Batch assembly line traditional Chinese medicinal material detection device, method and equipment and storage medium

Abstract

The invention provides a batch assembly line traditional Chinese medicinal material detection device, method and equipment and a storage medium, and belongs to the technical field of data processing and intelligent detection. Comprising a main control unit which is respectively connected with a conveying belt system and a laser-induced breakdown spectroscopy automatic focusing detection system, the conveyor belt system carries and transports to-be-detected traditional Chinese medicinal material samples; the depth camera collects three-dimensional image information of a to-be-detected traditional Chinese medicinal material sample and transmits the complete three-dimensional image information of the to-be-detected traditional Chinese medicinal material sample to the main control unit; after receiving the complete three-dimensional image information, the main control unit controls the conveying belt system to stop running; the three-axis displacement platform controls the laser-induced breakdown spectroscopy automatic focusing detection system to move to each detection point according to the detection task parameters to obtain spectral data of the traditional Chinese medicinal materials; wherein the detection task parameters are determined based on the three-dimensional image information; and the main control unit analyzes the spectral data of the traditional Chinese medicinal materials and determines qualified information of the to-be-detected traditional Chinese medicinal material sample.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a batch assembly line Chinese medicinal material detection device, method, equipment and storage medium. Background Art

[0002] With the rapid development of the Traditional Chinese Medicine (TCM) industry, demand for TCMs in pharmaceuticals, healthcare products, and other fields continues to grow, and market demands for their quality control are becoming increasingly stringent. To ensure the safety and efficacy of TCMs, rigorous testing of their composition and quality is essential. However, traditional testing methods often require significant manpower and resources, are time-consuming, and are unable to meet the needs of large-scale batch testing. This inefficient testing method is particularly insufficient given the current growing market demand.

[0003] Therefore, how to conduct more efficient testing of Chinese medicinal materials has become an urgent problem to be solved in the industry. Summary of the Invention

[0004] The present invention provides a batch production line Chinese medicinal material detection device, method, equipment and storage medium, which are used to solve the problem of how to more efficiently detect Chinese medicinal materials in the prior art.

[0005] The present invention provides a batch production line Chinese medicinal material detection device. The system comprises: a conveyor belt system, a laser-induced breakdown spectroscopy autofocus detection system, a main control unit, a depth camera fixed to a fixed frame, and a three-axis displacement platform; the laser-induced breakdown spectroscopy autofocus detection system is connected to the three-axis displacement platform; the main control unit is respectively connected to the conveyor belt system, the laser-induced breakdown spectroscopy autofocus detection system, the depth camera, and the three-axis displacement platform; Wherein, the conveyor belt system carries and transports the Chinese medicinal material samples to be tested; The depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be detected, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be detected to the main control unit; After receiving the complete three-dimensional image information, the main control unit controls the conveyor belt system to stop running; wherein the three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; wherein the detection task parameters are determined based on the three-dimensional image information; The main control unit analyzes the spectrum data of the Chinese medicinal materials to determine the qualification information of the Chinese medicinal materials sample to be tested.

[0006] According to the batch assembly line Chinese medicinal material detection device provided by the present invention, the conveyor belt system includes: a conveyor belt drive module, a conveyor belt stepper motor, a conveyor belt driving wheel, a conveyor belt driven wheel, and a conveyor belt; Wherein, the conveyor belt drive module is in communication connection with the main control unit and is used to control the operation of the conveyor belt stepper motor; The conveyor belt stepping motor is used to drive the conveyor belt driving wheel, and the conveyor belt driving wheel is used to drive the conveyor belt driven wheel to rotate through the conveyor belt; Wherein, the conveyor belt is used to carry the Chinese medicinal material samples to be tested.

[0007] According to the batch assembly line Chinese medicinal material detection device provided by the present invention, the three-axis displacement platform includes: a three-axis displacement platform control module, an X-axis slider, an X-axis guide rail, an X-axis stepping servo motor, a Z-axis stepping servo motor, a Z-axis guide rail, a Z-axis slider, a Y-axis transmission shaft, a Y-axis stepping servo motor, a left Y-axis slider, a left Y-axis guide rail, a right Y-axis slider, and a right Y-axis guide rail; Among them, the three-axis displacement platform control module controls the operation of the X-axis stepper servo motor, the Z-axis stepper servo motor, and the Y-axis stepper servo motor according to the detection task parameters, and then controls the movement of the X-axis slider, the Y-axis slider, and the Z-axis slider to achieve position control of the laser induced breakdown spectroscopy autofocus detection system; Among them, the X-axis slider and the X-axis guide rail realize the movement of the laser induced breakdown spectroscopy automatic focus detection system on the X-axis, the Z-axis guide rail and the Z-axis slider realize the movement of the laser induced breakdown spectroscopy automatic focus detection system on the Z-axis, and the left Y-axis slider, the left Y-axis guide rail, the Y-axis transmission shaft, the right Y-axis slider and the right Y-axis guide rail work together to realize the movement of the laser induced breakdown spectroscopy automatic focus detection system on the Y-axis.

[0008] According to the batch assembly line Chinese medicinal material detection device provided by the present invention, the laser-induced breakdown spectroscopy autofocus detection system includes: a linear motor, a laser, a spectral signal acquisition optical path system, a laser ranging sensor, a laser focusing optical path system, a spectrometer, a linear motor guide rail, a linear motor slider, a linear motor driver and a main control board, wherein the laser, the spectral signal acquisition optical path system, the laser ranging sensor and the laser focusing optical path system are mounted on the linear motor slider; The main control board controls the operation of the linear motor driver according to the detection task parameters sent by the main control unit, and the linear motor driver is used to control the start, stop and movement of the linear motor; The linear motor is used to control the linear motor slider to slide on the linear motor guide rail to control the laser, the spectrum signal collection optical path system, the laser ranging sensor and the laser focusing optical path system to achieve an automatic focusing function.

[0009] According to the batch production line Chinese medicinal material detection device provided by the present invention, the laser is used to generate a high-energy laser beam, and the laser focusing optical path system focuses the laser beam generated by the laser so that the laser beam is focused on the detection point on the surface of the Chinese medicinal material sample to be detected; The spectral signal collection optical path system is used to collect the optical signal generated by the laser beam excitation and transmit the optical signal to the spectrometer; The spectrometer is used to perform spectroscopic processing on the optical signal and convert the optical signal into spectral data.

[0010] According to the batch production line Chinese medicinal material detection device provided by the present invention, the laser rangefinder detects the distance information between the Chinese medicinal material sample to be detected and the laser focus point of the laser emitted by the laser, and transmits the distance information to the main control board; The main control board generates distance adjustment feedback information according to the distance information, and transmits the distance adjustment feedback information to the linear motor driver to ensure that the laser beam is focused on the detection point position on the surface of the Chinese medicinal material sample to be detected.

[0011] The present invention also provides a batch assembly line Chinese medicinal material detection method based on the batch assembly line Chinese medicinal material detection device, comprising: When the conveyor belt system transports the Chinese medicinal material sample to be tested, the depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be tested, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be tested to the main control unit; When the main control unit receives the complete three-dimensional image information, it generates detection task parameters based on the complete three-dimensional image information and sends the detection task parameters to the three-axis displacement platform; wherein the detection task parameters include: the spatial position of the detection point and the detection order.

[0012] The three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; The main control unit analyzes the spectrum data of the Chinese medicinal materials, determines spectrum analysis results, and determines the qualification information of the Chinese medicinal materials sample to be tested according to the spectrum analysis results.

[0013] According to the batch assembly line Chinese medicinal material detection method provided by the present invention, the main control unit analyzes the Chinese medicinal material spectral data to determine the spectral analysis results, including: After performing data clipping and spectrum data smoothing on the Chinese medicinal material spectrum data, the Chinese medicinal material smoothed spectrum data is obtained; After background fitting is performed on the smoothed spectrum data of the Chinese medicinal material, spectrum background fitting data is obtained; After subtracting the spectrum background fitting data from the smoothed spectrum data of the Chinese medicinal material, the net spectrum signal data of the Chinese medicinal material is obtained; Extracting characteristic peaks from the net spectrum signal data of the Chinese medicinal materials to obtain characteristic peak information; The characteristic peak information is qualitatively analyzed and quantitatively analyzed to determine the element composition information of the Chinese herbal medicine sample to be detected and the content information of each element in the Chinese herbal medicine sample to be detected; A spectrum analysis result is obtained based on the element composition information and the content information of each element.

[0014] According to the batch assembly line Chinese medicinal material detection method provided by the present invention, when the spectral analysis result meets the quality standard of the Chinese medicinal material sample to be detected, the qualified information of the Chinese medicinal material sample to be detected is determined to be qualified, and the main control unit controls the conveyor belt system to transport the next Chinese medicinal material sample to be detected; Alternatively, when the spectral analysis result does not meet the quality standard of the Chinese medicinal material sample to be tested, the qualified information of the Chinese medicinal material sample to be tested is determined to be unqualified, and the main control unit controls the conveyor belt system to remove the Chinese medicinal material sample to be tested.

[0015] According to the batch assembly line Chinese medicinal material detection method provided by the present invention, the method further includes: Performing image processing on the RGB image in the complete three-dimensional image information, extracting the contour area of ​​the Chinese medicinal material sample, and generating a regular grid structure within the contour area; Determining the number of detection points and their spatial distribution on the sample surface according to the intersection positions of the grid; Extracting three-dimensional coordinate information corresponding to each detection point based on the spatial distribution and the depth data in the depth image captured by the depth camera; According to the spatial coordinates of the detection points and the geometric features of the Chinese medicinal material samples to be detected, detection task parameters including the spatial positions of the detection points and their detection sequence are planned and generated.

[0016] According to the batch assembly line Chinese medicinal material detection method provided by the present invention, the method further includes: The spectral analysis results corresponding to each detection point are associated with their three-dimensional spatial coordinates, and the associated content is superimposed and displayed in the corresponding RGB image in an annotated manner to achieve image visualization of the detection results; at the same time, the annotated image is stored together with the corresponding three-dimensional image information.

[0017] The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the batch assembly line Chinese medicinal material detection method as described above is implemented.

[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the batch-line Chinese medicinal material detection method as described above is implemented.

[0019] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned batch pipeline Chinese medicinal material detection methods.

[0020] The batch production line Chinese medicinal material detection device, method, equipment and storage medium provided by the present invention enable the system to accurately collect three-dimensional image information of Chinese medicinal material samples, including size, shape and spatial position, through the introduction of a depth camera. This information is transmitted to the main control unit for generating accurate detection task parameters, thereby guiding the three-axis displacement platform and LIBS autofocus detection system to perform precise positioning and detection. This real-time control and adjustment capability ensures the flexibility and adaptability of the detection process and can adapt to Chinese medicinal material samples of different shapes and sizes. The three-axis displacement platform controls the LIBS autofocus detection system to move to various detection points of the sample according to the detection task parameters to collect spectral data. The main control unit analyzes the collected spectral data, determines the type and content of the elements in the sample, completes qualitative and quantitative analysis, and thus determines the qualified information of the sample. Through automation and precise control, batch, efficient and accurate quality inspection of Chinese medicinal material samples is realized, meeting the needs of modern production lines for Chinese medicinal material quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive efforts. Figure 1 This is a schematic structural diagram of a batch production line Chinese medicinal material testing device provided by the present invention; Figure 2A schematic diagram of the structure of a three-axis displacement platform provided in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a laser-induced breakdown spectroscopy autofocus detection system provided in an embodiment of the present application; Figure 4 This is a schematic diagram of the overall architecture of the batch production line Chinese medicinal material testing device provided by the present invention; Figure 5 The batch production line Chinese medicinal material detection method provided in the embodiment of this application; Figure 6 A flowchart of the rapid detection device provided in an embodiment of the present application; Figure 7 The depth camera image processing flow chart provided by the present invention; Figure 8 RGB image processing flow chart of the depth camera provided by the present invention; Figure 9 Flow chart of spectrum analysis processing provided by the present invention; Figure 10 is a flow chart of the quantitative analysis method of the present invention; Figure 11 The detection path and detection point distribution map of the licorice sample provided by the present invention; Figure 12 Spectral comparison diagram of eight detection points of the licorice sample provided by the present invention; Figure 13 It is a structural schematic diagram of the electronic device provided by the present invention.

[0022] Reference numerals: 1: Conveyor belt drive module, 2: Conveyor belt stepper motor, 3: Conveyor belt driving pulley, 4: Conveyor belt driven pulley, 5: Conveyor belt, 6: Laser induced breakdown spectroscopy autofocus detection system, 7: X-axis slider, 8: X-axis guide rail, 9: X-axis stepper servo motor, 10: Three-axis displacement platform control module, 11: Connecting rod, 12: Depth camera, 13: Z-axis stepper servo motor, 14: Z-axis guide rail, 15: Z-axis slider, 16: Y-axis transmission shaft, 17: Y-axis stepper servo motor, 18: Left Y-axis slider, 19: Left Y-axis guide rail, 20: Right Y-axis slider, 21: Right Y-axis guide rail, 22: Linear motor, 23: Laser, 24: Spectral signal acquisition optical path system, 25: Laser ranging sensor, 26: Laser focusing optical path system, 27: Spectrometer, 28: Linear motor guide rail, 29: Linear motor slider, 30: Linear motor driver, 31: Main control board, 32: Fixed bracket. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0024] Figure 1 This is a schematic diagram of the structure of the batch production line Chinese medicinal material detection device provided by the present invention. Figure 2 A schematic diagram of the structure of a three-axis displacement platform provided in an embodiment of the present invention is shown in FIG. Figure 1 and Figure 2 As shown, it includes: a laser induced breakdown spectroscopy autofocus detection system 6, a main control unit and a depth camera 12 fixed to a fixed frame 32, a three-axis displacement platform, and a conveyor belt system arranged under the laser induced breakdown spectroscopy autofocus detection system 6; the depth camera 12 is fixed to the fixed frame 32 through a connecting rod 11.

[0025] The conveyor belt system consists of a conveyor belt drive module 1, a conveyor belt stepper motor 2, a conveyor belt driving wheel 3, a conveyor belt driven wheel 4, and a conveyor belt 5.

[0026] The three-axis displacement platform consists of an X-axis slider 7, an X-axis guide rail 8, an X-axis stepper servo motor 9, a three-axis displacement platform control module 10, a Z-axis stepper servo motor 13, a Z-axis guide rail 14, a Z-axis slider 15, a Y-axis transmission shaft 16, a Y-axis stepper servo motor 17, a left Y-axis slider 18, a left Y-axis guide rail 19, a right Y-axis slider 20, and a right Y-axis guide rail 21.

[0027] In the present invention, the X-axis slider 7 and the X-axis guide rail 8 realize the movement of the laser induced breakdown spectroscopy automatic focus detection system 6 on the X-axis, the Z-axis guide rail 14 and the Z-axis slider 15 realize the movement of the laser induced breakdown spectroscopy automatic focus detection system 6 on the Z-axis, the left Y-axis slider 18, the left Y-axis guide rail 19, the Y-axis transmission shaft 16, the right Y-axis slider 20 and the right Y-axis guide rail 21 work together to realize the movement of the laser induced breakdown spectroscopy automatic focus detection system 6 on the Y-axis, the Y-axis transmission shaft 16 ensures the synchronous movement of the left and right Y-axis guide rails to prevent offset during operation, the left Y-axis guide rail 19 and the right Y-axis guide rail 21 form a stable dual-track displacement system, which improves the structural strength and avoids vibration and errors caused by single-track operation.

[0028] In the present invention, the X-axis stepper servo motor 9, the Y-axis stepper servo motor 17 and the Z-axis stepper servo motor 13 control the movement of the sliders on the X, Y and Z axes, plan the path and issue execution instructions according to the task parameters, and achieve high-precision position adjustment.

[0029] Optionally, the laser induced breakdown spectroscopy autofocus detection system includes: a linear motor, a laser, a spectral signal acquisition optical path system, a laser ranging sensor, a laser focusing optical path system, a spectrometer, a linear motor guide rail, a linear motor slider, a linear motor driver and a main control board, wherein the laser, the spectral signal acquisition optical path system, the laser ranging sensor and the laser focusing optical path system are mounted on the linear motor slider; The main control board is used to control the operation of the linear motor driver according to the detection task parameters sent by the main control unit, and the linear motor driver is used to control the start, stop and movement of the linear motor; The linear motor is used to control the linear motor slider to slide on the linear motor guide rail to control the laser, the spectrum signal collection optical path system, the laser ranging sensor and the laser focusing optical path system to achieve an automatic focusing function.

[0030] Figure 3 This is a schematic diagram of the structure of the laser induced breakdown spectroscopy autofocus detection system provided in the embodiment of the present application, as shown in FIG. Figure 3 As shown, it includes: a linear motor 22, a laser 23, a spectrum signal collection optical path system 24, a laser ranging sensor 25, a laser focusing optical path system 26, a spectrometer 27, a linear motor guide rail 28, a linear motor slider 29, a linear motor driver 30 and a main control board 31, wherein the laser 23, the spectrum signal collection optical path system 24, the laser ranging sensor 25 and the laser focusing optical path system 26 are mounted on the linear motor slider 29, and the linear motor 22 controls the linear motor slider 29 to slide on the linear motor guide rail 28, so that the linear motor 22 controls the laser 23, the spectrum signal collection optical path system 24, the laser ranging sensor 25 and the laser focusing optical path system 26 to realize the automatic focusing function; Laser 23 generates a high-energy laser beam, excites plasma on the sample surface, and acquires spectral signals. Laser focusing optical system 26 finely focuses the laser beam, ensuring that the laser energy is concentrated on a specific area on the sample surface. Spectral signal acquisition optical system 24 collects the plasma optical radiation generated by laser excitation and transmits the optical signal via optical fiber to spectrometer 27. Spectrometer 27 receives the optical signal, performs spectroscopic processing, and converts it into spectral data for analysis.

[0031] The laser rangefinder 25 measures the distance between the sample surface and the laser focal point in real time, ensuring precise focus. Because the spectral signal acquisition optical system 24 and the laser focusing optical system 26 are fixed in position, the laser rangefinder 25 transmits the measured distance data to the main control board 31, which provides critical feedback information to enable fine-tuning of the linear motor driver 30 to ensure the laser focus is precisely on the sample surface.

[0032] The main control board 31 serves as the core control unit of the LIBS autofocus detection system, coordinating the precise operation of all components. It is responsible for triggering the laser 23, transmitting data from the laser ranging sensor 25, sending instructions to the spectrometer 27 to collect spectral data, and controlling the displacement of the linear motor driver 30.

[0033] In the present invention, the laser ranging sensor 25 first measures the distance between the sample and the focal position and transmits the measured data to the main control board 31. Based on this feedback, the main control board 31 calculates the required displacement adjustment and fine-tunes the linear motor 22 via the linear motor driver 30. The laser focusing optical system 26 precisely focuses the laser on the sample surface, while the spectral signal acquisition optical system 24 collects the plasma radiation signal and transmits it to the spectrometer 27 for analysis. This process ensures the high precision and efficiency of the detection system, providing strong technical support for the quality control of traditional Chinese medicines.

[0034] Optionally, the conveyor belt system includes: a conveyor belt drive module, a conveyor belt stepper motor, a conveyor belt driving wheel, a conveyor belt driven wheel, and a conveyor belt; Wherein, the conveyor belt drive module is in communication connection with the main control unit and is used to control the operation of the conveyor belt stepper motor; The conveyor belt stepping motor is used to drive the conveyor belt driving wheel, and the conveyor belt driving wheel is used to drive the conveyor belt driven wheel to rotate through the conveyor belt; Wherein, the conveyor belt is used to carry the Chinese medicinal material samples to be tested.

[0035] In this invention, the conveyor belt drive module is responsible for controlling the start and stop of the conveyor belt's stepper motor. Through precise control instructions, the conveyor belt drive module ensures that the stepper motor accurately drives the conveyor belt's driving pulley, achieving uniform speed operation of the conveyor belt. This design ensures that Chinese medicinal material samples can be continuously and stably transported to the testing area, laying a solid foundation for subsequent accurate testing.

[0036] As a key component of power conversion, the conveyor belt stepper motor receives the control signal from the conveyor belt drive module, drives the conveyor belt driving wheel to rotate, and drives the conveyor belt driven wheel to rotate.

[0037] The design of the conveyor belt fully considers the stability and safety of the sample. It not only provides a smooth transportation surface, but also ensures the precise positioning of the sample during the testing process, providing a guarantee for the realization of efficient automated testing.

[0038] Figure 4 This is a schematic diagram of the overall architecture of the batch production line Chinese medicinal material testing device provided by the present invention, as shown in FIG. Figure 4As shown, it includes: a depth camera, a laser-induced breakdown spectroscopy autofocus detection system, a three-axis displacement platform, a conveyor system and a main control unit.

[0039] The depth camera is used to collect three-dimensional image information of the Chinese medicinal material sample to be tested, which includes the sample RGB image and depth map. After obtaining the complete three-dimensional image information, the information is transmitted to the main control unit; the main control unit jointly analyzes the RGB image and depth map data in the three-dimensional image information, extracts the contour information of the Chinese medicinal material sample, and calculates the three-dimensional physical coordinates of the sample in space; based on the extracted spatial geometric characteristics and distribution information, it automatically generates detection task parameters including the spatial position of the detection point and its detection order, and sends the parameters to the main control board to assist the laser induced breakdown spectroscopy automatic focus detection system to adjust the focus position to ensure detection accuracy, especially when the sample surface is uneven; the laser induced breakdown spectroscopy automatic focus detection system combines a laser distance sensor and a linear motor to realize dynamic automatic focus of the laser, so that the laser is always focused on the detection point position on the sample surface, ensuring the stability of the spectral signal during the laser induced breakdown spectroscopy detection process.

[0040] The three-axis displacement platform provides precise displacement control of the X, Y, and Z axes to achieve precise positioning and movement of the laser-induced breakdown spectroscopy autofocus detection system. Its function is to support matrix scanning detection or multi-point detection of samples, and through cooperation with the autofocus function, it can complete the comprehensive analysis of complex-shaped samples; the conveyor belt system is used to transfer batch samples from the entrance to the laser-induced breakdown spectroscopy detection area in sequence, and transmit them to the exit after the detection is completed. Its function is to ensure the continuity and efficiency of batch detection and is suitable for assembly line operation requirements; the main control unit is the central control unit of the entire system. As the host computer of the entire system, it communicates with each subsystem through the USB interface, coordinates the operation of the depth camera, laser-induced breakdown spectroscopy autofocus detection system, three-axis displacement platform system, conveyor belt system, and the display of quantitative and qualitative analysis of spectral data.

[0041] By incorporating a depth camera, this system enables high-precision acquisition of three-dimensional spatial information from traditional Chinese medicine (TCM) samples, including RGB images and depth maps. The main control unit, incorporating image processing and analysis algorithms, processes the captured images to precisely extract the sample's outline and accurately determine its three-dimensional physical coordinates (X, Y, and Z) in space. Based on this information, the system automatically generates detection task parameters tailored to the sample's spatial morphology and structural characteristics, guiding the three-axis displacement platform and LIBS autofocus detection system for precise positioning and detection. After receiving the complete three-dimensional image information, the main control unit generates the detection task parameters based on this information. This real-time control and adjustment capability ensures flexibility and adaptability in the detection process, accommodating TCM samples of varying shapes and sizes. Based on the detection task parameters, the three-axis displacement platform controls the LIBS autofocus detection system to move to various detection points on the sample for spectral data acquisition. The main control unit analyzes the collected spectral data, determines the type and content of elements in the sample, completes qualitative and quantitative analysis, and thus determines the qualified information of the sample. Through automation and precise control, it realizes batch, efficient and accurate quality inspection of Chinese medicinal materials samples, meeting the quality control needs of Chinese medicinal materials in modern production lines.

[0042] Figure 5 The batch production line Chinese medicinal material detection method provided in the embodiment of the present application includes: Step 510: When the conveyor belt system is transporting the Chinese medicinal material sample to be tested, the depth camera collects three-dimensional image information of the Chinese medicinal material sample to be tested, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to the main control unit; wherein the complete three-dimensional image information includes an RGB image and a depth map; Step 520: Upon receiving the complete three-dimensional image information, the main control unit extracts the contours of the complete three-dimensional image information using an image processing and analysis algorithm, calculates the three-dimensional physical coordinates of the Chinese medicinal material sample in space, generates detection task parameters based on the morphological characteristics and size information of the Chinese medicinal material sample, and sends the detection task parameters to the three-axis displacement platform; wherein the detection task parameters include: the spatial position of the detection points and the detection order; Step 530: The three-axis displacement platform controls the LIBS autofocus detection system to move to each detection point corresponding to the to-be-detected Chinese medicinal material sample according to the detection task parameters, so that the LIBS autofocus detection system collects spectral data of the to-be-detected Chinese medicinal material sample to obtain Chinese medicinal material spectral data. In step 540 , the main control unit analyzes the spectrum data of the Chinese medicinal materials, determines spectrum analysis results, and determines qualification information of the Chinese medicinal materials sample to be tested based on the spectrum analysis results.

[0043] The main control unit analyzes and processes the collected spectral data of the Chinese medicinal material samples, determines the corresponding spectral analysis results based on the qualitative and quantitative algorithm models, and judges whether the Chinese medicinal material samples to be tested meet the set quality standards based on the analysis results, and then determines whether they are qualified or not.

[0044] After all pre-set test points have been inspected, the main control unit integrates the analysis results from the inspection process and outputs the test results. These results include a three-dimensional structural image of the TCM sample, the spatial distribution of the test points, and the qualitative and quantitative analysis results corresponding to each test point. The main control unit further annotates these analysis results within the sample outline represented by the RGB image, achieving visual visualization of the test data. Finally, the inspection image and corresponding test data are synchronously stored in a database for subsequent quality traceability, result review, and data management.

[0045] In this application, all hardware devices, including the conveyor belt, depth camera, three-axis displacement platform, laser, and spectrometer, must first be connected to the main control unit. Through the human-computer interface, system parameters such as conveyor belt speed, laser energy, and spectrometer sampling frequency must be set to ensure that all devices are in standby mode.

[0046] The Chinese herbal medicine sample to be tested is placed manually or automatically on a conveyor belt and then transported to the inspection area. When the sample enters the depth camera's operating range, the camera begins capturing a 3D image of the sample and determines whether the sample has been fully identified. If the sample is fully identified, the conveyor belt stops; if not, it continues until the sample is fully identified.

[0047] The three-dimensional image information of the sample collected by the depth camera includes RGB images and depth maps, and the image information is transmitted to the main control unit. Based on the received RGB images and depth maps, the main control unit combines image processing and analysis algorithms to complete the sample contour extraction and the precise positioning of its three-dimensional physical coordinates. On this basis, the system automatically generates detection task parameters that match the sample characteristics, including the spatial position of the detection points and their execution order, and transmits these parameters to the three-axis displacement platform control module. The three-axis displacement platform control module controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point based on the detection parameters, and automatically focuses on each point to stimulate the generation of plasma on the sample surface. At the same time, the spectrometer collects the spectral signal of the plasma radiation to complete the acquisition of spectral data.

[0048] The collected spectral data is processed to generate qualitative and quantitative spectral results. Based on these analysis results and the pre-set quality standards, the sample is judged to be qualified. Samples that meet the quality standards are considered qualified, while those that do not meet the standards are considered unqualified.

[0049] All test results, including sample number, test time, and element concentration, are stored in a database to support subsequent query and tracking. The above test and analysis steps are repeated for all test points of each sample until all points are tested. After completing the test of a sample, the system automatically enters standby mode, awaiting the next batch of samples. This process ensures the continuity and efficiency of batch sample testing, making it suitable for assembly line operations.

[0050] Optionally, the main control unit analyzes the spectrum data of the Chinese medicinal materials to determine the spectrum analysis results, including: After performing data clipping and spectrum data smoothing on the Chinese medicinal material spectrum data, the Chinese medicinal material smoothed spectrum data is obtained; After background fitting is performed on the smoothed spectrum data of the Chinese medicinal material, spectrum background fitting data is obtained; After subtracting the spectrum background fitting data from the smoothed spectrum data of the Chinese medicinal material, the net spectrum signal data of the Chinese medicinal material is obtained; Extracting characteristic peaks from the net spectrum signal data of the Chinese medicinal materials to obtain characteristic peak information; The characteristic peak information is qualitatively analyzed and quantitatively analyzed to determine the element composition information of the Chinese herbal medicine sample to be detected and the content information of each element in the Chinese herbal medicine sample to be detected; A spectrum analysis result is obtained based on the element composition information and the content information of each element.

[0051] In an alternative embodiment, Figure 6 The workflow diagram of the rapid detection device provided in the embodiment of the present application is as follows: Figure 6 As shown in the figure, the rapid detection device includes a depth camera, a laser-induced breakdown spectroscopy autofocus detection system, a three-axis displacement platform system, and a conveyor belt system. Its workflow is as follows: During the device initialization phase, after the system is started, the main control unit connects to the device and detects the status of the depth camera, LIBS autofocus detection system, three-axis displacement platform, and conveyor belt system. It also completes the parameter configuration of the laser, spectrometer, and conveyor belt. After the configuration is completed, the system enters the standby state.

[0052] Sample loading and conveying identification: samples can be placed on the conveyor belt by manual delivery or automatic loading. After the conveyor belt starts, the depth camera collects images of the running area in real time and determines whether the sample is recognized: if the sample cannot be recognized, the conveyor belt continues to run until the sample enters the field of view; when the sample is successfully recognized, the system enters the image acquisition stage.

[0053] Image Information Collection and Upload,The depth camera collects complete three-dimensional image information including RGB,image and depth map, and uploads it to the main control unit.

[0054] Image analysis and task parameter generation: The main control unit processes the uploaded image information, extracts the sample's outline, identifies the sample type, and calculates its 3D physical coordinates in space. Combining the sample's geometry and spatial distribution, the system generates task parameters tailored to the sample's characteristics. These parameters include the spatial location of the test points and their execution order.

[0055] The three-axis displacement platform performs the detection task. The main control unit transmits the detection task parameters to the three-axis platform control module, controls the laser system to move to each detection point, and performs autofocus and LIBS detection to obtain spectral data.

[0056] Spectral analysis and quality judgment: The main control computer performs qualitative and quantitative analysis on the spectral data of each detection point to determine whether the Chinese medicinal material sample meets the established quality standards: if it fails, the system will control the execution of sample rejection; if it passes, the sample will be output and enter subsequent processing.

[0057] Results are visualized and recorded. The system annotates the spectral analysis results of each test point on the sample image, generating a sample element distribution map for visual expression of the test results. The test results, including the sample number, test time, and element distribution map, are stored in a database for subsequent traceability and query.

[0058] Circular testing: after the current sample test is completed, the system automatically starts the conveyor belt to load and test the next sample until all samples are tested, realizing efficient and continuous batch testing of Chinese medicinal materials.

[0059] Figure 7 The depth camera image processing flow chart provided by the present invention is as follows: Figure 7 Shown, including: Image acquisition: A depth camera is used to capture an RGB image and depth map of the target scene. The RGB image is used to record visual information such as the scene's color and texture; the depth map is used to obtain distance information between objects in the scene and the camera.

[0060] Image data transmission: The collected RGB image data and depth map data are transmitted to the main control unit via USB transmission.

[0061] Processing and Analysis by the Main Control Unit: After receiving the transmitted image data, the control unit pre-processes and analyzes the RGB image and depth map. It performs operations such as color correction and noise reduction on the RGB image, and performs outlier processing and hole filling on the depth map to improve image data quality.

[0062] Image processing: Targeted processing is performed on the RGB image and depth map. Image contour extraction and regular grid layout are performed on the RGB image to automatically generate grid detection points that fall within the sample area; the depth map is used to calculate the three-dimensional size of the object.

[0063] Coordinate conversion steps: RGB images and depth images may have coordinate system deviations based on different imaging principles. Therefore, during the process of 3D reconstruction of samples and generation of detection tasks, the spatial coordinates of the two need to be unified. Specifically, the RGB image and the depth map are registered using the camera intrinsic parameters preset by the depth camera (including focal length, principal point coordinates, etc.). Through the coordinate mapping relationship, the 3D spatial depth information represented by each pixel in the depth map is accurately mapped to the corresponding RGB image pixel position, achieving spatial alignment of the image and depth data. Furthermore, the main control unit can accurately obtain the 3D coordinate information (X, Y, Z) of each detection point of the target sample in the actual physical space in the fused image, providing an accurate spatial basis for subsequent detection task parameter generation, laser focus control, and displacement path planning.

[0064] Detection parameter generation step: Based on the processed RGB image and depth map information, comprehensive calculation is performed to generate detection parameters, including the spatial position of the detection points and their execution order.

[0065] It should be noted that the three-dimensional size of the object is calculated based on the internal parameters of the depth camera. The two-dimensional pixel coordinates (u, v) and the corresponding depth value Z of each sample are converted into three-dimensional physical coordinates (X, Y, Z) in the depth camera coordinate system. The calculation formula for the three-dimensional coordinates is as follows: in, 、 is the focal length of the camera, is the principal point of the optical axis.

[0066] Figure 8 The depth camera RGB image processing flow chart provided by the present invention is as follows: Figure 8 Shown, including: Image preprocessing: Convert the color image to a grayscale image; perform Gaussian blur processing on the grayscale image to remove noise; perform edge detection on the image based on the Canny operator to obtain an edge image.

[0067] Contour extraction: Extract all external contours in the edge image and select the contour with the largest area as the contour area of ​​the sample to be detected.

[0068] Sample area mask generation: Generate a single-channel binary mask image based on the maximum contour. This mask image is used to subsequently determine whether the detection point falls within the sample area.

[0069] Detection grid division: The entire image area is divided into a regular grid with a step size determined by the contour size, and the image is traversed. For each grid cell, it is determined whether all four vertices are within the sample mask; if the conditions are met, the grid is considered a valid detection area.

[0070] Checkpoint Marking: For grid cells that meet the requirements, the following steps are performed: a red rectangular border is drawn on the image to identify the grid; bold dots are drawn at grid intersections to mark the locations of the LIBS detection system's task points. The access paths to all checkpoints are planned using a "snake scanning" strategy: starting from the first checkpoint in the upper left corner of the image, the system scans horizontally from left to right. After completing the inspection of the current row, the system proceeds to the next row and scans horizontally from right to left. This process is repeated to complete the scanning of all grid points.

[0071] After generating the detection points and combining them with the depth information, the following detection parameter generation process is performed: Depth extraction of detection points: The main control unit extracts the depth value of each detection point in the Z-axis direction of the three-dimensional spatial coordinates based on the depth map information obtained by the depth camera, and obtains the three-dimensional physical coordinates (X, Y, Z) of each detection point; Parameter matching calculation: Based on the three-dimensional morphological features of the sample and the spatial distribution of the detection points, the main control unit automatically generates the task parameters for laser-induced breakdown spectroscopy detection, including but not limited to: the three-dimensional spatial coordinates of each detection point; the detection path sequence, etc. Parameter output and transmission: The detection task parameters are integrated into a task instruction set and sent to the three-axis displacement platform control module and the laser-induced breakdown spectroscopy detection system to complete precise focusing and stable detection.

[0072] Figure 9 The spectrum analysis process flow chart provided by the present invention is as follows: Figure 9 Shown, including: First, the sample is excited by laser to generate a plasma spectrum signal, the original spectrum data of the sample is collected using a spectrometer, and the collected spectrum data is transmitted to the main control computer.

[0073] The main control computer crops the received raw spectral data, deletes the data of repeated bands, and merges the raw spectral data.

[0074] The Savitzky-Golay filter is used to reduce random noise in the spectrum, ensuring that the main features of the spectral signal are retained and providing high-quality spectral data for subsequent analysis. Smoothing is performed to reduce high-frequency noise interference. The smoothed spectrum is the smoothed spectrum data of Chinese medicinal materials. : in, is the position index, is half the length of the selection window, are the coefficients of the Savitzky-Golay filter, which depend on the polynomial order and window length. The window length and polynomial order can be flexibly adjusted to suit the characteristics of different spectral signals.

[0075] The background signal of the spectrum is fitted using the Percentile Filter method. The background signal is obtained according to the set window size and percentage. If the sliding window size is set to , then for each point The window is: in, Smoothed spectral data. Then sort the data in the window of each point to get the ordered sequence of each point : Finally give the appropriate percentile , calculate the index of percentile , get the spectral background fitting data , the formula is: in, Indicates rounding up. is in sorted sequence The position index in , is the first value as the current point The background signal output.

[0076] Smooth spectral data according to the smoothed Chinese medicinal materials Subtract spectral background fitting data Get the net spectral signal data of Chinese medicinal materials , the formula is: ; in, This operation is used to avoid negative signals after background signal subtraction.

[0077] Net spectral signal data of Chinese medicinal materials Detect characteristic peaks and identify the positions of characteristic spectral lines. The peak detection conditions are: in, is the preset intensity threshold used to exclude low-intensity noise; The peak width range can be set dynamically according to the height of the peak, which is used to judge the relative size of adjacent points. The data that meets the peak detection conditions is set to .

[0078] The element information of the sample is obtained by comparing the element information in the NIST database with the wavelength of the characteristic peak. The conditions that need to be met are: ; in, is the wavelength of the element information from the NIST database, Represents the position index of the element in the NIST database, Indicates the wavelength comparison threshold range.

[0079] The extracted characteristic peaks were quantitatively analyzed using a support vector regression (SVR) model. The content of the analyte in the target sample was calculated based on the trained regression model.

[0080] The main control computer generates and displays a test report based on the results of qualitative and quantitative analysis. The report includes the element type, content and other test parameters of the target sample.

[0081] This process achieves high-precision analysis of spectral data by combining signal processing technologies such as data cropping, smoothing, and background subtraction with the SVR machine learning algorithm. It has the characteristics of simple operation, fast detection, and accurate results. It is widely applicable to the qualitative and quantitative detection of samples such as Chinese medicinal materials, soil, and metals.

[0082] In an alternative embodiment, Figure 10 This is a flow chart of the quantitative analysis method of the present invention. This process achieves high-precision prediction of element concentrations in samples through spectral preprocessing, feature extraction, model training, and validation. Specifically, it includes the following steps: After collecting the sample's spectral data, preprocessing is performed. This mainly includes operations such as data smoothing and background subtraction, which aim to remove noise and interference signals, improve the quality of the spectral data, and lay the foundation for subsequent feature extraction and modeling.

[0083] Extract characteristic peaks associated with the target element from the preprocessed spectrum. Peak extraction involves identifying peak position, intensity, and other key parameters to ensure the extracted features accurately reflect the sample's composition.

[0084] Before building a model, you need to first The purpose of preprocessing is to eliminate the differences in different feature dimensions, ensure the uniformity of the data, and improve the training efficiency of the model. Its characteristic spectrum matrix is ​​expressed as: ; in, It is Spectral intensity value at a characteristic wavelength; is the number of characteristic wavelengths extracted. In addition, for the characteristic matrix Perform normalization to ensure that the scales of different features are consistent: in, is the mean of the feature, Is the standard deviation of the feature. After normalization, ensuring that the data is in the same dimension helps the stability and convergence speed of the model. When constructing the SVR model, use the normalized feature data To train the model, the normalized data is input into the SVR model to calculate the support vector and regression function.

[0085] The regression function is of the form: in, For the Normalized feature data of training samples; is the kernel function used to map the input data into a high-dimensional feature space; and is the Lagrange multiplier, which represents the weight of the support vector; is the bias term; is the number of training samples. Kernel function The radial basis kernel function (RBF) is used. The expression of the RBF kernel function is: in, is the kernel parameter, which controls the similarity between samples.

[0086] The optimization goal of the SVR model is to minimize the trade-off between prediction error and model complexity. During model training, the following objective function is optimized: in, and is the slack variable, which represents the deviation beyond the ϵ interval; is a regularization parameter that controls the trade-off between error tolerance and model complexity. In addition, the following constraints need to be met during model optimization: Tune hyperparameters through cross-validation 、 and , to obtain the optimal regression model.

[0087] After completing the SVR model training, the normalized data can be used to predict the concentration. The predicted concentration value is: in, is the normalized feature data of the test sample, is the predicted sample concentration.

[0088] The performance of the SVR model is evaluated by the coefficient of determination (R2), and the formula for the coefficient of determination is: in is the mean of the actual concentration values.

[0089] The validated model is applied to the quantitative analysis of the sample. The output includes the predicted concentration of the elements in the sample, analysis report, and other relevant information for users to review and use.

[0090] This process significantly improves the applicability of laser-induced breakdown spectroscopy technology in quantitative analysis by combining feature extraction and machine learning models. It has the advantages of high precision, high efficiency and scalability, and can be used for rapid component detection in many fields such as traditional Chinese medicine.

[0091] In an optional embodiment, in order to verify the effectiveness of the method for extracting and detecting the contour of a Chinese medicinal material sample based on a depth camera according to the present invention, the following experiment was conducted.

[0092] This example uses samples of various common Chinese medicinal herbs, such as licorice, as test objects. These samples are placed on a conveyor belt, and a RealSense D455 depth camera captures their RGB and depth images in real time. The system first preprocesses the captured images to remove background interference. Then, using the image processing algorithm, it extracts the complete contour area of ​​the sample and generates a corresponding binary mask image.

[0093] Combining the sample's contour morphology and three-dimensional spatial characteristics, the system automatically generates a targeted detection point layout plan based on the sample structure type. Figure 11 The detection path and detection point distribution diagram of the licorice sample provided by the present invention are as follows: Figure 11 As shown in the figure, for a licorice sample, the system automatically plans and arranges eight inspection points within its main area. The inspection trajectory and point information are generated in real time by the main control unit through image processing and coordinate conversion algorithms, ensuring that the inspection points fall precisely within the sample.

[0094] Subsequently, the main control unit controls the three-axis displacement platform and the LIBS spectrum detection device to collect spectra at each detection point in turn. Figure 12 The spectrum comparison diagram of eight detection points of the liquorice sample provided by the present invention, the detection results, such as Figure 12 As shown in the figure, the spectral data of the licorice sample at different detection points have minimal differences, and the spectral line intensity is consistent, indicating that the detection system has good stability and repeatability. After completing the detection of a sample, the solution in the present invention will continue to test the samples on the conveyor belt one by one according to the above process until the machine stops working.

[0095] According to the Chinese medicinal materials detection scheme of this application, this application has successfully obtained and organized a set of detailed experimental data. Referring to the draft of the general rules for the verification of medicinal materials and medicinal pieces stipulated in the "Chinese Pharmacopoeia", 8 groups of angelica medicinal materials containing copper (Cu) elements were configured as test samples, and the copper content is shown in Table 1. In order to verify the reliability and accuracy of the quantitative analysis method, 1,000 sets of spectral data were collected for each group of samples for model training. Subsequently, for samples 1 to 7, each group of samples was independently tested three times to obtain the quantitative detection results of the copper element, and the results are shown in Table 2. The experimental results clearly demonstrate the accuracy of this patented method in the detection of heavy metal Cu elements in Chinese medicinal materials, and provide strong data support for quantitative analysis.

[0096] Table 1 Element contents of seven samples

[0097] Table 2 Copper content test results

[0098] These data not only verify the feasibility of the quantitative analysis algorithm, but also prove the accuracy and reliability of the method described in this application, providing strong support for the practical application of batch production line LIBS rapid detection equipment for traditional Chinese medicine.

[0099] Figure 13 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 13As shown, the electronic device may include: a processor 1310, a communications interface 1320, a memory 1330, and a communication bus 1340. The processor 1310, the communications interface 1320, and the memory 1330 communicate with each other via the communication bus 1340. The processor 1310 may call the logic instructions in the memory 1330 to execute a batch-line Chinese medicinal material detection method, which includes: When the conveyor belt system transports the Chinese medicinal material sample to be tested, the depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be tested, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be tested to the main control unit; When the main control unit receives the complete three-dimensional image information, it extracts the contour of the complete three-dimensional image information according to the image processing and analysis algorithm, and then calculates the three-dimensional physical coordinates of the Chinese medicinal material sample in space, and generates detection task parameters based on the morphological characteristics and size information of the Chinese medicinal material sample, and sends the detection task parameters to the three-axis displacement platform; wherein, the detection task parameters include: the spatial position of the detection point and the detection order; The three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; The main control unit analyzes the spectrum data of the Chinese medicinal materials, determines spectrum analysis results, and determines the qualification information of the Chinese medicinal materials sample to be tested according to the spectrum analysis results.

[0100] Furthermore, the logic instructions in the aforementioned memory 1330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0101] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the batch pipeline Chinese medicinal material detection method provided by the above methods, which includes: When the conveyor belt system transports the Chinese medicinal material sample to be tested, the depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be tested, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be tested to the main control unit; When the main control unit receives the complete three-dimensional image information, it extracts the contour of the complete three-dimensional image information according to the image processing and analysis algorithm, and then calculates the three-dimensional physical coordinates of the Chinese medicinal material sample in space, and generates detection task parameters based on the morphological characteristics and size information of the Chinese medicinal material sample, and sends the detection task parameters to the three-axis displacement platform; wherein, the detection task parameters include: the spatial position of the detection point and the detection order; The three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; The main control unit analyzes the spectrum data of the Chinese medicinal materials, determines spectrum analysis results, and determines the qualification information of the Chinese medicinal materials sample to be tested according to the spectrum analysis results.

[0102] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the batch-line Chinese medicinal material detection method provided by the above methods, the method comprising: When the conveyor belt system transports the Chinese medicinal material sample to be tested, the depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be tested, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be tested to the main control unit; When the main control unit receives the complete three-dimensional image information, it extracts the contour of the complete three-dimensional image information according to the image processing and analysis algorithm, and then calculates the three-dimensional physical coordinates of the Chinese medicinal material sample in space, and generates detection task parameters based on the morphological characteristics and size information of the Chinese medicinal material sample, and sends the detection task parameters to the three-axis displacement platform; wherein, the detection task parameters include: the spatial position of the detection point and the detection order; The three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; The main control unit analyzes the spectrum data of the Chinese medicinal materials, determines spectrum analysis results, and determines the qualification information of the Chinese medicinal materials sample to be tested according to the spectrum analysis results.

[0103] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0104] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A batch production line Chinese medicinal material detection device, characterized in that: include: A conveyor belt system, a laser-induced breakdown spectroscopy autofocus detection system, a main control unit, a depth camera fixed to a fixed frame, and a three-axis displacement platform; the laser-induced breakdown spectroscopy autofocus detection system is connected to the three-axis displacement platform; the main control unit is respectively communicated with the conveyor belt system, the laser-induced breakdown spectroscopy autofocus detection system, the depth camera, and the three-axis displacement platform; Wherein, the conveyor belt system carries and transports the Chinese medicinal material samples to be tested; The depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be detected, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be detected to the main control unit; After receiving the complete three-dimensional image information, the main control unit controls the conveyor belt system to stop running; wherein the three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; wherein the detection task parameters are determined based on the three-dimensional image information; The main control unit analyzes the spectrum data of the Chinese medicinal materials to determine the qualification information of the Chinese medicinal materials sample to be tested.

2. The batch production line Chinese medicinal material detection device according to claim 1, characterized in that: The conveyor belt system includes: a conveyor belt drive module, a conveyor belt stepper motor, a conveyor belt driving wheel, a conveyor belt driven wheel, and a conveyor belt; Wherein, the conveyor belt drive module is in communication connection with the main control unit and is used to control the operation of the conveyor belt stepper motor; The conveyor belt stepping motor is used to drive the conveyor belt driving wheel, and the conveyor belt driving wheel is used to drive the conveyor belt driven wheel to rotate through the conveyor belt; Wherein, the conveyor belt is used to carry the Chinese medicinal material samples to be tested.

3. The batch production line Chinese medicinal material detection device according to claim 1, characterized in that: The three-axis displacement platform includes: a three-axis displacement platform control module, an X-axis slider, an X-axis guide rail, an X-axis stepper servo motor, a Z-axis stepper servo motor, a Z-axis guide rail, a Z-axis slider, a Y-axis transmission shaft, a Y-axis stepper servo motor, a left Y-axis slider, a left Y-axis guide rail, a right Y-axis slider, and a right Y-axis guide rail; Among them, the three-axis displacement platform control module controls the operation of the X-axis stepper servo motor, the Z-axis stepper servo motor, and the Y-axis stepper servo motor according to the detection task parameters, and then controls the movement of the X-axis slider, the Y-axis slider, and the Z-axis slider to achieve position control of the laser induced breakdown spectroscopy autofocus detection system; Among them, the X-axis slider and the X-axis guide rail realize the movement of the laser induced breakdown spectroscopy automatic focus detection system on the X-axis, the Z-axis guide rail and the Z-axis slider realize the movement of the laser induced breakdown spectroscopy automatic focus detection system on the Z-axis, and the left Y-axis slider, the left Y-axis guide rail, the Y-axis transmission shaft, the right Y-axis slider and the right Y-axis guide rail work together to realize the movement of the laser induced breakdown spectroscopy automatic focus detection system on the Y-axis.

4. The batch production line Chinese medicinal material detection device according to claim 3 is characterized in that: The laser-induced breakdown spectroscopy autofocus detection system includes: a linear motor, a laser, a spectrum signal acquisition optical path system, a laser ranging sensor, a laser focusing optical path system, a spectrometer, a linear motor guide rail, a linear motor slider, a linear motor driver and a main control board. The laser, the spectrum signal acquisition optical path system, the laser ranging sensor and the laser focusing optical path system are mounted on the linear motor slider; The main control board controls the operation of the linear motor driver according to the detection task parameters sent by the main control unit, and the linear motor driver is used to control the start, stop and movement of the linear motor; The linear motor is used to control the linear motor slider to slide on the linear motor guide rail to control the laser, the spectrum signal collection optical path system, the laser ranging sensor and the laser focusing optical path system to achieve an automatic focusing function.

5. The batch production line Chinese medicinal material detection device according to claim 4, characterized in that: The laser is used to generate a high-energy laser beam, and the laser focusing optical path system focuses the laser beam generated by the laser so that the laser beam is focused on a detection point on the surface of the Chinese medicinal material sample to be detected; The spectral signal collection optical path system is used to collect the optical signal generated by the laser beam excitation and transmit the optical signal to the spectrometer; The spectrometer is used to perform spectroscopic processing on the optical signal and convert the optical signal into spectral data.

6. The batch production line Chinese medicinal material detection device according to claim 5, characterized in that: The laser rangefinder detects the distance information between the Chinese medicinal material sample to be detected and the laser focus point of the laser emitted by the laser, and transmits the distance information to the main control board; The main control board generates distance adjustment feedback information according to the distance information, and transmits the distance adjustment feedback information to the linear motor driver to ensure that the laser beam is focused on the detection point position on the surface of the Chinese medicinal material sample to be detected.

7. A method for batch production line Chinese medicinal materials detection based on the batch production line Chinese medicinal materials detection device according to any one of claims 1 to 6, characterized in that: include: When the conveyor belt system transports the Chinese medicinal material sample to be tested, the depth camera collects the three-dimensional image information of the Chinese medicinal material sample to be tested, and transmits the complete three-dimensional image information of the Chinese medicinal material sample to be tested to the main control unit; When the main control unit receives the complete three-dimensional image information, it extracts the contour of the complete three-dimensional image information according to the image processing and analysis algorithm, and then calculates the three-dimensional physical coordinates of the Chinese medicinal material sample in space, and generates detection task parameters based on the morphological characteristics and size information of the Chinese medicinal material sample, and sends the detection task parameters to the three-axis displacement platform; wherein, the detection task parameters include: the spatial position of the detection point and the detection order; The three-axis displacement platform controls the laser-induced breakdown spectroscopy autofocus detection system to move to each detection point corresponding to the Chinese medicinal material sample to be detected according to the detection task parameters, so that the laser-induced breakdown spectroscopy autofocus detection system collects spectral data of the Chinese medicinal material sample to be detected to obtain Chinese medicinal material spectral data; The main control unit analyzes the spectrum data of the Chinese medicinal materials, determines spectrum analysis results, and determines the qualification information of the Chinese medicinal materials sample to be tested according to the spectrum analysis results.

8. The batch production line Chinese medicinal material detection method according to claim 7, characterized in that: The main control unit analyzes the spectrum data of the Chinese medicinal materials to determine the spectrum analysis results, including: After performing data clipping and spectrum data smoothing on the Chinese medicinal material spectrum data, the Chinese medicinal material smoothed spectrum data is obtained; After background fitting is performed on the smoothed spectrum data of the Chinese medicinal material, spectrum background fitting data is obtained; After subtracting the spectrum background fitting data from the smoothed spectrum data of the Chinese medicinal material, the net spectrum signal data of the Chinese medicinal material is obtained; Extracting characteristic peaks from the net spectrum signal data of the Chinese medicinal materials to obtain characteristic peak information; The characteristic peak information is qualitatively analyzed and quantitatively analyzed to determine the element composition information of the Chinese herbal medicine sample to be detected and the content information of each element in the Chinese herbal medicine sample to be detected; A spectrum analysis result is obtained based on the element composition information and the content information of each element.

9. The batch production line Chinese medicinal material detection method according to claim 7, characterized in that: Determining the qualified information of the Chinese medicinal material sample to be tested according to the spectral analysis result includes: When the spectrum analysis result meets the quality standard of the Chinese medicinal material sample to be tested, the qualified information of the Chinese medicinal material sample to be tested is determined to be qualified, and the main control unit controls the conveyor belt system to transport the next Chinese medicinal material sample to be tested; Alternatively, when the spectral analysis result does not meet the quality standard of the Chinese medicinal material sample to be tested, the qualified information of the Chinese medicinal material sample to be tested is determined to be unqualified, and the main control unit controls the conveyor belt system to remove the Chinese medicinal material sample to be tested.

10. The batch production line Chinese medicinal material detection method according to claim 7, characterized in that: The method further comprises: The spectral analysis results and three-dimensional spatial coordinates corresponding to each detection point are associated, and the associated content is superimposed and displayed in the corresponding RGB image in an annotated manner to achieve image visualization of the detection results; at the same time, the annotated image is stored together with the corresponding three-dimensional image information.

11. The batch production line Chinese medicinal material detection method according to claim 7, characterized in that: The method further comprises: Performing image processing on the RGB image in the complete three-dimensional image information, extracting the contour area of ​​the Chinese medicinal material sample, and generating a regular grid structure within the contour area; Determining the number of detection points and the spatial distribution of the detection points on the surface of the Chinese medicinal material sample according to the intersection positions of the grid; Extracting three-dimensional coordinate information corresponding to each detection point based on the spatial distribution and the depth data in the depth image captured by the depth camera; According to the spatial coordinates of the detection points and the geometric features of the Chinese medicinal material samples to be detected, detection task parameters including the spatial positions of the detection points and the detection sequence are planned and generated.

Images