Pea protein production device with filtering structure and filtering method

Abstract

The present invention relates to the technical field of pea protein production, and specifically discloses a pea protein production device and filtering method with a filtering structure, comprising an upper cover plate, a lower cover plate, a first side plate, a second side plate, a third side plate, and a fourth side plate. The upper cover plate is provided with a feed port, the fourth side plate is provided with a discharge port, and a coarse filter screen, a fine filter screen, and a nano-membrane screen are sequentially arranged from the upper cover plate to the lower cover plate. The bottom of each layer of filter screen is fixedly connected to a vibrator, and a plurality of protruding rods are fixedly provided on the inner wall of the fourth side plate. A groove is formed between every two protruding rods and adapted to one end of the filter screen. A pressure sensor, a turbidity meter, and a temperature sensor are provided at the filter screen. The present invention constructs a vibration regulation prediction model. Through the monitoring data of the sensors of each layer of filter screen, the optimal vibration frequency and vibration duration are output in real time, thereby achieving precise control of filter screen blockage, ensuring that the entire filtration process is in an efficient filtration state, and significantly improving production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of pea protein production, and in particular to a pea protein production device with a filtering structure and a filtering method. Background Art

[0002] As a high-quality plant-based protein source, pea protein production is experiencing increasing demand. During the pea protein production process, pea liquid must be filtered to separate the pea residue and slurry. The retained slurry is then precipitated and purified to produce high-quality pea protein. The filtration process directly impacts pea protein purity and production efficiency.

[0003] Traditional filtration devices achieve solid-liquid separation through static screening or single-frequency mechanical vibration. However, the presence of impurities such as starch and fiber in pea liquid can easily cause filter blockage, reduce filtration efficiency, and even affect protein activity. Although some devices can alleviate blockage through electric beating or centrifugal vibration of the filter plate, the fixed vibration parameters cannot respond to dynamic working conditions such as the degree of filter blockage and slurry viscosity. When the vibration parameters are set to a large value, local overload is likely to occur, causing filter deformation and reducing the service life of the equipment. When the vibration parameters are set to a small value, incomplete filtration is likely to occur, reducing filtration efficiency. Summary of the Invention

[0004] In order to solve the above problems, the present invention provides a pea protein production device with a filtering structure, the main body of which is a rectangular parallelepiped, including an upper cover plate, a lower cover plate, a first side plate, a second side plate, a third side plate and a fourth side plate, the upper cover plate is provided with a feed port, the fourth side plate is provided with a discharge port, and a coarse filter screen, a fine filter screen and a nano-membrane screen are arranged in sequence from the upper cover plate to the lower cover plate, the bottom of the coarse filter screen is fixedly connected to a vibrator a, the bottom of the fine filter screen is fixedly connected to a vibrator b, the bottom of the nano-membrane screen is fixedly connected to a vibrator c, and the fourth side plate A plurality of protruding rods are fixed on the inner wall, all of which are perpendicular to the first side plate, and a groove is formed between every two protruding rods, which is adapted to one side of each layer of filter screen. A turbidity meter a is horizontally provided at the upper protruding rod at the coarse filter screen, and a pressure sensor a is vertically provided at the lower protruding rod. A turbidity meter b is horizontally provided at the upper protruding rod at the fine filter screen, and a pressure sensor b is vertically provided at the lower protruding rod. A temperature sensor is horizontally provided at the upper protruding rod at the nanomembrane net, and a pressure sensor c is vertically provided at the lower protruding rod.

[0005] Furthermore, handles a, b and c are respectively provided on the outer wall of the second side panel. Handle a is fixedly connected to the coarse filter screen through the connecting block a, handle b is fixedly connected to the fine filter screen through the connecting block b, and handle c is fixedly connected to the nano-membrane net through the connecting block c. The filter screen is driven by pulling the handle, so that each layer of filter screen can be taken out of the device for cleaning; the two side edges of each layer of filter screen are tightly fitted with the first side panel and the third side panel respectively, and a cavity is formed between each two layers of filter screen. A buffer plate is fixedly provided at the lower part of the nano-membrane net, which plays a role in buffering and collecting the filtered pea liquid. There is an angle between the buffer plate and the fourth side panel, and the angle range is 45°~60°. The two side edges of the buffer plate are respectively sealed with the first side panel and the third side panel.

[0006] Furthermore, the pore size of the coarse filter is 100~300um, the pore size of the fine filter is 10~50um, and the pore size of the nano-membrane mesh is 2~50nm.

[0007] Furthermore, the upper part of the feed port is fixedly connected to a flap, and a control panel is provided on the first side panel for controlling all equipment. Vibrator a, vibrator b and vibrator c are all provided with connectors for convenient connection to an external power supply. The vibration frequencies of vibrator a, vibrator b and vibrator c are 10~150Hz, and different frequency values ​​are output in real time according to the system command.

[0008] A filtration method for a pea protein production device having a filtration structure, comprising the following steps:

[0009] 1. Open the lid, pour the pea slurry into the feed port, and close the lid.

[0010] 2. Start the switch. As the pea slurry flows into the coarse filter layer, the pressure sensor a at the coarse filter monitors the pressure difference before and after the coarse filter. , turbidity meter a monitors the concentration of suspended matter in the inlet pea slurry Then the pea slurry flows into the fine filter layer, and the pressure sensor b at the fine filter monitors the pressure difference before and after the fine filter. , turbidity meter b monitors the concentration of suspended matter in the outlet pea slurry Finally, the pea slurry flows into the nano-membrane network layer, and the pressure sensor c at the nano-membrane network monitors the transmembrane pressure difference. , temperature sensors monitor friction heat .

[0011] 3. Based on the historical database, the random forest algorithm is used to explore the nonlinear relationship between vibration regulation and variables such as filter pressure difference and suspended solids concentration, and a vibration regulation prediction model is constructed.

[0012] Fourth, use the test sample data to evaluate the prediction results. Assume that the test set is , where each sample Each corresponds to a set of actual values ​​of vibration frequency and vibration duration , the prediction result obtained by predicting each sample through the model If the prediction result With actual value The error is within 5%, which means the prediction result is accurate. The final calculated accuracy is 89.3%, and the model prediction result is good.

[0013] 5. What will be monitored 、 、 、 、 、 The six parameters are used as the input layer and input into the vibration adjustment prediction model in the control panel. The prediction model outputs the vibration frequency and vibration duration indicators. At this time, vibrator a, vibrator b and vibrator c are mobilized to work according to the output indicators.

[0014] 6. The vibration adjustment prediction model dynamically adjusts the vibration frequency and vibration duration of each vibrator according to the real-time monitoring data until the filtering is completed.

[0015] The beneficial effects of the present invention are as follows:

[0016] 1. The present invention embeds a vibration regulation prediction model into the device system and proposes an intelligent vibration control system. Based on the historical experimental database, the vibration regulation prediction model is constructed using the random forest algorithm. By monitoring the pressure difference, turbidity and temperature changes of each layer of the filter, the prediction model outputs the optimal vibration frequency and vibration duration in real time. The system adjusts the vibrator of each layer of the filter according to the output indicators to achieve precise control of the filter clogging, ensuring that the entire filtration process maintains an efficient filtration state, avoiding filter clogging and improving production efficiency.

[0017] 2. Compared with the traditional continuous fixed vibration mode, the present invention not only reduces the occurrence of local overload or incomplete filtration, but also increases or decreases the vibration frequency and duration according to the multi-dimensional working conditions of the filter, significantly reducing energy consumption.

[0018] 3. The present invention improves product quality by setting up three-stage filter screens. The coarse filter screen layer intercepts large particle fibers such as pea dregs, the fine filter screen layer removes micron-sized starch, and the nano-membrane screen intercepts colloidal impurities, thereby achieving step-by-step fine separation and improving the purity of pea protein. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic cross-sectional view of a pea protein production device with a filtering structure according to the present invention;

[0020] Figure 2This is a schematic side view of the structure of a pea protein production device with a filtering structure according to the present invention;

[0021] Figure 3 This is a schematic diagram of the overall structure of the pea protein production device with a filtering structure of the present invention;

[0022] Figure 4 This is a schematic diagram of the bottom structure of the filter screen of the pea protein production device with a filtering structure according to the present invention;

[0023] Figure 5 This is a schematic diagram of the structure of the vibrator a of the pea protein production device with a filtering structure according to the present invention;

[0024] Figure 6 This is a flow chart of the test result evaluation of the random forest algorithm of the present invention.

[0025] Figure markings: 1. Upper cover plate, 2. Lower cover plate, 3. First side plate, 4. Second side plate, 5. Third side plate, 6. Fourth side plate, 7. Feed port, 8. Discharge port, 9. Coarse filter screen, 10. Fine filter screen, 11. Nano-membrane net, 12. Vibrator a, 13. Vibrator b, 14. Vibrator c, 15. Protruding rod, 16. Turbidity meter a, 17. Pressure sensor a, 18. Turbidity meter b, 19. Pressure sensor b, 20. Temperature sensor, 21. Pressure sensor c, 22. Handle a, 23. Handle b, 24. Handle c, 25. Connecting block a, 26. Connecting block b, 27. Connecting block c, 28. Buffer plate, 29. Flip cover, 30. Control panel, 31. Connector. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0027] A pea protein production device with a filtering structure, such as Figure 1-5As shown, its main body is a rectangular parallelepiped, including an upper cover plate 1, a lower cover plate 2, a first side plate 3, a second side plate 4, a third side plate 5 and a fourth side plate 6. The upper cover plate 1 is provided with a feed port 7, and the fourth side plate 6 is provided with a discharge port 8. A coarse filter screen 9, a fine filter screen 10 and a nano-membrane net 11 are sequentially arranged from the upper cover plate 1 to the lower cover plate 2. The bottom of the coarse filter screen 9 is fixedly connected to a vibrator a12, the bottom of the fine filter screen 10 is fixedly connected to a vibrator b13, and the bottom of the nano-membrane net 11 is fixedly connected to a vibrator c14. The vibrator is used to adjust the vibration frequency and vibration duration in real time. A plurality of convex rods 15 are fixedly provided on the inner wall of the fourth side plate 6. All convex rods 15 are perpendicular to the first side plate 3. A groove is formed between every two convex rods 15. The coarse filter screen 9 is fixedly connected to the vibrator a12. A turbidity meter a16 is horizontally provided at the upper protruding rod 15, and a pressure sensor a17 is vertically provided at the lower protruding rod 15. A turbidity meter b18 is horizontally provided at the upper protruding rod 15 at the fine filter 10, and a pressure sensor b19 is vertically provided at the lower protruding rod 15. A temperature sensor 20 is horizontally provided at the upper protruding rod 15 at the nanomembrane net 11, and a pressure sensor c21 is vertically provided at the lower protruding rod 15. The pressure sensor of each layer of filter screen is used to monitor the pressure difference before and after each layer of filter screen, the turbidity meter is used to measure the concentration of suspended matter, and the temperature sensor is used to monitor the frictional heat between the membrane layers. The size of one end of each layer of filter screen plate is adapted to the size of the groove formed between the upper protruding rod 15 and the pressure sensor.

[0028] On the basis of the above scheme, the present invention can be further improved. A handle a22, a handle b23 and a handle c24 are respectively provided on the outer wall of the second side panel 4. The handle a22 is fixedly connected to the coarse filter screen 9 through the connecting block a25, the handle b23 is fixedly connected to the fine filter screen 10 through the connecting block b26, and the handle c24 is fixedly connected to the nano-membrane net 11 through the connecting block c27. The filter screen is driven by pulling the handle, so that each layer of filter screen can be taken out of the device for easy cleaning; the two side edges of each layer of filter screen are tightly fitted with the first side panel 3 and the third side panel 5 respectively, and a cavity is formed between each two layers of filter screen. A buffer plate 28 is fixedly provided at the lower part of the nano-membrane net 11, which plays a role in buffering and collecting the filtered pea liquid to avoid liquid splashing. There is an angle between the buffer plate 28 and the fourth side panel 6, and the angle range is 45°~60°. The two side edges of the buffer plate 28 are respectively sealed with the first side panel 3 and the third side panel 5.

[0029] Based on the above scheme, the present invention can be further improved. The pore size of the coarse filter 9 is 100~300um, which is used to filter out large particles of impurities such as pea dregs. The pore size of the fine filter 10 is 10~50um, which is used to filter out fine particles such as starch. The pore size of the nano-membrane net 11 is 2~50nm, which is used to intercept colloidal impurities.

[0030] On the basis of the above scheme, the present invention can be further improved. The upper part of the feed port 7 is fixedly connected to the flap 29. A control panel 30 is provided on the first side panel 3, in which a vibration regulation prediction model is embedded for controlling all electrical equipment. Vibrator a12, vibrator b13 and vibrator c14 are all provided with connectors 31 for convenient connection to an external power supply. The vibration frequencies of vibrator a12, vibrator b13 and vibrator c14 are 10~150Hz, and different frequency values ​​are output in real time according to the system command.

[0031] A filtration method for a pea protein production device having a filtration structure, comprising the following steps:

[0032] 1. Open the flip cover 29, pour the pea slurry from the feed port 7, and close the flip cover 29.

[0033] 2. Start the switch. As the pea slurry flows into the coarse filter 9 layer, the pressure sensor a17 at the coarse filter 9 monitors the pressure difference before and after the coarse filter 9. , turbidity meter a16 monitors the concentration of suspended solids in the inlet pea slurry Then the pea slurry flows into the fine filter 10 layer, and the pressure sensor b19 at the fine filter 10 monitors the pressure difference before and after the fine filter 10 , turbidity meter b18 monitors the concentration of suspended matter in the outlet pea slurry Finally, the pea slurry flows into the nano-membrane network 11 layer, and the pressure sensor c21 at the nano-membrane network 11 monitors the transmembrane pressure difference. , temperature sensor 20 monitors friction heat .

[0034] 3. Based on the historical database, the random forest algorithm is used to explore the nonlinear relationship between vibration regulation and variables such as filter pressure difference and suspended solids concentration, and to construct a vibration regulation prediction model. Among them, the core of the present invention lies in the construction of a vibration regulation prediction model. According to the actual process of pea protein filtration production, variables such as the vibration frequency and vibration duration of the vibrator and the pressure difference before and after the filter belong to a complex data set, and there is a complex nonlinear relationship between the variables. Therefore, machine learning-random forest is selected as the core algorithm of the vibration regulation prediction model. The random forest algorithm generates multiple decision trees by randomly selecting training data and feature subsets, and averages or votes on the prediction results of each decision tree to obtain the final prediction result.

[0035] The model building process includes collecting data sets, sample sampling, feature sampling, building decision trees, generating decision tree models and integrating prediction results. First, read the pressure difference before and after the coarse filter from the historical database. , inlet suspended matter concentration , pressure difference before and after fine filter , outlet suspended matter concentration , transmembrane pressure difference and temperature As the independent variable, vibration frequency and vibration duration are used as the dependent variables for prediction. A complete set of indicator data is used as a training sample value. After removing abnormal data, all sample data is read into a set to construct training and test samples, as shown in Tables 1 and 2. A sample consists of a complete row of data. Assuming that there are N training sample rows, a sample is randomly selected from the training sample set and placed into the sampling set. This sample is then placed back into the original training sample set. After N random sampling operations, a training subset containing N samples is obtained.

[0036] Table 1. Training sample data

[0037]

[0038] Table 2. Test sample data

[0039]

[0040] Fourth, randomly select m features from the feature set, sort the data records according to the feature, and split the data records according to the sorted feature values. If all records have the same category, they are marked as leaf nodes. If the records have different categories, continue to recursively check the node until the number of decisions reaches the default value of 100. The construction of the vibration regulation prediction model is completed, the test results are evaluated using the test sample data, and the prediction accuracy of the model is calculated.

[0041] Assume that the test set is , where each sample Each corresponds to a set of actual values ​​of vibration frequency and vibration duration , the prediction result obtained by predicting each sample through the model If the prediction result With actual value If the error is within 5%, , the final counter value is divided by the number of test set samples , the prediction accuracy of the vibration regulation prediction model can be obtained. The flow chart is as follows Figure 6 As shown, the accuracy is calculated after training ,in, Indicates the number of samples predicted correctly, Indicates the number of samples in the test set.

[0042] 5. When the device is running for 98 seconds, , , , , , , the parameters are automatically input into the vibration adjustment prediction model in the control panel 30, the prediction model outputs the optimal vibration frequency of 38Hz, the vibration duration is 9s, the vibrator works according to the optimal vibration value, and when the equipment runs to the 107th second, it is monitored , , , , , ,The prediction model outputs the optimal vibration frequency of 20 Hz and the vibration duration of 4 s. The vibrator continues to work according to the new optimal vibration value, ..., and this filtering process is repeated.

[0043] 6. The vibration adjustment prediction model dynamically adjusts the vibration frequency and vibration duration of each vibrator according to the real-time monitoring data until the filtering is completed.

[0044] All hollow components of the present invention are connected to the control panel 30 using existing electrical connection means. The control panel 30 encapsulates a vibration adjustment prediction model and is equipped with an automatic control system, data acquisition and storage components, and a touch screen display.

Claims

1. A filtering method for a pea protein production device with a filtering structure, wherein the main body of the pea protein production device with a filtering structure is a rectangular parallelepiped, comprising an upper cover plate (1), a lower cover plate (2), a first side plate (3), a second side plate (4), a third side plate (5) and a fourth side plate (6), wherein the upper cover plate (1) is provided with a feed port (7), the fourth side plate (6) is provided with a discharge port (8), and a coarse filter screen (9), a fine filter screen (10) and a nano-membrane screen (11) are sequentially arranged in a direction from the upper cover plate (1) to the lower cover plate (2), wherein the bottom of the coarse filter screen (9) is fixedly connected to a vibrator a (12), the bottom of the fine filter screen (10) is fixedly connected to a vibrator b (13), and the bottom of the nano-membrane screen (11) is fixedly connected to a vibrator c (14). Connecting to the vibrator c (14), a plurality of protruding rods (15) are fixedly provided on the inner wall of the fourth side plate (6), and every two protruding rods (15) form a concave groove, which is adapted to one side of each layer of the filter screen. A turbidity meter a (16) is horizontally provided on the upper protruding rod (15) at the coarse filter screen (9), and a pressure sensor a (17) is vertically provided on the lower protruding rod (15). A turbidity meter b (18) is horizontally provided on the upper protruding rod (15) at the fine filter screen (10), and a pressure sensor b (19) is vertically provided on the lower protruding rod (15). A temperature sensor (20) is horizontally provided on the upper protruding rod (15) at the nano-membrane net (11), and a pressure sensor c (21) is vertically provided on the lower protruding rod (15). The outer wall of the second side panel (4) is provided with a handle a (22), a handle b (23) and a handle c (24), respectively. The handle a (22) is fixedly connected to the coarse filter (9) through a connecting block a (25), the handle b (23) is fixedly connected to the fine filter (10) through a connecting block b (26), and the handle c (24) is fixedly connected to the nano-membrane net (11) through a connecting block c (27). The two sides of each layer of the filter are tightly fitted with the first side panel (3) and the third side panel (5), respectively. A buffer plate (28) is fixedly provided at the bottom of the nano-membrane net (11), and an angle is formed between the buffer plate (28) and the fourth side panel (6), and the angle range is 45°~60°. The two sides of the buffer plate (28) are sealed and connected to the first side panel (3) and the third side panel (5), respectively. The pore size of the coarse filter (9) is 100-300 μm, the pore size of the fine filter (10) is 10-50 μm, and the pore size of the nano-membrane net (11) is 2-50 nm; The upper portion of the feed port (7) is fixedly connected to a flap (29), the first side panel (3) is provided with a control panel (30), the vibrator a (12), the vibrator b (13) and the vibrator c (14) are all provided with a joint (31), and the vibration frequency of the vibrator a (12), the vibrator b (13) and the vibrator c (14) is 10 to 150 Hz; It is characterized by: The filtering method comprises the following steps:

1. Open the flip cover (29), pour the pea slurry into the container from the feed port (7), and close the flip cover (29); 2. Start the switch, the pressure sensor a (17) at the coarse filter (9) starts to monitor the pressure difference ΔP1 before and after the coarse filter (9), the turbidity meter a (16) monitors the suspended matter concentration C1 in the inlet pea slurry, the pressure sensor b (19) at the fine filter (10) monitors the pressure difference ΔP2 before and after the fine filter (10), the turbidity meter b (18) monitors the suspended matter concentration C2 in the outlet pea slurry, the pressure sensor c (21) at the nano-membrane mesh (11) monitors the transmembrane pressure difference ΔP3, and the temperature sensor (20) monitors the friction heat T; 3. Based on the historical database, the random forest algorithm was used to explore the nonlinear relationship between vibration regulation and variables such as filter pressure difference and suspended solids concentration, and a vibration regulation prediction model was constructed; Fourth, use the test sample data to evaluate the prediction results. Assume that the test set is D={d1,d2,......,d n }, where each sample d n Each corresponds to a set of actual values ​​c of vibration frequency and vibration duration n , the prediction result c obtained by predicting each sample through the model , n , if the prediction result c , n With the actual value c n If the error is within 5%, the prediction result is accurate; 5. The monitored six parameters ΔP1, C1, ΔP2, C2, ΔP3, and T are used as input layers and input into the vibration adjustment prediction model in the control panel (30). The prediction model outputs vibration frequency and vibration duration indicators. At this time, vibrator a (12), vibrator b (13), and vibrator c (14) are mobilized to work according to the output indicators; 6. The vibration adjustment prediction model dynamically adjusts the vibration frequency and vibration duration of each vibrator according to the real-time monitoring data until the filtering is completed.

Images