A fully automatic intelligent modular human digestion bionic device and method

Abstract

The present invention relates to the fields of environmental science engineering and bionic technology, and in particular to a fully automatic intelligent modular human digestion bionic device and method. The present invention creates a modular human bionic complete digestive system that accurately simulates the human digestion process, including key organs such as the oral cavity, stomach and small intestine. Each module has real-time measurement, precise control and sample sampling functions to ensure that the digestion process is highly controllable and observable. The intelligent control system uses sensor technology and microprocessor algorithms to automatically adjust and optimize the operation of the modules. The modular structure makes the system easy to assemble and maintain, and can be personalized according to needs, providing flexible and customized solutions for digestive physiology research. The system includes modules such as oral digestion, gastric digestion, small intestinal digestion, digestate recovery, sample detection, power supply and digestive fluid supply. Each module plays a specific role and jointly ensures the accuracy and controllability of the simulated digestion process.

Description

Technical Field

[0001] The invention relates to the fields of environmental science engineering and bionic technology, in particular to a fully automatic intelligent modular human digestion bionic device and method. Background Art

[0002] The widespread use of in vitro simulation devices for the human digestive tract has greatly facilitated the research in the fields of food science and human nutrition, and has gradually been recognized by the academic community. In modern food processing research, objective and accurate evaluation of the digestion process of food in the human body is crucial for determining the composition of food, and the use of in vitro simulation devices for the human digestive tract will play a key role in this regard.

[0003] Current technology usually uses a conical flask or beaker as a device to simulate gastric digestion. In the simulated digestion experiment, a certain amount of food is first placed in a conical flask or beaker, and then simulated gastric juice or intestinal juice is added thereto; then, the conical flask or beaker is placed on a constant temperature water bath shaker and vibrated for a period of time to simulate the digestion process of the human stomach. After digestion is completed, the digested and undigested substances are separated by centrifugation or filtration. However, when a conical flask or beaker is used as a device to simulate gastric digestion, the measurement results of this type of digestion experiment are not accurate enough because the digestion products therein have an inhibitory effect on the reaction. There are many types of existing invention patents for digestion simulation, and the core technical problems they solve are also different.

[0004] The human digestive bionic device is an in vitro test system used to evaluate or predict the oral bioavailability of specific chemicals in a solid matrix. The device can simulate the physiological environment and digestion and absorption process of the human gastrointestinal tract and is suitable for research in the fields of digestion metabolism, nutritional dynamics, bioavailability, safety evaluation, etc. of food, drugs, pollutants, etc. However, the human digestive bionic device currently faces some technical challenges, which are mainly manifested in the following aspects: (1) The construction of the simulation system lacks unified standards and specifications, resulting in differences in simulation methods and conditions used by different research institutions and laboratories, affecting the comparability and repeatability of the results; (2) The complexity and accuracy of the simulation system need to be improved. The current simulation system can often only simulate part of the functions of the human gastrointestinal tract, cannot fully reflect the dynamic changes of the human gastrointestinal tract and the co-metabolism of microorganisms, and cannot consider the influence of individual differences and physiological status; (3) The application scope and effect of the simulation system need to be expanded. The current simulation system is mainly used to evaluate the bioavailability of single or simple foods or compounds. There is still a lack of effective evaluation methods and indicators for the interactions and synergistic effects of complex foods or compounds, as well as their long-term effects on human health. Summary of the invention

[0005] The present invention overcomes the deficiencies of the prior art and provides a fully automatic intelligent modular human digestion bionic device and method.

[0006] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0007] The first aspect of the present invention discloses a fully automatic intelligent modular human digestion bionic device, including an oral digestion module, a stomach digestion module, a large intestine digestion module, a small intestine digestion module, a digestive fluid supply module, a power supply module and an intelligent control module;

[0008] The oral digestion module includes a mechanical arm, simulated teeth, an oral monitoring sensor installation module, a switch, a movable joint, a saliva access port, an oral heating module, a simulated tongue and simulated lips; the oral heating module is used to adjust the internal temperature of the oral digestion module; the simulated teeth can move up and down to simulate chewing; the simulated tongue is used to stir the food to be tested;

[0009] The stomach digestion module is connected to the oral digestion module, and includes a gastric juice access port, a gastric peristaltic pump, a gastric wall, a gastric heating module, a gastric monitoring sensor installation module, and a gastric sample sampling port; the gastric peristaltic pump is embedded on the external gastric wall, and the peristaltic movement of the stomach is simulated by the rotation of the gastric peristaltic pump; the internal gastric wall is provided with folds and villi;

[0010] The small intestinal digestion module is connected to the stomach digestion module, and the small intestinal digestion module includes a small intestinal liquid access port, a small intestinal monitoring sensor installation module, a small intestinal peristaltic pump, a small intestinal wall, a small intestinal heating module, and a small intestinal sample sampling port; the small intestinal peristaltic pump is embedded in the external small intestinal wall, and the peristaltic movement of the small intestine is simulated by the rotation of the small intestinal peristaltic pump; the internal small intestinal wall is provided with folds and villi;

[0011] The large intestine digestion module is connected to the small intestine digestion module, and the large intestine digestion module includes a large intestine liquid access port, a large intestine peristaltic pump, a large intestine wall, a large intestine monitoring sensor installation module, a large intestine heating module and a large intestine sample sampling port; the large intestine peristaltic pump is embedded in the external large intestine wall, and the peristaltic movement of the large intestine is simulated by the rotation of the large intestine peristaltic pump; the internal large intestine wall is provided with folds and villi.

[0012] Furthermore, in a preferred embodiment of the present invention, the stomach heating module, the small intestine heating module, and the large intestine heating module are all water bath mechanisms; and the oral heating module is an air heating mechanism.

[0013] Furthermore, in a preferred embodiment of the present invention, the digestive fluid supply module includes a saliva supply module, a gastric fluid supply module, a small intestinal fluid supply module and a large intestinal fluid supply module; the saliva supply module is connected to the saliva access port via a saliva delivery tube; the gastric fluid supply module is connected to the gastric fluid access port via a gastric fluid delivery tube; the small intestinal fluid supply module is connected to the small intestinal fluid access port via a small intestinal fluid delivery tube; and the large intestinal fluid supply module is connected to the large intestinal fluid access port via a large intestinal fluid delivery tube.

[0014] Furthermore, in a preferred embodiment of the present invention, the saliva delivery tube, the gastric juice delivery tube, the small intestinal juice delivery tube and the large intestinal juice delivery tube are all provided with a suction pump.

[0015] Furthermore, in a preferred embodiment of the present invention, the intelligent control module is communicatively connected with the monitoring sensors in each digestion module.

[0016] Furthermore, in a preferred embodiment of the present invention, each monitoring sensor installation module is used to install various types of monitoring sensors, including temperature sensors, pH sensors, pressure sensors and humidity sensors.

[0017] The second aspect of the present invention discloses a control method for a fully automatic intelligent modular human digestion bionic device, which is applied to any one of the fully automatic intelligent modular human digestion bionic devices described above, and comprises the following steps:

[0018] Obtaining operation log information of the digestive bionic device, obtaining historical working data of the digestive bionic device according to the operation log information, and performing feature engineering processing on the historical working data to obtain feature engineering data;

[0019] Constructing a support vector regression model, and importing the feature engineering data into the support vector regression model for training to obtain a trained support vector regression model;

[0020] When the digestive bionic device is in the process of simulation, the real-time working data of each digestive module of the digestive bionic device is obtained at a preset time node through each sensor, and the real-time working data of each digestive module is processed based on the hierarchical clustering algorithm and the genetic algorithm to obtain the effective real-time working data of each digestive module;

[0021] Importing the effective real-time working data of each digestion module into the trained support vector regression model for prediction, and obtaining the predicted working data of each digestion module within a preset future time;

[0022] Obtaining preset working data of each digestion module within a preset future time period, comparing and analyzing the predicted working data of each digestion module within the preset future time period with the corresponding preset working data, and generating an analysis result;

[0023] If it is the first analysis result, an optimal control scheme is generated, and the digestive bionic device is regulated based on the optimal control scheme; if it is the second analysis result, the digestive bionic device is not regulated.

[0024] Furthermore, in a preferred embodiment of the present invention, the real-time working data of each digestion module is processed based on a hierarchical clustering algorithm and a genetic algorithm to obtain effective real-time working data of each digestion module, specifically:

[0025] S202: each real-time working data is regarded as a separate data point, and the cosine similarity between each data point is calculated, and the two data points with the largest cosine similarity are merged into a population to obtain a plurality of populations;

[0026] S204: defining a fitness function, calculating the fitness of each population based on the fitness function, and comparing the fitness of each population with a preset fitness;

[0027] S206: If the fitness of a certain population is not greater than the preset fitness, the population is defined as a noise data population, and the noise data population is completely eliminated;

[0028] S208: Acquire the real-time working data of each population whose fitness is greater than the preset fitness, and regard the real-time working data of the population whose fitness is greater than the preset fitness as a single data point, and repeat steps S202 to S206;

[0029] S210: until the fitness of all populations is greater than the preset fitness, the real-time working data of each population is obtained to obtain the effective real-time working data of each digestion module.

[0030] Furthermore, in a preferred embodiment of the present invention, the predicted working data of each digestion module within a preset future time is compared and analyzed with the corresponding preset working data to generate an analysis result, specifically:

[0031] Constructing a timestamp, and based on the timestamp, sorting the predicted working data of each digestion module within a preset future time and the corresponding preset working data based on a time series;

[0032] After the sorting is completed, a two-dimensional coordinate system is constructed, and a time series-based predicted working data curve graph and a preset working data curve graph are constructed in the two-dimensional coordinate system based on the predicted working data of each digestion module in the preset future time and the corresponding preset working data;

[0033] Calculate the overlap between the predicted working data curve graph and the preset working data curve graph in the two-dimensional coordinate system based on the Euclidean distance algorithm to obtain the overlap between the predicted working data of the corresponding digestion module within the preset future time and the corresponding preset working data;

[0034] Repeat the above steps until the overlap between the predicted working data of each digestion module within the preset future time and the corresponding preset working data is calculated; and the overlap between the predicted working data of each digestion module within the preset future time and the corresponding preset working data is compared with the preset overlap;

[0035] If the overlap between the predicted working data of a certain digestion module within the preset future time and the corresponding preset working data is not greater than the preset overlap, the digestion module is marked as a module that needs to be regulated; if the overlap between the predicted working data of a certain digestion module within the preset future time and the corresponding preset working data is greater than the preset overlap, the digestion module is marked as a module that does not need to be regulated;

[0036] If there is a module that needs to be regulated in the digestive bionic device, a first analysis result is generated; if there is no module that needs to be regulated in the digestive bionic device, a second analysis result is generated.

[0037] Furthermore, in a preferred embodiment of the present invention, if it is the first analysis result, an optimal control scheme is generated, and the digestive bionic device is controlled based on the optimal control scheme, specifically:

[0038] Obtaining operation log information of the digestion bionic device, and retrieving historical control schemes corresponding to various abnormal operation conditions of each digestion module of the digestion bionic device from the operation log information, and obtaining historical control accuracy corresponding to each historical control scheme;

[0039] The historical control scheme corresponding to the maximum historical control accuracy is calibrated as the optimal control scheme corresponding to the corresponding abnormal operation condition, and the optimal control scheme corresponding to various abnormal operation conditions of each digestion module is obtained; and the historical working data of each digestion module before various abnormal operation conditions occur is obtained from the operation log information;

[0040] Bundling the optimal control schemes corresponding to various abnormal operating conditions of each digestion module with the historical working data before the various abnormal operating conditions occurred to obtain a plurality of data packets; constructing a database, and importing the plurality of data packets into the database to obtain a characteristic database;

[0041] If the analysis result is the first analysis result, the real-time working data corresponding to the module to be regulated in the digestive bionic device at the preset time node is obtained, and the data packet corresponding to the module to be regulated is extracted from the characteristic database, that is, the data packet corresponding to the same digestive module as the module to be regulated;

[0042] Calculate the hash value between the real-time working data corresponding to the module to be regulated at a preset time node and the historical working data in the extracted data packet by using a perceptual hash algorithm to obtain multiple hash values;

[0043] The data packet corresponding to the maximum hash value is obtained, and the optimal control scheme for controlling the module to be controlled is extracted from the data packet corresponding to the maximum hash value, and the optimal control scheme is sent to the intelligent control module to control the digestive bionic device based on the optimal control scheme.

[0044] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: the device is designed to accurately simulate the key links of the human digestive process, including digestive organs such as the mouth, stomach and small intestine. Each module has real-time measurement, precise control and sample sampling functions, ensuring the high controllability and observability of the digestive process. In addition, the system is equipped with an intelligent control system, which uses advanced sensor technology and microprocessor control algorithms to automatically adjust and optimize the operation of each module. The modular structural design makes the system easy to assemble and maintain, and the modules can be personalized according to specific research needs, providing a flexible and customizable experimental solution for digestive physiology research. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0046] Figure 1 This is a schematic diagram of the overall structure of the fully automatic intelligent modular human digestion bionic device;

[0047] Figure 2 This is the module diagram of bionic oral digestion simulation;

[0048] Figure 3 This is a diagram of the bionic stomach digestion simulation module;

[0049] Figure 4 This is the module diagram of bionic small intestine digestion simulation;

[0050] Figure 5 This is the module diagram of bionic large intestine digestion simulation;

[0051] Figure 6 It is a diagram of the module for supplying digestive fluid;

[0052] The reference numerals are as follows: 1. housing; 2. oral digestion module; 3. stomach digestion module; 4. small intestine digestion module; 5. large intestine digestion module; 6. digestive fluid supply module; 7. power supply module; 8. intelligent control module; 9. sample recovery module; 201. robotic arm; 202. simulated teeth; 203. oral monitoring sensor installation module; 204. switch; 205. movable joint; 206. oral heating module; 207. simulated tongue; 208. simulated lips; 301. gastric fluid access port; 302. gastric peristaltic pump; 303. gastric wall; 304. gastric heating module; 305. Gastric monitoring sensor installation module; 306. Gastric sample sampling port; 401. Small intestinal fluid access port; 402. Small intestinal monitoring sensor installation module; 403. Small intestinal peristaltic pump; 404. Small intestinal wall; 405. Small intestinal heating module; 501. Large intestinal fluid access port; 502. Large intestinal peristaltic pump; 503. Large intestinal wall; 504. Large intestinal monitoring sensor installation module; 505. Large intestinal heating module; 601. Saliva supply module; 602. Gastric fluid supply module; 603. Small intestinal fluid supply module; 604. Large intestinal fluid supply module; 606. Liquid extraction pump. DETAILED DESCRIPTION

[0053] In order to more clearly understand the above-mentioned purposes, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. These drawings are all simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the structures related to the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict.

[0054] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the invention, unless otherwise specified, "multiple" means two or more.

[0055] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0056] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thoroughly understood.

[0057] like Figure 1 As shown, the first aspect of the present invention discloses a fully automatic intelligent modular human digestion bionic device, including an oral digestion module 2, a stomach digestion module 3, a large intestine digestion module 5, a small intestine digestion module 4, a digestive fluid supply module 6, a power supply module 7 and an intelligent control module 8;

[0058] like Figure 2As shown, the oral digestion module 2 includes a mechanical arm 201, an imitation tooth 202, an oral monitoring sensor installation module 203, a switch 204, a movable joint 205, a saliva inlet, an oral heating module 206, an imitation tongue 207 and an imitation lip 208; the oral heating module 206 is used to adjust the internal temperature of the oral digestion module 2; the imitation tooth 202 can move up and down to simulate chewing; the imitation tongue 207 is used to stir the food to be tested; wherein, the mechanical arm is a three-axis linkage mechanical arm. The imitation tooth 202 and the imitation tongue 207 can be driven to perform bionic chewing motion through the linkage cooperation of a power mechanism such as a ball joint mechanism and an electric telescopic mechanism.

[0059] like Figure 3 As shown, the stomach digestion module 3 is connected to the oral digestion module 2, and the stomach digestion module 3 includes a gastric juice inlet 301, a stomach peristaltic pump 302, a stomach wall 303, a stomach heating module 304, a stomach monitoring sensor installation module 305, and a stomach sample sampling port 306; the stomach peristaltic pump 302 is embedded on the external stomach wall 303, and the peristaltic movement of the stomach is simulated by the rotation of the stomach peristaltic pump 302; the internal stomach wall 303 is provided with wrinkles and villi;

[0060] like Figure 4 As shown, the small intestinal digestion module 4 is connected to the stomach digestion module 3, and the small intestinal digestion module 4 includes a small intestinal liquid access port 401, a small intestinal monitoring sensor installation module 402, a small intestinal peristaltic pump 403, a small intestinal wall 404, a small intestinal heating module 405 and a small intestinal sample sampling port; the small intestinal peristaltic pump 403 is embedded on the external small intestinal wall 404, and the peristaltic movement of the small intestine is simulated by the rotation of the small intestinal peristaltic pump 403; the internal small intestinal wall 404 is provided with wrinkles and villi;

[0061] like Figure 5 As shown, the large intestine digestion module 5 is connected to the small intestine digestion module 4, and the large intestine digestion module 5 includes a large intestine liquid access port 501, a large intestine peristaltic pump 502, a large intestine wall 503, a large intestine monitoring sensor installation module 504, a large intestine heating module 505 and a large intestine sample sampling port; the large intestine peristaltic pump 502 is embedded in the external large intestine wall 503, and the peristaltic movement of the large intestine is simulated by the rotation of the large intestine peristaltic pump 502; the internal large intestine wall 503 is provided with folds and villi.

[0062] Furthermore, in a preferred embodiment of the present invention, the stomach heating module 304, the small intestine heating module 405, and the large intestine heating module 505 are all water bath mechanisms; and the oral heating module 206 is an air heating mechanism.

[0063] like Figure 6As shown, further, in a preferred embodiment of the present invention, the digestive fluid supply module 6 includes a saliva supply module 601, a gastric fluid supply module 602, a small intestinal fluid supply module 603 and a large intestinal fluid supply module 604; the saliva supply module 601 is connected to the saliva access port through a saliva delivery tube; the gastric fluid supply module 602 is connected to the gastric fluid access port 301 through a gastric fluid delivery tube; the small intestinal fluid supply module 603 is connected to the small intestinal fluid access port 401 through a small intestinal fluid delivery tube; the large intestinal fluid supply module 604 is connected to the large intestinal fluid access port 501 through a large intestinal fluid delivery tube.

[0064] The digestive fluid stored in the saliva supply module 601, the gastric fluid supply module 602, the small intestinal fluid supply module 603 and the large intestinal fluid supply module is also transported to each digestive module through a peristaltic pump.

[0065] Furthermore, in a preferred embodiment of the present invention, the saliva delivery tube, the gastric juice delivery tube, the small intestinal juice delivery tube and the large intestinal juice delivery tube are all provided with a suction pump 606.

[0066] Furthermore, in a preferred embodiment of the present invention, the intelligent control module 8 is communicatively connected with the monitoring sensors in each digestion module.

[0067] Furthermore, in a preferred embodiment of the present invention, each monitoring sensor installation module is used to install various types of monitoring sensors, including temperature sensors, pH sensors, pressure sensors and humidity sensors. Each digestion part is monitored in real time by each sensor. The temperature, pH, depth, peristalsis, etc. of each digestion module are monitored and regulated in real time by the intelligent control module 8, and each module has an independent sampling port for automatic sampling after sufficient reaction.

[0068] The working principle of the device is as follows: first, the oral digestion module 2 is heated by the oral heating module 206. When the temperature reaches a predetermined temperature, the sample to be tested is placed in the oral digestion module 2, the imitation teeth 202 move up and down to simulate chewing, and the imitation tongue 207 stirs the sample to be tested evenly, so that the imitation teeth 202 simulate chewing, and the imitation tongue 207 simulates the stirring of the tongue; saliva is supplied by the saliva supply module 601 to simulate saliva secretion, and at this time, there is simulated saliva on the imitation teeth 202, so that the simulated saliva performs preliminary digestion of food; when the chewing is sufficient, the switch 204 is turned on, and the mechanical arm 201 is tilted, so that the chewed sample to be tested is passed into the bionic stomach digestion module 3; wherein, the oral monitoring sensor installation module 203 is for various sensors to be connected to the intelligent control module 8, so that the digestion part can be monitored in real time through the connected sensors;

[0069] Before the chewed sample passes through the oral digestion module 2 and enters the bionic stomach digestion module 3, the water temperature is increased and the water pressure is changed through the power supply module 7 and the stomach heating module 304, so that the bionic stomach module reaches the preset temperature and real peristalsis. At the same time, the stomach peristaltic pump 302 peristalsizes to strengthen the peristaltic strength of the bionic stomach, and the gastric juice supply module 602 provides gastric juice to the bionic stomach to simulate the secretion of gastric digestive juice; the intelligent control module 8 controls the condition of the bionic stomach to be consistent with the real stomach in the human body, and the sample is passed into the bionic stomach for simulated digestion. After the reaction is sufficient, the intelligent control module 8 can control the sample sampling device to automatically sample the bionic stomach digestion in the stomach sample sampling port 306. After the sampling is completed, the digested sample is passed into the bionic small intestine digestion module 4 with the action of the peristaltic pump and gravity; wherein, the stomach wall 303 simulates the real human stomach environment with wrinkles and villi, providing more carriers for the microorganisms in the stomach;

[0070] After being digested by the bionic oral digestion module 2 and the bionic gastric digestion module, the bionic intestinal digestion module is passed into the bionic intestinal digestion module, which includes a bionic small intestine digestion module 4 and a bionic large intestine digestion module 5. As above, before the digested material enters, the intelligent control module 8 controls the environment inside the intestine to be consistent with the real human intestinal environment. The digested material enters the small intestine digestion module 4 for reaction. After the reaction is sufficient, it is passed into the bionic large intestine digestion module 5 after automatic sampling is completed. After the reaction is sufficient, sampling is also performed at the small intestine sample sampling port and the large intestine sample sampling port. Then the remaining food residues are passed into the digested material recovery module for recovery. Specifically, after the gastric digestion module is fully digested, the test material is passed into the small intestine digestion module 4 through the peristalsis of the gastric peristaltic pump 302. Before entering, the small intestine is heated in a water bath by the small intestine heating module 405. When the temperature inside the small intestine is stabilized to the temperature inside the human body, the small intestine fluid supply module 603 supplies small intestine fluid to simulate the secretion of small intestine fluid. The peristaltic movement of the small intestine is simulated by controlling the small intestine peristaltic pump 403 and the small intestine heating module 405 to adjust the water pressure change. The small intestine wall 404 is designed to be consistent with the surface of the human small intestine, with wrinkles and villi. When the object to be tested enters the bionic small intestine, digestive fluid is secreted, the intestine peristsalizes, and after the metabolic reaction is sufficient, the object to be tested enters the large intestine digestion module 5. After the digestion module 4 of the small intestine is fully digested, the object to be tested is passed into the digestion module of the large intestine through the peristalsis of the peristaltic pump 403 of the small intestine. Before entering, the large intestine is heated in a water bath by the heating module 505 of the large intestine. After the temperature inside the large intestine is stabilized to the temperature inside the human body, the large intestine fluid supply module 604 supplies large intestine fluid to simulate the secretion of large intestine fluid. The peristaltic movement of the large intestine is simulated by adjusting the water pressure change by controlling the peristaltic pump 502 of the large intestine and the heating module 505 of the large intestine. The design of the wall of the large intestine 503 is consistent with the surface of the human large intestine, with wrinkles and villi. When the object to be tested enters the interior of the bionic large intestine, the digestive fluid is secreted, the intestine peristsalizes, and after the metabolic reaction is sufficient, it is discharged to the sample recovery module 9.

[0071] In summary, the device includes modules such as oral digestion, gastric digestion, small intestinal digestion, digestate recovery, sample detection, power supply and digestive fluid supply, which can simulate food contamination conditions under different environments. The oral digestion module 2 simulates chewing, saliva secretion and other processes; the gastric digestion module simulates gastric juice secretion, mixing and stirring, etc.; the small intestinal digestion module 4 simulates pancreatic juice secretion and food absorption; the digestate recovery module recovers digestion products, the sample detection module monitors experimental parameters, the power supply module 7 provides power support, and the digestive fluid supply module 6 provides the required digestive fluid; the intelligent control module 8 monitors and adjusts the system operation to ensure the accuracy and controllability of the simulated digestion process.

[0072] This device is designed to accurately simulate the key links of the human digestive process, including digestive organs such as the mouth, stomach and small intestine. Each module has real-time measurement, precise control and sample sampling functions, ensuring the high controllability and observability of the digestive process. In addition, the system is equipped with an intelligent control system, which uses advanced sensor technology and microprocessor control algorithms to automatically adjust and optimize the operation of each module. The modular structural design makes the system easy to assemble and maintain, and the modules can be personalized according to specific research needs, providing a flexible and customizable experimental solution for digestive physiology research.

[0073] The second aspect of the present invention discloses a control method for a fully automatic intelligent modular human digestion bionic device, which is applied to any one of the fully automatic intelligent modular human digestion bionic devices described above, and comprises the following steps:

[0074] Obtaining operation log information of the digestive bionic device, obtaining historical working data of the digestive bionic device according to the operation log information, and performing feature engineering processing on the historical working data to obtain feature engineering data;

[0075] Constructing a support vector regression model, and importing the feature engineering data into the support vector regression model for training to obtain a trained support vector regression model;

[0076] When the digestive bionic device is in the process of simulation, the real-time working data of each digestive module of the digestive bionic device is obtained at a preset time node through each sensor, and the real-time working data of each digestive module is processed based on the hierarchical clustering algorithm and the genetic algorithm to obtain the effective real-time working data of each digestive module;

[0077] Importing the effective real-time working data of each digestion module into the trained support vector regression model for prediction, and obtaining the predicted working data of each digestion module within a preset future time;

[0078] Obtaining preset working data of each digestion module within a preset future time period, comparing and analyzing the predicted working data of each digestion module within the preset future time period with the corresponding preset working data, and generating an analysis result;

[0079] If it is the first analysis result, an optimal control scheme is generated, and the digestive bionic device is regulated based on the optimal control scheme; if it is the second analysis result, the digestive bionic device is not regulated.

[0080] It should be noted that the support vector regression model is a machine learning algorithm model used to predict the value of a continuous target variable. The support vector regression model is based on the support vector machine algorithm and fits the data by finding the best hyperplane in the feature space, thereby predicting the predicted working data of the human digestive bionic device in the preset future time.

[0081] Furthermore, in a preferred embodiment of the present invention, the real-time working data of each digestion module is processed based on a hierarchical clustering algorithm and a genetic algorithm to obtain effective real-time working data of each digestion module, specifically:

[0082] S202: each real-time working data is regarded as a separate data point, and the cosine similarity between each data point is calculated, and the two data points with the largest cosine similarity are merged into a population to obtain a plurality of populations;

[0083] S204: defining a fitness function, calculating the fitness of each population based on the fitness function, and comparing the fitness of each population with a preset fitness;

[0084] S206: If the fitness of a certain population is not greater than the preset fitness, the population is defined as a noise data population, and the noise data population is completely eliminated;

[0085] S208: Acquire the real-time working data of each population whose fitness is greater than the preset fitness, and regard the real-time working data of the population whose fitness is greater than the preset fitness as a single data point, and repeat steps S202 to S206;

[0086] S210: until the fitness of all populations is greater than the preset fitness, the real-time working data of each population is obtained to obtain the effective real-time working data of each digestion module.

[0087] Among them, the fitness function is defined by relevant technical personnel in combination with indicators such as problem relevance, monotonicity, and comparability.

[0088] It should be noted that in the results of hierarchical clustering, noise data can be identified based on the shape and characteristics of the clustering tree. Usually, noise data is distributed in the lower layers of the clustering tree and is far away from other data points. The hierarchical clustering algorithm is used to perform preliminary clustering analysis on the data, so as to preliminarily cluster valid data and invalid data (noise data). However, since the hierarchical clustering algorithm is sensitive to noise and outliers, especially in agglomerative hierarchical clustering, outliers may have a greater impact on the clustering results, resulting in clustering errors, such as clustering valid data into invalid data, or clustering invalid data into valid data. Therefore, it is necessary to further evaluate and correct the clustering effect through genetic algorithms. Genetic algorithms are global optimization algorithms that can globally search in the solution space by simulating natural selection and genetic processes to avoid falling into local optimal solutions, which helps to find better clustering results. Therefore, using genetic algorithms to optimize the results of hierarchical clustering can improve the clustering quality and the accuracy of screening noise data, thereby obtaining more meaningful data representation and analysis results.

[0089] In summary, the real-time working data of each digestion module are cleaned and processed through hierarchical clustering algorithm and genetic algorithm to remove invalid data and obtain the effective real-time working data of each digestion module, thereby improving the accuracy and reliability of data analysis.

[0090] Furthermore, in a preferred embodiment of the present invention, the predicted working data of each digestion module within a preset future time is compared and analyzed with the corresponding preset working data to generate an analysis result, specifically:

[0091] Constructing a timestamp, and based on the timestamp, sorting the predicted working data of each digestion module within a preset future time and the corresponding preset working data based on a time series;

[0092] After the sorting is completed, a two-dimensional coordinate system is constructed, and a time series-based predicted working data curve graph and a preset working data curve graph are constructed in the two-dimensional coordinate system based on the predicted working data of each digestion module in the preset future time and the corresponding preset working data;

[0093] Calculate the overlap between the predicted working data curve graph and the preset working data curve graph in the two-dimensional coordinate system based on the Euclidean distance algorithm to obtain the overlap between the predicted working data of the corresponding digestion module within the preset future time and the corresponding preset working data;

[0094] Repeat the above steps until the overlap between the predicted working data of each digestion module within the preset future time and the corresponding preset working data is calculated; and the overlap between the predicted working data of each digestion module within the preset future time and the corresponding preset working data is compared with the preset overlap;

[0095] If the overlap between the predicted working data of a certain digestion module within the preset future time and the corresponding preset working data is not greater than the preset overlap, the digestion module is marked as a module that needs to be regulated; if the overlap between the predicted working data of a certain digestion module within the preset future time and the corresponding preset working data is greater than the preset overlap, the digestion module is marked as a module that does not need to be regulated;

[0096] If there is a module that needs to be regulated in the digestive bionic device, a first analysis result is generated; if there is no module that needs to be regulated in the digestive bionic device, a second analysis result is generated.

[0097] It should be noted that the principle of calculating the overlap between two curves using the Euclidean distance algorithm is: first, define the point sets on the two curves, then calculate the Euclidean distance between the two sets of point pairs (that is, the straight-line distance between the two points), then sum up the distances of all point pairs and divide by the number of point pairs to get the average distance between the two curves. Finally, this average distance is normalized with the total length of the curve to get an overlap value between 0 (no overlap at all) and 1 (complete overlap), which is used to measure the similarity between the two curves.

[0098] If the overlap between the predicted working data of a certain digestion module in the preset future time and the corresponding preset working data is not greater than the preset overlap, it means that the working data of the digestion module in the preset future time period may be abnormal, and the digestion module is marked as a module requiring regulation. The working data includes temperature, humidity, pressure, etc.

[0099] Furthermore, in a preferred embodiment of the present invention, if it is the first analysis result, an optimal control scheme is generated, and the digestive bionic device is controlled based on the optimal control scheme, specifically:

[0100] Obtaining operation log information of the digestion bionic device, and retrieving historical control schemes corresponding to various abnormal operation conditions of each digestion module of the digestion bionic device from the operation log information, and obtaining historical control accuracy corresponding to each historical control scheme;

[0101] The historical control scheme corresponding to the maximum historical control accuracy is calibrated as the optimal control scheme corresponding to the corresponding abnormal operation condition, and the optimal control scheme corresponding to various abnormal operation conditions of each digestion module is obtained; and the historical working data of each digestion module before various abnormal operation conditions occur is obtained from the operation log information;

[0102] Bundling the optimal control schemes corresponding to various abnormal operating conditions of each digestion module with the historical working data before the various abnormal operating conditions occurred to obtain a plurality of data packets; constructing a database, and importing the plurality of data packets into the database to obtain a characteristic database;

[0103] If the analysis result is the first analysis result, the real-time working data corresponding to the module to be regulated in the digestive bionic device at the preset time node is obtained, and the data packet corresponding to the module to be regulated is extracted from the characteristic database, that is, the data packet corresponding to the same digestive module as the module to be regulated;

[0104] Calculate the hash value between the real-time working data corresponding to the module to be regulated at a preset time node and the historical working data in the extracted data packet by using a perceptual hash algorithm to obtain multiple hash values;

[0105] Among them, the perceptual hashing algorithm is used to first convert the two data sets into perceptual hash values ​​(such as pHash values), which can capture the main content and structural information in the data sets. Then, the Hamming distance (i.e., the number of different bits) between the two perceptual hash values ​​is calculated. The smaller the Hamming distance, the more similar the two data sets are in visual content. Finally, the Hamming distance is normalized to a similarity score between 0 and 1 to measure the similarity between the two data sets.

[0106] The data packet corresponding to the maximum hash value is obtained, and the optimal control scheme for controlling the module to be controlled is extracted from the data packet corresponding to the maximum hash value, and the optimal control scheme is sent to the intelligent control module to control the digestive bionic device based on the optimal control scheme.

[0107] It should be noted that the operation log information of the digestive bionic device refers to the detailed data and descriptions about the device's working status, performance parameters, operation history, fault diagnosis, maintenance activities, etc., which are automatically recorded by the system during the operation of the device. This information helps to analyze the operation of the device, optimize the operating process, predict and deal with potential problems, thereby improving the operating efficiency and reliability of the device.

[0108] In summary, the present invention utilizes an artificial intelligence algorithm to automatically adjust the working status of each module according to the collected data and the preset digestion model to ensure that the working parameters of each digestion module are always in line with the preset requirements, so as to achieve the best digestion simulation effect, and ensure that the simulation system is closer to the anatomical structure of the real human digestive tract while ensuring feasibility, thereby improving the credibility and realism of the simulation.

[0109] In addition, the control method further comprises the following steps:

[0110] After the control module of the digestive bionic device is controlled by the optimal control scheme, the real-time working data of the module to be controlled is obtained at a set time node, and the similarity between the real-time working data and the predicted working data is calculated;

[0111] If the similarity between the real-time working data and the predicted working data is not greater than the preset similarity, a Markov chain is introduced, and the state transition probability of the module to be regulated is calculated based on the Markov chain and in combination with the real-time working data;

[0112] Determine whether the state transition probability is greater than a preset probability, and if so, obtain the state transition type of the module to be regulated;

[0113] The correlation between the state transfer type and the bionic test result is analyzed based on the grey correlation analysis method. If the correlation is greater than a preset correlation, the digestive bionic device is controlled to stop the test and the test is marked as an invalid test.

[0114] It should be noted that after the module to be regulated of the digestive bionic device is regulated by the optimal control scheme, if the real-time working data of the module to be regulated is still abnormal, the Markov chain is used to determine whether the module has an abnormal operation. That is, if the state transition probability is greater than the preset probability, it means that the module to be regulated has transferred from a normal working state to an abnormal working state. If it is greater than, the state transition type of the module to be regulated is obtained. If the correlation between the state transition type and the bionic test result is greater than the preset correlation, it means that the abnormal operation of the module has affected the reliability and accuracy of the test result. At this time, the digestive bionic device is controlled to stop the test and the test is marked as an invalid test.

[0115] In addition, the control method further comprises the following steps:

[0116] Prefabricate the preset temperatures corresponding to the digestion modules in the digestion bionic device at each test stage, construct a preset temperature distribution diagram according to the preset temperatures, and obtain the preset temperature distribution diagram corresponding to the digestion bionic device at each test stage;

[0117] Constructing a knowledge graph, and importing the preset temperature distribution graph corresponding to each test stage of the digestive bionic device into the knowledge graph;

[0118] Acquire the real-time test phase of the digestive bionic device during the test process, and obtain a preset temperature distribution diagram of the digestive bionic device at the current time node according to the real-time test phase;

[0119] Acquire actual temperature information of each digestion module in the digestion bionic device, and construct an actual temperature distribution diagram of the digestion bionic device at a current time node according to the actual temperature information;

[0120] Calculate the Pearson correlation coefficient between the actual temperature distribution diagram of the digestive bionic device at the current time node and the preset temperature distribution diagram;

[0121] If the Pearson correlation coefficient is greater than the preset coefficient value, it means that the temperature state of the digestive bionic device at the current time node is normal;

[0122] If the Pearson correlation coefficient is not greater than the preset coefficient value, it means that the temperature state of the digestive bionic device at the current time node is abnormal. At this time, the actual temperature distribution diagram and the preset temperature distribution diagram of the digestive bionic device at the current time node are subjected to feature extraction processing based on the ORB algorithm to obtain the actual isotherm diagram and the preset isotherm diagram;

[0123] Constructing a virtual space, importing the actual isotherm map and the preset isotherm map into the virtual space, and performing registration processing on the actual isotherm map and the preset isotherm map in the virtual space;

[0124] The line segment area where the actual isotherm map overlaps with the preset isotherm map is marked as a normal temperature area, and the line segment area where the actual isotherm map overlaps with the preset isotherm map is marked as an abnormal temperature area.

[0125] It should be noted that the Pearson correlation coefficient is a statistical method to measure the strength and direction of the linear relationship between two variables. In the scenario of judging the similarity between two temperature distribution maps, the temperature distribution map can be regarded as a set of data points, where the coordinates of each point represent the temperature value at a specific location. By calculating the Pearson correlation coefficient of these two sets of temperature data points, the strength and direction of the linear relationship between the two temperature distribution maps are quantified. Values ​​close to 1 indicate strong positive correlation and high similarity, values ​​close to -1 indicate strong negative correlation and low similarity, and values ​​close to 0 indicate no significant linear relationship and large differences.

[0126] Among them, the ORB (Oriented FAST and Rotated BRIEF) algorithm is a feature extraction and matching method commonly used in computer vision and image processing. The ORB algorithm quickly detects corner points in the temperature distribution map (using the FAST key point detector), calculates the gradient direction of these corner points (to ensure rotation invariance), and generates a rotation-invariant BRIEF descriptor to extract feature points. These feature points are then used to construct the isotherm map, thereby extracting the isotherm map based on the temperature distribution map.

[0127] This method can quickly determine whether the temperature of each digestion module of the digestion bionic device during the test is normal, and can analyze the temperature abnormal area, so that the temperature abnormal area can be quickly regulated to ensure the reliability of the test results.

[0128] The above is based on the ideal embodiment of the present invention, and its description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. A control method for a fully automatic intelligent modular human digestion bionic device, characterized in that: The digestive bionic device comprises an oral digestive module, a stomach digestive module, a large intestine digestive module, a small intestine digestive module, a digestive fluid supply module, a power supply module and an intelligent control module; The oral digestion module includes a mechanical arm, simulated teeth, an oral monitoring sensor installation module, a switch, a movable joint, a saliva access port, an oral heating module, a simulated tongue and simulated lips; the oral heating module is used to adjust the internal temperature of the oral digestion module; the simulated teeth can move up and down to simulate chewing; the simulated tongue is used to stir the food to be tested; The stomach digestion module is connected to the oral digestion module, and includes a gastric juice access port, a gastric peristaltic pump, a gastric wall, a gastric heating module, a gastric monitoring sensor installation module, and a gastric sample sampling port; the gastric peristaltic pump is embedded on the external gastric wall, and the peristaltic movement of the stomach is simulated by the rotation of the gastric peristaltic pump; the internal gastric wall is provided with folds and villi; The small intestinal digestion module is connected to the stomach digestion module, and the small intestinal digestion module includes a small intestinal liquid access port, a small intestinal monitoring sensor installation module, a small intestinal peristaltic pump, a small intestinal wall, a small intestinal heating module, and a small intestinal sample sampling port; the small intestinal peristaltic pump is embedded in the external small intestinal wall, and the peristaltic movement of the small intestine is simulated by the rotation of the small intestinal peristaltic pump; the internal small intestinal wall is provided with folds and villi; The large intestine digestion module is connected to the small intestine digestion module, and the large intestine digestion module includes a large intestine liquid access port, a large intestine peristaltic pump, a large intestine wall, a large intestine monitoring sensor installation module, a large intestine heating module, and a large intestine sample sampling port; the large intestine peristaltic pump is embedded in the external large intestine wall, and the peristaltic movement of the large intestine is simulated by the rotation of the large intestine peristaltic pump; the internal large intestine wall is provided with folds and villi; The control method comprises the following steps: Obtaining operation log information of the digestive bionic device, obtaining historical working data of the digestive bionic device according to the operation log information, and performing feature engineering processing on the historical working data to obtain feature engineering data; Constructing a support vector regression model, and importing the feature engineering data into the support vector regression model for training to obtain a trained support vector regression model; When the digestive bionic device is in the process of simulation, the real-time working data of each digestive module of the digestive bionic device is obtained at a preset time node through each sensor, and the real-time working data of each digestive module is processed based on the hierarchical clustering algorithm and the genetic algorithm to obtain the effective real-time working data of each digestive module; Importing the effective real-time working data of each digestion module into the trained support vector regression model for prediction, and obtaining the predicted working data of each digestion module within a preset future time; Obtaining preset working data of each digestion module within a preset future time period, comparing and analyzing the predicted working data of each digestion module within the preset future time period with the corresponding preset working data, and generating an analysis result; If it is the first analysis result, an optimal control scheme is generated, and the digestion bionic device is regulated based on the optimal control scheme; if it is the second analysis result, the digestion bionic device is not regulated; Among them, the predicted working data of each digestion module in the preset future time is compared and analyzed with the corresponding preset working data to generate the analysis results, specifically: Constructing a timestamp, and based on the timestamp, sorting the predicted working data of each digestion module within a preset future time and the corresponding preset working data based on a time series; After the sorting is completed, a two-dimensional coordinate system is constructed, and a time series-based predicted working data curve graph and a preset working data curve graph are constructed in the two-dimensional coordinate system based on the predicted working data of each digestion module in the preset future time and the corresponding preset working data; Calculate the overlap between the predicted working data curve graph and the preset working data curve graph in the two-dimensional coordinate system based on the Euclidean distance algorithm to obtain the overlap between the predicted working data of the corresponding digestion module within the preset future time and the corresponding preset working data; Repeat the above steps until the overlap between the predicted working data of each digestion module within the preset future time and the corresponding preset working data is calculated; and the overlap between the predicted working data of each digestion module within the preset future time and the corresponding preset working data is compared with the preset overlap; If the overlap between the predicted working data of a certain digestion module within the preset future time and the corresponding preset working data is not greater than the preset overlap, the digestion module is marked as a module that needs to be regulated; if the overlap between the predicted working data of a certain digestion module within the preset future time and the corresponding preset working data is greater than the preset overlap, the digestion module is marked as a module that does not need to be regulated; If there is a module that needs to be regulated in the digestive bionic device, a first analysis result is generated; if there is no module that needs to be regulated in the digestive bionic device, a second analysis result is generated.

2. The control method of a fully automatic intelligent modular human digestion bionic device according to claim 1, characterized in that: The stomach heating module, the small intestine heating module, and the large intestine heating module are all water bath mechanisms; the oral heating module is an air heating mechanism.

3. The control method of a fully automatic intelligent modular human digestion bionic device according to claim 1 is characterized by: The digestive fluid supply module includes a saliva supply module, a gastric fluid supply module, a small intestinal fluid supply module and a large intestinal fluid supply module; the saliva supply module is connected to the saliva access port via a saliva delivery tube; the gastric fluid supply module is connected to the gastric fluid access port via a gastric fluid delivery tube; the small intestinal fluid supply module is connected to the small intestinal fluid access port via a small intestinal fluid delivery tube; and the large intestinal fluid supply module is connected to the large intestinal fluid access port via a large intestinal fluid delivery tube.

4. The control method of the fully automatic intelligent modular human digestion bionic device according to claim 3 is characterized by: The saliva delivery tube, the gastric juice delivery tube, the small intestinal juice delivery tube and the large intestinal juice delivery tube are all provided with a liquid extraction pump.

5. The control method of a fully automatic intelligent modular human digestion bionic device according to claim 1, characterized in that: The intelligent control module is communicatively connected with the monitoring sensors in each digestion module.

6. The control method of a fully automatic intelligent modular human digestion bionic device according to claim 1, characterized in that: Each monitoring sensor installation module is used to install various types of monitoring sensors, including temperature sensors, pH sensors, pressure sensors and humidity sensors.

7. The control method of a fully automatic intelligent modular human digestion bionic device according to claim 1, characterized in that: Based on the hierarchical clustering algorithm and genetic algorithm, the real-time working data of each digestion module is processed to obtain the effective real-time working data of each digestion module, which is as follows: S202: each real-time working data is regarded as a separate data point, and the cosine similarity between each data point is calculated, and the two data points with the largest cosine similarity are merged into a population to obtain a plurality of populations; S204: defining a fitness function, calculating the fitness of each population based on the fitness function, and comparing the fitness of each population with a preset fitness; S206: If the fitness of a certain population is not greater than the preset fitness, the population is defined as a noise data population, and the noise data population is completely eliminated; S208: Acquire the real-time working data of each population whose fitness is greater than the preset fitness, and regard the real-time working data of the population whose fitness is greater than the preset fitness as a single data point, and repeat steps S202 to S206; S210: until the fitness of all populations is greater than the preset fitness, the real-time working data of each population is obtained to obtain the effective real-time working data of each digestion module.

8. The control method of a fully automatic intelligent modular human digestion bionic device according to claim 1, characterized in that: If it is the first analysis result, an optimal control scheme is generated, and the digestive bionic device is controlled based on the optimal control scheme, specifically: Obtaining operation log information of the digestion bionic device, and retrieving historical control schemes corresponding to various abnormal operation conditions of each digestion module of the digestion bionic device from the operation log information, and obtaining historical control accuracy corresponding to each historical control scheme; The historical control scheme corresponding to the maximum historical control accuracy is calibrated as the optimal control scheme corresponding to the corresponding abnormal operation condition, and the optimal control scheme corresponding to various abnormal operation conditions of each digestion module is obtained; and the historical working data of each digestion module before various abnormal operation conditions occur is obtained from the operation log information; Bundling the optimal control schemes corresponding to various abnormal operating conditions of each digestion module with the historical working data before the various abnormal operating conditions occurred to obtain a plurality of data packets; constructing a database, and importing the plurality of data packets into the database to obtain a characteristic database; If the analysis result is the first analysis result, the real-time working data corresponding to the module to be regulated in the digestive bionic device at the preset time node is obtained, and the data packet corresponding to the module to be regulated is extracted from the characteristic database, that is, the data packet corresponding to the same digestive module as the module to be regulated; Calculate the hash value between the real-time working data corresponding to the module to be regulated at a preset time node and the historical working data in the extracted data packet by using a perceptual hash algorithm to obtain multiple hash values; The data packet corresponding to the maximum hash value is obtained, and the optimal control scheme for controlling the module to be controlled is extracted from the data packet corresponding to the maximum hash value, and the optimal control scheme is sent to the intelligent control module to control the digestive bionic device based on the optimal control scheme.

Images