+

CN117129439A - A waste plastic identification system and method based on near-infrared spectroscopy - Google Patents

A waste plastic identification system and method based on near-infrared spectroscopy Download PDF

Info

Publication number
CN117129439A
CN117129439A CN202310718011.2A CN202310718011A CN117129439A CN 117129439 A CN117129439 A CN 117129439A CN 202310718011 A CN202310718011 A CN 202310718011A CN 117129439 A CN117129439 A CN 117129439A
Authority
CN
China
Prior art keywords
computer
sample
tested
waste plastic
identification system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310718011.2A
Other languages
Chinese (zh)
Inventor
晋刚
陈梓锋
林扬添
刘志洲
梁锦彬
李俊宇
张佳栋
许国恩
萧浩坤
罗宇恒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN202310718011.2A priority Critical patent/CN117129439A/en
Publication of CN117129439A publication Critical patent/CN117129439A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/12—Details of acquisition arrangements; Constructional details thereof
    • G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W30/00—Technologies for solid waste management
    • Y02W30/50—Reuse, recycling or recovery technologies
    • Y02W30/62—Plastics recycling; Rubber recycling

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biochemistry (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention discloses a waste plastic identification system and method based on near infrared spectrum; the device comprises a camera, a spectrum probe, a transmission platform, a computer and a mechanical arm; the plastic to be tested moves under the action of the conveying platform, the photo shot by the camera is transmitted to the computer in real time for processing, and the position information of the plastic is calculated; the mechanical arm drives the near infrared spectrum probe to move to the upper side of the plastic, the near infrared spectrum signal of the plastic is collected and transmitted back to the computer, and the computer analyzes and identifies the spectrum to obtain the type information of the plastic. Compared with the prior art, the plastic identification system based on the near infrared spectrum realizes automation and intellectualization of plastic identification, and has the characteristics of high separation efficiency, high speed and low cost.

Description

一种基于近红外光谱的废弃塑料识别系统及方法A waste plastic identification system and method based on near-infrared spectroscopy

技术领域Technical field

本发明涉及无损检测设备生产领域，特别是在废品回收和环保产业中的生产领域，尤其涉及一种基于近红外光谱的废弃塑料识别系统及方法。The present invention relates to the field of non-destructive testing equipment production, especially in the production field of waste recycling and environmental protection industries, and in particular to a waste plastic identification system and method based on near-infrared spectrum.

背景技术Background technique

塑料凭借其低成本、易加工、耐用性强等一系列优点在生产生活中得到了广泛应用，是重要的基础材料。目前我国塑料行业发展迅速，大量塑料废弃物的不规范回收处置带来了极大的能源浪费，对环境造成了严重污染。目前我国的塑料制品回收主要依靠人工回收，这种回收方式效率低，对人体健康危害大。Plastic has been widely used in production and life due to its low cost, easy processing, strong durability and other advantages, and is an important basic material. At present, my country's plastics industry is developing rapidly. The non-standard recycling and disposal of a large amount of plastic waste has brought great waste of energy and caused serious pollution to the environment. At present, the recycling of plastic products in our country mainly relies on manual recycling, which is inefficient and harmful to human health.

同时目前废旧塑料分选识别的技术比较多样，但识别准确率低，测试耗时较长，精度不高，严重制约了塑料回收企业的生产能力。At the same time, the current technologies for sorting and identifying waste plastics are relatively diverse, but the identification accuracy is low, the testing takes a long time, and the accuracy is not high, which seriously restricts the production capacity of plastic recycling enterprises.

现有利用光谱信号对废弃塑料种类进行识别的方法有近红外高光谱成像法及单探头扫描成像法两种方法。检测方法虽然可以基本达到分拣的要求，但是至少存在以下不足：Existing methods for identifying waste plastic types using spectral signals include near-infrared hyperspectral imaging and single-probe scanning imaging. Although the detection method can basically meet the requirements of sorting, it has at least the following shortcomings:

一、检测成本高：近红外高光谱成像法的设备昂贵，废弃塑料识别系统的搭建成本很高，高于单探头系统。1. High detection cost: The equipment of the near-infrared hyperspectral imaging method is expensive, and the construction cost of the waste plastic identification system is very high, which is higher than that of a single-probe system.

二、检测效率低：单探头扫描成像法由于需要对整个识别区域进行逐点扫描，其耗费时间较长，检测速度慢，尤其不适合运动过程中废弃塑料的光谱采集。2. Low detection efficiency: Since the single-probe scanning imaging method needs to scan the entire identification area point by point, it takes a long time and has a slow detection speed. It is especially not suitable for spectral collection of waste plastics during movement.

发明内容Contents of the invention

本发明的目的在于克服上述现有技术的缺点和不足，提供一种实时、快速、低成本的基于近红外光谱的废弃塑料识别系统及方法。The purpose of the present invention is to overcome the shortcomings and deficiencies of the above-mentioned prior art and provide a real-time, fast, low-cost waste plastic identification system and method based on near-infrared spectrum.

本发明通过下述技术方案实现：The present invention is realized through the following technical solutions:

一种基于近红外光谱的废弃塑料识别系统，包括摄像头1、光谱探头2、传送平台3、计算机4、机械臂5；A waste plastic identification system based on near-infrared spectrum, including a camera 1, a spectrum probe 2, a transmission platform 3, a computer 4, and a robotic arm 5;

所述光谱探头2安装在机械臂5的端部；机械臂5用于采集传送平台3上待测样品的光谱信息，并将该光谱信息传递给计算机4；The spectrum probe 2 is installed at the end of the robotic arm 5; the robotic arm 5 is used to collect the spectral information of the sample to be measured on the transmission platform 3, and transfer the spectral information to the computer 4;

所述摄像头1用于采集指定区域的图像信息，并将该图像信息传递给计算机4。The camera 1 is used to collect image information of a designated area and transmit the image information to the computer 4 .

所述摄像头1、光谱探头2、机械臂5分别与计算机4信号连接。The camera 1, spectrum probe 2, and robotic arm 5 are respectively connected with the computer 4 via signals.

所述机械臂5带动光谱探头2能够平行于传送平台3的平面内移动。The mechanical arm 5 drives the spectrum probe 2 to move parallel to the plane of the transmission platform 3 .

所述摄像头1位于传送平台3上方，The camera 1 is located above the transmission platform 3,

所述计算机4对摄像头1传递来的信息进行分析，并识别待测样品位置。The computer 4 analyzes the information transmitted from the camera 1 and identifies the position of the sample to be tested.

所述计算机4向机械臂5发送动作信号，驱使光谱探头2运动至指定区域。The computer 4 sends an action signal to the robotic arm 5 to drive the spectrum probe 2 to move to a designated area.

一种基于近红外光谱的废弃塑料识别系统的识别方法，包括如下步骤：An identification method of a waste plastic identification system based on near-infrared spectroscopy, including the following steps:

待测样品随传送带被运送至传送平台3，位于传送平台3上的摄像头1探测到待测样品的图像信息，并将图像信息传输到计算机4；The sample to be tested is transported to the transfer platform 3 along with the conveyor belt. The camera 1 located on the transfer platform 3 detects the image information of the sample to be tested and transmits the image information to the computer 4;

计算机4处理待测样品的图像信息，获得其位于传送带上的实时位置，计算待测样品与光谱探头2的相对位置；The computer 4 processes the image information of the sample to be tested, obtains its real-time position on the conveyor belt, and calculates the relative position of the sample to be tested and the spectrum probe 2;

机械臂5驱动光谱探头2迅速移动到待测样品正上方并采集其光谱信息，将光谱信息传输到计算机4；The robotic arm 5 drives the spectrum probe 2 to quickly move directly above the sample to be measured and collects its spectral information, and transmits the spectral information to the computer 4;

计算机4将采集待测样品的光谱信息与预训练的机器算法模型数据做比对，提取待测样品的材料种类信息。Computer 4 compares the collected spectral information of the sample to be tested with the pre-trained machine algorithm model data, and extracts the material type information of the sample to be tested.

所述图像信息的处理分析流程为：The image information processing and analysis flow is:

将待测样品的位置信息转换为实际世界坐标系中的位置信息；Convert the position information of the sample to be tested into position information in the actual world coordinate system;

对相机内外部参数进行标定，进行畸变矫正及坐标系矩阵变换，得到像素点在绝对坐标系中的位置；Calibrate the internal and external parameters of the camera, perform distortion correction and coordinate system matrix transformation, and obtain the position of the pixel in the absolute coordinate system;

将采集的图像进行预处理，即采用滤波及二值化处理；Preprocess the collected images, that is, use filtering and binarization;

计算预处理后的图像信息以获得待测样品的轮廓与形心位置。Calculate the preprocessed image information to obtain the contour and centroid position of the sample to be tested.

所述预训练的机器算法模型数据做比对流程为：The comparison process of the pre-trained machine algorithm model data is:

将采集的光谱数据进行预处理，保留光谱有效信息；Preprocess the collected spectral data to retain effective spectral information;

将预处理后的光谱数据进行组合分类算法建模；Model the preprocessed spectral data using a combined classification algorithm;

将采集到的光谱数据输入到机器算法模型中得到其预测的类别；Input the collected spectral data into the machine algorithm model to obtain its predicted category;

根据预测类型控制下位机对塑料进行筛选分拣。According to the prediction type, the lower computer is controlled to screen and sort the plastics.

所述光谱数据的预处理为导数处理、光滑处理或者主成分分析。The preprocessing of the spectral data is derivative processing, smoothing processing or principal component analysis.

本发明相对于现有技术，具有如下的优点及效果：Compared with the existing technology, the present invention has the following advantages and effects:

本系统将单光谱探头与机械臂相结合形成塑料快速识别系统，克服了单光谱探头扫描成像所花费时间长和近红外高光谱成像的设备成本高的缺点，实现了运动过程中塑料待测样品的快速检测。与传统的光谱识别系统相比，本系统实现快速、低成本、智能化塑料识别，提高了识别效率，降低成本。This system combines a single-spectrum probe with a robotic arm to form a rapid identification system for plastics. It overcomes the shortcomings of the long scanning imaging time of the single-spectrum probe and the high equipment cost of near-infrared hyperspectral imaging, and realizes the identification of plastic samples to be tested during movement. rapid detection. Compared with traditional spectral identification systems, this system achieves fast, low-cost, and intelligent plastic identification, improves identification efficiency, and reduces costs.

依托机器学习算法实现分拣塑料制品的精准识别，大大提高对废弃塑料制品种类识别的速度与准确率。在实际分拣识别过程中，将会有大量废弃塑料的光谱和图像数据被采集捕获，本发明所搭建的系统将会对实际获得的有利于识别分拣的有效信息进行筛选和保留，不断扩充、丰富建模数据，从而提高分拣的效率和精度。Relying on machine learning algorithms to achieve accurate identification of sorted plastic products, it greatly improves the speed and accuracy of identifying types of waste plastic products. In the actual sorting and identification process, a large amount of spectral and image data of waste plastics will be collected and captured. The system built by the present invention will screen and retain the actually obtained effective information that is beneficial to identification and sorting, and continuously expand it. , enrich modeling data to improve sorting efficiency and accuracy.

附图说明Description of the drawings

图1为本发明基于近红外光谱的废弃塑料识别系统结构示意图。Figure 1 is a schematic structural diagram of the waste plastic identification system based on near-infrared spectrum of the present invention.

具体实施方式Detailed ways

下面结合具体实施例对本发明作进一步具体详细描述。The present invention will be further described in detail below with reference to specific embodiments.

一种基于近红外光谱的废弃塑料识别系统，包括摄像头1、光谱探头2、传送平台3、计算机4、机械臂5；A waste plastic identification system based on near-infrared spectrum, including a camera 1, a spectrum probe 2, a transmission platform 3, a computer 4, and a robotic arm 5;

所述光谱探头2安装在机械臂5的端部；机械臂5用于采集传送平台3上待测样品的光谱信息，并将该光谱信息传递给计算机4；The spectrum probe 2 is installed at the end of the robotic arm 5; the robotic arm 5 is used to collect the spectral information of the sample to be measured on the transmission platform 3, and transfer the spectral information to the computer 4;

所述摄像头1用于采集指定区域的图像信息，并将该图像信息传递给计算机4。The camera 1 is used to collect image information of a designated area and transmit the image information to the computer 4 .

所述摄像头1、光谱探头2、机械臂5分别与计算机4信号连接。The camera 1, spectrum probe 2, and robotic arm 5 are respectively connected with the computer 4 via signals.

所述机械臂5带动光谱探头2能够平行于传送平台3的平面内移动。The mechanical arm 5 drives the spectrum probe 2 to move parallel to the plane of the transmission platform 3 .

所述摄像头1位于传送平台3上方，The camera 1 is located above the transmission platform 3,

所述计算机4对摄像头1传递来的信息进行分析，并识别待测样品位置。The computer 4 analyzes the information transmitted from the camera 1 and identifies the position of the sample to be tested.

所述计算机4向机械臂5发送动作信号，驱使光谱探头2运动至指定区域。The computer 4 sends an action signal to the robotic arm 5 to drive the spectrum probe 2 to move to a designated area.

塑料通过传送平台3向前输送；摄像头1采集传送平台图像信息；计算机4接收图像信号并分析待测样品的位置信息；计算机4向机械臂5发出动作信号，将光谱探头2移动至待测样品上方；光谱探头2采集待测样品光谱信号；计算机4分析光谱信号，提取待测样品材料种类信息，与预训练的机器算法模型数据做比对，对其所属可能的类别做标记并进行可视化展示。The plastic is transported forward through the transmission platform 3; the camera 1 collects the image information of the transmission platform; the computer 4 receives the image signal and analyzes the position information of the sample to be tested; the computer 4 sends an action signal to the robotic arm 5 and moves the spectrum probe 2 to the sample to be tested Above; the spectrum probe 2 collects the spectral signal of the sample to be tested; the computer 4 analyzes the spectral signal, extracts the material type information of the sample to be tested, compares it with the pre-trained machine algorithm model data, marks its possible categories and displays them visually .

一种基于近红外光谱的废弃塑料识别系统的识别方法，可通过如下步骤实现：An identification method of a waste plastic identification system based on near-infrared spectroscopy can be achieved through the following steps:

待测样品随传送带被运送至传送平台3，位于传送平台3上的摄像头1探测到待测样品的图像信息，并将图像信息传输到计算机4；The sample to be tested is transported to the transfer platform 3 along with the conveyor belt. The camera 1 located on the transfer platform 3 detects the image information of the sample to be tested and transmits the image information to the computer 4;

计算机4处理待测样品的图像信息，获得其位于传送带上的实时位置，计算待测样品与光谱探头2的相对位置；The computer 4 processes the image information of the sample to be tested, obtains its real-time position on the conveyor belt, and calculates the relative position of the sample to be tested and the spectrum probe 2;

机械臂5驱动光谱探头2迅速移动到待测样品正上方并采集其光谱信息，将光谱信息传输到计算机4；The robotic arm 5 drives the spectrum probe 2 to quickly move directly above the sample to be measured and collects its spectral information, and transmits the spectral information to the computer 4;

计算机4将采集待测样品的光谱信息与预训练的机器算法模型数据做比对，提取待测样品的材料种类信息。Computer 4 compares the collected spectral information of the sample to be tested with the pre-trained machine algorithm model data, and extracts the material type information of the sample to be tested.

所述图像信息的处理分析流程为：The image information processing and analysis flow is:

将待测样品的位置信息转换为实际世界坐标系中的位置信息；Convert the position information of the sample to be tested into position information in the actual world coordinate system;

对相机内外部参数进行标定，进行畸变矫正及坐标系矩阵变换，得到像素点在绝对坐标系中的位置；Calibrate the internal and external parameters of the camera, perform distortion correction and coordinate system matrix transformation, and obtain the position of the pixel in the absolute coordinate system;

将采集的图像进行预处理，即采用滤波及二值化处理；Preprocess the collected images, that is, use filtering and binarization;

计算预处理后的图像信息以获得待测样品的轮廓与形心位置。Calculate the preprocessed image information to obtain the contour and centroid position of the sample to be tested.

所述预训练的机器算法模型数据做比对流程为：The comparison process of the pre-trained machine algorithm model data is:

将采集的光谱数据进行预处理，保留光谱有效信息；Preprocess the collected spectral data to retain effective spectral information;

将预处理后的光谱数据进行组合分类算法建模；Model the preprocessed spectral data using a combined classification algorithm;

将采集到的光谱数据输入到机器算法模型中得到其预测的类别；Input the collected spectral data into the machine algorithm model to obtain its predicted category;

根据预测类型控制下位机对塑料进行筛选分拣。According to the prediction type, the lower computer is controlled to screen and sort the plastics.

所述光谱数据的预处理为导数处理、光滑处理或者主成分分析。The preprocessing of the spectral data is derivative processing, smoothing processing or principal component analysis.

如上所述，便可较好地实现本发明。As described above, the present invention can be better implemented.

本发明的实施方式并不受上述实施例的限制，其他任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化，均应为等效的置换方式，都包含在本发明的保护范围之内。The implementation of the present invention is not limited to the above-mentioned embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent substitutions and are included in within the protection scope of the present invention.

Claims (10)

1.一种基于近红外光谱的废弃塑料识别系统，其特征在于，包括摄像头(1)、光谱探头(2)、传送平台(3)、计算机(4)、机械臂(5)；1. A waste plastic identification system based on near-infrared spectrum, characterized by including a camera (1), a spectrum probe (2), a transmission platform (3), a computer (4), and a robotic arm (5); 所述光谱探头(2)安装在机械臂(5)的端部；机械臂(5)用于采集传送平台(3)上待测样品的光谱信息，并将该光谱信息传递给计算机(4)；The spectrum probe (2) is installed at the end of the robotic arm (5); the robotic arm (5) is used to collect spectral information of the sample to be measured on the transmission platform (3), and transfer the spectral information to the computer (4) ; 所述摄像头(1)用于采集指定区域的图像信息，并将该图像信息传递给计算机(4)。The camera (1) is used to collect image information of a designated area and transfer the image information to the computer (4). 2.根据权利要求1所述基于近红外光谱的废弃塑料识别系统，其特征在于，所述摄像头(1)、光谱探头(2)、机械臂(5)分别与计算机(4)信号连接。2. The waste plastic identification system based on near-infrared spectrum according to claim 1, characterized in that the camera (1), spectrum probe (2), and robotic arm (5) are respectively connected with the computer (4) via signals. 3.根据权利要求2所述基于近红外光谱的废弃塑料识别系统，其特征在于，所述机械臂(5)带动光谱探头(2)能够平行于传送平台(3)的平面内移动。3. The waste plastic identification system based on near-infrared spectrum according to claim 2, characterized in that the mechanical arm (5) drives the spectrum probe (2) to move parallel to the plane of the transmission platform (3). 4.根据权利要求2所述基于近红外光谱的废弃塑料识别系统，其特征在于，所述摄像头(1)位于传送平台(3)上方。4. The waste plastic identification system based on near-infrared spectrum according to claim 2, characterized in that the camera (1) is located above the transfer platform (3). 5.根据权利要求2所述基于近红外光谱的废弃塑料识别系统，其特征在于，所述计算机(4)对摄像头(1)传递来的信息进行分析，并识别待测样品位置。5. The waste plastic identification system based on near-infrared spectrum according to claim 2, characterized in that the computer (4) analyzes the information transmitted by the camera (1) and identifies the position of the sample to be tested. 6.根据权利要求2所述基于近红外光谱的废弃塑料识别系统，其特征在于，所述计算机(4)向机械臂(5)发送动作信号，驱使光谱探头(2)运动至指定区域。6. The waste plastic identification system based on near-infrared spectrum according to claim 2, characterized in that the computer (4) sends an action signal to the mechanical arm (5) to drive the spectrum probe (2) to move to a designated area. 7.权利要求1-6中任一项所述基于近红外光谱的废弃塑料识别系统的识别方法，其特征在于包括如下步骤：7. The identification method of the waste plastic identification system based on near-infrared spectrum according to any one of claims 1-6, characterized in that it includes the following steps: 待测样品随传送带被运送至传送平台(3)，位于传送平台(3)上的摄像头(1)探测到待测样品的图像信息，并将图像信息传输到计算机(4)；The sample to be tested is transported to the transfer platform (3) along with the conveyor belt. The camera (1) located on the transfer platform (3) detects the image information of the sample to be tested and transmits the image information to the computer (4); 计算机(4)处理待测样品的图像信息，获得其位于传送带上的实时位置，计算待测样品与光谱探头(2)的相对位置；The computer (4) processes the image information of the sample to be tested, obtains its real-time position on the conveyor belt, and calculates the relative position of the sample to be tested and the spectrum probe (2); 机械臂(5)驱动光谱探头(2)迅速移动到待测样品正上方并采集其光谱信息，将光谱信息传输到计算机(4)；The robotic arm (5) drives the spectrum probe (2) to quickly move directly above the sample to be measured and collects its spectral information, and transmits the spectral information to the computer (4); 计算机(4)将采集待测样品的光谱信息与预训练的机器算法模型数据做比对，提取待测样品的材料种类信息。The computer (4) compares the collected spectral information of the sample to be tested with the pre-trained machine algorithm model data, and extracts the material type information of the sample to be tested. 8.根据权利要求7所述基于近红外光谱的废弃塑料识别系统的识别方法，其特征在于：所述图像信息的处理分析流程为：8. The identification method of the waste plastic identification system based on near-infrared spectrum according to claim 7, characterized in that: the processing and analysis flow of the image information is: 将待测样品的位置信息转换为实际世界坐标系中的位置信息；Convert the position information of the sample to be tested into position information in the actual world coordinate system; 对相机内外部参数进行标定，进行畸变矫正及坐标系矩阵变换，得到像素点在绝对坐标系中的位置；Calibrate the internal and external parameters of the camera, perform distortion correction and coordinate system matrix transformation, and obtain the position of the pixel in the absolute coordinate system; 将采集的图像进行预处理，即采用滤波及二值化处理；Preprocess the collected images, that is, use filtering and binarization; 计算预处理后的图像信息以获得待测样品的轮廓与形心位置。Calculate the preprocessed image information to obtain the contour and centroid position of the sample to be tested. 9.根据权利要求7所述基于近红外光谱的废弃塑料识别系统的识别方法，其特征在于：所述预训练的机器算法模型数据做比对流程为：9. The identification method of the waste plastic identification system based on near infrared spectrum according to claim 7, characterized in that: the pre-trained machine algorithm model data comparison process is: 将采集的光谱数据进行预处理，保留光谱有效信息；Preprocess the collected spectral data to retain effective spectral information; 将预处理后的光谱数据进行组合分类算法建模；Model the preprocessed spectral data using a combined classification algorithm; 将采集到的光谱数据输入到机器算法模型中得到其预测的类别；Input the collected spectral data into the machine algorithm model to obtain its predicted category; 根据预测类型控制下位机对塑料进行筛选分拣。According to the prediction type, the lower computer is controlled to screen and sort the plastics. 10.根据权利要求9所述基于近红外光谱的废弃塑料识别系统的识别方法，其特征在于：所述光谱数据的预处理为导数处理、光滑处理或者主成分分析。10. The identification method of the waste plastic identification system based on near-infrared spectrum according to claim 9, characterized in that: the preprocessing of the spectral data is derivative processing, smoothing processing or principal component analysis.
CN202310718011.2A 2023-06-16 2023-06-16 A waste plastic identification system and method based on near-infrared spectroscopy Pending CN117129439A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310718011.2A CN117129439A (en) 2023-06-16 2023-06-16 A waste plastic identification system and method based on near-infrared spectroscopy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310718011.2A CN117129439A (en) 2023-06-16 2023-06-16 A waste plastic identification system and method based on near-infrared spectroscopy

Publications (1)

Publication Number Publication Date
CN117129439A true CN117129439A (en) 2023-11-28

Family

ID=88849856

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310718011.2A Pending CN117129439A (en) 2023-06-16 2023-06-16 A waste plastic identification system and method based on near-infrared spectroscopy

Country Status (1)

Country Link
CN (1) CN117129439A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101881725A (en) * 2010-06-11 2010-11-10 浙江大学 Automatic Monitoring System of Greenhouse Crop Growth Status Based on Reflectance Spectrum
CN112693032A (en) * 2020-12-10 2021-04-23 上海大学 High-flux intelligent sorting method and system for recycling waste plastics
US20220331841A1 (en) * 2021-04-16 2022-10-20 Digimarc Corporation Methods and arrangements to aid recycling
CN116106253A (en) * 2023-03-07 2023-05-12 福建师范大学 Rapid and intelligent classification method for living source waste plastics based on machine learning
CN220271166U (en) * 2023-06-16 2023-12-29 华南理工大学 A waste plastic identification system based on near-infrared spectroscopy

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101881725A (en) * 2010-06-11 2010-11-10 浙江大学 Automatic Monitoring System of Greenhouse Crop Growth Status Based on Reflectance Spectrum
CN112693032A (en) * 2020-12-10 2021-04-23 上海大学 High-flux intelligent sorting method and system for recycling waste plastics
US20220331841A1 (en) * 2021-04-16 2022-10-20 Digimarc Corporation Methods and arrangements to aid recycling
CN116106253A (en) * 2023-03-07 2023-05-12 福建师范大学 Rapid and intelligent classification method for living source waste plastics based on machine learning
CN220271166U (en) * 2023-06-16 2023-12-29 华南理工大学 A waste plastic identification system based on near-infrared spectroscopy

Similar Documents

Publication Publication Date Title
CN110806736B (en) A method for detecting quality information of forgings in intelligent manufacturing production line of die forging
CN105699258B (en) A kind of fine aggregate on-line measuring device and method
CN110458807A (en) A Machine Vision Detection System for Railway Track Defects
CN109261539B (en) A garbage sorting system and method based on visual recognition and convolutional neural network
CN111266304B (en) A coal block identification, detection and sorting system
CN108971190A (en) A kind of separating domestic garbage method based on machine vision
CN114252452A (en) Apparatus and method for on-line detection of appearance defects and contour dimensions of a small rotary body
CN106238342A (en) The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof
CN105548185A (en) Automobile wheel hub screw hole recognition method based on machine vision and shielding method and system
CN104056790A (en) Intelligent potato sorting method and apparatus
CN220271166U (en) A waste plastic identification system based on near-infrared spectroscopy
CN102980892B (en) On-line examination system and method for steel pipe
CN114581782A (en) Fine defect detection method based on coarse-to-fine detection strategy
CN113487570A (en) High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model
CN110665848A (en) Construction solid waste sorting system based on CCD camera and hyperspectral camera detection
CN111784688A (en) Flower automatic grading method based on deep learning
CN116777836A (en) A multimodal data-driven quality inspection method for injection molding process products
CN113245222B (en) Visual real-time detection and sorting system and sorting method for foreign matters in panax notoginseng
CN114511519A (en) An image processing-based detection method for missing bolts at the bottom of trains
CN204440490U (en) An online detection device for surface defects of shaft sleeve parts based on compressive sensing
CN117893812A (en) A method for quickly identifying degradable plastics and a recycling device
CN119303860A (en) An intelligent picking method for defective red dates
CN110716033B (en) Method and device for rapid evaluation of impurities in seed cotton during the purchasing process
CN207081666U (en) A kind of zipper detecting device based on machine vision
CN117129439A (en) A waste plastic identification system and method based on near-infrared spectroscopy

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载