Production line intelligent scheduling method for quinoa processing

Abstract

The invention relates to the technical field of intelligent control, in particular to a production line intelligent scheduling method for quinoa processing, and the method comprises the steps: collecting real-time data; extracting image features; determining a first temporary conveyor belt; determining a second temporary conveyor belt; abnormal conveyor belt judgment; adjusting parameters; and performing priority scheduling. According to the invention, through real-time acquisition and comprehensive analysis of parameters such as material images, load weight and gas particle concentration, tight logic relevance among the real-time parameters is embodied. The material image change rate is combined with the load weight, so that the abnormal state of the conveying belt can be accurately recognized; and the gas particle concentration is combined with the image density, so that the real-time monitoring on abnormal conditions is further enhanced. Through collaborative analysis and dynamic adjustment of the parameters, occurrence of an abnormal conveyor belt can be accurately judged, and the problems of poor scheduling efficiency and low emergency response speed during production due to excessive dependence on static data and artificial experience are effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and particularly to an intelligent scheduling method for a quinoa processing production line. Background Art

[0002] As a crop with high nutritional value, quinoa has received extensive attention globally in recent years. With the growth of market demand, the production process of quinoa also faces multiple pressures of improving production efficiency, ensuring product quality, and reducing costs. Therefore, how to optimize the production scheduling of quinoa and improve the intelligent level of the production line has become an important issue for promoting the sustainable and healthy development of the quinoa processing industry.

[0003] Currently, the production scheduling of quinoa mostly relies on traditional manual management and experience-based scheduling methods. These methods usually set the production process manually, allocate production tasks manually, and adjust production resources. Although this method can operate effectively in small-scale production, there are many problems in large-scale and complex quinoa processing production. For example, manual scheduling is easily affected by human factors, with low scheduling efficiency, slow response speed, and inability to respond to sudden abnormal situations in the production process in real time, such as equipment failures and raw material supply fluctuations. In addition, traditional scheduling methods are difficult to obtain and process various data on the production line (such as equipment status, product quality, production progress, etc.) in real time, so it is difficult to achieve precise resource optimization and dynamic production adjustment.

[0004] It can be seen that the following problems exist in the prior art: due to the dependence on manual experience in production scheduling, the scheduling efficiency is low and it is impossible to respond to changes in production in real time; due to the dependence on static data, the response speed to sudden situations during the processing is low. Summary of the Invention

[0005] For this reason, the present invention provides an intelligent scheduling method for a quinoa processing production line to overcome the problems in the prior art of poor scheduling efficiency during production and low response speed to sudden situations due to excessive dependence on static data and manual experience through a multi-dimensional real-time data acquisition and dynamic threshold adjustment mechanism.

[0006] To achieve the above object, the present invention provides an intelligent scheduling method for a quinoa processing production line, including: Collecting real-time material images, real-time load weights at each material conveyor belt in the quinoa production line operating at a preset conveying speed, and real-time gas particle concentrations above each material conveyor belt; Extracting the real-time density and real-time image change rate from the real-time material images; Determining a number of first temporary conveyor belts according to the real-time load weights of the material conveyor belts and a preset load change threshold; Determine a number of second temporary conveyor belts based on the real-time gas particle concentration and the real-time image change rate of each of the first temporary conveyor belts; Determine a number of abnormal conveyor belts based on the real-time density and the real-time load weight of any two of the second temporary conveyor belts; Adjust the preset conveyor speed to form an adjusted conveyor speed, or adjust the preset load change threshold to form an adjusted load change threshold according to the position coordinates of all the abnormal conveyor belts within a preset adjustment duration; Redetermine the abnormal conveyor belts based on the adjusted conveyor speed or the adjusted load change threshold, and generate a scheduling priority list according to the real-time load weight and position coordinates of all the material conveyor belts other than the abnormal conveyor belts; Divert the abnormal conveyor belts based on the scheduling priority list.

[0007] Further, the process of determining a number of first temporary conveyor belts according to the real-time load weight of each of the material conveyor belts and the preset load change threshold includes: Calculate the difference in the load weight at each adjacent moment within a preset first determination duration to obtain a number of load change rates; Calculate the standard deviation of all the load change rates to obtain a load change fluctuation value; When the load change fluctuation value is greater than the preset load change threshold, determine that the material conveyor belt is the first temporary conveyor belt to determine a number of first temporary conveyor belts.

[0008] Further, the process of determining a number of second temporary conveyor belts according to the real-time gas particle concentration and the real-time image change rate of each of the first temporary conveyor belts includes: Calculate the standard deviation of the real-time gas particle concentration within a preset second determination duration to obtain a concentration fluctuation value; Calculate the standard deviation of the real-time image change rate within the preset second determination duration to obtain an image change fluctuation value; Determine a number of second temporary conveyor belts according to the concentration fluctuation value and the image change fluctuation value.

[0009] Further, the process of determining a number of second temporary conveyor belts according to the concentration fluctuation value and the image change fluctuation value includes: Calculate the relative deviation of the concentration fluctuation value and a preset concentration fluctuation threshold to obtain a concentration fluctuation deviation; Calculate the relative deviation of the image change fluctuation value and a preset image change fluctuation threshold to obtain an image change fluctuation deviation; Calculate the relative deviation of the concentration fluctuation deviation and the image change fluctuation deviation to obtain a consistency deviation; When the consistent deviation is less than a preset consistent deviation threshold, calculate the absolute value of the difference between the concentration fluctuation values at adjacent moments within the preset second determination duration to obtain a number of concentration fluctuation change values, and calculate the absolute value of the difference between the image change fluctuation deviations at adjacent moments within the preset second determination duration to obtain a number of image fluctuation change values; Determine a number of second temporary conveyor belts according to all the concentration fluctuation change values and the image fluctuation change values.

[0010] Further, the process of determining a number of second temporary conveyor belts according to all the concentration fluctuation change values and the image fluctuation change values includes: Draw a change curve within the preset second determination duration according to all the concentration fluctuation change values to obtain a first curve; Draw a change curve within the preset second determination duration according to all the image fluctuation change values to obtain a second curve; Calculate the cosine similarity between the first curve and the second curve to obtain a change consistency; When the change consistency is less than a preset standard consistency, determine the first temporary conveyor belt as the second temporary conveyor belt to determine a number of second temporary conveyor belts.

[0011] Further, the process of determining a number of abnormal conveyor belts according to the real-time density and the real-time load weight of any two of the second temporary conveyor belts includes: Calculate the difference between the real-time load weights of any two of the second temporary conveyor belts to obtain a weight difference value; When the weight difference value is less than a preset standard difference value, determine a number of abnormal conveyor belts according to the real-time density of any two of the second temporary conveyor belts.

[0012] Further, the process of determining a number of abnormal conveyor belts according to the real-time density of any two of the second temporary conveyor belts includes: Calculate the standard deviation of the real-time density of a single second temporary conveyor belt within a preset abnormal determination duration to obtain a density fluctuation value; Calculate the correlation coefficient between the density fluctuation values of any two of the second temporary conveyor belts to obtain a number of density fluctuation synchronization degrees; When the density fluctuation synchronization degree is less than a preset fluctuation synchronization threshold, determine the corresponding two second temporary conveyor belts as the abnormal conveyor belts to determine a number of abnormal conveyor belts.

[0013] Further, the process of adjusting the preset conveyor speed to form an adjusted conveyor speed or adjusting the preset load change threshold to form an adjusted load change threshold according to the number and position coordinates of all the abnormal conveyor belts within a preset adjustment duration includes: Calculate the Euclidean distances from the position coordinates at each moment within the preset adjustment duration to the preset reference coordinate to obtain a number of scattered determination distances; Calculate the standard deviation of all the scattered determination distances to obtain the degree of dispersion; Calculate the standard deviation of all the degrees of dispersion within the preset adjustment duration to obtain the dispersion fluctuation value; Adjust the preset conveyor speed according to the dispersion fluctuation value and the number of abnormal conveyor belts to form an adjusted conveyor speed, or adjust the preset load change threshold to form an adjusted load change threshold.

[0014] Further, the process of adjusting the preset conveyor speed according to the dispersion fluctuation value and the number of abnormal conveyor belts to form an adjusted conveyor speed, or adjusting the preset load change threshold to form an adjusted load change threshold includes: When the dispersion fluctuation value is greater than the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is greater than the preset number threshold, reduce the preset conveyor speed according to the relative deviation between the dispersion fluctuation value and the preset dispersion fluctuation threshold and a preset first adjustment coefficient to form an adjusted conveyor speed; When the dispersion fluctuation value is less than or equal to the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is less than the preset number threshold, calculate the standard deviation of the number of abnormal conveyor belts at each moment within the preset adjustment duration to obtain the number fluctuation value; When the number fluctuation value is greater than the preset number fluctuation threshold, increase the preset load change threshold according to the relative deviation between the number fluctuation value and the preset number fluctuation threshold and a preset second adjustment coefficient to form an adjusted load change threshold.

[0015] Further, the process of generating a scheduling priority list according to the real-time load weights and position coordinates of all the material conveyor belts other than the abnormal conveyor belts includes: Calculate the relative deviations of the real-time load weights of the material conveyor belts other than the abnormal conveyor belts from the preset standard load to obtain a number of load deviation values; Calculate the Euclidean distances from each material conveyor belt to the nearest abnormal conveyor belt according to the position coordinates of each material conveyor belt and the position coordinates of each abnormal conveyor belt to form a number of priority distance values; Normalize all the load deviation values to form a number of load deviation normalization values; Normalize all the priority distance values to form a number of priority distance normalization values; Perform weighted summation on the load deviation values, preset load deviation weights, load deviation priority distance values, and preset priority distance weights of each material conveyor belt to obtain a number of priority scheduling indices; Sort all the above-mentioned priority scheduling indices from largest to smallest to generate a scheduling priority list.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: By collecting and comprehensively analyzing parameters such as material images, load weights, and gas particle concentrations in real time, the close logical correlation between the real-time parameters is reflected. The combination of the change rate of the material image and the load weight helps to accurately identify the abnormal state of the conveyor belt; while the combination of the gas particle concentration and the image density further strengthens the real-time monitoring of abnormal situations. Through the collaborative analysis and dynamic adjustment of these parameters, it is possible to accurately judge the occurrence of an abnormal conveyor belt, timely adjust the conveying speed or the load change threshold, thereby optimizing the scheduling efficiency and stability of the production line, realizing a more intelligent quinoa processing process, and effectively solving the problems of poor scheduling efficiency during production and low response speed to emergencies caused by over-reliance on static data and manual experience.

[0017] Furthermore, by monitoring and analyzing the load changes of the material conveyor belt in real time, it is possible to effectively identify the conveyor belts with large load fluctuations and timely discover potential load unevenness problems. By calculating the load change rate and the fluctuation value, the system can accurately determine which conveyor belts may affect the smooth operation of the production line, thereby providing a reliable basis for subsequent scheduling and adjustment, not only improving the stability of the production line, but also optimizing resource allocation and avoiding production delays or equipment wear caused by load unevenness.

[0018] Furthermore, by simultaneously monitoring the gas particle concentration and the image change rate, it is possible to effectively identify possible accumulation or poor flow problems on the material conveyor belt. By calculating the concentration fluctuation value and the image change fluctuation value, it is possible to accurately judge which conveyor belts need to be focused on in a short time, thereby optimizing resource allocation. This helps to discover potential production bottlenecks in advance, ensure the smooth operation of the production line, reduce efficiency losses caused by material accumulation or poor flow, and improve the overall stability and reliability of the production process.

[0019] Furthermore, by comprehensively analyzing the concentration fluctuation value and the image change fluctuation value, it is possible to more accurately identify the conveyor belts with potential abnormalities. By calculating the consistent deviation and the fluctuation change value, it is possible to dynamically capture the change trend of the state of the material conveyor belt and timely discover the situation of material accumulation or poor flow, not only improving the identification accuracy of abnormal conveyor belts, but also effectively reducing the possibility of misjudgment, optimizing resource allocation, and ensuring the efficient operation and stability of the production line.

[0020] Furthermore, by comparing the change trends of the concentration fluctuation value and the image fluctuation value, and quantifying the change consistency of the two using cosine similarity, the correlation between material flow, stacking state, and visual changes can be dynamically reflected, effectively determining whether there are abnormalities in the conveyor belt. When the change trends of the two are highly consistent, it indicates that the states of these conveyor belts are similar, which can exclude noise interference and misjudgment, more accurately identify and optimize the conveyor belts that need attention, and contribute to ensuring the smooth operation of the production line.

[0021] Furthermore, by calculating the weight difference value and the density difference value, conveyor belts showing significant deviations can be effectively identified, thus achieving precise anomaly detection. The initial screening using the weight difference value is because the material loads of adjacent conveyor belts should remain relatively balanced. If there is a large load difference, it indicates problems such as uneven material conveyance or blockage. If the weight difference is small, the density difference is further used to confirm whether there are abnormal density changes. Density changes usually represent abnormal material distribution. Therefore, further density analysis can effectively improve the accurate identification of abnormal conveyor belts, contribute to optimizing the operating efficiency of the conveyor belts, and reducing material waste and unnecessary downtime during the production process.

[0022] Furthermore, by calculating the density fluctuation synchronization degree, it is possible to determine whether there are abnormal fluctuations or instability phenomena among the second temporary conveyor belts with small load weight differences. Setting a threshold for the density fluctuation synchronization degree can effectively avoid misjudgment and ensure the accurate identification of abnormal conveyor belts, thereby improving the operating stability of the production line and reducing downtime and material losses.

[0023] Furthermore, by analyzing the dispersion degree and the fluctuation value, the change trend of the number and location of abnormal conveyor belts can be reflected, enabling the scheduling system to dynamically respond to the actual operating conditions of the production line. By using the dispersion degree and the fluctuation value to determine whether it is necessary to adjust the conveyor speed or the load threshold, when the number of abnormal conveyor belts increases or the distribution is uneven, the parameters of the production line can be adjusted in a timely manner to avoid equipment damage or reduced production efficiency caused by uneven load or overload, contributing to enhancing the stability and efficiency of the production line and ensuring the smooth progress of the material conveyance process.

[0024] Furthermore, through this dynamic analysis of the dispersion fluctuation value and the number of abnormal conveyor belts, the actual operating state of the production line can be accurately identified, and then the adjustment of the conveyor speed and the load change threshold can be optimized. Specifically, when there are large load fluctuations and too many abnormal conveyor belts, the conveyor speed is reduced to relieve the load pressure and prevent equipment overload; when the load fluctuations are small and the number of abnormal conveyor belts is small, the load change threshold is increased to improve the working efficiency of the production line. This adjustment mechanism can effectively cope with the fluctuations in different production states, ensure the stable operation of the production line, improve the overall stability and load handling capacity of the production line, and avoid production delays or equipment damage caused by excessive or too small loads. By comparing the fluctuation value and the quantity threshold and using the adjustment coefficient, reasonable adjustment measures are ensured in different scenarios.

[0025] Furthermore, by comprehensively considering the load conditions of the material conveyor belts and the spatial distance from the abnormal conveyor belts, the scheduling priorities of each conveyor belt can be accurately determined. The weighted fusion of the load deviation and the distance can reflect the working load of the conveyor belt and the urgency of the distance from the abnormal source. The normalization operation enables different parameters to have a unified dimension in calculation, avoiding the influence of different numerical ranges on the results. Finally, through the scheduling priority ranking, it can be ensured that when the production line processes the abnormal conveyor belts, resources and scheduling orders are reasonably allocated, and the material conveyor belts with load abnormalities or close to the abnormal conveyor belts are preferentially processed, improving the production efficiency and the operating stability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a flowchart of the intelligent scheduling method for the production line used in this embodiment for quinoa processing; Figure 2 is a decision logic diagram for determining the first temporary conveyor belt in this embodiment; Figure 3 is a decision logic diagram for determining the second temporary conveyor belt in this embodiment; Figure 4 is a decision logic diagram for determining the abnormal conveyor belt in this embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to make the objectives and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0029] Please refer to Figure 1As shown, it is a flowchart of an intelligent scheduling method for a quinoa processing production line in this embodiment; An intelligent scheduling method for a quinoa processing production line in this embodiment includes: Collect real-time material images, real-time load weights, and real-time gas particle concentrations above each material conveyor belt in a quinoa production line operating at a preset conveying speed; Extract the real-time density and real-time image change rate from the real-time material images; Determine a number of first temporary conveyor belts according to the real-time load weights of the material conveyor belts and a preset load change threshold; Determine a number of second temporary conveyor belts according to the real-time gas particle concentrations and the real-time image change rate of the first temporary conveyor belts; Determine a number of abnormal conveyor belts according to the real-time density and the real-time load weights of any two of the second temporary conveyor belts; Adjust the preset conveying speed according to the position coordinates of all the abnormal conveyor belts within a preset adjustment duration to form an adjusted conveying speed, or adjust the preset load change threshold to form an adjusted load change threshold; Re-determine the abnormal conveyor belts based on the adjusted conveying speed or the adjusted load change threshold, and generate a scheduling priority list according to the real-time load weights and position coordinates of all the material conveyor belts other than the abnormal conveyor belts; Divert the abnormal conveyor belts based on the scheduling priority list.

[0030] In a quinoa production line, by installing multiple sensors and imaging devices on each material conveyor belt, multiple key parameters are collected in real time. These parameters include: Real-time material image: A high-resolution camera or image recognition system is used to capture the quinoa material image on the conveyor belt in real time, which is used to analyze the distribution, stacking state, and flow of the material; The real-time density and real-time image change rate are important parameters extracted from the real-time material image, which are used to reflect the distribution and dynamic changes of the material: The real-time density refers to the quantity or stacking degree of quinoa material per unit area. By performing image processing and analysis on the collected material image, the distribution of the material is calculated using the pixel values in the image. Through image segmentation and region analysis, the material region is separated from the background, and the pixel density within the material region is statistically analyzed to obtain the distribution density of the material.

[0031] The real-time image change rate is used to measure the change rate of the image content when materials move or accumulate on the conveyor belt. By comparing consecutive acquired image frames, the difference in the image content is calculated, such as using the frame difference method algorithm to quantify the degree of image change. The image change rate reflects the dynamic changes of the materials and can determine whether there is material accumulation or unsmooth flow.

[0032] Real-time load weight: Using load cells, monitor the real-time weight of the materials on each conveyor belt; Real-time gas particle concentration: Install gas sensors or particle sensors (such as PM2.5 sensors, laser particle size sensors, etc.) to monitor the particle concentration in the air above the conveyor belt.

[0033] Finally, based on the scheduling priority list, determine which conveyor belts need to be shunted according to the priority scores of each material conveyor belt. First, those conveyor belts with higher priorities will be scheduled preferentially, especially the material conveyor belts with smaller load deviations and closer distances to the abnormal conveyor belt. These conveyor belts will undertake more material transfer tasks. For the abnormal conveyor belt, according to its priority and load conditions, the materials will be shunted to these conveyor belts with higher priorities to reduce the load of the abnormal conveyor belt and maintain the smooth operation of the production line. During the shunting process, if an abnormal situation or overloading occurs on a certain conveyor belt, according to the priority list, the system will automatically transfer the materials from this abnormal conveyor belt to the conveyor belt with a higher priority. By adjusting the load distribution of the conveyor belts in real time, ensure that the materials can be evenly distributed to each conveyor belt, avoid local overload or blockage, and achieve real-time smooth scheduling.

[0034] The preset conveyor speed refers to the default running speed of the material conveyor belt in the quinoa production line under normal operation conditions, which depends on the characteristics of the materials, the processing capacity of the production line, and the maximum load-bearing capacity of the equipment. It is usually set between 1 m / s and 5 m / s. In this embodiment, it is set to 3 m / s, which can ensure that the materials can be evenly distributed within the standard time and avoid uneven load or abnormal accumulation caused by too fast or too slow conveyor speed.

[0035] The preset load change threshold refers to the load fluctuation range set by the system to judge whether there is an abnormal change in the load of the material conveyor belt. It depends on the weight of the materials and the load-bearing capacity of the conveyor belt. It is usually set between 5% and 20%. In this embodiment, it is set to 10%, which can effectively avoid misjudgment caused by slight load changes and ensure that adjustment measures are taken in a timely manner when the load fluctuates greatly, ensuring the stability of the production line.

[0036] The preset adjustment time refers to the time window used to evaluate abnormal conveyor belt status and adjust related parameters (such as conveying speed or load change threshold) during the production process. It depends on the operating cycle of the production line and the sensitivity of the system to abnormal responses. It is usually set between 1 minute and 10 minutes. In this embodiment, it is set to 5 minutes, which can ensure that abnormal conditions in the production line are effectively identified and adjusted in a shorter time, while avoiding the failure to fully evaluate the load and flow status due to too short a time.

[0037] In a parallel quinoa processing production line running at a preset transmission speed, in order to process quinoa in large quantities, multiple material conveyor belts with the same function are set up, and the quinoa materials transported by each material conveyor belt are consistent. First, the real-time material image, real-time load weight, and gas particle concentration information above the conveyor belt are collected on each conveyor belt, and the real-time density and image change rate in the material image are extracted at the same time. Then, according to the real-time load weight of each conveyor belt and the preset load change threshold, several first temporary conveyor belts are identified, which show potential load problems. Then, combined with the gas particle concentration and image change rate of each conveyor belt, several second temporary conveyor belts are further screened out, which have material accumulation or poor transmission. According to the real-time density, load weight and position coordinates of these conveyor belts, abnormal conveyor belts are finally identified, and the transmission speed or load change threshold is adjusted according to the position coordinates of these abnormal conveyor belts. Finally, based on the adjusted parameters, the abnormal conveyor belts are re-determined and a scheduling priority list is generated. According to the list, the abnormal conveyor belts are preferentially diverted to ensure the smooth operation and efficiency of the production line during batch processing.

[0038] By collecting and comprehensively analyzing parameters such as material images, load weight, and gas particle concentration in real time, the close logical correlation between the real-time parameters is reflected. The combination of material image change rate and load weight helps to accurately identify abnormal conditions of the conveyor belt; and the combination of gas particle concentration and image density further strengthens the real-time monitoring of abnormal conditions. Through the coordinated analysis and dynamic adjustment of these parameters, it is possible to accurately determine the occurrence of abnormal conveyor belts, and adjust the conveyor speed or load change threshold in time, thereby optimizing the scheduling efficiency and stability of the production line, achieving a more intelligent quinoa processing process, and effectively solving the problems of poor scheduling efficiency and low response speed to emergencies during production due to over-reliance on static data and manual experience.

[0039] Please continue reading Figure 2 As shown, it is a decision logic diagram for determining the first temporary conveyor belt in this embodiment; The process of determining a plurality of first temporary conveyor belts according to the real-time load weight of each material conveyor belt and a preset load change threshold comprises: Calculate the differences in the load weights at adjacent moments within a preset first determination duration to obtain a number of load change rates; Calculate the standard deviation of all the load change rates to obtain a load change fluctuation value; When the load change fluctuation value is greater than the preset load change threshold, determine that the material conveyor belt is the first temporary conveyor belt to identify a number of first temporary conveyor belts.

[0040] The preset first determination duration refers to the time window for calculating the load change rate of the material conveyor belt, which depends on the operating rhythm of the production line and the speed of material conveyance. It is usually set between 1 minute and 5 minutes. In this embodiment, it is set to 3 minutes, which can accurately capture the change trend of the material load in a relatively short time, avoid being overly sensitive while ensuring the response speed, thereby effectively identifying potential load fluctuation problems and ensuring the stable operation of the production line.

[0041] Determine the first temporary conveyor belts by analyzing the load changes of the material conveyor belts, that is, those conveyor belts with large load fluctuations. First, the system calculates the differences in the load weights at adjacent moments of each material conveyor belt within the preset first determination duration to obtain the load change rate. Then, calculate the standard deviation of the load change rates of all material conveyor belts to obtain the load change fluctuation value. When the load change fluctuation value exceeds the preset load change threshold, the system determines that the material conveyor belt is the first temporary conveyor belt, that is, the conveyor belt with potential abnormalities, which is further used for subsequent scheduling and adjustment.

[0042] By real-time monitoring and analyzing the load changes of the material conveyor belts, it is possible to effectively identify the conveyor belts with large load fluctuations and timely discover potential load unevenness problems. By calculating the load change rate and the fluctuation value, the system can accurately determine which conveyor belts may affect the stable operation of the production line, thereby providing a reliable basis for subsequent scheduling and adjustment, not only improving the stability of the production line, but also optimizing resource allocation and avoiding production delays or equipment losses caused by load unevenness.

[0043] Specifically, the process of determining a number of second temporary conveyor belts based on the real-time gas particle concentration and the real-time image change rate of each of the first temporary conveyor belts includes: Calculate the standard deviation of the real-time gas particle concentration within a preset second determination duration to obtain a concentration fluctuation value; Calculate the standard deviation of the real-time image change rate within the preset second determination duration to obtain an image change fluctuation value; Determine a number of second temporary conveyor belts based on the concentration fluctuation value and the image change fluctuation value.

[0044] The preset second determination duration refers to the time window used to calculate the gas particle concentration and the fluctuation of the image change rate on the material conveyor belt. It depends on the operating cycle of the production line, the material handling speed, and the fluctuation frequency to be captured. It is usually set between 30 seconds and 3 minutes. In this embodiment, it is set to 1 minute, which can fully capture the change trend of the material conveyor belt in a relatively short time, and timely identify potential accumulation or poor flow problems, so as to quickly adjust the operating state of the production line and ensure production efficiency and stability.

[0045] The second temporary conveyor belts, that is, those conveyor belts where material accumulation or poor flow may occur, are determined by analyzing the real-time gas particle concentration and the real-time image change rate. First, calculate the standard deviation of the real-time gas particle concentration of each material conveyor belt within the preset second determination duration to obtain the concentration fluctuation value. Then, calculate the standard deviation of the real-time image change rate within the same time period to obtain the image change fluctuation value. Then, based on the magnitudes of the concentration fluctuation value and the image change fluctuation value, several second temporary conveyor belts, that is, those conveyor belts that may be affected by material accumulation or flow problems, are determined for further scheduling and optimization of the production line.

[0046] By simultaneously monitoring the gas particle concentration and the image change rate, it is possible to effectively identify potential accumulation or poor flow problems on the material conveyor belt. By calculating the concentration fluctuation value and the image change fluctuation value, it is possible to accurately determine which conveyor belts need to be focused on in a relatively short time, thus optimizing resource allocation. This helps to detect potential production bottlenecks in advance, ensure the smooth operation of the production line, reduce efficiency losses caused by material accumulation or poor flow, and improve the overall stability and reliability of the production process.

[0047] Specifically, the process of determining several second temporary conveyor belts based on the concentration fluctuation value and the image change fluctuation value includes: Calculate the relative deviation between the concentration fluctuation value and the preset concentration fluctuation threshold to obtain the concentration fluctuation deviation; Calculate the relative deviation between the image change fluctuation value and the preset image change fluctuation threshold to obtain the image change fluctuation deviation; Calculate the relative deviation between the concentration fluctuation deviation and the image change fluctuation deviation to obtain the consistency deviation; When the consistency deviation is less than the preset consistency deviation threshold, calculate the absolute value of the difference between the concentration fluctuation values at adjacent moments within the preset second determination duration to obtain several concentration fluctuation change values, and calculate the absolute value of the difference between the image change fluctuation deviations at adjacent moments within the preset second determination duration to obtain several image fluctuation change values; Determine several second temporary conveyor belts based on all the concentration fluctuation change values and the image fluctuation change values.

[0048] By analyzing the concentration fluctuation value and the image change fluctuation value in detail, the second temporary conveyor belt, i.e., the conveyor belt where material accumulation or poor flow may occur, is further determined. First, calculate the relative deviation of the concentration fluctuation value from the preset concentration fluctuation threshold to obtain the concentration fluctuation deviation. Then, calculate the relative deviation of the image change fluctuation value from the preset image change fluctuation threshold to obtain the image change fluctuation deviation. Next, calculate the relative deviation of the concentration fluctuation deviation and the image change fluctuation deviation to obtain the consistency deviation. When the consistency deviation is less than the preset consistency deviation threshold, continue to calculate the changes of the concentration fluctuation value and the image fluctuation deviation within the preset second determination duration to obtain the concentration fluctuation change value and the image fluctuation change value. Finally, based on these fluctuation change values, several second temporary conveyor belts are determined for subsequent scheduling and optimization.

[0049] By comprehensively analyzing the concentration fluctuation value and the image change fluctuation value, the conveyor belts with potential abnormalities can be identified more accurately. By calculating the consistency deviation and the fluctuation change value, the changing trend of the material conveyor belt state can be dynamically captured, and the situations of material accumulation or poor flow can be discovered in time. This not only improves the recognition accuracy of abnormal conveyor belts but also effectively reduces the possibility of misjudgment, optimizes resource allocation, and ensures the efficient operation and stability of the production line.

[0050] Please continue to refer to Figure 3 as shown, which is the determination logic diagram for determining the second temporary conveyor belt in this embodiment; The process of determining several second temporary conveyor belts based on all the concentration fluctuation change values and the image fluctuation change values includes: Draw a change curve within the preset second determination duration based on all the concentration fluctuation change values to obtain the first curve; Draw a change curve within the preset second determination duration based on all the image fluctuation change values to obtain the second curve; Calculate the cosine similarity of the first curve and the second curve to obtain the change consistency; When the change consistency is less than the preset standard consistency, determine the first temporary conveyor belt as the second temporary conveyor belt to determine several second temporary conveyor belts.

[0051] The preset standard consistency refers to the threshold for determining the similarity degree of two change curves, which depends on the process requirements of the production line and the demand for curve matching accuracy. It is usually set between 0.8 and 0.95. In this embodiment, it is set to 0.9, which can ensure that under the condition of consistent change trends, the conveyor belts with similar change fluctuation characteristics are determined as the same category, thereby optimizing subsequent production scheduling and resource allocation.

[0052] By comparing the change trends of the concentration fluctuation change values and the image fluctuation change values, the second temporary conveyor belt is further confirmed. First, a change curve is plotted based on all the concentration fluctuation change values to obtain the first curve, and then a change curve is also plotted for the image fluctuation change values to obtain the second curve. Next, the cosine similarity of these two curves is calculated to obtain the change consistency. If the change consistency is less than the preset standard consistency, it is determined that there is a large inconsistency between the first temporary conveyor belt and the second temporary conveyor belt, and then the two are determined to be the same conveyor belt, and these conveyor belts are further determined as the second temporary conveyor belt.

[0053] By comparing the change trends of the concentration fluctuation change values and the image fluctuation change values, and quantifying the change consistency of the two using cosine similarity, it can dynamically reflect the correlation between material flow, accumulation state and visual changes, and effectively judge whether the conveyor belt is abnormal. When the change trends of the two are highly consistent, it indicates that the states of these conveyor belts are similar, which can exclude noise interference and misjudgment, can more accurately identify and optimize the conveyor belts that need attention, and helps to ensure the smooth operation of the production line.

[0054] Specifically, the process of determining several abnormal conveyor belts according to the real-time density and the real-time load weight of any two of the second temporary conveyor belts includes: Calculate the difference between the real-time load weights of any two of the second temporary conveyor belts to obtain a weight difference value; When the weight difference value is less than the preset standard difference value, several abnormal conveyor belts are determined according to the real-time density of any two of the second temporary conveyor belts.

[0055] The preset standard difference value is a threshold used to determine whether the load weight difference between two conveyor belts is significant, which depends on the type of material, the specifications of the conveyor belt, and the operating stability of the production line. It is usually set between 0.5 kg and 5 kg. In this embodiment, it is set to 2 kg, which can ensure that even when the load change is small, abnormalities can still be effectively detected and the stable operation of the production line can be guaranteed.

[0056] First, calculate the difference between the real-time load weights of any two second temporary conveyor belts to obtain a weight difference value. If this difference value is less than the preset standard difference value, the system then further analyzes according to the real-time density of the two conveyor belts to determine whether there are abnormal conveyor belts. This analysis determines whether there are abnormalities by comparing the density differences between the conveyor belts. If inconsistencies or abnormal manifestations are found, these conveyor belts are marked as abnormal conveyor belts.

[0057] By calculating the weight difference value and the density difference value, it is possible to effectively identify those conveyor belts that exhibit significant deviations, thereby achieving precise anomaly detection. Using the weight difference value for preliminary screening is because the material loads of adjacent conveyor belts should be relatively balanced. If there is a large load difference, it indicates problems such as uneven material conveyance or blockage. If the weight difference is small, then further confirmation of whether there is an abnormal density change is made through the density difference. Density changes usually represent anomalies in material distribution. Therefore, further density analysis can effectively improve the accurate identification of abnormal conveyor belts, contribute to optimizing the operating efficiency of conveyor belts, and reduce material waste and unnecessary downtime during the production process.

[0058] Please continue to refer to Figure 4 as shown, which is the determination logic diagram for determining abnormal conveyor belts in this embodiment; Specifically, the process of determining a number of abnormal conveyor belts based on the real-time density of any two of the second temporary conveyor belts includes: Calculating the standard deviation of the real-time density of a single second temporary conveyor belt within a preset abnormal determination duration to obtain a density fluctuation value; Calculating the correlation coefficient of the density fluctuation values of any two of the second temporary conveyor belts to obtain a number of density fluctuation synchronization degrees; When the density fluctuation synchronization degree is less than a preset fluctuation synchronization degree threshold, it is determined that the corresponding two second temporary conveyor belts are both the abnormal conveyor belts to determine a number of abnormal conveyor belts.

[0059] The preset abnormal determination duration refers to the time window length used when determining whether a conveyor belt is abnormal, which depends on the operating rate of the production line, the characteristics of the material conveyor belt, and the occurrence frequency of abnormal phenomena. It is usually set between 5 minutes and 2 hours. In this embodiment, it is set to 30 minutes, which can capture the density fluctuations and load changes of the material conveyor belt within a reasonable time range, ensure accurate identification of abnormal situations, and at the same time avoid misjudgments caused by too long or too short time windows.

[0060] The preset fluctuation synchronization degree threshold is a standard value used to determine whether there is an abnormal synchronization phenomenon in the density fluctuations of two conveyor belts, which depends on factors such as the load distribution between conveyor belts, the stability of the production process, and the fluidity of the material. It is usually set between 0.2 and 0.5. In this embodiment, it is set to 0.3, which can accurately distinguish normal fluctuations and abnormal fluctuations, ensure timely discovery of inconsistent conveyor belt operations in actual production, and avoid problems such as material accumulation or overload caused by poor synchronization.

[0061] First, calculate the standard deviation of the real-time density of each second temporary conveyor belt within a preset abnormal determination duration to obtain a density fluctuation value. Then, calculate the correlation coefficient of the density fluctuation values between any two second temporary conveyor belts to obtain their density fluctuation synchronization degree. If the density fluctuation synchronization degree of two conveyor belts is lower than a preset fluctuation synchronization degree threshold, then determine these two conveyor belts as abnormal conveyor belts. In this way, through the synchronization of density fluctuations, conveyor belts with large fluctuations and out-of-sync can be effectively detected and determined as abnormal conveyor belts.

[0062] By calculating the density fluctuation synchronization degree, it can be determined whether there are abnormal fluctuations or instability phenomena between the second temporary conveyor belts with small differences in load weights. Setting the fluctuation synchronization degree threshold can effectively avoid misjudgment and ensure the accurate identification of abnormal conveyor belts, thereby improving the operation stability of the production line, reducing downtime and material losses.

[0063] Specifically, the process of adjusting the preset conveyor speed to form an adjusted conveyor speed or adjusting the preset load change threshold to form an adjusted load change threshold according to the number and position coordinates of all the abnormal conveyor belts within a preset adjustment duration includes: Calculate the Euclidean distance from each position coordinate at each moment within the preset adjustment duration to a preset reference coordinate to obtain a number of dispersion determination distances; Calculate the standard deviation of all the dispersion determination distances to obtain a dispersion degree; Calculate the standard deviation of all the dispersion degrees within the preset adjustment duration to obtain a dispersion fluctuation value; Adjust the preset conveyor speed to form an adjusted conveyor speed or adjust the preset load change threshold to form an adjusted load change threshold according to the dispersion fluctuation value and the number of abnormal conveyor belts.

[0064] First, calculate a number of dispersion determination distances based on the Euclidean distance between the position coordinate of each abnormal conveyor belt and the preset reference coordinate within the preset adjustment duration. These distances reflect the distribution of each abnormal conveyor belt. Then, calculate the standard deviation of these dispersion determination distances to obtain a dispersion degree to further understand the change in the overall distribution of abnormal conveyor belts. Next, calculate the standard deviation of these dispersion degrees to obtain a dispersion fluctuation value, which represents the degree of fluctuation in the distribution of abnormal conveyor belts during the adjustment duration. Finally, adjust the preset conveyor speed or load change threshold based on the dispersion fluctuation value and the number of abnormal conveyor belts to optimize the material transfer and load distribution of the production line.

[0065] By analyzing the dispersion and fluctuation values, the changing trends of the number and positions of abnormal conveyor belts can be reflected, enabling dynamic response to the actual operating conditions of the production line. Whether to adjust the conveyor speed or load threshold is determined by the dispersion and fluctuation values, so as to ensure that when the number of abnormal conveyor belts increases or their distribution becomes uneven, the parameters of the production line can be adjusted in a timely manner, avoiding equipment damage or reduced production efficiency caused by uneven load or overload, helping to improve the stability and efficiency of the production line, and ensuring the smooth progress of the material conveying process.

[0066] Specifically, the process of adjusting the preset conveyor speed to form an adjusted conveyor speed, or adjusting the preset load change threshold to form an adjusted load change threshold according to the dispersion fluctuation value and the number of abnormal conveyor belts includes: When the dispersion fluctuation value is greater than the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is greater than the preset number threshold, the preset conveyor speed is reduced according to the relative deviation between the dispersion fluctuation value and the preset dispersion fluctuation threshold and a preset first adjustment coefficient to form an adjusted conveyor speed; When the dispersion fluctuation value is less than or equal to the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is less than the preset number threshold, the standard deviation of the number of abnormal conveyor belts at each moment within the preset adjustment duration is calculated to obtain a number fluctuation value; When the number fluctuation value is greater than the preset number fluctuation threshold, the preset load change threshold is increased according to the relative deviation between the number fluctuation value and the preset number fluctuation threshold and a preset second adjustment coefficient to form an adjusted load change threshold.

[0067] The preset dispersion fluctuation threshold is a key parameter for determining the operating state of the production line, depending on the load stability of the production line and the adjustment ability of the equipment. It is usually set between 1% and 5%. In this embodiment, it is set to 3%, which can ensure timely adjustment of the conveyor speed when large fluctuations occur, prevent the system from being overloaded due to excessive load, and ensure the stability of the production line.

[0068] The preset number threshold is used to determine whether the number of abnormal conveyor belts reaches the standard for adjustment, depending on the load capacity of the production line and the equipment tolerance. It is usually set between 3 and 10. In this embodiment, it is set to 5, which can effectively identify the situation of too many abnormal conveyor belts, so as to perform appropriate scheduling and adjustment, ensure the continuous normal operation of the production line, and avoid excessive production fluctuations caused by too many abnormal conveyor belts.

[0069] The preset first adjustment coefficient is used to adjust the transmission speed when the dispersion fluctuation value is large. It depends on the carrying capacity of the production line and the sensitivity of the adjustment reaction, and is usually set between 0.1 and 0.5. In this embodiment, it is set to 0.3, which can ensure that when there are large fluctuations in the production line, the speed can be adjusted in time to relieve the load pressure, and at the same time avoid the decrease in production efficiency caused by excessive adjustment.

[0070] The preset second adjustment coefficient is used to adjust the load change threshold when the quantity fluctuation value is large. It depends on the balance between the tolerance of load change and production efficiency, and is usually set between 0.5 and 1.5. In this embodiment, it is set to 1.2, which can moderately increase the load change threshold when the load fluctuates greatly, so as to reduce unnecessary intervention, and at the same time ensure that the production line can flexibly respond to different load fluctuation requirements.

[0071] First, according to the dispersion fluctuation value and the number of abnormal conveyor belts, it is judged whether it is necessary to adjust the transmission speed or the load change threshold. When the dispersion fluctuation value is greater than the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is greater than the preset quantity threshold, it means that the load fluctuation of the production line is large and the number of abnormal conveyor belts is large. At this time, the system will relieve the load pressure by reducing the preset transmission speed to ensure the stability of the production line. If the dispersion fluctuation value is less than or equal to the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is less than the preset quantity threshold, it indicates that the load fluctuation is small and the number of abnormal conveyor belts is small. At this time, calculate the fluctuation value of the number of abnormal conveyor belts, and judge whether it is necessary to adjust the load change threshold according to this fluctuation value. When the quantity fluctuation value is greater than the preset quantity fluctuation threshold, it means that the load fluctuation is large, and it is necessary to increase the load change threshold to avoid the impact of excessive load fluctuation on the production line.

[0072] Through this dynamic analysis of the dispersion fluctuation value and the number of abnormal conveyor belts, the actual operating state of the production line can be accurately identified, and then the adjustment of the transmission speed and the load change threshold can be optimized. Specifically, when there are large load fluctuations and too many abnormal conveyor belts, the load pressure is reduced by reducing the transmission speed to avoid equipment overload; when the load fluctuation is small and the number of abnormal conveyor belts is small, the working efficiency of the production line is improved by increasing the load change threshold. This adjustment mechanism can effectively cope with the fluctuations in different production states, ensure the stable operation of the production line, improve the overall stability and load handling capacity of the production line, avoid production delays or equipment damage caused by too large or too small loads, and ensure that reasonable adjustment measures are taken in different scenarios through the comparison of fluctuation values, quantity thresholds and the use of adjustment coefficients.

[0073] Specifically, the process of generating the scheduling priority list according to the real-time load weights and position coordinates of all the material conveyor belts other than the abnormal conveyor belts includes: Calculate the relative deviation between the real-time load weight of each of the material conveyors other than the abnormal conveyor and the preset standard load to obtain a number of load deviation values; Calculate the Euclidean distance from each material conveyor to the nearest abnormal conveyor based on the position coordinates of each material conveyor and the position coordinates of each abnormal conveyor to form a number of priority distance values; Normalize all the load deviation values to form a number of load deviation normalization values; Normalize all the priority distance values to form a number of priority distance normalization values; Perform weighted summation on the load deviation values, preset load deviation weights, load deviation priority distance values, and preset priority distance weights of each material conveyor to obtain a number of priority scheduling indices; Sort all the priority scheduling indices from largest to smallest to generate a scheduling priority list.

[0074] The preset standard load refers to the benchmark load value used to evaluate the load condition of the material conveyor in the design or scheduling system, which depends on the maximum load-bearing capacity of the material conveyor, the expected working load, and the requirements of the specific production process. It is usually set between 80% and 100% of the rated load capacity of the material conveyor. In this embodiment, it is set to 90% of the rated load of the material conveyor, which can ensure that the conveyor is within the normal operating load range and avoid failures or efficiency drops caused by overloading.

[0075] The preset load deviation weight is important for measuring the influence of the load deviation on the scheduling priority. It depends on the sensitivity to the load during the production process and its impact on the equipment performance. It is usually set between 0.1 and 0.5. In this embodiment, the preset load deviation weight is set to 0.3, which can ensure that the load deviation has sufficient influence on the scheduling decision and avoid equipment loss or performance reduction caused by uneven load.

[0076] The preset priority distance weight is used to measure the degree of influence of the distance between the material conveyor and the abnormal conveyor on the scheduling priority. It depends on the urgency of the material conveyor to respond quickly when an abnormality occurs. It is usually set between 0.5 and 0.9. In this embodiment, it is set to 0.7, which can give priority to the material conveyors closer to the abnormal conveyor to ensure a faster response in case of an emergency and reduce the negative impact of the abnormal conveyor.

[0077] A scheduling priority list is generated by calculating the real-time load deviation of each material conveyor belt and the distance to the abnormal conveyor belt. First, calculate the load deviation of each material conveyor belt, and obtain the load deviation value by comparing it with the preset standard load. Then, according to the spatial position of the material conveyor belt and the abnormal conveyor belt, calculate the Euclidean distance from each conveyor belt to the nearest abnormal conveyor belt to obtain the priority distance value. Next, normalize the load deviation and the priority distance by converting each data point into a value between 0 and 1 to eliminate the influence of different dimensions. First, calculate the maximum and minimum values of the load deviation and the maximum and minimum values of the priority distance, and then use the normalization formula (the difference between the value of each data point and the minimum value divided by the difference between the maximum value and the minimum value) to scale the value of each data point according to its range. In this way, the normalized data can eliminate the dimension difference, ensure that different indicators can be compared and processed under the same standard, and facilitate subsequent weighted summation and priority sorting. Subsequently, the load deviation value, the priority distance value and the corresponding weights are weighted and summed to obtain the priority scheduling index. Finally, all material conveyor belts are sorted according to the priority scheduling index, arranged from large to small, to generate the final scheduling priority list.

[0078] By comprehensively considering the load situation of the material conveyor belt and the spatial distance to the abnormal conveyor belt, accurately judge the scheduling priority of each conveyor belt. The weighted fusion of the load deviation and the distance can reflect the working load of the conveyor belt and the urgency of the distance from the abnormal source. The normalization operation makes different parameters have a unified dimension when calculating, avoiding the influence of different numerical ranges on the results. Finally, through the scheduling priority sorting, it can ensure that when the production line processes the abnormal conveyor belt, reasonably allocate resources and scheduling order, give priority to processing the material conveyor belt with load abnormality or close to the abnormal conveyor belt, and improve production efficiency and equipment operation stability.

[0079] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. An intelligent scheduling method for a quinoa processing production line, characterized in that, Including: Collecting real-time material images, real-time load weights at each material conveyor belt in the quinoa production line operating at a preset transmission speed, and real-time gas particle concentrations above each material conveyor belt; Extracting the real-time density and real-time image change rate from the real-time material images; Determining a number of first temporary conveyor belts according to the real-time load weights of the material conveyor belts and a preset load change threshold; Determining a number of second temporary conveyor belts according to the real-time gas particle concentrations and the real-time image change rate of the first temporary conveyor belts; Determining a number of abnormal conveyor belts according to the real-time density and the real-time load weights of any two of the second temporary conveyor belts; Adjusting the preset transmission speed to form an adjusted transmission speed, or adjusting the preset load change threshold to form an adjusted load change threshold according to the position coordinates of all the abnormal conveyor belts within a preset adjustment duration; Re-determining the abnormal conveyor belts based on the adjusted transmission speed or the adjusted load change threshold, and generating a scheduling priority list according to the real-time load weights and position coordinates of all the material conveyor belts other than the abnormal conveyor belts; Diverting the abnormal conveyor belts based on the scheduling priority list.

2. The intelligent scheduling method for the quinoa processing production line according to claim 1, characterized in that The process of determining a number of first temporary conveyor belts according to the real-time load weights of the material conveyor belts and a preset load change threshold includes: Calculating the differences in the load weights at adjacent moments within a preset first determination duration to obtain a number of load change rates; Calculating the standard deviation of all the load change rates to obtain a load change fluctuation value; When the load change fluctuation value is greater than the preset load change threshold, determining the material conveyor belt as the first temporary conveyor belt to determine a number of first temporary conveyor belts.

3. The intelligent scheduling method for the quinoa processing production line according to claim 2, wherein The process of determining a number of second temporary conveyor belts according to the real-time gas particle concentrations and the real-time image change rate of the first temporary conveyor belts includes: Calculating the standard deviation of the real-time gas particle concentrations within a preset second determination duration to obtain a concentration fluctuation value; Calculating the standard deviation of the real-time image change rate within the preset second determination duration to obtain an image change fluctuation value; Determining a number of second temporary conveyor belts according to the concentration fluctuation value and the image change fluctuation value.

4. The intelligent scheduling method for the quinoa processing production line according to claim 3, characterized in that, The process of determining a number of second temporary conveyor belts according to the concentration fluctuation value and the image change fluctuation value includes: Calculating the relative deviation between the concentration fluctuation value and a preset concentration fluctuation threshold to obtain a concentration fluctuation deviation; Calculating the relative deviation between the image change fluctuation value and a preset image change fluctuation threshold to obtain an image change fluctuation deviation; Calculating the relative deviation between the concentration fluctuation deviation and the image change fluctuation deviation to obtain a consistency deviation; When the consistency deviation is less than a preset consistency deviation threshold, calculating the absolute values of the differences in the concentration fluctuation values at adjacent moments within the preset second determination duration to obtain a number of concentration fluctuation change values, and calculating the absolute values of the differences in the image change fluctuation deviations at adjacent moments within the preset second determination duration to obtain a number of image fluctuation change values; Determining a number of second temporary conveyor belts according to all the concentration fluctuation change values and the image fluctuation change values.

5. The intelligent scheduling method for the quinoa processing production line according to claim 4, wherein The process of determining a number of second temporary conveyor belts based on all the concentration fluctuation values and the image fluctuation values includes: Drawing a change curve within the preset second determination duration based on all the concentration fluctuation values to obtain a first curve; Drawing a change curve within the preset second determination duration based on all the image fluctuation values to obtain a second curve; Calculating the cosine similarity between the first curve and the second curve to obtain a change consistency; When the change consistency is less than the preset standard consistency, determining the first temporary conveyor belt as the second temporary conveyor belt to determine a number of second temporary conveyor belts.

6. The intelligent scheduling method for the quinoa processing production line according to claim 5, wherein The process of determining a number of abnormal conveyor belts based on the real-time density and the real-time load weight of any two of the second temporary conveyor belts includes: Calculating the difference between the real-time load weights of any two of the second temporary conveyor belts to obtain a weight difference value; When the weight difference value is less than the preset standard difference value, determining a number of abnormal conveyor belts based on the real-time density of any two of the second temporary conveyor belts.

7. The intelligent scheduling method for the quinoa processing production line according to claim 6, characterized in that The process of determining a number of abnormal conveyor belts based on the real-time density of any two of the second temporary conveyor belts includes: Calculating the standard deviation of the real-time density of a single second temporary conveyor belt within the preset abnormal determination duration to obtain a density fluctuation value; Calculating the correlation coefficient of the density fluctuation values of any two of the second temporary conveyor belts to obtain a number of density fluctuation synchronization degrees; When the density fluctuation synchronization degree is less than the preset fluctuation synchronization threshold, determining the corresponding two second temporary conveyor belts as the abnormal conveyor belts to determine a number of abnormal conveyor belts.

8. The intelligent scheduling method for the quinoa processing production line according to claim 7, characterized in that, The process of adjusting the preset conveyor speed to form an adjusted conveyor speed or adjusting the preset load change threshold to form an adjusted load change threshold according to the number and position coordinates of all the abnormal conveyor belts within the preset adjustment duration includes: Calculating the Euclidean distance from each position coordinate at each moment within the preset adjustment duration to a preset reference coordinate to obtain a number of dispersion determination distances; Calculating the standard deviation of all the dispersion determination distances to obtain a dispersion degree; Calculating the standard deviation of all the dispersion degrees within the preset adjustment duration to obtain a dispersion fluctuation value; Adjusting the preset conveyor speed to form an adjusted conveyor speed or adjusting the preset load change threshold to form an adjusted load change threshold according to the dispersion fluctuation value and the number of abnormal conveyor belts.

9. The intelligent scheduling method for the quinoa processing production line according to claim 8, characterized in that, The process of adjusting the preset conveyor speed to form an adjusted conveyor speed or adjusting the preset load change threshold to form an adjusted load change threshold according to the dispersion fluctuation value and the number of abnormal conveyor belts includes: When the dispersion fluctuation value is greater than the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is greater than the preset number threshold, reducing the preset conveyor speed according to the relative deviation between the dispersion fluctuation value and the preset dispersion fluctuation threshold and a preset first adjustment coefficient to form an adjusted conveyor speed; When the dispersion fluctuation value is less than or equal to the preset dispersion fluctuation threshold and the number of abnormal conveyor belts is less than the preset number threshold, calculating the standard deviation of the number of abnormal conveyor belts at each moment within the preset adjustment duration to obtain a number fluctuation value; When the quantity fluctuation value is greater than the preset quantity fluctuation threshold, increase the preset load change threshold according to the relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold and a preset second adjustment coefficient to form an adjusted load change threshold.

10. The intelligent scheduling method for the quinoa processing production line according to claim 9, characterized in that, The process of generating a scheduling priority list based on the real-time load weights and position coordinates of all the material conveyors other than the abnormal conveyor includes: Calculating the relative deviations of the real-time load weights of the material conveyors other than the abnormal conveyor from the preset standard load to obtain a number of load deviation values; Calculating the Euclidean distances from each material conveyor to the nearest abnormal conveyor according to the position coordinates of each material conveyor and the position coordinates of each abnormal conveyor to form a number of priority distance values; Normalizing all the load deviation values to form a number of load deviation normalization values; Normalizing all the priority distance values to form a number of priority distance normalization values; Performing weighted summation on the load deviation values, the preset load deviation weights, the load deviation priority distance values, and the preset priority distance weights of each material conveyor to obtain a number of priority scheduling indices; Sorting all the priority scheduling indices from largest to smallest to generate a scheduling priority list.

Images