Control method and system for separation of pomegranate extract and by-product

Abstract

The invention relates to the technical field of separation control, in particular to a control method and system for separation of pomegranate extract and by-products. Firstly, the dissociation degree of pomegranate pulp and pomegranate peel is calculated through real-time image acquisition and a deep learning model, so that the separation effect is monitored in real time, and data support is provided for subsequent control; secondly, the dissociation degree serves as a reward item of a PPO algorithm, working parameters of an ultrasonic generator are dynamically controlled, the separation efficiency of ultrasonic waves is optimized, and therefore effective control over separation between peel and pulp is achieved; finally, a Gaussian variable speed equation is provided for controlling separation of by-products, the rotating speed change of centrifugal equipment is accurately controlled according to the density difference of the pomegranate seeds and the pomegranate peels, it is ensured that efficient separation of the pomegranate seeds and the pomegranate peels is achieved at the optimal rotating speed, and therefore accurate separation control over the by-products is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of separation control, and in particular to a control method and system for separating a pomegranate extract from by-products. Background Art

[0002] Pomegranate is a nutritious fruit that contains a large number of natural functional factors, such as polyphenols, tannic acid, anthocyanins and vitamin C. In the traditional pomegranate processing, the pomegranate seeds and peels produced after the pulp is extracted are often not fully utilized, but are wasted as by-products, resulting in a serious waste of resources. Pomegranate seeds and peels are not only rich in phytochemicals, but also have certain industrial application value, such as pomegranate seed oil and natural pigments in pomegranate peels. The resource utilization of these by-products helps to improve the overall production efficiency and environmental benefits.

[0003] Although there are some methods to try to recycle pomegranate by-products, there are certain technical difficulties in the separation process because pomegranate seeds and pomegranate peels are usually mixed together during the pulp extraction process and have large morphological differences. Existing separation control technology is difficult to efficiently and accurately control the separation equipment to complete the separation of pomegranate seeds and pomegranate peels, thereby limiting its further resource utilization. Even if traditional mechanical separation, screening or hydraulic separation methods are used, the separation of the two cannot be accurately controlled, resulting in a large amount of valuable pomegranate by-products. Waste of resources. Therefore, it is urgent to develop a new and accurate separation control technology to achieve efficient and reliable by-product separation and recovery.

[0004] To this end, a control method and system for separating pomegranate extract from by-products are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a control method and system for separating pomegranate extract from by-products, calculate the dissociation degree of pomegranate pulp and pomegranate peel through real-time image acquisition and deep learning model, and provide a basis for optimizing ultrasonic processing parameters; optimize the control of ultrasonic parameters by taking the dissociation degree as a reward item of PPO algorithm to achieve more efficient separation of pulp and peel; design a speed curve according to the density difference between pomegranate seeds and pomegranate peel through Gaussian speed equation, accurately control the speed change of centrifugal equipment, thereby achieving efficient and accurate separation.

[0006] To achieve the above object, the present invention provides the following technical solutions: A control method for separating a pomegranate extract from by-products, comprising: The pomegranate raw material is sent to a crusher for preliminary crushing to obtain pre-treated pomegranates; The pretreated pomegranate is placed in a separation kettle, and ultrasonic waves are applied to the medium in the separation kettle through an ultrasonic generator, and images in the separation kettle are collected to observe and calculate the degree of dissociation of the pomegranate pulp and the pomegranate peel, and the degree of dissociation is used as a reward item of the PPO algorithm to control the ultrasonic parameters of the ultrasonic generator; the ultrasonic parameters include ultrasonic frequency, ultrasonic power, ultrasonic amplitude and action time; When the dissociation degree is greater than a first threshold, the ultrasonic generator is changed to a constant power, and the pomegranate pulp in the separation kettle is subjected to a pressurized liquid extraction method to extract functional factors to obtain an extract; the extraction rate change of the functional factors in the extract is measured by a sensor, and if the extraction rate change of the concentration within the first time interval is less than a second threshold, the extract and the by-products in the separation kettle are preliminarily separated; The collected by-products are placed in a centrifugal device and stirred to make the by-products evenly distributed in the medium, the densities of the pomegranate seeds and the pomegranate peels in the by-products are calculated respectively, and a Gaussian speed-changing equation is designed according to the density difference between the two, and the speed of the centrifugal device is controlled by the Gaussian speed-changing equation; When the centrifugal device stops running, the separated pomegranate seeds and pomegranate peels are collected.

[0007] Further, calculating the degree of dissociation of the pomegranate pulp and the pomegranate peel includes: Collect real-time images from the separation kettle and perform denoising, color space conversion and contrast enhancement to obtain pre-processed images; Segmenting the pomegranate pulp and pomegranate peel in the preprocessed image through a deep learning model to generate a corresponding segmentation mask image; Calculating the degree of dissociation according to the mask area of ​​the pomegranate peel and the total mask area in the segmentation mask image; The calculation formula of the dissociation degree is: ; in, represents the degree of dissociation, represents the mask area of ​​the pomegranate peel, Represents the total area of ​​the mask.

[0008] Furthermore, performing ultrasonic parameter control on the ultrasonic generator includes: S201: Initialize the policy network, value network, action space and reward function of the PPO algorithm; S202: selecting a set of ultrasound parameters as an initial action, and obtaining an environmental state according to the dissociation degree; S203: using the strategy network to analyze the environmental state and adjust the ultrasonic parameters; S204: controlling the ultrasonic generator according to the adjusted ultrasonic parameters, and calculating the reward value; S205: storing the interaction data into the experience pool, and using the value network to calculate the advantage function; S206: Optimizing the strategy network by cutting the strategy loss function and updating the value network by minimizing the mean square error; S207: Adjust the ultrasound parameters according to the optimized strategy network, and determine whether the dissociation degree is greater than a first threshold. If so, stop iteration; otherwise, return to S204.

[0009] Further, the extraction conditions for functional factor extraction are: The extraction medium is an ethanol-water mixed solvent, the extraction temperature is 50°C, the extraction pressure is 15MPa, the extraction time is 45 minutes, and the ultrasonic power is 500W.

[0010] Furthermore, the calculation formula of the Gaussian speed change equation is: ; Where t represents the time variable, Indicates the density of pomegranate seeds, represents the density of the pomegranate peel, represents the initial speed, Indicates the speed adjustment coefficient, represents the natural index, represents the mean value of the curve, Represents standard deviation.

[0011] The present invention also provides a control system for separating pomegranate extract and by-products, comprising: A pre-processing module is used to feed the pomegranate raw material into a crusher for preliminary crushing to obtain pre-processed pomegranates; A dissociation module, for placing the pretreated pomegranate into a separation kettle, applying ultrasonic waves to the medium in the separation kettle through an ultrasonic generator, and simultaneously collecting images in the separation kettle to observe and calculate the degree of dissociation of the pomegranate pulp and the pomegranate peel, and using the degree of dissociation as a reward item of the PPO algorithm to control the ultrasonic parameters of the ultrasonic generator; the ultrasonic parameters include ultrasonic frequency, ultrasonic power, ultrasonic amplitude and action time; The first separation module is used for, when the dissociation degree is greater than a first threshold value, changing the ultrasonic generator to a constant power, and extracting the functional factors from the pomegranate pulp in the separation kettle by a pressurized liquid extraction method to obtain an extract; measuring the extraction rate change of the functional factors in the extract by a sensor, and if the extraction rate change of the concentration within the first time interval is less than a second threshold value, preliminarily separating the extract and the by-products in the separation kettle; The second separation module is used to put the collected by-products into a centrifugal device and stir them to make the by-products evenly distributed in the medium, calculate the density of the pomegranate seeds and pomegranate peels in the by-products respectively, and design a Gaussian variable speed equation according to the density difference between the two, and control the speed of the centrifugal device by the Gaussian variable speed equation; when the centrifugal device stops running, collect the separated pomegranate seeds and pomegranate peels.

[0012] Further, calculating the degree of dissociation of the pomegranate pulp and the pomegranate peel includes: Collect real-time images from the separation kettle and perform denoising, color space conversion and contrast enhancement to obtain pre-processed images; Segmenting the pomegranate pulp and pomegranate peel in the preprocessed image through a deep learning model to generate a corresponding segmentation mask image; Calculating the degree of dissociation according to the mask area of ​​the pomegranate peel and the total mask area in the segmentation mask image; The calculation formula of the dissociation degree is: ; in, represents the degree of dissociation, represents the mask area of ​​the pomegranate peel, Represents the total area of ​​the mask.

[0013] Furthermore, performing ultrasonic parameter control on the ultrasonic generator includes: S201: Initialize the policy network, value network, action space and reward function of the PPO algorithm; S202: selecting a set of ultrasound parameters as an initial action, and obtaining an environmental state according to the dissociation degree; S203: using the strategy network to analyze the environmental state and adjust the ultrasonic parameters; S204: controlling the ultrasonic generator according to the adjusted ultrasonic parameters, and calculating the reward value; S205: storing the interaction data into the experience pool, and using the value network to calculate the advantage function; S206: Optimizing the strategy network by cutting the strategy loss function and updating the value network by minimizing the mean square error; S207: Adjust the ultrasound parameters according to the optimized strategy network, and determine whether the dissociation degree is greater than a first threshold. If so, stop iteration; otherwise, return to S204.

[0014] Further, the extraction conditions for functional factor extraction are: The extraction medium is an ethanol-water mixed solvent, the extraction temperature is 50°C, the extraction pressure is 15MPa, the extraction time is 45 minutes, and the ultrasonic power is 500W.

[0015] Furthermore, the calculation formula of the Gaussian speed change equation is: ; Where t represents the time variable, Indicates the density of pomegranate seeds, represents the density of the pomegranate peel, represents the initial speed, Indicates the speed adjustment coefficient, represents the natural index, represents the mean of the curve and represents the standard deviation.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. By collecting images in the separation kettle in real time and performing denoising, color space conversion and contrast enhancement, the image quality can be significantly improved to ensure that the deep learning model can accurately segment the pomegranate pulp and peel; the generated segmentation mask map provides an accurate basis for calculating the degree of dissociation, and the dissociation effect is evaluated in real time based on the ratio of the peel mask area to the total mask area. This process improves the separation accuracy and enables the ultrasonic parameters to be dynamically adjusted according to the degree of dissociation, thereby achieving more efficient and accurate separation of the pulp and peel, improving production efficiency and raw material utilization.

[0017] 2. By using the degree of dissociation as a reward item for the PPO algorithm, the ultrasonic generator can be intelligently adjusted, and the frequency, power, amplitude, action time and other parameters of the ultrasonic wave can be dynamically adjusted according to the degree of dissociation calculated in real time. Whenever the degree of dissociation increases, the PPO algorithm will give rewards, thereby continuously optimizing the ultrasonic parameters and improving the separation efficiency. This adaptive control method not only improves the separation effect of the pulp and peel, but also reduces energy waste, ensuring the efficiency and stability of the production process.

[0018] 3. By calculating the density of pomegranate seeds and pomegranate peels in the by-products and using the density difference between the two to design the Gaussian speed-changing equation, the speed change of the centrifugal equipment can be accurately controlled so that it can be optimized and adjusted according to the sedimentation characteristics of different substances during the separation process. By dynamically adjusting the speed, it can ensure that the two are separated under the most suitable conditions. This speed-changing control method based on density difference can efficiently and accurately complete the separation of pomegranate seeds and peels. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a control method for separating a pomegranate extract from by-products provided in an embodiment of the present invention; Figure 2 Ultrasonic parameter control flow chart provided by an embodiment of the present invention; Figure 3 A structural diagram of a control system for separating pomegranate extract and by-products provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0021] A control method and system for separating pomegranate extract and by-products, such as Figure 1 As shown, including: S100: sending the pomegranate raw material into a crusher for preliminary crushing to obtain pre-treated pomegranate; S200: placing the pretreated pomegranate into a separation kettle, applying ultrasonic waves to the medium in the separation kettle through an ultrasonic generator, collecting images in the separation kettle to observe and calculate the degree of dissociation of the pomegranate pulp and the pomegranate peel, and using the degree of dissociation as a reward item of the PPO algorithm to control the ultrasonic parameters of the ultrasonic generator; the ultrasonic parameters include ultrasonic frequency, ultrasonic power, ultrasonic amplitude and action time; Further, calculating the degree of dissociation of the pomegranate pulp and the pomegranate peel includes: Collect real-time images from the separation kettle and perform denoising, color space conversion and contrast enhancement to obtain pre-processed images; Segmenting the pomegranate pulp and pomegranate peel in the preprocessed image through a deep learning model to generate a corresponding segmentation mask image; Calculating the degree of dissociation according to the mask area of ​​the pomegranate peel and the total mask area in the segmentation mask image; The calculation formula of the dissociation degree is: ; in, represents the degree of dissociation, represents the mask area of ​​the pomegranate peel, Represents the total area of ​​the mask.

[0022] Specifically, an industrial camera is used to collect images of the pomegranate pulp and pomegranate peel in the separation kettle, and the images are collected every 15 seconds. Gaussian filtering is used to remove noise in the image, and the image is converted from RGB space to HSV space. The image contrast is enhanced by histogram equalization to make the color features of the pulp and peel more prominent. The pomegranate pulp and pomegranate peel in the preprocessed image are segmented by a deep learning model to generate a corresponding segmentation mask map, wherein the deep learning model can be U-Net, DeepLab v3 or other semantic segmentation models. The obtained segmentation mask map can calculate the dissociation degree according to the area (i.e., the number of pixels) occupied by the pulp and peel in the image. The dissociation degrees at some moments are shown in Table 1.

[0023] Table 1 Changes in dissociation degree of pomegranate pulp and pomegranate peel at different times

[0024] By collecting real-time images in the separation kettle and performing denoising, color space conversion, and contrast enhancement, the image quality can be effectively improved, ensuring that the subsequent deep learning model can accurately segment the pomegranate pulp and peel. The segmentation mask generated by the deep learning model can accurately distinguish the areas of the pulp and peel, and further calculate the degree of dissociation based on the ratio of the peel mask area to the total mask area, thereby monitoring the effect of the extraction process in real time. This method can efficiently and accurately evaluate the separation effect and provide a basis for the optimization of ultrasonic treatment parameters.

[0025] Further, the ultrasonic generator is subjected to ultrasonic parameter control such as Figure 2 As shown, including: S201: Initialize the policy network, value network, action space and reward function of the PPO algorithm; S202: selecting a set of ultrasound parameters as an initial action, and obtaining an environmental state according to the dissociation degree; S203: using the strategy network to analyze the environmental state and adjust the ultrasonic parameters; S204: controlling the ultrasonic generator according to the adjusted ultrasonic parameters, and calculating the reward value; S205: storing the interaction data into the experience pool, and using the value network to calculate the advantage function; S206: Optimizing the strategy network by cutting the strategy loss function and updating the value network by minimizing the mean square error; S207: Adjust the ultrasound parameters according to the optimized strategy network, and determine whether the dissociation degree is greater than a first threshold. If so, stop iteration; otherwise, return to S204.

[0026] Specifically, initialize the policy network , initialize the value network , initialize the action space ,in represents the ultrasonic frequency, P represents the ultrasonic power, V represents the ultrasonic amplitude, and T represents the action time. and Indicates the lower and upper limits of each parameter. In this embodiment, the action space is set as shown in Table 2, and the initialization reward function is defined as: ,in represents the reward function, represents the dissociation weight, represents the energy consumption weight; the initial action is defined as , obtain the environmental state according to the degree of dissociation , according to the current policy network Analyze the state of the environment , and then get a new set of actions , that is, the adjusted ultrasonic parameters; the ultrasonic generator is controlled by the adjusted ultrasonic parameters, and the reward value is calculated ; The interactive data Store it in the experience pool and use the time difference method to calculate the advantage function. The calculation formula of the advantage function is: ; in, Indicates action and environmental status The advantage function under Represents the discount factor, usually ranging from 0.95 to 0.99. Indicates the environmental status The estimated value of the value network below, Indicates the environmental status The estimated value of the value network; update the parameters of the policy network by cutting the policy loss function , the update formula of the clipping strategy loss function is: ; in, represents the clipping strategy loss function, represents the expected value, represents the minimum function, represents the probability ratio of the new and old strategies, represents the cutting strategy function, represents the clipping threshold, which is usually 0.1~0.2. The formula for minimizing the mean square error is: ; in, Indicates minimizing the mean square error; adjust the ultrasound parameters according to the optimized strategy network, and iterate cyclically until the degree of dissociation is greater than the first threshold. In this embodiment, the first threshold is 0.95. The data of the ultrasound parameters during some iterations are shown in Table 3.

[0027] Table 2 Lower and upper limits of the action space parameters of the PPO algorithm

[0028] By using the degree of dissociation as a reward item in the PPO algorithm, the adaptive optimization of the ultrasonic generator parameters can be achieved. After each ultrasonic action, the system evaluates the separation effect by calculating the degree of dissociation in real time. If the degree of dissociation increases, a reward is given, otherwise the reward is reduced. This feedback-based intelligent control method can dynamically adjust parameters such as ultrasonic frequency, power, amplitude, and action time to accurately achieve efficient separation of pomegranate pulp and peel, thereby continuously optimizing the extraction process, improving separation efficiency, reducing energy consumption, and ensuring stable product quality.

[0029] Table 3 Data changes of ultrasound parameters at different times during the iteration process

[0030] S300: when the dissociation degree is greater than a first threshold, the ultrasonic generator is changed to a constant power, and the pomegranate pulp in the separation kettle is subjected to a pressurized liquid extraction method to extract functional factors to obtain an extract; a change in the extraction rate of the functional factors in the extract is measured by a sensor, and if the change in the extraction rate of the concentration within the first time interval is less than a second threshold, the extract and the by-products in the separation kettle are preliminarily separated; Specifically, in this embodiment, the first time interval is 2 minutes, the extraction rate change is mainly measured for the extraction rate of polyphenols, and the second threshold is 0.1%, that is, if the difference in the polyphenol extraction rate does not exceed 0.1% in two consecutive measurements, the extraction is stopped and the extract and the by-products are separated; in addition, the extraction rate change can also be targeted at pectin, organic acids, flavonoids or other functional factors.

[0031] Further, the extraction conditions for functional factor extraction are: The extraction medium is an ethanol-water mixed solvent, the extraction temperature is 50°C, the extraction pressure is 15MPa, the extraction time is 45 minutes, and the ultrasonic power is 500W.

[0032] The functional factors of pomegranate pulp are extracted by pressurized liquid extraction method. By using appropriate extraction conditions, the functional factors in pomegranate can be efficiently extracted.

[0033] S400: placing the collected by-products into a centrifugal device and stirring them to make the by-products evenly distributed in the medium, respectively calculating the density of pomegranate seeds and pomegranate peels in the by-products, and designing a Gaussian speed-changing equation according to the density difference between the two, and controlling the speed of the centrifugal device by the Gaussian speed-changing equation; Furthermore, the calculation formula of the Gaussian speed change equation is: ; Where t represents the time variable, Indicates the density of pomegranate seeds, represents the density of the pomegranate peel, represents the initial speed, Indicates the speed adjustment coefficient, represents the natural index, represents the mean value of the curve, Represents standard deviation.

[0034] Specifically, Responsible for adjusting the maximum speed, Responsible for adjusting the time when the maximum speed is reached, Responsible for adjusting the speed change rate. In this embodiment , , , .

[0035] By calculating the density of pomegranate seeds and peels in the by-products and using the density difference between the two to design the Gaussian speed equation, the speed of the centrifuge can be accurately controlled so that it can be adaptively adjusted according to the material characteristics at different stages. The smooth speed change of the Gaussian curve optimizes the separation process, ensures efficient and accurate separation of pomegranate seeds and peels, and improves production efficiency and separation quality.

[0036] S500: After the centrifugal device stops running, the separated pomegranate seeds and pomegranate peels are collected. Embodiment 2

[0037] In order to improve the utilization rate of raw materials, a beverage company upgraded the separation control equipment of the original production line and adopted a control system for separating pomegranate extract and by-products proposed by the present invention, including: A pre-processing module is used to feed the pomegranate raw material into a crusher for preliminary crushing to obtain pre-processed pomegranates; A dissociation module, for placing the pretreated pomegranate into a separation kettle, applying ultrasonic waves to the medium in the separation kettle through an ultrasonic generator, and simultaneously collecting images in the separation kettle to observe and calculate the degree of dissociation of the pomegranate pulp and the pomegranate peel, and using the degree of dissociation as a reward item of the PPO algorithm to control the ultrasonic parameters of the ultrasonic generator; the ultrasonic parameters include ultrasonic frequency, ultrasonic power, ultrasonic amplitude and action time; The first separation module is used for, when the dissociation degree is greater than a first threshold value, changing the ultrasonic generator to a constant power, and extracting the functional factors from the pomegranate pulp in the separation kettle by a pressurized liquid extraction method to obtain an extract; measuring the extraction rate change of the functional factors in the extract by a sensor, and if the extraction rate change of the concentration within the first time interval is less than a second threshold value, preliminarily separating the extract and the by-products in the separation kettle; The second separation module is used to put the collected by-products into a centrifugal device and stir them to make the by-products evenly distributed in the medium, calculate the density of the pomegranate seeds and pomegranate peels in the by-products respectively, and design a Gaussian variable speed equation according to the density difference between the two, and control the speed of the centrifugal device by the Gaussian variable speed equation; when the centrifugal device stops running, collect the separated pomegranate seeds and pomegranate peels.

[0038] Further, calculating the degree of dissociation of the pomegranate pulp and the pomegranate peel includes: Collect real-time images from the separation kettle and perform denoising, color space conversion and contrast enhancement to obtain pre-processed images; Segmenting the pomegranate pulp and pomegranate peel in the preprocessed image through a deep learning model to generate a corresponding segmentation mask image; Calculating the degree of dissociation according to the mask area of ​​the pomegranate peel and the total mask area in the segmentation mask image; The calculation formula of the dissociation degree is: ; in, represents the degree of dissociation, represents the mask area of ​​the pomegranate peel, Represents the total area of ​​the mask.

[0039] Furthermore, performing ultrasonic parameter control on the ultrasonic generator includes: S201: Initialize the policy network, value network, action space and reward function of the PPO algorithm; S202: selecting a set of ultrasound parameters as an initial action, and obtaining an environmental state according to the dissociation degree; S203: using the strategy network to analyze the environmental state and adjust the ultrasonic parameters; S204: controlling the ultrasonic generator according to the adjusted ultrasonic parameters, and calculating the reward value; S205: storing the interaction data into the experience pool, and using the value network to calculate the advantage function; S206: Optimizing the strategy network by cutting the strategy loss function and updating the value network by minimizing the mean square error; S207: Adjust the ultrasound parameters according to the optimized strategy network, and determine whether the dissociation degree is greater than a first threshold. If so, stop iteration; otherwise, return to S204.

[0040] Further, the extraction conditions for functional factor extraction are: The extraction medium is an ethanol-water mixed solvent, the extraction temperature is 50°C, the extraction pressure is 15MPa, the extraction time is 45 minutes, and the ultrasonic power is 500W.

[0041] Furthermore, the calculation formula of the Gaussian speed change equation is: ; Where t represents the time variable, Indicates the density of pomegranate seeds, represents the density of the pomegranate peel, represents the initial speed, Indicates the speed adjustment coefficient, represents the natural index, represents the mean value of the curve, Represents standard deviation.

[0042] The data comparison before and after the control system upgrade is shown in Table 4. The data shows that through the upgraded pomegranate extract and by-product separation control system, the dissociation rate of pulp and peel increased by 12%, the dissociation time was shortened by 15 minutes, the extraction rate of functional factors (polyphenols) increased by 7.5%, and the by-product separation rate reached 92%. These improvements not only significantly improved the raw material utilization rate and production efficiency, but also optimized the extraction effect of functional factors and improved product quality, fully demonstrating the comprehensive advantages of the upgraded system in time efficiency, resource utilization and separation accuracy.

[0043] Table 4 Data comparison before and after control system upgrade

[0044] Through the combination of the ultrasonic generator control system and the PPO algorithm, the ultrasonic parameters can be adjusted in real time according to the degree of dissociation of the pomegranate pulp and peel, thereby optimizing the separation process. The ultrasonic power switches to constant power after reaching the preset dissociation threshold to ensure stable energy output and improve separation efficiency. In the functional factor extraction stage, by real-time monitoring of the extraction rate changes, the initial separation of liquid and by-products is automatically judged and performed to ensure the efficiency and stability of the extraction process. Subsequently, the by-products are separated by a centrifugal device with Gaussian variable speed control, which not only improves the separation accuracy, but also reduces energy consumption, and ultimately achieves efficient separation of pomegranate seeds and peels.

[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A control method for separating pomegranate extract and by-products, characterized in that: include: The pomegranate raw material is sent to a crusher for preliminary crushing to obtain pre-treated pomegranates; The pretreated pomegranate is placed in a separation kettle, and ultrasonic waves are applied to the medium in the separation kettle through an ultrasonic generator, and images in the separation kettle are collected to observe and calculate the degree of dissociation of the pomegranate pulp and the pomegranate peel, and the degree of dissociation is used as a reward item of the PPO algorithm to control the ultrasonic parameters of the ultrasonic generator; the ultrasonic parameters include ultrasonic frequency, ultrasonic power, ultrasonic amplitude and action time; When the dissociation degree is greater than a first threshold, the ultrasonic generator is changed to a constant power, and the pomegranate pulp in the separation kettle is subjected to a pressurized liquid extraction method to extract functional factors to obtain an extract; the extraction rate change of the functional factors in the extract is measured by a sensor, and if the extraction rate change of the concentration within the first time interval is less than a second threshold, the extract and the by-products in the separation kettle are preliminarily separated; The collected by-products are placed in a centrifugal device and stirred to make the by-products evenly distributed in the medium, the densities of the pomegranate seeds and the pomegranate peels in the by-products are calculated respectively, and a Gaussian speed-changing equation is designed according to the density difference between the two, and the speed of the centrifugal device is controlled by the Gaussian speed-changing equation; When the centrifugal device stops running, the separated pomegranate seeds and pomegranate peels are collected.

2. The method for controlling the separation of pomegranate extract and by-products according to claim 1, characterized in that: Calculation of the degree of dissociation of pomegranate pulp and pomegranate peel includes: Collect real-time images from the separation kettle and perform denoising, color space conversion and contrast enhancement to obtain pre-processed images; Segmenting the pomegranate pulp and pomegranate peel in the preprocessed image through a deep learning model to generate a corresponding segmentation mask image; Calculating the degree of dissociation according to the mask area of ​​the pomegranate peel and the total mask area in the segmentation mask image; The calculation formula of the dissociation degree is: ； in, represents the degree of dissociation, represents the mask area of ​​the pomegranate peel, Represents the total area of ​​the mask.

3. The method for controlling the separation of pomegranate extract and by-products according to claim 1, characterized in that: The ultrasonic parameter control of the ultrasonic generator comprises: S201: Initialize the policy network, value network, action space and reward function of the PPO algorithm; S202: selecting a set of ultrasound parameters as an initial action, and obtaining an environmental state according to the dissociation degree; S203: using the strategy network to analyze the environmental state and adjust the ultrasonic parameters; S204: controlling the ultrasonic generator according to the adjusted ultrasonic parameters, and calculating the reward value; S205: storing the interaction data into the experience pool, and using the value network to calculate the advantage function; S206: Optimizing the strategy network by cutting the strategy loss function and updating the value network by minimizing the mean square error; S207: Adjust the ultrasound parameters according to the optimized strategy network, and determine whether the dissociation degree is greater than a first threshold. If so, stop iteration; otherwise, return to S204.

4. The method for controlling the separation of pomegranate extract and by-products according to claim 1, characterized in that: The extraction conditions of the pressurized liquid phase extraction method are: The extraction medium is an ethanol-water mixed solvent, the extraction temperature is 50°C, the extraction pressure is 15MPa, the extraction time is 45 minutes, and the ultrasonic power is 500W.

5. The method for controlling the separation of pomegranate extract and by-products according to claim 1, characterized in that: The calculation formula of the Gaussian speed change equation is: ； Where t represents the time variable, Indicates the density of pomegranate seeds, represents the density of the pomegranate peel, represents the initial speed, Indicates the speed adjustment coefficient, represents the natural index, represents the mean value of the curve, Represents standard deviation.

6. A control system for separating pomegranate extract and by-products, characterized in that: include: A pre-processing module is used to feed the pomegranate raw material into a crusher for preliminary crushing to obtain pre-processed pomegranates; A dissociation module, for placing the pretreated pomegranate into a separation kettle, applying ultrasonic waves to the medium in the separation kettle through an ultrasonic generator, and simultaneously collecting images in the separation kettle to observe and calculate the degree of dissociation of the pomegranate pulp and the pomegranate peel, and using the degree of dissociation as a reward item of the PPO algorithm to control the ultrasonic parameters of the ultrasonic generator; the ultrasonic parameters include ultrasonic frequency, ultrasonic power, ultrasonic amplitude and action time; The first separation module is used for, when the dissociation degree is greater than a first threshold value, changing the ultrasonic generator to a constant power, and extracting the functional factors from the pomegranate pulp in the separation kettle by a pressurized liquid extraction method to obtain an extract; measuring the extraction rate change of the functional factors in the extract by a sensor, and if the extraction rate change of the concentration within the first time interval is less than a second threshold value, preliminarily separating the extract and the by-products in the separation kettle; The second separation module is used to put the collected by-products into a centrifugal device and stir them to make the by-products evenly distributed in the medium, calculate the density of the pomegranate seeds and pomegranate peels in the by-products respectively, and design a Gaussian variable speed equation according to the density difference between the two, and control the speed of the centrifugal device by the Gaussian variable speed equation; when the centrifugal device stops running, collect the separated pomegranate seeds and pomegranate peels.

7. A control system for separating pomegranate extract and by-products according to claim 6, characterized in that: Calculation of the degree of dissociation of pomegranate pulp and pomegranate peel includes: Collect real-time images from the separation kettle and perform denoising, color space conversion and contrast enhancement to obtain pre-processed images; Segmenting the pomegranate pulp and pomegranate peel in the preprocessed image through a deep learning model to generate a corresponding segmentation mask image; Calculating the degree of dissociation according to the mask area of ​​the pomegranate peel and the total mask area in the segmentation mask image; The calculation formula of the dissociation degree is: ； in, represents the degree of dissociation, represents the mask area of ​​the pomegranate peel, Represents the total area of ​​the mask.

8. A control system for separating pomegranate extract and by-products according to claim 6, characterized in that: The ultrasonic parameter control of the ultrasonic generator comprises: S201: Initialize the policy network, value network, action space and reward function of the PPO algorithm; S202: selecting a set of ultrasound parameters as an initial action, and obtaining an environmental state according to the dissociation degree; S203: using the strategy network to analyze the environmental state and adjust the ultrasonic parameters; S204: controlling the ultrasonic generator according to the adjusted ultrasonic parameters, and calculating the reward value; S205: storing the interaction data into the experience pool, and using the value network to calculate the advantage function; S206: Optimizing the strategy network by cutting the strategy loss function and updating the value network by minimizing the mean square error; S207: Adjust the ultrasound parameters according to the optimized strategy network, and determine whether the dissociation degree is greater than a first threshold. If so, stop iteration; otherwise, return to S204.

9. A control system for separating pomegranate extract and by-products according to claim 6, characterized in that: The extraction conditions for functional factor extraction are: The extraction medium is an ethanol-water mixed solvent, the extraction temperature is 50°C, the extraction pressure is 15MPa, the extraction time is 45 minutes, and the ultrasonic power is 500W.

10. A control system for separating pomegranate extract and by-products according to claim 6, characterized in that: The calculation formula of the Gaussian speed change equation is: ； Where t represents the time variable, Indicates the density of pomegranate seeds, represents the density of the pomegranate peel, represents the initial speed, Indicates the speed adjustment coefficient, represents the natural index, represents the mean value of the curve, Represents standard deviation.

Images