Research on the classification algorithm and operation parameters optimization of the system for separating non-ferrous metals from end-of-life vehicles based on machine vision

Wang, Chao; Hu, Zhili; Pang, Qiu; Hua, Lin

doi:10.1016/j.wasman.2019.08.043

Cited by 21 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to other techniques, optical-based sorting technology mainly focuses on the visual characteristics of metal scraps. Few previous works have been devoted to this area, and the existing identification methods mostly focus on mere colour information or feeding handcrafted features, such as chrominance and texture values, into a traditional machine learning algorithm (Kutila et al, 2005; Wang et al, 2019). However, these manually extracted features do not guarantee the best description of the input data for machine learning classification models due to the complexity of the industry environment.…”

Section: Introductionmentioning

confidence: 99%

A robust identification method for nonferrous metal scraps based on deep learning and superpixel optimization

Qin

Zhang

et al. 2021

Waste Manag Res

View full text Add to dashboard Cite

End-of-life vehicles (ELVs) provide a particularly potent source of supply for metals. Hence, the recycling and sorting techniques for ferrous and nonferrous metal scraps from ELVs significantly increase metal resource utilization. However, different kinds of nonferrous metal scraps, such as aluminium (Al) and copper (Cu), are not further automatically classified due to the lack of proper techniques. The purpose of this study is to propose an identification method for different nonferrous metal scraps, facilitate the further separation of nonferrous metal scraps, achieve better management of recycled metal resources and increase sustainability. A convolutional neural network (CNN) and SEEDS (superpixels extracted via energy-driven sampling) were adopted in this study. To build the classifier, 80 training images of randomly chosen Al and Cu scraps were taken, and some practical methods were proposed, including training patch generation with SEEDS, image data augmentation and automatic labelling methods for enormous training data. To obtain more accurate results, SEEDS was also used to optimize the coarse results obtained from the pretrained CNN model. Five indicators were adopted to evaluate the final identification results. Furthermore, 15 test samples concerning different classification environments were tested through the proposed model, and it performed well under all of the employed evaluation indexes, with an average precision of 0.98. The results demonstrate that the proposed model is robust for metal scrap identification, which can be expanded to a complex industrial environment, and it presents new possibilities for highly accurate automatic nonferrous metal scrap classification.

show abstract

Section: Introductionmentioning

confidence: 99%

A robust identification method for nonferrous metal scraps based on deep learning and superpixel optimization

Qin

Zhang

et al. 2021

Waste Manag Res

View full text Add to dashboard Cite

show abstract

“…Manual sorting still exists in developing countries with low labor costs. However, with the gradual increase in labor cost and concerns for health, automatic sorting is becoming popular [1][2][3][4][5][6]. Automated waste sorting technology can be classified into two types: direct sorting and indirect sorting [1].…”

Section: Introduction 1backgroundmentioning

confidence: 99%

“…Indirect sorting involves two steps, the first step is identification, dependent on various sensors such as color or grayscale machine vision, X-ray transmission (XRT), X-ray fluorescence (XRF), laser-induced breakdown spectroscopy (LIBS), electromagnetic sensor (EMS), spectroscopy, etc. [4,[13][14][15][16]. The second step is separation based on the identification results.…”

Section: Introduction 1backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Combination of Dual-Energy X-ray Transmission and Variable Gas-Ejection for the In-Line Automatic Sorting of Many Types of Scrap in One Measurement

Tian-zhong

2021

Applied Sciences

View full text Add to dashboard Cite

As an important part of pretreatment before recycling, sorting has a great impact on the quality, efficiency, cost and difficulty of recycling. In this paper, dual-energy X-ray transmission (DE-XRT) combined with variable gas-ejection is used to improve the quality and efficiency of in-line automatic sorting of waste non-ferrous metals. A method was proposed to judge the sorting ability, identify the types, and calculate the mass and center-of-gravity coordinates according to the shading of low-energy, the line scan direction coordinate and transparency natural logarithm ratio of low energy to high energy (R_value). The material identification was satisfied by the nearest neighbor algorithm of effective points in the material range to the R_value calibration surface. The flow-process of identification was also presented. Based on the thickness of the calibration surface, the material mass and center-of-gravity coordinates were calculated. The feasibility of controlling material falling points by variable gas-ejection was analyzed. The experimental verification of self-made materials showed that identification accuracy by count basis was 85%, mass and center-of-gravity coordinates calculation errors were both below 5%. The method proposed features high accuracy, high efficiency, and low operation cost and is of great application value even to other solid waste sorting, such as plastics, glass and ceramics.

show abstract

“…The role of particle shape in a granular systems and the technical difficulties presented when modelling particle shapes are discussed in Garboczi et al (2017) and Peña et al (2007). For simplicity, many researchers in the field of waste management have carried out simulation using some basic shapes, such as sphere and cube, to represent the realistic particles (Gao et al, 2020; Pita and Castilho, 2017; Wang et al, 2019). In the review by Lu et al (2015), different non-spherical particle models, including polygon formulations, super-quadric equations, and composite techniques, were described and analyzed.…”

Section: Introductionmentioning

confidence: 99%

Solid waste shape description and generation based on spherical harmonics and probability density function

Qin

Zhang

et al. 2021

Waste Manag Res

View full text Add to dashboard Cite

Transport and separation processes of solid waste can only be modelled successfully with discrete element methods in case the shape of the particles can be described accurately. The existing techniques for morphological data acquisition, such as computed tomography, laser scanning technique, optical interferometer, stereo photography and structured light technique, are laborious and require a large amount of realistic solid waste samples. Therefore, there is a pressing need for an alternative method to describe the shape of solid waste particles and to generate multiple variations of particles with almost similar shapes. In this paper, a new method to describe solid waste particles is proposed that is frequency-based and uses spherical harmonics (SHs). Additionally, a new shape generation method is introduced that uses the shape description of a single particle to generate an array of related shapes based on a probability density function with a dimensionless control factor η. The newly proposed methods were successfully applied to describe the complex shapes of pieces of metal and plastic scrap. The shapes of these pieces of scrap can be described adequately with 15° of SH expansion and the overall divergence is within 0.1 mm. Five different values for η were tested, which generated shapes with the same distribution as the original particle. Rising levels of η cause the morphological variation of the generated particles to increase. These new methods improve the modelling of transportation and separation processes.

show abstract

Research on the classification algorithm and operation parameters optimization of the system for separating non-ferrous metals from end-of-life vehicles based on machine vision

Cited by 21 publications

References 18 publications

A robust identification method for nonferrous metal scraps based on deep learning and superpixel optimization

A robust identification method for nonferrous metal scraps based on deep learning and superpixel optimization

Combination of Dual-Energy X-ray Transmission and Variable Gas-Ejection for the In-Line Automatic Sorting of Many Types of Scrap in One Measurement

Solid waste shape description and generation based on spherical harmonics and probability density function

Contact Info

Product

Resources

About