Multi-channel spectrum identification device applied to identification of deteriorated codonopsis pilosula medicinal material

Abstract

The utility model relates to a multi-channel spectrum identification device applied to identification of a deteriorated codonopsis pilosula medicinal material. The device comprises a multi-channel visible-infrared spectrum module, a light source module, a rotary conductive slip ring, a main controller and a rotary gear motor. The multi-channel visible-infrared spectrum module and the light source module are respectively connected with a rotor of the rotary conductive slip ring, and the rotor of the rotary conductive slip ring is connected with the rotary gear motor; a stator of the rotary conductive slip ring is connected with the main controller; the rotary speed reducing motor is connected with the main controller; and the main controller is connected with an LCD (Liquid Crystal Display). The device is simple in structure and portable, can realize real-time detection, can effectively reduce detection errors caused by a single detection point, can identify and screen the quality of the codonopsis pilosula medicinal material in a medicinal material producing area and a rough machining field, is high in reliability, and does not depend on ambient light to work.

Description

Technical Field

[0001] The utility model relates to the technical field of spectral analysis, in particular to a multi-channel spectral recognition device applied to the identification of deteriorated Codonopsis pilosula medicinal materials. Background Technique

[0002] Codonopsis pilosula has the effects of invigorating the spleen and benefiting the lungs, nourishing blood and promoting fluid production. It is a commonly used tonic traditional Chinese medicine in clinical practice and is the main medicine in many important prescriptions and proprietary Chinese medicines. In addition to being used as a medicinal material, Codonopsis pilosula is also widely used in medicinal diets and health products. Codonopsis pilosula is a commodity medicinal material. However, for a long time, the unstable quality of the medicinal material has always been the "bottleneck" restricting the development of the Codonopsis pilosula industry and the development and utilization of resources.

[0003] Due to the large amount of sugar contained in Codonopsis pilosula, it tastes sweet and is soft and moist, making it difficult to store. The processing methods in the producing areas are backward, resulting in uneven quality of Codonopsis pilosula products, and there are deterioration phenomena such as mildew, discoloration, and sulfur fumigation. Therefore, it is a key problem to be solved urgently to establish a on-site and real-time rapid detection system for the quality of Codonopsis pilosula medicinal materials in the origin area to effectively and real-time monitor the quality of the medicinal materials. Content of the Utility Model

[0004] The technical problem to be solved by the utility model is to provide a multi-channel spectral recognition device applied to the identification of deteriorated Codonopsis pilosula medicinal materials that can realize real-time detection.

[0005] To solve the above problems, a multi-channel spectral recognition device applied to the identification of deteriorated Codonopsis pilosula medicinal materials of the utility model is characterized in that: the device includes a multi-channel visible-infrared spectral module, a light source module, a rotary conductive slip ring, a main controller, and a rotary reduction motor; the multi-channel visible-infrared spectral module and the light source module are respectively connected to the rotor of the rotary conductive slip ring, and the rotor of the rotary conductive slip ring is connected to the rotary reduction motor; the stator of the rotary conductive slip ring is connected to the main controller; the rotary reduction motor is connected to the main controller, and the main controller is connected to an LCD display.

[0006] The multi-channel visible-infrared spectral module is composed of visible light and infrared spectral modules of several channels.

[0007] The wavelength of the light source module matches the wavelength range of the multi-channel visible-infrared spectral module.

[0008] The wavelength range of the light source module is between the visible light and near-infrared light wavelength ranges.

[0009] The light source module is composed of a combination of a full-spectrum LED diode and a near-infrared spectral LED diode.

[0010] The wavelength range of the full-spectrum LED diode is 380~700nm; the wavelength range of the near-infrared spectrum LED diode is 650~1050nm.

[0011] The utility model has the following advantages compared with the prior art:

[0012] 1. The multi-channel visible-infrared spectrum module is provided in the utility model. Based on the spectrum analysis of the multi-channel visible-infrared spectrum module, the characteristic spectrum of Codonopsis pilosula is analyzed, and the spectrum of normal Codonopsis pilosula is distinguished from the spectra of other Codonopsis pilosula with deterioration phenomena, so as to improve the on-site recognition ability and accuracy of deteriorated Codonopsis pilosula.

[0013] 2. By rotating the multi-channel visible-infrared spectrum module and the spectrum module to collect spectral data, the utility model can realize real-time detection and effectively reduce the detection error caused by a single detection point.

[0014] 3. The utility model has a simple and portable structure, can identify and screen the quality of Codonopsis pilosula at the medicinal material production area and the primary processing site, has high reliability, and does not depend on ambient light for work. Description of the Drawings

[0015] The following further details the specific embodiments of the utility model with reference to the drawings.

[0016] Figure 1 It is a schematic structural diagram of the utility model.

[0017] Figure 2 It is a working principle diagram of the utility model.

[0018] Figure 3 It is a distribution diagram of PCA of the utility model.

[0019] In the figure: 1 - multi-channel visible-infrared spectrum module; 2 - light source module; 3 - rotary conductive slip ring; 4 - main controller; 5 - rotary reduction motor; 6 - LCD display. Specific Embodiments

[0020] As Figure 1 shown, a multi-channel spectrum recognition device applied to the identification of deteriorated Codonopsis pilosula includes a multi-channel visible-infrared spectrum module 1, a light source module 2, a rotary conductive slip ring 3, a main controller 4 and a rotary reduction motor 5.

[0021] The multi-channel visible-infrared spectrum module 1 and the light source module 2 are respectively connected to the rotor of the rotary conductive slip ring 3, the rotor of the rotary conductive slip ring 3 is connected to the rotary reduction motor 5; the stator of the rotary conductive slip ring 3 is connected to the main controller 4. The rotary reduction motor 5 is connected to the main controller 4, and the main controller 4 is connected to an LCD display 6.

[0022] Among them: The multi-channel visible-infrared spectroscopy module 1 is composed of visible light and infrared spectroscopy modules of several channels. The multi-channel visible-infrared spectroscopy module 1 preferably uses the AS7265x chip launched by ams AG.

[0023] The wavelength of the light source module 2 matches the wavelength range of the multi-channel visible-infrared spectroscopy module 1.

[0024] The wavelength range of the light source module 2 is between the visible light and near-infrared light wavelength ranges.

[0025] The light source module 2 is composed of a combination of a full-spectrum LED diode and a near-infrared spectroscopy LED diode.

[0026] The wavelength range of the full-spectrum LED diode is 380 - 700 nm; the wavelength range of the near-infrared spectroscopy LED diode is 650 - 1050 nm. The near-infrared spectroscopy LED preferably uses the SFH 4736 of Osram.

[0027] The main controller 3 is a separate single-chip microcomputer processing unit.

[0028] The multi-channel visible-infrared spectroscopy module 1, the rotary conductive slip ring 4 and the main controller 3 together form a multi-channel infrared spectroscopy detection system.

[0029] Working principle: The rotary reduction motor 5 drives the rotor of the rotary conductive slip ring 3, as well as the multi-channel visible-infrared spectroscopy module 1 and the light source module 2 to rotate to collect spectral data, and transmits the data to the main controller 4 through the rotary conductive slip ring 3 for processing. According to the diffuse reflection characteristic spectra of Codonopsis pilosula or medicinal material powder, the quality status of Codonopsis pilosula is identified and distinguished through algorithm modeling.

[0030] Working process:

[0031] As Figure 2 shown, the light source module 2 and the multi-channel visible-infrared spectroscopy module 1 form a rotatable sensor data acquisition end, and power supply and signal conduction are provided through the rotary conductive slip ring 3. The light emitted by the light source module 2 is diffusely reflected by Codonopsis pilosula or medicinal material powder and then received by the multi-channel visible-infrared spectroscopy module 1. After the multi-channel visible-infrared spectroscopy module 1 receives the diffuse reflection light signal, it transmits the spectral data to the main controller 4 through the rotary conductive slip ring 3 for data processing. The recognition result after the main controller 4 processes the data is presented on the LCD monitor 6.

[0032] Before being put into use, it is necessary to first establish a model through an algorithm. The PCA-KNN algorithm is used in this utility model to establish the model. The specific steps are as follows:

[0033] First, calibrate the LED spectrum of the light source module 2 with reference to the whiteboard. Then, collect multi-channel spectral data of a large number of Codonopsis pilosula herbs of various qualities. After calibrating and normalizing the data, perform PCA dimensionality reduction through the main controller 4, and then establish a model through the KNN pattern recognition algorithm. The spectral data is used to establish and identify the spectral model based on the diffuse reflection spectrum of Codonopsis pilosula herbs. As Figure 3 shown, in the figure, the samples numbered D+ are deteriorated samples (including discoloration, mildew, and sulfur fumigation), and the samples numbered N+ represent normal samples. There are obvious distribution differences between the deteriorated samples and the normal samples in the PCA distribution map.

[0034] Then, transplant the trained PCA-KNN algorithm model program into the main controller 4. Preferably, the main controller 4 selects an STM32 single-chip microcomputer. The data collected by the multi-channel visible-infrared spectral module 1 is processed by the model algorithm of the main controller 4, and the final processing and recognition results are presented on the LCD monitor 6.

[0035] The present utility model mainly uses this section of spectrum as data for identification to distinguish normal-quality Codonopsis pilosula from other deteriorated Codonopsis pilosula, thereby improving the on-site identification of deteriorated Codonopsis pilosula herbs in environments such as the place of origin of herbs and rough processing sites.

Claims

1. A multi-channel spectral recognition device for identifying deteriorated Codonopsis pilosula medicinal materials, characterized in that: The device comprises a multi-channel visible-infrared spectrum module (1), a light source module (2), a rotating conductive slip ring (3), a main controller (4) and a rotating reduction motor (5); the multi-channel visible-infrared spectrum module (1) and the light source module (2) are respectively connected to the rotor of the rotating conductive slip ring (3); the rotor of the rotating conductive slip ring (3) is connected to the rotating reduction motor (5); the stator of the rotating conductive slip ring (3) is connected to the main controller (4); the rotating reduction motor (5) is connected to the main controller (4); and the main controller (4) is connected to an LCD display (6).

2. A multi-channel spectral recognition device for identifying deteriorated Codonopsis pilosula medicinal materials as claimed in claim 1, characterized in that: The multi-channel visible-infrared spectrum module (1) is composed of several channels of visible light and infrared spectrum modules.

3. A multi-channel spectral recognition device for identifying deteriorated Codonopsis pilosula medicinal materials as claimed in claim 1, characterized in that: The wavelength of the light source module (2) matches the wavelength range of the multi-channel visible-infrared spectrum module (1).

4. A multi-channel spectral recognition device for identifying deteriorated Codonopsis pilosula medicinal materials as claimed in claim 3, characterized in that: The wavelength range of the light source module (2) is between the visible light and near-infrared light wavelength ranges.

5. A multi-channel spectral recognition device for identifying deteriorated Codonopsis pilosula medicinal materials as claimed in claim 4, characterized in that: The light source module (2) is composed of a full-spectrum LED diode and a near-infrared spectrum LED diode.

6. A multi-channel spectral recognition device for identifying deteriorated Codonopsis pilosula medicinal materials as claimed in claim 5, characterized in that: The wavelength range of the full-spectrum LED diode is 380-700nm; the wavelength range of the near-infrared spectrum LED diode is 650-1050nm.

Images