A method and system for online detection of traditional Chinese medicine extraction

Abstract

The invention discloses an online detection method and system for traditional Chinese medicine extraction, which relates to the field of near-infrared technology of traditional Chinese medicine extracts. The method comprises the following steps: separating a quantitative traditional Chinese medicine extract from an output pipeline to form a portion to be detected, collecting environmental data of the portion to be detected, and reintegrating the portion to be detected into the output pipeline after near-infrared detection of the portion to be detected is completed; performing ultrasonic treatment on the portion to be detected to obtain an ultrasonic treatment liquid, collecting ultrasonic data of the ultrasonic treatment liquid, and generating first component data based on the ultrasonic data; using a near-infrared probe to collect spectral data of the ultrasonic treatment liquid, and generating second component data based on the spectral data; verifying the spectral data of the near-infrared inspection through the ultrasonic data and dielectric spectral data, that is, using the component concentration value and the component density value in the verification data as the component concentration value and the component density value after calibration of the near-infrared detection, so that the online detection data of the traditional Chinese medicine extract is accurate and has a small error.

Description

Technical Field

[0001] The present invention relates to the technical field of near-infrared detection of traditional Chinese medicine extracts, and in particular to an online detection method and system for traditional Chinese medicine extraction. Background Art

[0002] Near-infrared detection of Chinese herbal medicine extracts refers to the online detection of Chinese herbal medicine extracts through near-infrared light (electromagnetic waves between visible light and mid-infrared light), so that the concentration data of the components of Chinese herbal medicine extracts can be obtained in real time, ensuring the stable control of the Chinese herbal medicine extraction process;

[0003] The existing Chinese patent application with publication number CN112525834A discloses an online detection and analysis system and method for Chinese herbal medicine liquid components. The online detection system and method for Chinese herbal medicine extraction are used to use an online spectral detection device to perform component detection and analysis on the constant temperature test liquid after filtration and defoaming. However, the single online spectral detection is prone to errors, resulting in inaccurate online detection of Chinese herbal medicine extracts, thereby affecting the stable control of the Chinese herbal medicine extraction process. Summary of the Invention

[0004] In order to overcome the above technical problems, the purpose of the present invention is to provide an online detection method and system for Chinese medicine extraction, so as to solve the problem in the prior art that single online spectral detection is prone to errors, resulting in inaccurate online detection of Chinese medicine extracts.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A specific first aspect provides an online detection method for traditional Chinese medicine extraction, comprising:

[0007] S1: Separate a quantitative amount of Chinese medicine extract from the output pipeline to form a portion to be detected, collect environmental data of the portion to be detected, and reintegrate the portion to be detected into the output pipeline after near-infrared detection is completed on the portion to be detected;

[0008] S2: performing ultrasonic treatment on the portion to be detected to obtain an ultrasonic treatment liquid, collecting ultrasonic data of the ultrasonic treatment liquid, and generating first component data based on the ultrasonic data;

[0009] S3: using a near-infrared probe to collect spectral data of the ultrasonically treated liquid, and generating second component data based on the spectral data;

[0010] S4: using a dielectric spectrum probe to collect dielectric spectrum data of the ultrasonic treatment liquid, and generating third component data based on the dielectric spectrum data;

[0011] S5: cross-validating the second component data based on the first component data and the third component data to obtain validation component data;

[0012] S6: deriving the Chinese medicinal component data of the ultrasonic treatment solution based on the verified component data, and using the Chinese medicinal component data as the Chinese medicinal component data of the Chinese medicinal extract;

[0013] S7: Repeat S1 to S6 to perform near-infrared detection on the Chinese medicine extract at regular intervals.

[0014] As a further solution of the present invention: S1 comprises the following steps:

[0015] S1.1: Extracting the raw materials in an extraction tank to form a Chinese medicine extract;

[0016] S1.2: The extraction tank delivers the Chinese medicine extract to the output pipeline;

[0017] S1.3: The Chinese medicine extract in the output pipe enters the cavity to be tested through the driving mechanism, forming a portion to be tested;

[0018] S1.4: Install a temperature sensor in the cavity to be tested and collect temperature data;

[0019] S1.5: After the detection portion completes the near-infrared detection, the driving mechanism is used again to allow the Chinese medicine extract in the detection cavity to enter the output pipe.

[0020] As a further solution of the present invention: S2 comprises the following steps:

[0021] S2.1: Install an ultrasonic generator and an ultrasonic sensor outside the part to be detected;

[0022] S2.2: Based on the temperature data, an ultrasonic generator is used to perform ultrasonic treatment on the part to be tested to form an ultrasonic treatment liquid;

[0023] S2.3: The ultrasonic sensor collects ultrasonic data of the ultrasonic treatment liquid;

[0024] S2.4: Generate first component data based on the ultrasonic data.

[0025] As a further solution of the present invention: a near-infrared probe is provided outside the part to be detected. After the ultrasonic generator performs ultrasonic treatment on the part to be detected, the near-infrared probe is used to collect spectral data of the ultrasonic treatment liquid, and the second component data is generated based on the spectral data.

[0026] As a further solution of the present invention: a dielectric spectrum probe is provided outside the part to be detected. After the ultrasonic generator performs ultrasonic treatment on the part to be detected, the dielectric spectrum probe is used to collect dielectric spectrum data of the ultrasonic treatment liquid, and third component data is generated based on the dielectric spectrum data.

[0027] As a further solution of the present invention: the Chinese medicine component data includes the component concentration value and component density value of the Chinese medicine extract.

[0028] As a further solution of the present invention: S5 comprises the following steps:

[0029] S5.1: S5.1: Establish a rectangular coordinate system based on the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data, where the x-axis is the component concentration value and the y-axis is the component density value;

[0030] S5.2: Mark the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data as first coordinates, second coordinates, and third coordinates based on a rectangular coordinate system;

[0031] S5.3: Forming a triangular area of ​​collected data based on the first coordinate, the second coordinate, and the third coordinate in a rectangular coordinate system, and displaying the triangular area of ​​collected data on an interface;

[0032] S5.4: Pre-set a region area threshold, and compare the area of ​​the triangular region of the collected data with the region area threshold;

[0033] S5.5: If the area of ​​the collected data triangle is less than or equal to the area threshold, then:

[0034] ;

[0035] S5.6: If the area of ​​the collected data triangle is greater than the area threshold, then:

[0036] Calculate the center coordinates of the triangular area of ​​the collected data, eliminate the component data farthest from the center coordinates, and use the average of the other two component data as the verification component data.

[0037] As a further solution of the present invention: the component concentration value and component density value in the verification component data are used as detection data of the traditional Chinese medicine extract, and the component concentration value and component density value in the verification component data are marked as detection coordinates based on a rectangular coordinate system.

[0038] As a further solution of the present invention: the triangular area of ​​the collected data and the detection coordinates are interfaced and displayed together based on a rectangular coordinate system.

[0039] A second aspect specifically provides an online detection system for traditional Chinese medicine extraction, characterized by comprising:

[0040] The lower computer is used to implement the above-mentioned detection method, obtain the Chinese medicine component data, and convert the Chinese medicine component data into digital signals;

[0041] The upper computer obtains the digital signal from the lower computer through the wireless network and displays the digital signal on the interface.

[0042] Beneficial effects of the present invention:

[0043] In the present invention, the Chinese medicine extract in the detection cavity 3 is ultrasonically treated by an ultrasonic generator to homogenize the Chinese medicine extract in the detection cavity 3. On the one hand, ultrasonic data can be collected by an ultrasonic sensor, and on the other hand, the accuracy of spectral data collected by the near-infrared probe can be improved. Then, spectral data and dielectric spectrum data are collected by the near-infrared probe and the dielectric spectrum probe. The first component data, second component data and third component data of the Chinese medicine extract are generated according to the ultrasonic data, spectral data and dielectric spectrum data respectively. The first component data and the third component data cross-validate the second component data to obtain verification component data. The Chinese medicine component data of the ultrasonically treated liquid is obtained based on the verification component data. The Chinese medicine component data is used as the Chinese medicine component data of the Chinese medicine extract, that is, the component concentration value and component density value in the verification data are used as the component concentration value and component density value after calibration of the near-infrared detection, so that the online detection data of the Chinese medicine extract is accurate and the error is small.

[0044] In the present invention, the collected data triangular area and the detection coordinates are displayed together in an interface based on a rectangular coordinate system, which is convenient for intuitively distinguishing the accuracy of the online near-infrared detection data. For example, if the area of ​​the triangular area is large and the distance between the three coordinates is also large, it means that the first component data, the second component data and the third component data collected by the three detections are all values ​​with large errors and can be rejected. If only one of the coordinates is far away from the other two coordinates, it means that the component data corresponding to this coordinate is large and can be rejected during collection. Then, the component data corresponding to the other two coordinates are used to calibrate the component data of the traditional Chinese medicine extract to ensure the accuracy of the component data collection of the traditional Chinese medicine extract. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention will be further described below with reference to the accompanying drawings.

[0046] Figure 1 This is a flow chart of an online detection method for traditional Chinese medicine extraction according to the present invention;

[0047] Figure 2 This is a flow chart of an online detection system for traditional Chinese medicine extraction according to the present invention;

[0048] Figure 3 It is a structural schematic diagram of a chamber to be detected in an online detection method for traditional Chinese medicine extraction according to the present invention.

[0049] Explanation of the accompanying symbols: 1. Extraction tank; 2. Output pipe; 3. Chamber to be tested; 4. Driving mechanism. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0051] As an embodiment of the present invention, Figure 1-Figure 3 As shown, a method for online detection of traditional Chinese medicine extraction is disclosed, comprising:

[0052] S1: Separate a quantitative amount of Chinese medicine extract from the output pipe to form a portion to be detected, collect environmental data of the portion to be detected, and reintegrate the portion to be detected into the output pipe 2 after near-infrared detection is completed. Specifically:

[0053] In the first step, the Chinese medicine extract is prepared in the extraction tank 1. The specific extraction method of the Chinese medicine in the extraction tank 1 is adaptively selected by those skilled in the art according to the type of the specific Chinese medicine, so as to ensure that the Chinese medicine components can be extracted from the raw materials. When the raw materials are extracted in the extraction tank 1, a Chinese medicine extract is formed. The bottom end of the extraction tank 1 is sealed and connected to an output pipe 2.

[0054] In the second step, when the extraction operation of the raw materials in the extraction tank 1 is completed, the automatic valve (solenoid valve or other automatically controlled valve) provided between the extraction tank 1 and the output pipe 2 can be opened to ensure that the Chinese medicine extract in the extraction tank 1 can enter the output pipe 2 through the automatic valve;

[0055] In the third step, a chamber to be detected 3 and a driving mechanism 4 are set in the middle position of the side of the output pipe 2, wherein the chamber to be detected 3 is directly connected to the inside of the output pipe 2, and the driving mechanism 4 is set at the top of the chamber to be detected 3. The driving mechanism 4 includes a fixed frame and a hydraulic push rod (the hydraulic push rod can also be replaced by an electric push rod, a pneumatic push rod or other mechanisms that can provide reciprocating driving force). The fixed frame is fixed to the top of the chamber to be detected 3 by bolts, and the hydraulic push rod is fixed to the middle position of the top surface of the fixed frame by bolts. The hydraulic push rod includes a hydraulic cylinder and a hydraulic rod. The output end of the hydraulic rod is connected to a piston, which fits in the chamber to be detected 3 and It can slide freely in the vertical direction in the chamber to be detected 3. When the hydraulic cylinder is opened, the hydraulic cylinder can drive the piston through the hydraulic rod to move the piston upward in the chamber to be detected 3. When the piston moves upward in the chamber to be detected 3, the space in the chamber to be detected 3 will increase, so the chamber to be detected 3 can absorb the Chinese medicine extract in the output pipe 2 and enter the chamber to be detected 3. Since the angle between the chamber to be detected 3 and the output pipe 2 is in a vertical state, the Chinese medicine extract inside the chamber to be detected 3 will be stable and will not flow with the flow of the Chinese medicine extract in the output pipe 2, thereby ensuring the stability and accuracy of the Chinese medicine extract data collection;

[0056] The fourth step is to set a temperature sensor in the chamber to be tested 3. The temperature sensor is set on the inner wall of the chamber to be tested 3 to collect temperature data of the Chinese medicine extract in the chamber to be tested 3, that is, the temperature value of the Chinese medicine extract. The location and number of the temperature sensors are adaptively selected by those skilled in the art according to the space size inside the chamber to be tested 3.

[0057] In the fifth step, when the detection of the Chinese medicine extract in the chamber to be detected 3 is completed, the hydraulic cylinder will be opened again. The hydraulic cylinder pushes the piston through the hydraulic rod, causing the piston to move downward in the chamber to be detected 3, and the Chinese medicine extract in the chamber to be detected 3 is discharged into the output pipe 2, so that the chamber to be detected 3 can repeatedly absorb the Chinese medicine extract, and will not cause waste of the Chinese medicine extract during detection.

[0058] S2: Performing ultrasonic treatment on the part to be detected to obtain ultrasonic treatment liquid, collecting ultrasonic data of the ultrasonic treatment liquid, and generating first component data based on the ultrasonic data, specifically:

[0059] The first step is to set an ultrasonic generator and an ultrasonic sensor outside the part to be detected. It should be noted that the ultrasonic generator is used to ultrasonically treat the Chinese medicine extract in the detection cavity 3. The type and power of the ultrasonic generator are adaptively selected by those skilled in the art according to the volume of the extraction tank 1 and the type of Chinese medicine extract in the extraction tank 1;

[0060] In the second step, based on the temperature data, an ultrasonic generator is used to perform ultrasonic treatment on the part to be detected to form an ultrasonic treatment liquid. It should be noted that the temperature data refers to the temperature value of the traditional Chinese medicine extract, which is collected by a temperature sensor set in the cavity 3 to be detected. When the ultrasonic wave (20-100kHz) emitted by the ultrasonic generator propagates in the traditional Chinese medicine extract, it will produce periodic pressure changes and form tiny bubbles (cavitation bubbles). The liquid molecules in the traditional Chinese medicine extract will move at high speed under the action of the ultrasonic wave, thereby enhancing the penetration and mass transfer of the traditional Chinese medicine extract and achieving homogenization of the traditional Chinese medicine extract. Since the volume of the cavity 3 to be detected is small and the amount of the traditional Chinese medicine extract inside it is also limited, the ultrasonic generator can achieve homogenization of the traditional Chinese medicine extract in the cavity 3 to be detected in a short time, and the processing time can be arbitrarily set by those skilled in the art.

[0061] In the third step, the ultrasonic sensor collects ultrasonic data of the ultrasonic treatment liquid. When the ultrasonic generator performs ultrasonic treatment on the Chinese herbal medicine extract, the ultrasonic sensor collects ultrasonic data. The ultrasonic data includes the sound velocity (v) of the ultrasonic wave propagating in the Chinese herbal medicine extract and the attenuation coefficient (α) of the ultrasonic wave propagating in the Chinese herbal medicine extract. Specifically:

[0062] according to It can be seen that , among which is the density value of the components of the Chinese medicine extract, is the sound velocity of ultrasonic waves propagating in Chinese herbal medicine extracts, is the elastic modulus of the Chinese medicine extract, ;

[0063] Therefore, the density of the components of the Chinese herbal medicine extract can be directly calculated based on the sound velocity of the ultrasonic wave propagating in the Chinese herbal medicine extract.

[0064] according to , the viscosity value η of the Chinese medicine extract can be directly calculated, where is the attenuation coefficient of ultrasonic wave propagating in Chinese medicine extract, f is the amplitude of ultrasonic wave, is the density of the components of the Chinese herbal medicine extract, and v is the speed of sound propagating in the Chinese herbal medicine extract;

[0065] Based on the sound velocity value, attenuation coefficient, component density value, viscosity value and temperature value of the Chinese medicine extract, the concentration value of the component of the Chinese medicine extract is predicted using the concentration prediction model, specifically:

[0066] Prepare N (N≥10000) sets of training data in advance. Each set of training data contains feature data and label data. The feature data are the speed of sound, attenuation coefficient, component density, viscosity, and temperature of the Chinese medicine extract. The label data are the component concentration values ​​directly measured through experiments.

[0067] The sound velocity, attenuation coefficient, component density, viscosity, and temperature values ​​in the training data are converted into feature vectors. The feature vectors are used as inputs to the concentration prediction model. The concentration prediction model outputs the component concentration values ​​predicted for the feature data. The component concentration values ​​in the label data corresponding to each set of feature data are used as prediction targets. The concentration prediction model is trained and training is stopped when the concentration prediction model reaches convergence. The convergence criterion is that the error between the component concentration values ​​predicted by the concentration prediction model and the component concentration values ​​in the label data is ≤0.001.

[0068] In the fourth step, the calculated component density value and the component concentration value predicted by the concentration prediction model based on the component density value are used as the first component data.

[0069] S3: Using a near-infrared probe to collect spectral data of the ultrasonically treated liquid, and generating second component data based on the spectral data. Specifically, a near-infrared probe is provided outside the portion to be detected. After the ultrasonic generator ultrasonically treats the portion to be detected, the near-infrared probe is used to collect spectral data of the ultrasonically treated liquid, and the second component data is generated based on the spectral data. It should be noted that:

[0070] Prepare multiple groups of Chinese herbal medicine extracts of different concentrations in advance (the concentration gradient can be arbitrarily set by those skilled in the art according to the number of components), then use a near-infrared probe to collect spectral data (absorbance and reflectance), and then establish a mathematical relationship between the spectral data and the component concentration values ​​of the Chinese herbal medicine extracts;

[0071] Prepare N (N≥10000) sets of training data in advance. Each set of training data contains feature data and label data. The feature data are absorbance, reflectance, temperature and component concentration. The label data are component density values ​​directly measured through experiments.

[0072] The absorbance, reflectance, temperature, and component concentration values ​​in the training data are converted into feature vectors. The feature vectors are used as inputs to the concentration prediction model. The concentration prediction model outputs the component density values ​​predicted for the feature data. The component density values ​​in the label data corresponding to each set of feature data are used as prediction targets. The concentration prediction model is trained and training is stopped when the concentration prediction model reaches convergence. The convergence criterion is that the error between the component density values ​​predicted by the concentration prediction model and the component density values ​​in the label data is ≤0.001.

[0073] S4: Using a dielectric spectrum probe to collect dielectric spectrum data of the ultrasonically treated liquid, and generating third component data based on the dielectric spectrum data. The dielectric spectrum data includes dielectric constant and conductivity. Specifically, a dielectric spectrum probe is provided outside the portion to be detected. After the ultrasonic generator ultrasonically treats the portion to be detected, the dielectric spectrum probe is used to collect dielectric spectrum data of the ultrasonically treated liquid, and the third component data is generated based on the dielectric spectrum data. It should be noted that:

[0074] Before collecting dielectric spectrum data using a dielectric spectrum probe, multiple groups of Chinese herbal medicine extracts with different concentrations are prepared in advance (the concentration gradient can be arbitrarily set by a person skilled in the art based on the number of components). The dielectric spectrum probe is then used to measure the dielectric constant and conductivity of each group of Chinese herbal medicine extracts. The relationship between the component concentration values ​​of the Chinese herbal medicine extracts and the dielectric constant, conductivity, and temperature values ​​of the Chinese herbal medicine extracts is fitted based on the dielectric constant, conductivity, and temperature values ​​of the Chinese herbal medicine extracts.

[0075] The density of components of Chinese herbal medicine extracts is based on the empirical formula: ,in is the dielectric constant, and is the proportionality coefficient, which is obtained by fitting the dielectric constant and component density values ​​corresponding to multiple groups of different concentrations;

[0076] The calculated component density value and component concentration value are used as the third component data;

[0077] S5: Cross-validate the second component data based on the first component data and the third component data to obtain validation component data, specifically:

[0078] The first step is to establish a rectangular coordinate system based on the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data, with the x-axis being the component concentration value and the y-axis being the component density value;

[0079] The second step is to mark the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data as the first coordinate, the second coordinate, and the third coordinate based on the rectangular coordinate system, wherein the component concentration value in the first component data corresponds to the x-axis value of the rectangular coordinate system, the component density value in the first component data corresponds to the y-axis value of the rectangular coordinate system, the component concentration value in the second component data corresponds to the x-axis value of the rectangular coordinate system, the component density value in the second component data corresponds to the y-axis value of the rectangular coordinate system, the component concentration value in the third component data corresponds to the x-axis value of the rectangular coordinate system, and the component density value in the third component data corresponds to the y-axis value of the rectangular coordinate system;

[0080] The third step is to form a triangular area of ​​collected data based on the first coordinate, the second coordinate and the third coordinate based on the rectangular coordinate system, and display the triangular area of ​​collected data on the interface. It should be noted that the triangular area refers to the area composed of the first coordinate, the second coordinate and the third coordinate corresponding to the first component data, the second component data and the third component data. The error sizes of the three tests can be directly judged according to the shape of the triangular area. For example, if the area of ​​the triangular area is large and the distance between the three coordinates is also large, it means that the first component data, the second component data and the third component data collected by the three tests are all values ​​with large errors and can be rejected. If only one of the coordinates is far away from the other two coordinates, it means that the component data corresponding to this coordinate is large and can be rejected during collection. Then, the component data corresponding to the other two coordinates are used to calibrate the component data of the traditional Chinese medicine extract to ensure the accuracy of the component data collection of the traditional Chinese medicine extract.

[0081] The fourth step is to pre-set the area threshold and compare the area of ​​the triangular area of ​​the collected data with the area threshold;

[0082] Step 5: If the area of ​​the triangular region of the collected data is less than or equal to the area threshold, then:

[0083] ;

[0084] It should be noted that the verification component data uses the average of the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data, that is, the sum of the component concentration value in the first component data, the component concentration value in the second component data, and the component concentration value in the third component data is calculated, and then the average component concentration value of the three component concentration values ​​is obtained, and the average component concentration value is used as The calculation method of the component density value is the same as that of the component concentration value, and the average component concentration value is used as the component density value in the verification component data;

[0085] If the area of ​​the triangular region of the collected data is greater than the area threshold, then:

[0086] Calculate the center coordinates of the triangular area of ​​the collected data, eliminate the component data farthest from the center coordinates, and use the average of the other two component data as the verification component data. It should be noted that the center coordinates of the three coordinates are calculated based on the first coordinate, the second coordinate, and the third coordinate, and then the first distance, the second distance, and the third distance from the first coordinate, the second coordinate, and the third coordinate to the center coordinate are calculated respectively, and the component data corresponding to the maximum value of the first distance, the second distance, and the third distance are eliminated. Then, the average concentration value and the average density value of the other two component data are calculated respectively, and the average concentration value and the average density value are used as the component concentration value and the component density value in the verification data;

[0087] The sixth step is to obtain the Chinese medicinal component data of the ultrasonic treatment liquid based on the verification component data, and use the Chinese medicinal component data as the Chinese medicinal component data of the Chinese medicinal extract. That is, the component concentration value and component density value in the verification data are used as the component concentration value and component density value after calibration of the near-infrared detection, so that the online detection data of the Chinese medicinal extract is accurate and has a small error;

[0088] Step 7: Repeat steps 1 to 6 until the online near-infrared detection of all the Chinese medicine extracts in the extraction tank 1 is completed. The working frequency of the online near-infrared detection can be set arbitrarily by those skilled in the art to ensure that the component data of the Chinese medicine extract can be collected.

[0089] It should also be noted that the component concentration value and component density value in the verification component data are used as the detection data of the traditional Chinese medicine extract, and the component concentration value and component density value in the verification component data are marked as detection coordinates based on the rectangular coordinate system;

[0090] The collected data triangular area and the detection coordinates are displayed together in an interface based on the rectangular coordinate system, which is convenient for intuitively distinguishing the accuracy of the online near-infrared detection data. For example, if the area of ​​the triangular area is large and the distance between the three coordinates is also large, it means that the first component data, the second component data and the third component data collected by the three detections are all values ​​with large errors and can be rejected. If only one of the coordinates is far away from the other two coordinates, it means that the component data corresponding to this coordinate is large and can be rejected during collection. Then, the component data corresponding to the other two coordinates are used to calibrate the component data of the traditional Chinese medicine extract to ensure the accuracy of the component data collection of the traditional Chinese medicine extract.

[0091] As an embodiment of the present invention, Figure 1-Figure 3 As shown, a traditional Chinese medicine extraction online detection system is disclosed, comprising:

[0092] The lower computer is used to implement the above-mentioned detection method, obtain the Chinese medicine component data, and convert the Chinese medicine component data into a digital signal. Specifically, the Chinese medicine extract in the detection cavity 3 is ultrasonically processed by an ultrasonic generator to homogenize the Chinese medicine extract in the detection cavity 3. On the one hand, ultrasonic data can be collected by the ultrasonic sensor, and on the other hand, the accuracy of the spectrum data collected by the near-infrared probe can be improved. The spectrum data and dielectric spectrum data are then collected by the near-infrared probe and the dielectric spectrum probe. The first component data, second component data and third component data of the Chinese medicine extract are respectively generated according to the ultrasonic data, spectrum data and dielectric spectrum data. The generation method of the first component data, the second component data and the third component data is the same as that in the above-mentioned embodiment and will not be repeated here. The first component data and the third component data cross-verify the second component data to obtain the verification component data, specifically:

[0093] Establishing a rectangular coordinate system based on the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data, wherein the x-axis represents the component concentration value and the y-axis represents the component density value;

[0094] Sequentially marking the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data as the first coordinate, the second coordinate, and the third coordinate based on the rectangular coordinate system, wherein the component concentration value in the first component data corresponds to the x-axis value of the rectangular coordinate system, the component density value in the first component data corresponds to the y-axis value of the rectangular coordinate system, the component concentration value in the second component data corresponds to the x-axis value of the rectangular coordinate system, the component density value in the second component data corresponds to the y-axis value of the rectangular coordinate system, the component concentration value in the third component data corresponds to the x-axis value of the rectangular coordinate system, and the component density value in the third component data corresponds to the y-axis value of the rectangular coordinate system;

[0095] A triangular area of ​​collected data is formed based on the first coordinate, the second coordinate and the third coordinate based on the rectangular coordinate system, and the triangular area of ​​collected data is displayed on the interface. It should be noted that the triangular area refers to the area composed of the first coordinate, the second coordinate and the third coordinate corresponding to the first component data, the second component data and the third component data. The error sizes of the three tests can be directly judged according to the shape of the triangular area. For example, if the area of ​​the triangular area is large and the distance between the three coordinates is also large, it means that the first component data, the second component data and the third component data collected by the three tests are all values ​​with large errors and can be rejected. If only one of the coordinates is far away from the other two coordinates, it means that the component data corresponding to this coordinate is large and can be rejected during collection. Then, the component data corresponding to the other two coordinates are used to calibrate the component data of the traditional Chinese medicine extract to ensure the accuracy of the component data collection of the traditional Chinese medicine extract.

[0096] Pre-set the area threshold, and compare the area of ​​the triangular area of ​​the collected data with the area threshold;

[0097] If the area of ​​the triangular region of the collected data is less than or equal to the area threshold, then:

[0098] ;

[0099] It should be noted that the verification component data uses the average of the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data. That is, the sum of the component concentration value in the first component data, the component concentration value in the second component data, and the component concentration value in the third component data is calculated, and then the average component concentration value of the three component concentration values ​​is obtained. The average component concentration value is used as the component concentration value in the verification component data. The calculation method of the component density value is the same as that of the component concentration value, and the average component concentration value is used as the component density value in the verification component data.

[0100] If the area of ​​the triangular region of the collected data is greater than the area threshold, then:

[0101] Calculate the center coordinates of the triangular area of ​​the collected data, eliminate the component data farthest from the center coordinates, and use the average of the other two component data as the verification component data. It should be noted that the center coordinates of the three coordinates are calculated based on the first coordinate, the second coordinate, and the third coordinate, and then the first distance, the second distance, and the third distance from the first coordinate, the second coordinate, and the third coordinate to the center coordinate are calculated respectively, and the component data corresponding to the maximum value of the first distance, the second distance, and the third distance are eliminated. Then, the average concentration value and the average density value of the other two component data are calculated respectively, and the average concentration value and the average density value are used as the component concentration value and the component density value in the verification data;

[0102] Based on the verification component data, the Chinese medicine component data of the ultrasonic treatment liquid is obtained, and the Chinese medicine component data is used as the Chinese medicine component data of the Chinese medicine extract. That is, the component concentration value and component density value in the verification data are used as the component concentration value and component density value after calibration of the near-infrared detection, so that the online detection data of the Chinese medicine extract is accurate and the error is small;

[0103] Repeat the above process until the online near-infrared detection of all the Chinese medicine extracts in the extraction tank 1 is completed. The working frequency of the online near-infrared detection can be set arbitrarily by those skilled in the art to ensure that the component data of the Chinese medicine extract can be collected;

[0104] Verify that the component concentration value and the component density value in the component data are used as the detection data of the traditional Chinese medicine extract, and mark the component concentration value and the component density value in the component data as detection coordinates based on a rectangular coordinate system;

[0105] The collected data triangular area and the detection coordinates are displayed together in an interface based on a rectangular coordinate system. Specifically, the collected data triangular area and the detection coordinates are converted into digital signals and transmitted to the host computer. The host computer displays the collected data triangular area and the detection coordinates together in an interface based on a rectangular coordinate system, so as to intuitively distinguish the accuracy of the online near-infrared detection data. For example, if the area of ​​the triangular area is large and the distance between the three coordinates is also large, it means that the first component data, the second component data and the third component data collected by the three detections are all values ​​with large errors and can be ignored. If only one of the coordinates is far away from the other two coordinates, it means that the component data corresponding to this coordinate is large and can be ignored during collection. Then, the component data corresponding to the other two coordinates are used to calibrate the component data of the traditional Chinese medicine extract to ensure the accuracy of the component data collection of the traditional Chinese medicine extract.

[0106] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for online detection of traditional Chinese medicine extraction, characterized in that: include: S1: Separate a quantitative amount of Chinese medicine extract from the output pipe to form a portion to be detected, collect environmental data of the portion to be detected, and after the portion to be detected completes near-infrared detection, reintegrate the portion to be detected into the output pipe (2); S2: performing ultrasonic treatment on the portion to be detected to obtain an ultrasonic treatment liquid, collecting ultrasonic data of the ultrasonic treatment liquid, and generating first component data based on the ultrasonic data; S3: using a near-infrared probe to collect spectral data of the ultrasonically treated liquid, and generating second component data based on the spectral data; S4: using a dielectric spectrum probe to collect dielectric spectrum data of the ultrasonic treatment liquid, and generating third component data based on the dielectric spectrum data; S5: cross-validating the second component data based on the first component data and the third component data to obtain validation component data; S6: deriving the Chinese medicinal component data of the ultrasonic treatment solution based on the verified component data, and using the Chinese medicinal component data as the Chinese medicinal component data of the Chinese medicinal extract; S7: Repeat S1 to S6 to perform near-infrared detection on the Chinese medicine extract at regular intervals; The Chinese medicine component data includes the component concentration value and component density value of the Chinese medicine extract; The S5 comprises the following steps: S5.1: Establish a rectangular coordinate system based on the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data, where the x-axis represents the component concentration value and the y-axis represents the component density value; S5.2: Mark the component concentration values ​​and component density values ​​in the first component data, the second component data, and the third component data as first coordinates, second coordinates, and third coordinates based on a rectangular coordinate system; S5.3: Forming a triangular area of ​​collected data based on the first coordinate, the second coordinate, and the third coordinate in a rectangular coordinate system, and displaying the triangular area of ​​collected data on an interface; S5.4: Pre-set a region area threshold, and compare the area of ​​the triangular region of the collected data with the region area threshold; S5.5: If the area of ​​the collected data triangle is less than or equal to the area threshold, then: S5.6: If the area of ​​the collected data triangle is greater than the area threshold, then: Calculate the center coordinates of the triangular area of ​​the collected data, eliminate the component data farthest from the center coordinates, and use the average of the other two component data as the verification component data.

2. A method for online detection of traditional Chinese medicine extraction according to claim 1, characterized in that, Said S1 comprises the following steps: S1.1: extracting the raw material in an extraction tank (1) to form a Chinese medicine extract; S1.2: The extraction tank (1) delivers the Chinese medicine extract to the output pipe (2); S1.3: The Chinese medicine extract in the output pipe (2) is caused to enter the chamber to be detected (3) through the driving mechanism (4), thereby forming a portion to be detected; S1.4: Install a temperature sensor in the chamber to be tested (3) to collect temperature data; S1.5: After the detection section completes the near-infrared detection, the driving mechanism (4) is used again to allow the Chinese medicine extract in the detection chamber (3) to enter the output pipe (2).

3. A method for online detection of traditional Chinese medicine extraction according to claim 2, characterized in that, The S2 comprises the following steps: S2.1: Install an ultrasonic generator and an ultrasonic sensor outside the part to be detected; S2.2: Based on the temperature data, an ultrasonic generator is used to perform ultrasonic treatment on the part to be inspected to form an ultrasonic treatment liquid; S2.3: The ultrasonic sensor collects ultrasonic data of the ultrasonic treatment liquid; S2.4: Generate first component data based on the ultrasonic data.

4. A method for online detection of traditional Chinese medicine extraction according to claim 3, characterized in that, A near-infrared probe is provided outside the part to be detected. After the ultrasonic generator performs ultrasonic treatment on the part to be detected, the near-infrared probe is used to collect spectral data of the ultrasonic treatment liquid, and second component data is generated based on the spectral data.

5. A method for online detection of traditional Chinese medicine extraction according to claim 3, characterized in that, A dielectric spectrum probe is provided outside the part to be detected. After the ultrasonic generator performs ultrasonic treatment on the part to be detected, the dielectric spectrum probe is used to collect dielectric spectrum data of the ultrasonic treatment liquid, and the third component data is generated based on the dielectric spectrum data.

6. A method for online detection of traditional Chinese medicine extraction according to claim 1, characterized in that, The component concentration values ​​and component density values ​​in the verification component data are used as detection data of the traditional Chinese medicine extract, and the component concentration values ​​and component density values ​​in the verification component data are marked as detection coordinates based on a rectangular coordinate system.

7. A method for online detection of traditional Chinese medicine extraction according to claim 6, characterized in that: The collected data triangular area and the detection coordinates are interfaced and displayed together based on a rectangular coordinate system.

8. A Chinese medicine extraction online detection system, characterized in that: include: A lower computer, which is used to implement the detection method according to any one of claims 1 to 7, obtain the Chinese medicine component data, and convert the Chinese medicine component data into a digital signal; The upper computer obtains the digital signal from the lower computer through the wireless network and displays the digital signal on the interface.

Images