Separation system for bio-based material manufacturing based on artificial intelligence

Abstract

The invention relates to the technical field of bio-based material manufacturing, and discloses an artificial intelligence-based separation system for bio-based material manufacturing, comprising: a bio-based material pretreatment module for performing primary treatment on raw materials of a bio-based material; and the separation device is used for carrying out separation treatment on the bio-based material by adopting a separation mode suitable for the type of the bio-based material according to the characteristics of the bio-based material. According to the separation system for manufacturing the bio-based material based on artificial intelligence, through intelligent control and dynamic parameter adjustment, the separation efficiency of the bio-based material can be remarkably improved, the production period is shortened, manual intervention and energy consumption are reduced through intelligent separation control and optimization capacity, the production cost is reduced, and the production efficiency is improved. By means of the self-adaptive separation capacity on complex bio-based material components, the production requirements of different kinds of bio-based materials can be met, and the application field of the bio-based materials is widened.

Description

Technical Field

[0001] The present invention relates to the technical field of biobased material manufacturing, and specifically to a separation system for biobased material manufacturing based on artificial intelligence. Background Art

[0002] With the global emphasis on sustainable development and environmental protection, biobased materials, as a kind of green and renewable materials, have gradually become a research hotspot in the field of materials science. The manufacturing process of biobased materials involves various complex separation technologies, and the efficiency and precision of these technologies directly affect the production cost, quality, and application scope of biobased materials.

[0003] Traditional biobased material separation technologies mainly rely on manual operations and equipment with fixed parameters, and there are many limitations. First, it is difficult to achieve precise control of the separation process through manual operations, and it is easily affected by human factors, resulting in low separation efficiency and unstable product quality. Second, equipment with fixed parameters cannot adapt to the complex changes in the composition of biobased materials and different types of production requirements, restricting the application scope of biobased materials. In addition, traditional separation technologies usually require a large amount of energy consumption and manual intervention, increasing the production cost and reducing the production efficiency.

[0004] In recent years, with the rapid development of artificial intelligence technology, its application in industrial automation and process control has gradually attracted attention. Artificial intelligence technology can analyze and process a large amount of data through deep learning algorithms to achieve intelligent control and optimization of complex systems. However, there are few reports on applying artificial intelligence technology to the separation system for biobased material manufacturing at present, and there is no mature solution in the existing technology that can effectively solve the problems such as low separation efficiency, high cost, and poor adaptability of biobased materials. Summary of the Invention

[0005] (1) Technical Problems to be Solved

[0006] Aiming at the deficiencies of the existing technology, the present invention provides a separation system for biobased material manufacturing based on artificial intelligence. Through intelligent control and dynamic parameter adjustment, it can significantly improve the separation efficiency of biobased materials, shorten the production cycle, reduce manual intervention and energy consumption through intelligent separation control and optimization capabilities, lower the production cost, and through the adaptive separation ability for complex biobased material compositions, it can meet the production requirements of different types of biobased materials, broaden the application field of biobased materials, and solve the problems of low separation efficiency, unstable product quality, and inability to adapt to the complex changes in the composition of biobased materials and different types of production requirements.

[0007] (2) Technical Solutions

[0008] To achieve the above object, the present invention provides the following technical solutions: A separation system for manufacturing biobased materials based on artificial intelligence, comprising:

[0009] A biobased material pretreatment module, which is used for preliminarily treating the raw materials of biobased materials;

[0010] A separation device, which is used for separating biobased materials by a separation method applicable to the type of biobased materials according to the characteristics of biobased materials;

[0011] A sensor module, which is distributed on the biobased material pretreatment module and the separation device and is used for real-time monitoring of various parameters during the separation process;

[0012] An artificial intelligence control system, based on a deep learning algorithm, performs real-time analysis and processing on the data collected by the sensor module, combines historical data and preset separation targets, dynamically adjusts the operating parameters of the separation device, and optimizes the separation process;

[0013] A data storage and analysis module: used for storing all data during the separation process. Through in-depth analysis of historical data, the system can continuously optimize its own control strategy.

[0014] Preferably, the sensor module includes:

[0015] A temperature sensor for real-time monitoring of temperature changes in the pretreatment unit and the separation device;

[0016] A pressure sensor for monitoring pressure changes in the separation device;

[0017] A pH value sensor for real-time monitoring of the acidity and alkalinity of the biobased material solution;

[0018] A concentration sensor for monitoring changes in the concentration of the target component in the biobased material solution;

[0019] A flow rate sensor for monitoring the flow rate of the biobased material solution in the separation device;

[0020] An optical sensor for detecting the optical properties of specific components in biobased materials;

[0021] The sensor network is connected to the artificial intelligence control system through wireless or wired communication technology; each sensor is equipped with a data acquisition module, which can convert the parameter data monitored in real time into digital signals and transmit them to the artificial intelligence control system through a communication protocol.

[0022] Preferably, the deep learning algorithm includes the following steps:

[0023] S1. Data preparation and preprocessing:

[0024] Collect the historical data collected by the sensor network during the manufacturing process of biobased materials, and remove the noise, missing values, and outliers in the data;

[0025] Extract key features from the original data to reduce the data dimension and improve the model training efficiency;

[0026] S2. Model selection and training:

[0027] According to the characteristics of the separation process and the type of sensor data, select a suitable deep learning model; use the historical data to train the deep learning model; during the training process, the model optimizes its internal parameters by learning the relationship between the input data and the output data;

[0028] Adopt the supervised learning method to optimize the model parameters by minimizing the error between the predicted value and the actual value;

[0029] S3. Model prediction and parameter optimization:

[0030] The trained deep learning model is used to predict the optimal parameter combination of the separation process in real time; the model outputs the predicted separation parameters according to the real-time data collected by the sensor network;

[0031] S4. Feedback and adaptive learning:

[0032] Monitor the actual operation during the separation process in real time, and adjust the deep learning model and the optimization algorithm according to the feedback data;

[0033] Adopt online learning technology to enable the deep learning model to update its parameters in real time to adapt to new data patterns.

[0034] Preferably, the separation device includes a housing, a control panel provided on the front of the housing, and a cover plate hinged above the housing;

[0035] An fixing plate is fixedly connected inside the housing, and a plurality of test tube containers and a driving assembly are arranged on the fixing plate. The driving assembly includes a motor for centrifugally driving the plurality of test tube containers.

[0036] Preferably, a plurality of fixing sleeves are rotatably connected inside the fixing plate, and the plurality of test tube containers are respectively installed inside the plurality of fixing sleeves. The motor is used to synchronously rotate and drive the plurality of fixing sleeves.

[0037] Preferably, a gear sleeve is rotatably connected to the top of the fixing plate, and tooth rings meshing with the outer surface of the gear sleeve are fixedly connected to the outer surfaces of the plurality of fixing sleeves;

[0038] The motor is fixed to the bottom of the fixed plate, and an output shaft of the motor is fixedly connected to a gear that meshes with an outer surface of the gear sleeve.

[0039] Preferably, a partition member is provided inside the test tube container, and the inside of the test tube container is separated into an upper cavity and a lower cavity by the partition member. The bottom end of the test tube container is provided with an opening, and a piston head is provided at the opening.

[0040] A magnetic attraction assembly and a plurality of distillation assemblies are provided at the bottom of the fixed plate. The magnetic attraction assembly includes a magnet sleeve for wrapping the test tube container.

[0041] Preferably, the partition member includes an annular block fixed inside the test tube container, and a blocking block is slidably connected to the bottom of the annular block through a guide rod.

[0042] (III) Beneficial effects

[0043] Compared with the prior art, the present invention provides a separation system for manufacturing bio-based materials based on artificial intelligence, and has the following beneficial effects:

[0044] Through intelligent control and dynamic parameter adjustment, the present invention can significantly improve the separation efficiency of bio-based materials, shorten the production cycle, improve the separation efficiency, and can accurately separate target components in bio-based materials, improve the product purity, reduce the impurity content, thereby improving the product quality. Through the intelligent separation control and optimization ability, the manual intervention and energy consumption are reduced, the production cost is lowered. Through the adaptive separation ability for complex bio-based material components, it can meet the production requirements of different types of bio-based materials, broaden the application field of bio-based materials, and enhance the adaptability.

[0045] Through the setting of the test tube container, the present invention is used to store bio-based materials to be separated. Through the drive of the motor in the drive assembly, a plurality of test tube containers can be driven to rotate, forming a centrifugal separation operation of the internal bio-based materials. And through the combination of the annular block and the blocking block, the internal space of the test tube container can be separated, facilitating the separate storage of the supernatant and cell debris impurities after centrifugal separation. When the blocking block moves downward, the cell debris impurities below can move downward, forming a separate storage operation for the supernatant and cell debris impurities.

[0046] The present invention adopts a driving frame and a transmission frame hinged at the bottom of the arc-shaped heating block, so that when the magnet sleeve in the magnetic suction component moves downward, it can drive the driving frame to move in a fan shape, and then drive the arc-shaped heating block to move along the horizontal track of the L-shaped rod, and finally wrap the test tube container to form a heating distillation separation work. It has the function of self-expansion and closing, and effectively cooperates with the magnetic suction component. It not only has a variety of bio-based material separation methods, but also a variety of separation methods can be combined in an orderly manner to form a continuous multi-separation work of bio-based materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the principle of the separation system for bio-based material manufacturing based on artificial intelligence of the present invention;

[0048] Figure 2 A schematic diagram of the steps of the deep learning algorithm of the present invention;

[0049] Figure 3 It is a schematic structural diagram of the separation device of the present invention;

[0050] Figure 4 For the present invention Figure 3 Schematic diagram of the structure of the middle cover;

[0051] Figure 5 For the present invention Figure 3 A schematic cross-sectional view of the middle shell;

[0052] Figure 6 For the present invention Figure 3 Schematic diagram of the structure of the middle cover;

[0053] Figure 7 For the present invention Figure 6 Bottom view of the structure of the middle cover plate;

[0054] Figure 8 For the present invention Figure 7 Transmission schematic diagram of the middle drive component and the magnetic attraction component;

[0055] Figure 9 For the present invention Figure 8 The transmission diagram of the magnetic suction component and the distillation component;

[0056] Figure 10 It is a schematic diagram of the combined cross section of the magnetic attraction component and the distillation component of the present invention.

[0057] In the figure: 1. housing; 2. fixing plate;

[0058] 3. Cover plate; 31. Sealing head; 32. Air guide tube;

[0059] 4. Test tube container; 41. Piston head; 42. Ring block; 43. Blocking block;

[0060] 5. Driving component; 51. Motor; 52. Fixed sleeve; 53. Gear sleeve; 54. Tooth ring; 55. Gear; 56. Belt group;

[0061] 6. Magnetic attraction component; 61. Magnet sleeve; 62. Transmission shaft; 63. Reciprocating lead screw; 64. Transmission frame;

[0062] 7. Distillation component; 71. L-shaped rod; 72. Arc heating block; 73. Driving frame. Detailed implementation mode

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment 1:

[0065] Referring to the attached Figure 1 - Figure 2 , a separation system for the manufacture of biobased materials based on artificial intelligence, comprising:

[0066] The biobased material pretreatment module is used for preliminarily treating the raw materials of biobased materials, such as crushing, dissolving, filtering, etc., to meet the requirements of subsequent separation processes;

[0067] The separation device is used for separating biobased materials according to the characteristics of biobased materials by using a separation method suitable for the type of biobased materials; or using a multi-stage separation technology, including but not limited to centrifugal separation, membrane separation, chromatographic separation, etc.; and the parameters of the separation device, such as rotation speed, pressure, temperature, flow rate, etc., can be dynamically adjusted through an artificial intelligence control system;

[0068] The sensor module is distributed on the biobased material pretreatment module and the separation device, and is used for real-time monitoring of various parameters in the separation process, such as temperature, pressure, pH value, concentration, flow rate, etc., and transmitting the data to the artificial intelligence control system;

[0069] The artificial intelligence control system, based on deep learning algorithms, performs real-time analysis and processing on the data collected by the sensor module, combines historical data and preset separation targets, dynamically adjusts the operating parameters of the separation device, and optimizes the separation process; this system can automatically identify complex changes in the composition of biobased materials and adaptively adjust the separation strategy to achieve efficient and accurate separation effects;

[0070] Data storage and analysis module: Used to store all data during the separation process, including sensor data, operating parameters, separation results, etc.; Through in-depth analysis of historical data, the system can continuously optimize its control strategy;

[0071] Through intelligent control and dynamic parameter adjustment, it can significantly improve the separation efficiency of bio-based materials, shorten the production cycle, and enhance the separation efficiency; It can accurately separate the target components in bio-based materials, improve product purity, reduce impurity content, and thus enhance product quality.

[0072] The intelligent separation control and optimization capabilities reduce manual intervention and energy consumption, lowering production costs; Through the adaptive separation ability for complex bio-based material components, it can meet the production requirements of different types of bio-based materials, broaden the application fields of bio-based materials, and enhance adaptability.

[0073] The control system based on artificial intelligence can monitor and adjust the separation process in real time, reduce production interruptions caused by operation errors or equipment failures, and improve production stability.

[0074] The sensor module includes:

[0075] A temperature sensor for real-time monitoring of temperature changes in the pretreatment unit and the separation device. Temperature is an important factor affecting the separation efficiency and product quality of bio-based materials. For example, during the enzymatic hydrolysis process, too high or too low temperature will affect the activity of enzymes;

[0076] A pressure sensor for monitoring pressure changes in the separation device, especially during membrane separation and centrifugal separation processes; Too high pressure may cause membrane blockage or damage to centrifugal equipment, while too low pressure may affect the separation efficiency;

[0077] A pH sensor for real-time monitoring of the pH value of the bio-based material solution. The pH value has a direct impact on the solubility, stability, and separation effect of bio-based materials. For example, some bio-based polymer materials are more easily separated at specific pH values;

[0078] A concentration sensor for monitoring changes in the concentration of target components in the bio-based material solution. Concentration information is crucial for optimizing the separation process. For example, in chromatographic separation, the concentration sensor can provide real-time feedback on the elution of target components;

[0079] A flow rate sensor for monitoring the flow rate of the bio-based material solution in the separation device. The flow rate directly affects the separation efficiency and product quality. For example, during membrane separation, too fast a flow rate may cause membrane blockage, while too slow a flow rate will reduce the separation efficiency;

[0080] An optical sensor for detecting the optical properties of specific components in bio-based materials. For example, some bio-based materials have characteristic absorption peaks at specific wavelengths, which can be used to monitor the content of target components and separation effects in real time;

[0081] The sensor network is connected to the artificial intelligence control system through wireless or wired communication technologies; each sensor is equipped with a data acquisition module that can convert the parameter data monitored in real time into digital signals and transmit them to the artificial intelligence control system through communication protocols.

[0082] Preferably, the deep learning algorithm includes the following steps:

[0083] S1. Data preparation and preprocessing:

[0084] Collect historical data collected by the sensor network during the manufacturing process of bio-based materials, including parameters such as temperature, pressure, pH value, concentration, flow rate, etc., as well as historical operating parameters and separation results of the separation device, such as product purity, separation efficiency, etc.; Remove noise, missing values, and outliers from the data; For example, smooth the temperature data by the moving average method and fill in the missing values in the pressure data using the interpolation method;

[0085] Extract key features from the original data to reduce the data dimension and improve the model training efficiency; For example, use principal component analysis (PCA) to extract the main features in the sensor data, or extract the frequency features in the time series data through Fourier transform;

[0086] S2. Model selection and training:

[0087] Select a suitable deep learning model according to the characteristics of the separation process and the type of sensor data; For example, for processing image-based sensor data, such as the spectral image of an optical sensor, a convolutional neural network can be selected; for processing time series data, such as flow rate, pressure, etc., a long short-term memory network can be selected; Use historical data to train the deep learning model; During the training process, the model optimizes its internal parameters by learning the relationship between the input data (sensor parameters) and the output data (separation results).

[0088] For example, the CNN model gradually extracts features in the data through convolutional layers, pooling layers, and fully connected layers, and adjusts the weights through the backpropagation algorithm to minimize the error between the predicted value and the actual value.

[0089] Adopt a supervised learning method to optimize the model parameters by minimizing the error between the predicted value and the actual value (such as the mean square error MSE).

[0090] For example, when training the LSTM model, use the gradient descent algorithm (such as the Adam optimizer) to adjust the weights of the model to improve the prediction accuracy of the model.

[0091] S3. Model Prediction and Parameter Optimization:

[0092] The trained deep learning model is used to predict the optimal parameter combination of the separation process in real time; the model outputs the predicted separation parameters according to the real-time data collected by the sensor network, such as centrifugal speed, membrane pore size, chromatographic column flow rate, etc.;

[0093] According to the prediction results of the deep learning model, the parameter optimization module uses genetic algorithm or particle swarm optimization algorithm PSO to search for the optimal solution in the parameter space predicted by the model; the optimization algorithm finds the optimal separation parameters by iteratively searching and evaluating different parameter combinations and combining the prediction results of the deep learning model;

[0094] For example, in the membrane separation process, the optimization module can dynamically adjust parameters such as membrane pore size, pressure and flow rate to achieve the best separation effect;

[0095] S4. Feedback and Adaptive Learning:

[0096] Monitor the actual operation during the separation process in real time and adjust the deep learning model and optimization algorithm according to the feedback data; the feedback mechanism enables the system to automatically adjust the separation strategy in the face of changes in the composition of bio-based materials or fluctuations in operating conditions, maintaining the stability and efficiency of the system;

[0097] Adopt online learning technology to enable the deep learning model to update its parameters in real time to adapt to new data patterns;

[0098] For example, when it is detected that the composition of the bio-based material has changed, the system can automatically adjust the weights of the model and optimize the separation parameters to ensure that the separation effect is not affected.

[0099] The working principle of the separation system for manufacturing bio-based materials based on artificial intelligence of the present invention is as follows:

[0100] Feed the bio-based material raw material into the pretreatment unit for preliminary treatment; monitor various parameters during the pretreatment process in real time through the sensor network, and automatically adjust the operating parameters of the pretreatment equipment by the artificial intelligence control system; feed the pretreated bio-based material into the separation device for separation; the sensor network monitors various parameters during the separation process in real time and transmits the data to the artificial intelligence control system; the artificial intelligence control system analyzes the collected data based on the deep learning algorithm, dynamically adjusts the operating parameters of the separation device, and optimizes the separation process; all data generated during the separation process is stored in the data storage and analysis module, and the system continuously optimizes its own control strategy by deeply analyzing historical data; the operator monitors the separation process in real time through the user interface and inputs separation targets and parameter adjustment instructions as needed.

[0101] Refer to the appendixFigure 3 - Figure 10 , the separation device includes a housing 1, a control panel disposed on the front surface of the housing 1, and a cover plate 3 hinged above the housing 1;

[0102] Inside the housing 1, there is a fixed connection with a fixing plate 2. On the fixing plate 2, there are provided several test tube containers 4 and a driving assembly 5. The driving assembly 5 includes a motor 51 for centrifugally driving the several test tube containers 4;

[0103] Through the setting of the test tube containers 4, it is used to store the bio-based materials to be separated. Through the drive of the motor 51 in the driving assembly 5, the several test tube containers 4 can be driven to rotate, forming the centrifugal separation work of the internal bio-based materials.

[0104] Refer to the appendix Figure 6 - Figure 8 , several fixing sleeves 52 are rotatably connected inside the fixing plate 2, and several test tube containers 4 are respectively installed inside the several fixing sleeves 52. The motor 51 is used to synchronously rotate and drive the several fixing sleeves 52;

[0105] By starting the motor 51, the several fixing sleeves 52 can be driven to rotate synchronously, forming the rotation of the several test tube containers 4, and further realizing the centrifugal separation work of the bio-based materials.

[0106] Refer to the appendix Figure 6 - Figure 8 , a gear sleeve 53 is rotatably connected to the top of the fixing plate 2, and tooth rings 54 meshing with the outer surface of the gear sleeve 53 are fixedly connected to the outer surfaces of the several fixing sleeves 52;

[0107] By the rotation of the gear sleeve 53, the tooth rings 54 on the several fixing sleeves 52 can be synchronously driven to rotate, thereby realizing the synchronous rotation of the several fixing sleeves 52, and finally driving the several test tube containers 4 to rotate, forming the centrifugal separation work of the bio-based materials;

[0108] The motor 51 is fixed to the bottom of the fixing plate 2, and the output shaft of the motor 51 is fixedly connected with a gear 55 meshing with the outer surface of the gear sleeve 53;

[0109] The motor 51 is connected to an external power supply and the control panel. It is a forward and reverse motor, and both the rotation speed and the number of rotations are adjustable. It is set by using the connection method and coding method of the existing technology, and is used to drive the gear 55 to rotate, and further drive the gear sleeve 53 to rotate.

[0110] Refer to the appendix Figure 10 , a partition member is provided inside the test tube container 4, and the inside of the test tube container 4 is separated into an upper cavity and a lower cavity by the partition member. The bottom end of the test tube container 4 is set to be open, and a piston head 41 is provided at the opening;

[0111] The test tube container 4 is used to store the bio-based materials that need to be separated, and the separator is used to separate the inside of the test tube container 4 to form a separate storage for the two separated products. The bottom end of the test tube container 4 is open and is blocked by a piston head 41, so that the product inside the lower cavity can be discharged through this position later.

[0112] A magnetic attraction component 6 and a plurality of distillation components 7 are provided at the bottom of the fixed plate 2. The magnetic attraction component 6 includes a magnet sleeve 61 for wrapping the test tube container 4.

[0113] When the test tube container 4 is wrapped by the magnet sleeve 61 and driven to rotate, the magnetic complex is attracted to the magnetic field region by the magnetic force under the action of the external magnetic field, and non-target substances not bound to the magnetic particles will not be attracted, thereby achieving separation.

[0114] Refer to the attached Figure 7 - Figure 10 The separator includes an annular block 42 fixed inside the test tube container 4, and a blocking block 43 is slidably connected to the bottom of the annular block 42 through a guide rod;

[0115] By combining the annular block 42 and the blocking block 43, the internal space of the test tube container 4 can be divided, so that the supernatant and cell debris impurities after centrifugation can be stored separately. When the blocking block 43 moves downward, the cell debris impurities at the bottom can move downward, so that the supernatant and cell debris impurities can be stored separately.

[0116] Embodiment 2: Based on embodiment 1, the difference is that;

[0117] Refer to the attached Figure 7 - Figure 10 The magnetic attraction assembly 6 includes a bottom transmission shaft 62 rotatably connected to the fixed plate 2, a reciprocating screw 63 is fixedly connected to the bottom end of the transmission shaft 62, and a transmission frame 64 is transmission-connected to the outer surface of the reciprocating screw 63;

[0118] The rotation of the transmission shaft 62 can drive the reciprocating screw 63 to rotate, and the rotation of the reciprocating screw 63 can drive the transmission frame 64 to reciprocate up and down;

[0119] There are a plurality of magnet sleeves 61, and the plurality of magnet sleeves 61 are ring-shaped and fixed to the outer surface of the transmission frame 64;

[0120] By providing a plurality of magnet sleeves 61, it is convenient to magnetically separate a plurality of test tube containers 4. By fixing the plurality of magnet sleeves 61 to the transmission frame 64, it is convenient to synchronously drive the plurality of magnet sleeves 61 to move up and down through the up and down movement of the transmission frame 64.

[0121] The blocking block 43 is made of a metal material that can be absorbed by the magnet sleeve 61, and the annular block 42 is made of a magnet;

[0122] Since the blocking block 43 is made of metal material, it is convenient for the magnet sleeve 61 to adsorb the blocking block 43. With the downward movement of the magnet sleeve 61, the blocking block 43 can be driven to move downward, forming the opening and closing of the separator, thereby separating the supernatant and the cell debris impurities.

[0123] It should be noted here that the magnet sleeve 61 can be used for magnetic separation of bio-based materials, and can also be used alone to control the separator;

[0124] The annular block 42 is made of magnetic material, so that the blocking block 43 can be adsorbed, so that the blocking block 43 moves upward, blocks the through hole of the annular block 42, and forms a closing operation of the separator. It should be noted here that the adsorption force of the annular block 42 is smaller than that of the magnet sleeve 61, so that when the magnet sleeve 61 and the annular block 42 adsorb the blocking block 43 at the same time, the blocking block 43 is preferentially adsorbed by the magnet sleeve 61;

[0125] The output shaft of the motor 51 is connected to the transmission shaft 62 via a belt set 56. The belt set 56 and the gear 55 are both provided with one-way bearings, and the two one-way bearings are installed in an opposite locking manner.

[0126] The motor 51 is connected to the transmission shaft 62 by a belt set 56, so that when the motor 51 is driven, the transmission shaft 62 can be driven to rotate by the belt set 56, so that the magnet sleeve 61 in the magnetic attraction assembly 6 is driven up and down;

[0127] One-way bearings are provided on the belt group 56 and the gear 55, and the two one-way bearings are installed in an opposite locking manner, so that when the motor 51 is driven clockwise, it can independently drive several test tube containers 4 to rotate to form a centrifugal separation operation. When the motor 51 is driven counterclockwise, it can independently drive the magnet sleeve 61 in the magnetic attraction component 6 to drive up and down. It has the function of multi-directional driving, effectively combines the driving component 5 and the magnetic attraction component 6 in a linkage manner, and further improves the energy saving and environmental protection of the equipment.

[0128] Embodiment 3: Based on embodiment 2, the difference is that;

[0129] Refer to the attached Figure 3 , Figure 4 and Figure 8 - Figure 10 The distillation assembly 7 includes an L-shaped rod 71 fixed to the bottom of the fixed plate 2, the bottom of the L-shaped rod 71 is slidably connected to an arc-shaped heating block 72 in a horizontal sliding manner, and a driving frame 73 is hinged between the bottom of the arc-shaped heating block 72 and the top of the driving frame 64;

[0130] The arc-shaped heating block 72 uses an electric heating instrument in the prior art to heat-treat the materials in the test tube container 4 to form a distillation separation operation;

[0131] The bottom of the arc-shaped heating block 72 is hinged to the transmission frame 64 through the driving frame 73, so that when the magnet sleeve 61 in the magnetic attraction assembly 6 moves downward, the driving frame 73 can be driven to perform a sector motion, and then the arc-shaped heating block 72 can be driven to move along the horizontal track of the L-shaped rod 71, finally forming a wrapping of the test tube container 4 to form a heating distillation separation operation, which has the functions of self-unfolding and closing, and effectively cooperates with the magnetic attraction assembly 6, improving the functionality and practicality of the separation device;

[0132] It should be noted here that the distillation assembly 7 can be used in cooperation with the magnet sleeve 61 in the magnetic attraction assembly 6;

[0133] For example, when the materials in the test tube container 4 are centrifugally separated into supernatant and cell debris impurities, when the magnet sleeve 61 moves downward a certain distance, the blockage block 43 made of metal materials can be adsorbed. With the continuous descent of the magnet sleeve 61, the blockage block 43 can be driven to move downward. Eventually, the cell debris impurities can enter the lower cavity. Then, with the continuous descent of the magnet sleeve 61, since the downward movement distance of the blockage block 43 is limited, the adsorption force of the blockage block 43 gradually decreases. When the adsorption force of the annular block 42 is greater than the adsorption force of the magnet sleeve 61, the blockage block 43 can be driven to reset and re-form the blockage operation. With the descent of the magnet sleeve 61, the arc-shaped heating block 72 can be driven to unfold and wrap the test tube container 4 to form a distillation separation operation of the supernatant, which is applicable to the separation operation of biological fermentation for producing lactic acid. It not only has multiple separation methods for bio-based materials, but also multiple separation methods can be combined in an orderly manner to form a continuous multi-separation operation of bio-based materials;

[0134] This method can be applicable to the separation operation of biological fermentation for producing lactic acid; in the process of biological fermentation for producing lactic acid, in addition to the target product lactic acid, the fermentation broth also contains a large amount of cell debris, undissolved biomass and other impurities. In order to extract high-purity lactic acid, it is usually necessary to first remove solid impurities such as cell debris by centrifugal separation to obtain a relatively pure supernatant. Then, distillation separation is used to further purify lactic acid and remove water and other low-boiling-point impurities in the supernatant;

[0135] A number of sealing heads 31 are fixedly connected to the cover plate 3, and air guide pipes 32 are fixedly connected to the interiors of the number of sealing heads 31, and one-way valves are arranged on the number of air guide pipes 32;

[0136] Through the setting of the sealing head 31, it is used to seal the top port of the test tube container 4. Through the setting of the air duct 32, it is used to export the gas in the test tube container 4 during the distillation operation. Finally, the bio-based material can be obtained through the condensation method. Through the setting of the one-way valve, it is used to conduct one-way control of the air duct 32.

[0137] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A separation system for the manufacture of biobased materials based on artificial intelligence, characterized in that, Including: A bio-based material pretreatment module for preliminarily treating the raw materials of bio-based materials; A separation device for separating bio-based materials by a separation method applicable to the type of bio-based materials according to the characteristics of the bio-based materials; A sensor module distributed on the bio-based material pretreatment module and the separation device for real-time monitoring of various parameters during the separation process; An artificial intelligence control system that, based on deep learning algorithms, performs real-time analysis and processing on the data collected by the sensor module, and dynamically adjusts the operating parameters of the separation device in combination with historical data and preset separation targets to optimize the separation process; A data storage and analysis module for storing all data during the separation process, and continuously optimizing its own control strategy through in-depth analysis of historical data.

2. The separation system for manufacturing biobased materials based on artificial intelligence according to claim 1, characterized in that: The sensor module includes: A temperature sensor for real-time monitoring of temperature changes in the pretreatment unit and the separation device; A pressure sensor for monitoring pressure changes in the separation device; A pH sensor for real-time monitoring of the pH value of the bio-based material solution; A concentration sensor for monitoring changes in the concentration of the target component in the bio-based material solution; A flow rate sensor for monitoring the flow rate of the bio-based material solution in the separation device; An optical sensor for detecting the optical properties of specific components in the bio-based materials.

3. The separation system for manufacturing bio-based materials based on artificial intelligence according to claim 1, characterized in that: The deep learning algorithm includes the following steps: S1. Data preparation and preprocessing: Collect historical data collected by the sensor network during the manufacturing process of bio-based materials, and remove noise, missing values, and outliers from the data; Extract key features from the original data to reduce the data dimension and improve the model training efficiency; S2. Model selection and training: Select a suitable deep learning model according to the characteristics of the separation process and the type of sensor data; use historical data to train the deep learning model; during the training process, the model optimizes its internal parameters by learning the relationship between the input data and the output data; Adopt a supervised learning method to optimize the model parameters by minimizing the error between the predicted value and the actual value; S3. Model prediction and parameter optimization: The trained deep learning model is used to real-time predict the optimal parameter combination of the separation process; the model outputs the predicted separation parameters according to the real-time data collected by the sensor network; According to the prediction results of the deep learning model, the parameter optimization module uses a genetic algorithm or a particle swarm optimization algorithm (PSO) to search for the optimal solution in the parameter space predicted by the model; the optimization algorithm finds the optimal separation parameters by iteratively searching and evaluating different parameter combinations and combining the prediction results of the deep learning model; S4. Feedback and adaptive learning: Real-time monitor the actual operation situation during the separation process, and adjust the deep learning model and the optimization algorithm according to the feedback data; Adopt online learning technology to enable the deep learning model to update its parameters in real-time to adapt to new data patterns.

4. The separation system for manufacturing biobased materials based on artificial intelligence according to any one of claims 1-3, characterized in that: The separation device includes a housing (1), a control panel provided on the front of the housing (1), and a cover plate (3) hinged above the housing (1); Inside the housing (1), a fixed plate (2) is fixedly connected. On the fixed plate (2), a number of test tube containers (4) and a driving assembly (5) are provided. The driving assembly (5) includes a motor (51) for centrifugally driving the number of test tube containers (4).

5. The separation system for manufacturing bio-based materials based on artificial intelligence according to claim 4, characterized in that: Inside the fixed plate (2), a number of fixing sleeves (52) are rotatably connected, and the number of test tube containers (4) are respectively installed inside the number of fixing sleeves (52). The motor (51) is used to synchronously rotate and drive the number of fixing sleeves (52).

6. The separation system for manufacturing biobased materials based on artificial intelligence according to claim 5, characterized in that: On the top of the fixed plate (2), a gear sleeve (53) is rotatably connected, and on the outer surfaces of the number of fixing sleeves (52), tooth ring gears (54) meshing with the outer surface of the gear sleeve (53) are fixedly connected; The motor (51) is fixed to the bottom of the fixed plate (2), and the output shaft of the motor (51) is fixedly connected with a gear (55) meshing with the outer surface of the gear sleeve (53).

7. The separation system for manufacturing biobased materials based on artificial intelligence according to claim 5, characterized in that: Inside the test tube container (4), a partition member is provided, and the inside of the test tube container (4) is separated into an upper cavity and a lower cavity by the partition member. The bottom end of the test tube container (4) is set to be open, and a piston head (41) is provided at the opening; At the bottom of the fixed plate (2), a magnetic attraction assembly (6) and a number of distillation assemblies (7) are provided. The magnetic attraction assembly (6) includes a magnet sleeve (61) for wrapping the test tube container (4).

8. The separation system for manufacturing biobased materials based on artificial intelligence according to claim 7, characterized in that: The partition member includes an annular block (42) fixed inside the test tube container (4). The bottom of the annular block (42) is slidably connected with a blocking block (43) through a guide rod.

Images