temperature interval for control processing.

[0120] By combining the number of consistent deviation diameter intervals and the control difficulty weight value, a comprehensive assessment of the control difficulty and necessity for adjustment in the current temperature range can be achieved. A higher temperature control requirement indicates a greater need for adjustment, and an attempt should be made to obtain a new matching temperature range; conversely, a lower temperature control requirement indicates no need for adjustment. Specifically, a larger number of consistent deviation diameter intervals indicates a more widespread problem; a smaller average control difficulty weight value indicates a more dispersed control difficulty across different diameter intervals, and a greater need for overall adjustment.

[0121] The significance of this step lies in achieving an adaptive match between the temperature range adjustment strategy and the difficulty of drying control, ensuring that the temperature range is adjusted first when the control difficulty is high, and the current range is maintained when the control difficulty is low, thereby ensuring a balance between drying efficiency and quality.

[0122] Continuing with the above embodiment, the number of consistent deviation diameter intervals is one, and the average control difficulty weight value of different consistent deviation diameter curves is 0.4. The system calculates the temperature control requirement value using the following formula: Temperature control requirement value = Number of consistent deviation diameter intervals × (1 - Average control difficulty weight value) = 1 × (1 - 0.4) = 0.6. The preset requirement threshold is set to 0.5. Since 0.6 is greater than 0.5, the system determines that the adjustment control strategy for the matching temperature interval is to acquire a new matching temperature interval. If no new matching temperature interval is found within the specified target time (10 minutes), the current matching temperature interval is used for control processing.

[0123] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0124] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0125] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for intelligent control of grain drying process based on image recognition, characterized in that, Specifically, it includes: The method involves using image recognition data to identify particles of the drying target, dividing the diameter groups according to the particle identification results, determining the image monitoring and processing strategy for the drying target based on the distribution data of different diameter groups, determining the compositional deviation of the diameter groups between different monitoring image frames based on the image monitoring and processing strategy, and determining the diameter groups of interest in the diameter groups based on the compositional deviation and the image monitoring and processing strategy. The determination method is used to determine the group of diameters of interest, and the drying control strategy is determined by using the group of diameters of interest and the distribution deviation of the group of diameters of interest in different monitoring image frames. Based on the drying control strategy, a matching temperature range is determined within the drying temperature range. Then, based on the variation of moisture content in different diameter ranges within the matching temperature range, the degree of consistency with the diameter group of interest, and the deviation from the degree of consistency with different drying temperature ranges, an adjustment control strategy for the matching temperature range is determined.

2. The intelligent control method for grain drying process based on image recognition as described in claim 1, characterized in that, The image recognition data is determined based on the recognition results of different monitoring image frames during the process of the drying target entering the drying tower.

3. The intelligent control method for grain drying process based on image recognition as described in claim 1, characterized in that, The particle identification of the drying target includes the diameter of the drying target in different monitoring image frames.

4. The intelligent control method for grain drying process based on image recognition as described in claim 1, characterized in that, The diameter groups are divided into groups, specifically including: Drying targets within the same diameter range are grouped into the same diameter group.

5. The intelligent control method for grain drying process based on image recognition as described in claim 1, characterized in that, The method for determining the image monitoring and processing strategy for the drying target is as follows: Based on the distribution data of different diameter groups, the proportion of drying targets in different diameter groups in the monitoring image frame is determined; By utilizing the proportion of dried targets in different diameter groups in different monitoring image frames, the matching diameter group in the diameter group is determined; Based on the matching diameter group and the average proportion of the dried target in different monitoring image frames of different matching diameter groups, the image monitoring and processing strategy for the dried target is determined.

6. The intelligent control method for grain drying process based on image recognition as described in claim 5, characterized in that, The matching diameter group is the diameter group in which the average proportion of the drying target in different monitoring image frames is greater than a preset proportion threshold.

7. The intelligent control method for grain drying process based on image recognition as described in claim 5, characterized in that, Based on the matching diameter group, an image monitoring and processing strategy for the drying target is determined, specifically including: If the number of matching diameter groups is less than a preset group number threshold, then the image monitoring and processing strategy for the drying target is determined to be the basic monitoring and processing strategy. That is, if there are newly added matching diameter groups and the proportion of drying targets is not greater than a preset proportion threshold, then a preset number of monitoring image frames are extracted in the future unit time period, and then the image monitoring and analysis processing of the monitoring image frames is performed according to the basic extraction cycle. Otherwise, the image monitoring and analysis processing of the monitoring image frames is performed according to the basic extraction cycle.

8. The intelligent control method for grain drying process based on image recognition as described in claim 1, characterized in that, The deviation of the diameter groups between the monitored image frames is determined based on the deviation of the associated groups between the monitored image frames.

9. The intelligent control method for grain drying process based on image recognition as described in claim 1, characterized in that, The method for determining the adjustment control strategy for the matching temperature range is as follows: Based on the variation of moisture content in different diameter intervals within the matched temperature range and the degree of consistency with the diameter group of interest, the diameter intervals whose deviation rate from the moisture content variation curves of different diameter groups of interest is not less than a preset deviation rate threshold are determined, and these are taken as the consistent deviation diameter intervals. Based on the degree of consistency of the consistent deviation diameter range in different drying temperature ranges, the drying temperature range to which the consistent deviation diameter range belongs is determined and used as the deviation matching temperature range. Based on the consistent deviation diameter range data within the matching temperature range and the deviation matching temperature ranges of different consistent deviation diameter ranges, the adjustment control strategy for the matching temperature range is determined.

10. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes an intelligent control method for grain drying process based on image recognition as described in any one of claims 1-9.

Images