Fully automatic intelligent modular biomimetic human digestive apparatus, and method

Abstract

A fully automatic intelligent modular biomimetic human digestive apparatus, and a method. A modular biomimetic complete human digestive system accurately simulates the human digestive process, and comprises key organs such as the oral cavity, the stomach, and the small intestine. Each module has real-time measurement, precise control, and sample collection functions, ensuring that the digestive process is highly controllable and observable. An intelligent control system utilizes sensor technology and microprocessor algorithms to automatically regulate and optimize module operations. The modular structure makes the system easy to assemble and maintain, enables customized configuration as required, and provides flexible, tailored solutions for digestive physiology research. The system comprises modules such as an oral digestion module, a gastric digestion module, a small intestine digestion module, a digesta recovery module, a sample testing module, a power supply module, and a digestive fluid supply module. Each module performs a specific function to collectively ensure the accuracy and controllability of the simulated digestive process.

Description

A full-automatic intelligent modular human body digestion bionic device and method TECHNICAL FIELD

[0001] The present application relates to the field of environmental science and engineering and bionics, in particular to a full-automatic intelligent modular human body digestion bionic device and method. BACKGROUND

[0002] The widespread application of human digestive tract in vitro simulation devices has greatly facilitated the research in the field 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 food digestion in the human body is crucial for determining food components, and the use of human digestive tract in vitro simulation devices will play a key role in this regard.

[0003] Current technology usually uses a triangular flask or a beaker as a device for simulating gastric digestion. In a simulated digestion experiment, a certain amount of food is first placed in a triangular flask or a beaker, and then simulated gastric juice or intestinal juice is added; then, the triangular flask or beaker is placed on a constant-temperature water bath shaker for a period of time to simulate the digestion process in the human stomach. After digestion, the digested and undigested substances are separated by centrifugation or filtration. However, when a triangular flask or a beaker is used as a device for simulating gastric digestion, the digestion products in it have an inhibitory effect on the reaction, resulting in inaccurate measurement results for such digestion experiments. There are many types of invention patents related to digestion simulation, and the core technical problems solved by each patent are different.

[0004] A human digestion bionic device is a biological in vitro test system used to evaluate or predict the oral bioavailability of specific chemical substances in solid matrices. This device can simulate the physiological environment and digestion and absorption process of the human gastrointestinal tract, and is suitable for research fields such as digestion and metabolism of food, drugs, pollutants, nutritional kinetics, bioavailability, and safety evaluation. However, human digestion bionic devices currently face some technical challenges, mainly in the following aspects: (1) the construction of the simulation system lacks uniform 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, as the current simulation system can only simulate part of the functions of the human gastrointestinal tract, and cannot fully reflect the dynamic changes and microbial co-metabolism of the human gastrointestinal tract, nor can it consider individual differences and physiological state influences; (3) the application range and effect of the simulation system need to be expanded, as the current simulation system is mainly used to evaluate the biological effectiveness of single or simple food or compounds, and lacks effective evaluation methods and indicators for the interaction and synergistic effects of complex food or compounds, as well as the long-term impact on human health. SUMMARY

[0005] The present application overcomes the deficiencies of the prior art and provides a full-automatic intelligent modular human body digestion bionic device and method.

[0006] To achieve the above-mentioned purposes, the present application adopts the technical scheme of:

[0007] The present application discloses a full-automatic intelligent modular human body digestion bionic device in the first aspect, comprising an oral cavity digestion module, a stomach digestion module, a large intestine digestion module, a small intestine digestion module, a digestion liquid supply module, a power supply module and an intelligent control module.

[0008] The oral cavity digestion module comprises a mechanical arm, artificial teeth, an oral cavity monitoring sensor installation module, a switch, a movable joint, a saliva inlet, an oral cavity heating module, an artificial tongue and a lip protector; the oral cavity heating module is used for adjusting the internal temperature of the oral cavity digestion module; the artificial teeth can move up and down to simulate chewing; the artificial tongue is used for stirring the food to be tested;

[0009] The stomach digestion module is connected with the oral cavity digestion module, and the stomach digestion module comprises a gastric juice inlet, a stomach peristaltic pump, a stomach wall, a stomach heating module, a stomach monitoring sensor installation module and a stomach sample sampling port; the stomach peristaltic pump is embedded on the external stomach wall and simulates the peristalsis of the stomach through rotation of the stomach peristaltic pump; the internal stomach wall is provided with folds and villi;

[0010] The small intestine digestion module is connected with the stomach digestion module, and the small intestine digestion module comprises a small intestine juice inlet, a small intestine monitoring sensor installation module, a small intestine peristaltic pump, a small intestine wall, a small intestine heating module and a small intestine sample sampling port; the small intestine peristaltic pump is embedded on the external small intestine wall and simulates the peristalsis of the small intestine through rotation of the small intestine peristaltic pump; the internal small intestine wall is provided with folds and villi;

[0011] The large intestine digestion module is connected with the small intestine digestion module, and the large intestine digestion module comprises a large intestine juice inlet, 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 on the external large intestine wall and simulates the peristalsis of the large intestine through rotation of the large intestine peristaltic pump; the internal large intestine wall is provided with folds and villi.

[0012] Further, in a preferred embodiment of the present application, the stomach heating module, the small intestine heating module and the large intestine heating module are all water bath mechanisms; and the oral cavity heating module is a gas heating mechanism.

[0013] Further, in a preferred embodiment of the present application, the digestive fluid supply module comprises a saliva supply module, a gastric juice supply module, a small intestine juice supply module, and a large intestine juice supply module; the saliva supply module is connected to the saliva inlet through a saliva delivery pipe; the gastric juice supply module is connected to the gastric juice inlet through a gastric juice delivery pipe; the small intestine juice supply module is connected to the small intestine juice inlet through a small intestine juice delivery pipe; and the large intestine juice supply module is connected to the large intestine juice inlet through a large intestine juice delivery pipe.

[0014] Further, in a preferred embodiment of the present application, the saliva delivery pipe, the gastric juice delivery pipe, the small intestine juice delivery pipe, and the large intestine juice delivery pipe are each provided with a liquid suction pump.

[0015] Further, in a preferred embodiment of the present application, the intelligent control module is in communication connection with the monitoring sensors in each digestive module.

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

[0017] The second aspect of the present application discloses a control method of a full-automatic intelligent modular human body digestion bionic device, which is applied to any one of the full-automatic intelligent modular human body digestion bionic devices and comprises the following steps:

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

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

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

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

[0022] acquire preset working data of each digestion module in a preset future time period, compare and analyze the predicted working data of each digestion module in the preset future time with the corresponding preset working data, and generate an analysis result;

[0023] If the first analysis result is obtained, an optimal regulation scheme is generated, and the digestion bionic device is regulated and processed based on the optimal regulation scheme; if the second analysis result is obtained, the digestion bionic device is not regulated and processed.

[0024] Further, in a preferred embodiment of the present application, 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 as follows:

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

[0026] S204: An adaptability function is defined, and the adaptability of each population is calculated based on the adaptability function, and the adaptability of each population is compared with a preset adaptability;

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

[0028] S208: Real-time working data in a population corresponding to each adaptability greater than the preset adaptability is acquired, and each real-time working data in the population corresponding to the adaptability greater than the preset adaptability is regarded as a single data point, and the steps of S202 to S206 are repeated;

[0029] S210: Until the adaptability of all populations is greater than the preset adaptability, real-time working data in each population is acquired to obtain effective real-time working data of each digestion module.

[0030] Further, in a preferred embodiment of the present application, 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 an analysis result, specifically as follows:

[0031] A time stamp is constructed, and the predicted working data of each digestion module in the preset future time and the corresponding preset working data are sorted based on time sequence based on the time stamp;

[0032] After sorting, a two-dimensional coordinate system is constructed, and the predicted working data curve and the preset working data curve based on time sequence 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] calculating the overlap degree between the predicted working data curve and the preset working data curve in the two-dimensional coordinate system based on the Euclidean distance algorithm, to obtain the overlap degree between the predicted working data of the corresponding digestion module in the preset future time and the corresponding preset working data;

[0034] repeating the above steps until the overlap degree between the predicted working data of each digestion module in the preset future time and the corresponding preset working data is calculated; and comparing the overlap degree between the predicted working data of each digestion module in the preset future time and the corresponding preset working data with the preset overlap degree;

[0035] If the overlap degree 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 degree, the digestion module is marked as a module that needs to be regulated; if the overlap degree between the predicted working data of a certain digestion module in the preset future time and the corresponding preset working data is greater than the preset overlap degree, 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 digestion bionic device, a first analysis result is generated; if there is no module that needs to be regulated in the digestion bionic device, a second analysis result is generated.

[0037] Further, in a preferred embodiment of the present application, if it is the first analysis result, an optimal regulation scheme is generated, and the digestion bionic device is regulated based on the optimal regulation scheme, specifically:

[0038] obtaining the running log information of the digestion bionic device, and retrieving the historical regulation scheme corresponding to each abnormal running condition of each digestion module of the digestion bionic device in the running log information, and obtaining the historical regulation accuracy corresponding to each historical regulation scheme;

[0039] labeling the historical regulation scheme corresponding to the maximum historical regulation accuracy as the optimal regulation scheme corresponding to the corresponding abnormal running condition, to obtain the optimal regulation scheme corresponding to each abnormal running condition of each digestion module; and obtaining the historical working data of each digestion module before the abnormal running condition in the running log information;

[0040] binding the optimal regulation scheme corresponding to each abnormal running condition of each digestion module with the historical working data before the abnormal running condition 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, real-time working data of a module to be regulated in the digestive bionic device at a preset time node is acquired, and a data packet corresponding to the module to be regulated is extracted from the characteristic database, that is, a data packet corresponding to the same digestive module as the module to be regulated;

[0042] A hash value between the real-time working data of the module to be regulated at the preset time node and historical working data in the extracted data packet is calculated by using a perceptual hash algorithm, to obtain a plurality of hash values;

[0043] The data packet corresponding to the maximum hash value is acquired, and an optimal regulation scheme for regulating the module to be regulated is extracted from the data packet corresponding to the maximum hash value, and the optimal regulation scheme is sent to the intelligent control module, so that the digestive bionic device is regulated and processed based on the optimal regulation scheme.

[0044] The present application solves the technical defects in the background art, and has the following beneficial effects: the device aims to accurately simulate each key link of the human digestive process, including the oral cavity, stomach and small intestine and other digestive organs, each module has real-time measurement, accurate control and sample sampling functions, ensuring high controllability and observability of the digestive process. And, the system is equipped with an intelligent control system, which uses advanced sensor technology and microprocessor control algorithm to automatically adjust and optimize the operation of each module. The modular structure design makes the system easy to assemble and maintain, and the modules can be individually configured according to specific research needs, providing a flexible and customizable experimental solution for digestive physiology research. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings of embodiments according to these drawings without creative labor.

[0046] Fig. 1 is a schematic diagram of the overall structure of the full-automatic intelligent modular human digestive bionic device;

[0047] Fig. 2 is a bionic oral cavity digestion simulation module diagram;

[0048] Fig. 3 is a bionic stomach digestion simulation module diagram;

[0049] Fig. 4 is a bionic small intestine digestion simulation module diagram;

[0050] Fig. 5 is a bionic large intestine digestion simulation module diagram;

[0051] Fig. 6 is a diagram of a digestive fluid supply module;

[0052] The reference signs are explained as follows: 1, housing; 2, oral cavity 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, mechanical arm; 202, artificial tooth; 203, oral cavity monitoring sensor installation module; 204, switch; 205, movable joint; 206, oral cavity heating module; 207, artificial tongue; 208, lip protector; 301, gastric juice inlet; 302, gastric peristaltic pump; 303, gastric wall; 304, gastric heating module; 305, gastric monitoring sensor installation module; 306, gastric sample sampling port; 401, small intestine fluid inlet; 402, small intestine monitoring sensor installation module; 403, small intestine peristaltic pump; 404, small intestine wall; 405, small intestine heating module; 501, large intestine fluid inlet; 502, large intestine peristaltic pump; 503, large intestine wall; 504, large intestine monitoring sensor installation module; 505, large intestine heating module; 601, saliva supply module; 602, gastric juice supply module; 603, small intestine fluid supply module; 604, large intestine fluid supply module; 606, fluid pump. DETAILED DESCRIPTION

[0053] In order to enable a person skilled in the art to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be further described in detail below in conjunction with the drawings and specific embodiments, which are all simplified schematic diagrams and only schematically show the basic structure of the present application, and therefore only show the structures related to the present application. It should be noted that the embodiments in the present 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", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the scope of protection of the present application. In addition, the terms "first", "second" and the like are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" and the like can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise stated, the meaning of "a plurality of" is two or more.

[0055] In the description of the present application, it is necessary to explain that, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "linking" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integrally connected; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, or the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood through specific circumstances.

[0056] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the related drawings. The preferred embodiments of the present application are shown in the drawings. However, the present application can be realized 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 application more thorough and comprehensive.

[0057] As shown in Figure 1, the first aspect of the present application discloses a full-automatic intelligent modular human body digestion bionic device, comprising an oral cavity digestion module 2, a stomach digestion module 3, a large intestine digestion module 5, a small intestine digestion module 4, a digestive juice supply module 6, a power supply module 7 and an intelligent control module 8;

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

[0059] As shown in Figure 3, the stomach digestion module 3 is connected with the oral cavity digestion module 2, and the stomach digestion module 3 comprises a gastric juice inlet 301, a gastric peristalsis pump 302, a gastric wall 303, a gastric heating module 304, a gastric monitoring sensor installation module 305 and a gastric sample sampling port 306; the gastric peristalsis pump 302 is embedded on the external gastric wall 303, and the gastric peristalsis pump 302 is rotated to simulate the peristalsis of the stomach; the internal gastric wall 303 is provided with wrinkles and villi;

[0060] As shown in Figure 4, the small intestine digestion module 4 is connected with the stomach digestion module 3, the small intestine digestion module 4 comprises a small intestine liquid inlet 401, a small intestine monitoring sensor installation module 402, a small intestine peristalsis pump 403, a small intestine wall 404, a small intestine part heating module 405 and a small intestine part sample sampling port; the small intestine peristalsis pump 403 is embedded on the external small intestine wall 404, the rotation of the small intestine peristalsis pump 403 simulates the peristalsis of the small intestine; the internal small intestine wall 404 is provided with folds and villi.

[0061] As shown in Figure 5, the large intestine digestion module 5 is connected with the small intestine digestion module 4, the large intestine digestion module 5 comprises a large intestine liquid inlet 501, a large intestine peristalsis pump 502, a large intestine wall 503, a large intestine monitoring sensor installation module 504, a large intestine part heating module 505 and a large intestine part sample sampling port; the large intestine peristalsis pump 502 is embedded on the external large intestine wall 503, the rotation of the large intestine peristalsis pump 502 simulates the peristalsis of the large intestine; the internal large intestine wall 503 is provided with folds and villi.

[0062] Further, in a preferred embodiment of the present application, the stomach part heating module 304, the small intestine part heating module 405 and the large intestine part heating module 505 are all water bath mechanisms; the oral cavity heating module 206 is a gas heating mechanism.

[0063] As shown in Figure 6, further, in a preferred embodiment of the present application, the digestion liquid supply module 6 comprises a saliva supply module 601, a stomach liquid supply module 602, a small intestine liquid supply module 603 and a large intestine liquid supply module 604; the saliva supply module 601 is connected with the saliva inlet through a saliva delivery pipe; the stomach liquid supply module 602 is connected with the stomach liquid inlet 301 through a stomach liquid delivery pipe; the small intestine liquid supply module 603 is connected with the small intestine liquid inlet 401 through a small intestine liquid delivery pipe; the large intestine liquid supply module 604 is connected with the large intestine liquid inlet 501 through a large intestine liquid delivery pipe.

[0064] The digestion liquid stored in the saliva supply module 601, the stomach liquid supply module 602, the small intestine liquid supply module 603 and the large intestine liquid supply module 604 is transported into each digestion module through the peristalsis pump

[0065] Further, in a preferred embodiment of the present application, the saliva delivery pipe, the stomach liquid delivery pipe, the small intestine liquid delivery pipe and the large intestine liquid delivery pipe are all provided with a liquid suction pump 606.

[0066] Further, in a preferred embodiment of the present application, the intelligent control module 8 is in communication connection with the monitoring sensors in each digestion module.

[0067] Further, in a preferred embodiment of the present application, each monitoring sensor installation module is used to install each type of monitoring sensor, including temperature sensors, pH sensors, pressure sensors, and humidity sensors. Each digestive part is monitored in real time by each sensor. The temperature, pH, depth, peristalsis, and the like of each digestive module are monitored and regulated in real time by the intelligent control module 8. After each module is fully reacted, there is an independent sampling port for automatic sampling.

[0068] The working principle of the device is as follows: first, the oral cavity digestion module 2 is heated by the oral cavity heating module 206, and when the temperature reaches a predetermined temperature, the sample to be measured is placed in the oral cavity digestion module 2. The artificial teeth 202 move up and down to simulate chewing, and the artificial tongue 207 stirs the sample to be measured uniformly to simulate the chewing of teeth by the artificial teeth 202 and the stirring of the tongue by the artificial tongue 207. Saliva is supplied by the saliva supply module 601 to simulate saliva secretion. At this time, the artificial teeth 202 have simulated saliva, thereby simulating the initial digestion of food by saliva. When the chewing is sufficient, the switch 204 is opened, and the mechanical arm 201 is tilted, thereby passing the fully chewed sample to be measured into the bionic stomach digestion module 3. The oral cavity monitoring sensor installation module 203 is connected to the intelligent control module 8 for each type of sensor to monitor the digestive part in real time.

[0069] Before the sample after being chewed by the oral cavity digestion module 2 enters the bionic stomach digestion module 3, the water temperature is raised and the water pressure is changed by the power supply module 7 and the stomach heating module 304, so that the bionic stomach module reaches a predetermined temperature and a real peristalsis. At the same time, the stomach peristalsis pump 302 peristalsis is enhanced to strengthen the peristalsis intensity of the bionic stomach. The stomach juice supply module 602 provides stomach juice for the bionic stomach to simulate the secretion of gastric juice. The intelligent control module 8 controls the bionic stomach to be consistent with the real human stomach in the body. 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 perform automatic sampling of the bionic stomach digestion in the stomach sampling port 306. After sampling is completed, the digested sample is passed into the bionic small intestine digestion module 4 under the action of the peristalsis pump and gravity. 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 the digestion by the bionic oral cavity digestion module 2 and the bionic stomach digestion module, the digestion product enters 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 digestion product enters, the intelligent control module 8 controls the environment inside the intestinal tract to be consistent with the environment inside the human intestinal tract. After the reaction of the digestion product in the small intestine digestion module 4, the digestion product is sampled automatically, and then enters the bionic large intestine digestion module 5. After the reaction is completed, the digestion product is sampled at the sample sampling port of the small intestine and the sample sampling port of the large intestine, and then the remaining food residue enters the digestion product recovery module for recovery. Specifically, after the digestion by the stomach digestion module, the digestion product enters the small intestine digestion module 4 through the peristalsis of the stomach peristalsis pump 302. Before entering, the small intestine part is heated by the small intestine heating module 405, and when the temperature inside the small intestine is stable at the temperature in the human body, the small intestine liquid supply module 603 supplies the small intestine liquid to simulate the secretion of the small intestine liquid. The water pressure is adjusted by controlling the small intestine peristalsis pump 403 and the small intestine heating module 405 to simulate the peristalsis of the small intestine. The small intestine wall 404 is designed to be consistent with the surface of the human small intestine, and has folds and villi. After the digestion product enters the bionic small intestine, the digestion liquid is secreted, and the intestinal tract peristalsis. After the reaction is completed, the digestion product enters the large intestine digestion module 5. After the digestion by the small intestine digestion module 4, the digestion product enters the large intestine digestion module through the peristalsis of the small intestine peristalsis pump 403. Before entering, the large intestine part is heated by the large intestine heating module 505, and when the temperature inside the large intestine is stable at the temperature in the human body, the large intestine liquid supply module 604 supplies the large intestine liquid to simulate the secretion of the large intestine liquid. The water pressure is adjusted by controlling the large intestine peristalsis pump 502 and the large intestine heating module 505 to simulate the peristalsis of the large intestine. The large intestine wall 503 is designed to be consistent with the surface of the human large intestine, and has folds and villi. After the digestion product enters the bionic large intestine, the digestion liquid is secreted, and the intestinal tract peristalsis. After the reaction is completed, the digestion product is discharged to the sample recovery module 9.

[0071] In summary, the device includes an oral cavity digestion module, a stomach digestion module, a small intestine digestion module, a digestion product recovery module, a sample detection module, a power supply module, and a digestion liquid supply module. The device can simulate food contamination in different environments, simulate chewing, saliva secretion, etc. through the oral cavity digestion module 2; simulate gastric juice secretion, mixing and stirring, etc. through the stomach digestion module; simulate pancreatic juice secretion and food absorption through the small intestine digestion module 4; recover the digestion product through the digestion product recovery module; monitor experimental parameters through the sample detection module; provide power support through the power supply module 7; provide the required digestion liquid through the digestion liquid supply module 6; and monitor and adjust the system operation through the intelligent control module 8 to ensure the accuracy and controllability of the simulated digestion process.

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

[0073] The second aspect of the present application discloses a control method of a full-automatic intelligent modular human digestive bionic device, which is applied to any one of the full-automatic intelligent modular human digestive bionic devices and comprises the following steps:

[0074] Obtaining the running log information of the digestive bionic device, obtaining the historical working data of the digestive bionic device according to the running 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 simulation process, the real-time working data of each digestive module of the digestive bionic device is obtained by each sensor at a preset time node, and the real-time working data of each digestive module is processed based on a hierarchical clustering algorithm and a genetic algorithm to obtain effective real-time working data of each digestive module;

[0077] The effective real-time working data of each digestive module is imported into the trained support vector regression model for prediction to obtain predicted working data of each digestive module within a preset future time;

[0078] Obtaining preset working data of each digestive module within a preset future time period, comparing and analyzing the predicted working data of each digestive module within the preset future time 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 controlled based on the optimal control scheme; if it is the second analysis result, the digestive bionic device is not controlled.

[0080] It should be noted that the support vector regression model is a machine learning algorithm model for predicting the numerical value of continuous target variables. The support vector regression model is based on the support vector machine algorithm, which finds the best hyperplane in the feature space to fit the data, thereby realizing the prediction of the predicted working data of the human body digestion bionic device in the preset future time.

[0081] Further, in a preferred embodiment of the present application, the real-time working data of each digestion module is processed based on the hierarchical clustering algorithm and the genetic algorithm to obtain the 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, the two data points with the largest cosine similarity are merged into a population, and a plurality of populations are obtained;

[0083] S204: Define a fitness function, calculate the fitness of each population based on the fitness function, and compare the fitness of each population with the 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 removed;

[0085] S208: Obtain the real-time working data in the population corresponding to each fitness greater than the preset fitness, and regard the real-time working data in the population corresponding to each fitness greater than the preset fitness as a separate 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 in each population is obtained, and the effective real-time working data of each digestion module is obtained.

[0087] Wherein, the fitness function is defined by relevant technical personnel in combination with problem relevance, monotonicity, comparability and other indicators.

[0088] It should be noted that in the result of hierarchical clustering, noise data can be identified according to the shape and characteristics of the clustering tree. Generally, noise data is distributed in the lower layer of the clustering tree and is far away from other data points. The hierarchical clustering algorithm is used to preliminarily cluster the data, so as to preliminarily cluster the effective data and invalid data (noise data). However, since the hierarchical clustering algorithm is sensitive to noise and outliers, especially in the agglomerative hierarchical clustering, outliers may have a great influence on the clustering result, thereby leading to clustering errors, such as clustering effective data into invalid data, or clustering invalid data into effective data. Therefore, the genetic algorithm is needed to further evaluate and correct the clustering effect. The genetic algorithm is a global optimization algorithm, which can search globally in the solution space by simulating natural selection and genetic process, thereby avoiding falling into local optimal solution, which helps to find better clustering results. Therefore, the hierarchical clustering result is optimized by using the genetic algorithm, which can improve the clustering quality and the accuracy of noise data screening, thereby obtaining more meaningful data representation and analysis results.

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

[0090] Further, in a preferred embodiment of the present application, 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] A time stamp is constructed, and the predicted working data of each digestion module within a preset future time and the corresponding preset working data are sorted based on time sequence based on the time stamp;

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

[0093] The overlap degree between the predicted working data curve and the preset working data curve is calculated in the two-dimensional coordinate system based on the Euclidean distance algorithm, and the overlap degree between the predicted working data and the corresponding preset working data of the corresponding digestion module within a preset future time is obtained;

[0094] The above steps are repeated until the overlap degree between the predicted working data and the corresponding preset working data of each digestion module within a preset future time is calculated; and the overlap degree between the predicted working data and the corresponding preset working data of each digestion module within a preset future time is compared with a preset overlap degree.

[0095] If the overlap degree 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 degree, the digestion module is marked as a module that needs to be regulated; if the overlap degree between the predicted working data of a certain digestion module in the preset future time and the corresponding preset working data is greater than the preset overlap degree, 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 digestion bionic device, a first analysis result is generated; if there is no module that needs to be regulated in the digestion bionic device, a second analysis result is generated.

[0097] It should be noted that the principle of calculating the overlap degree between two curves by the Euclidean distance algorithm is as follows: first, define the point sets on the two curves, then calculate the Euclidean distance (i.e. the straight line distance between two points) between the two sets of point pairs, then sum all the distances between the point pairs and divide by the number of point pairs to obtain the average distance between the two curves. Finally, normalize the average distance with the total length of the curve to obtain an overlap degree value between 0 (completely not overlapping) and 1 (completely overlapping), which measures the similarity of the two curves.

[0098] If the overlap degree 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 degree, 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 that needs to be regulated. The working data includes temperature, humidity, pressure, etc.

[0099] Further, in a preferred embodiment of the present application, if the first analysis result is generated, an optimal regulation scheme is generated, and the digestion bionic device is regulated based on the optimal regulation scheme, specifically:

[0100] Obtain the running log information of the digestion bionic device, and retrieve the historical regulation schemes corresponding to various abnormal running conditions of each digestion module of the digestion bionic device in the running log information, and obtain the historical regulation accuracy corresponding to each historical regulation scheme;

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

[0102] The optimal control scheme corresponding to each abnormal operating condition of each digestion module is bundled with historical working data before the abnormal operating condition occurs to obtain a plurality of data packets; a database is constructed, and the plurality of data packets are imported into the database to obtain a characteristic database;

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

[0104] The hash value between the real-time working data of the module to be controlled at the preset time node and the historical working data in the extracted data packet is calculated by using the perceptual hashing algorithm to obtain a plurality of hash values;

[0105] Among them, the perceptual hashing algorithm first converts two data sets into perceptual hash values (such as pHash values), which can capture the main content and structure information in the data set, then calculates the Hamming distance (i.e. the number of different bits) between the two perceptual hash values, the smaller the Hamming distance, the more similar the two data sets in visual content; finally, the Hamming distance is normalized to a similarity score between 0 and 1, which measures the similarity of 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 digestion bionic device based on the optimal control scheme.

[0107] It should be noted that the operation log information of the digestion bionic device refers to the detailed data and description of the device working state, performance parameters, operation history, fault diagnosis, maintenance activities and the like recorded automatically by the system during device operation. These information helps to analyze the operation of the device, optimize the operation process, predict and handle potential problems, thereby improving the operation efficiency and reliability of the device.

[0108] In summary, the present application uses artificial intelligence algorithm to automatically adjust the working state of each module according to the collected data and the preset digestion model, to ensure that the working parameters of each digestion module always meet the preset requirements, to achieve the best digestion simulation effect, and to ensure that the simulation system is closer to the anatomical structure of the real human digestive tract under the premise of ensuring feasibility, thereby improving the credibility and realism of the simulation.

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

[0110] acquiring real-time working data of the module to be regulated at a set time node after regulating the module to be regulated of the digestion bionic device through the optimal regulation scheme, and calculating similarity between the real-time working data and the predicted working data;

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

[0113] An association degree between the state transition type and a bionic test result is analyzed based on a grey correlation analysis method, and if the association degree is greater than a preset association degree, the digestion 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 digestion bionic device is regulated through the optimal regulation scheme, if the real-time working data of the module to be regulated is still abnormal, whether the module has an abnormal running condition is determined through the Markov chain, that is, if the state transition probability is greater than the preset probability, it is indicated that the module to be regulated has a normal working state transition to an abnormal working state, if greater, the state transition type of the module to be regulated is acquired, and if the association degree between the state transition type and the bionic test result is greater than the preset association degree, it is indicated that the abnormal running of the module has affected the reliability and accuracy of the test result, and at this time, the digestion bionic device is controlled to stop the test, and the test is marked as an invalid test.

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

[0116] A preset temperature corresponding to each digestion module in the prefabricated digestion bionic device at each test stage is acquired, a preset temperature distribution map is constructed according to the preset temperature, and a preset temperature distribution map corresponding to each test stage of the digestion bionic device is obtained;

[0117] A knowledge graph is constructed, and the preset temperature distribution map corresponding to each test stage of the digestion bionic device is imported into the knowledge graph;

[0118] A real-time test stage of the digestion bionic device in a test process is acquired, and a preset temperature distribution map of the digestion bionic device at a current time node is obtained according to the real-time test stage;

[0119] Actual temperature information of each digestion module in the digestion bionic device is acquired, and an actual temperature distribution map of the digestion bionic device at the current time node is constructed according to the actual temperature information.

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

[0121] If the Pearson correlation coefficient is greater than a preset coefficient value, it indicates 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 indicates that the temperature state of the digestive bionic device at the current time node is abnormal, and at this time, the actual temperature distribution map and the preset temperature distribution map of the digestive bionic device at the current time node are processed for feature extraction based on the ORB algorithm, to obtain an actual isotherm map and a preset isotherm map.

[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] Marking a line segment area where the actual isotherm map and the preset isotherm map coincide as a temperature normal area, and marking a line segment area where the actual isotherm map and the preset isotherm map coincide as a temperature abnormal area.

[0125] It should be noted that the Pearson correlation coefficient is a statistical method for measuring the strength and direction of linear relationship between two variables. In the context 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 position. By calculating the Pearson correlation coefficient of the two sets of temperature data points, the strength and direction of the linear relationship between the two temperature distribution maps are quantified. A value close to 1 indicates strong positive correlation and high similarity, a value close to -1 indicates strong negative correlation and low similarity, and a value close to 0 indicates no significant linear relationship and large difference.

[0126] Wherein, the ORB (Oriented FAST and Rotated BRIEF) algorithm is a commonly used feature extraction and matching method in computer vision and image processing. The ORB algorithm extracts feature points by quickly detecting corner points in the temperature distribution map (using the FAST key point detector), calculating the gradient direction of these corner points (to ensure rotation invariance), and generating rotation-invariant BRIEF descriptors. Then these feature points are used for the construction of isotherm map, so as to realize the extraction of isotherm map from temperature distribution map.

[0127] Through the method, whether the temperature of each digestion module of the digestion bionic device is normal during the test can be quickly judged, and an abnormal temperature area can be analyzed, so that the abnormal temperature area is quickly regulated to ensure the reliability of the test result. The above is based on the ideal embodiment of the application, which is more specific and detailed, but cannot be understood as limiting the scope of the application patent. It should be pointed out that for ordinary skilled persons in the art, without departing from the concept of the application, a number of modifications and improvements can be made, which belong to the protection scope of the application. Therefore, the protection scope of the application patent should be subject to the appended claims.

Claims

1. A fully automatic intelligent modular human body digestion bionic device, characterized in that, The oral cavity digestion module, the stomach digestion module, the large intestine digestion module, the small intestine digestion module, the digestive juice supply module, the power supply module and the intelligent control module are connected in series. The oral cavity digestion module comprises a mechanical arm, artificial teeth, an oral cavity monitoring sensor mounting module, a switch, a movable joint, a saliva inlet, an oral cavity heating module, an artificial tongue and a lip protector. The stomach digestion module is connected with the oral cavity digestion module, and comprises a gastric juice inlet, a gastric peristaltic pump, a gastric wall, a gastric heating module, a gastric monitoring sensor mounting module and a gastric sample sampling port. The small intestine digestion module is connected with the stomach digestion module, and comprises a small intestine juice inlet, a small intestine monitoring sensor mounting module, a small intestine peristaltic pump, a small intestine wall, a small intestine heating module and a small intestine sample sampling port. The large intestine digestion module is connected with the small intestine digestion module, and comprises a large intestine juice inlet, a large intestine peristaltic pump, a large intestine wall, a large intestine monitoring sensor mounting module, a large intestine heating module and a large intestine sample sampling port.

2. The full-automatic intelligent modular human body digestion bionic device according to claim 1, characterized in that: The gastric heating module, the small intestine heating module and the large intestine heating module are water bath mechanisms.

3. The full-automatic intelligent modular human body digestion bionic device according to claim 1, characterized in that: The digestive juice supply module comprises a saliva supply module, a gastric juice supply module, a small intestine juice supply module and a large intestine juice supply module.

4. The full-automatic intelligent modular human body digestion bionic device according to claim 3, characterized in that: The saliva supply module is connected with the saliva inlet through a saliva delivery pipe.

5. The fully automatic intelligent modular human body digestion bionic device according to claim 1, characterized in that: The saliva delivery pipe, the gastric juice delivery pipe, the small intestine juice delivery pipe and the large intestine juice delivery pipe are provided with liquid pumps.

6. The fully automatic intelligent modular human body digestion bionic device according to claim 1, characterized in that: The intelligent control module is in communication connection with the monitoring sensors in each digestion module.

7. A control method of a full-automatic intelligent modular human body digestion bionic device, applied to the full-automatic intelligent modular human body digestion bionic device of any one of claims 1-6, characterized in that, Each monitoring sensor mounting module is used for mounting each type of monitoring sensor, and the monitoring sensor comprises a temperature sensor, a pH sensor, a pressure sensor and a humidity sensor. The method comprises the following steps: Obtaining running log information of the digestion bionic device, obtaining historical working data of the digestion bionic device according to the running log information, and performing feature engineering processing on the historical working data to obtain feature engineering data. A support vector regression model is constructed, and the feature engineering data is imported into the support vector regression model for training to obtain a trained support vector regression model; When the digestion bionic device is in the simulation process, the real-time working data of each digestion module of the digestion bionic device is acquired by each sensor at a preset time node, and 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; The effective real-time working data of each digestion module is imported into the trained support vector regression model for prediction to obtain predicted working data of each digestion module within a preset future time; The preset working data of each digestion module within the preset future time period is acquired, the predicted working data of each digestion module within the preset future time is compared and analyzed with the corresponding preset working data, and an analysis result is generated; If it is the first analysis result, an optimal regulation and control scheme is generated, and the digestion bionic device is regulated and controlled based on the optimal regulation and control scheme; If it is the second analysis result, the digestion bionic device is not regulated and controlled.

8. The control method of a full-automatic intelligent modular human body digestion bionic device according to claim 7, characterized in that, 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 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 maximum cosine similarity are combined into a population to obtain a plurality of populations; S204: An adaptability function is defined, and the adaptability of each population is calculated based on the adaptability function, and the adaptability of each population is compared with a preset adaptability; S206: If the adaptability of a certain population is not greater than the preset adaptability, the population is defined as a noise data population, and the noise data population is completely removed; S208: The real-time working data in the population corresponding to the adaptability greater than the preset adaptability is acquired, and the real-time working data in the population corresponding to the adaptability greater than the preset adaptability is regarded as a separate data point, and the steps of S202 to S206 are repeated; S210: Until the adaptabilities of all populations are greater than the preset adaptability, the real-time working data in each population is acquired to obtain the effective real-time working data of each digestion module.

9. The control method of a full-automatic intelligent modular human body digestion bionic device according to claim 7, characterized in that, The predicted working data of each digestion module within the preset future time is compared and analyzed with the corresponding preset working data to generate an analysis result, specifically as follows: A timestamp is constructed, and the predicted working data of each digestion module within the preset future time and the corresponding preset working data are sorted based on time sequence based on the timestamp; After sorting, a two-dimensional coordinate system is constructed, and the predicted working data curve and the preset working data curve based on time sequence are constructed in the two-dimensional coordinate system based on the predicted working data of each digestion module within the preset future time and the corresponding preset working data; calculating, based on a Euclidean distance algorithm, an overlap degree between the predicted working data curve and a preset working data curve in the two-dimensional coordinate system, to obtain an overlap degree between predicted working data of a corresponding digestion module in a preset future time and corresponding preset working data; repeating the above steps until the overlap degree between predicted working data of each digestion module in a preset future time and corresponding preset working data is calculated; comparing the overlap degree between predicted working data of each digestion module in a preset future time and corresponding preset working data with a preset overlap degree; if the overlap degree between predicted working data of a certain digestion module in a preset future time and corresponding preset working data is not greater than the preset overlap degree, marking the digestion module as a module that needs to be regulated; if the overlap degree between predicted working data of a certain digestion module in a preset future time and corresponding preset working data is greater than the preset overlap degree, marking the digestion module as a module that does not need to be regulated; if there is a module that needs to be regulated in the digestion bionic device, generating a first analysis result; if there is no module that needs to be regulated in the digestion bionic device, generating a second analysis result.

10. The control method of a full-automatic intelligent modular human body digestion bionic device according to claim 9, characterized in that, if the analysis result is the first analysis result, generating an optimal regulation scheme and regulating the digestion bionic device based on the optimal regulation scheme, specifically: obtaining operation log information of the digestion bionic device, and retrieving historical regulation schemes corresponding to various abnormal operating conditions of each digestion module of the digestion bionic device in the operation log information, and obtaining historical regulation accuracy corresponding to each historical regulation scheme; designating the historical regulation scheme corresponding to the maximum historical regulation accuracy as the optimal regulation scheme corresponding to the corresponding abnormal operating condition, to obtain optimal regulation schemes corresponding to various abnormal operating conditions of each digestion module; and obtaining historical working data of each digestion module before various abnormal operating conditions in the operation log information; binding the optimal regulation schemes corresponding to various abnormal operating conditions of each digestion module with the historical working data before various abnormal operating conditions 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, obtaining real-time working data of a module that needs to be regulated in the digestion bionic device at a preset time node, and extracting a data packet corresponding to the module that needs to be regulated, i.e., a data packet corresponding to the same digestion module as the module that needs to be regulated, from the characteristic database; calculating, by a perceptual hashing algorithm, a hash value between the real-time working data of the module that needs to be regulated at the preset time node and the historical working data in the extracted data packet to obtain a plurality of hash values; obtaining the data packet corresponding to the maximum hash value, and extracting an optimal regulation scheme for regulating the module that needs to be regulated from the data packet corresponding to the maximum hash value, and sending the optimal regulation scheme to an intelligent control module to regulate the digestion bionic device based on the optimal regulation scheme.

Images