Sensor-based Particle Size Determination of Shredded Mixed Commercial Waste based on two-dimensional Images

Kandlbauer, Lisa; Khodier, Karim; Ninevski, Dimitar; Šarc, Renato

doi:10.1016/j.wasman.2020.11.003

Cited by 13 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complexity and versatility of the studied properties of recyclable materials favorably distinguish this study from alternative studies [5,[17][18][19][20][21][22] making its results more indicative and practically significant for implementation into real process flowsheets of waste processing. Thus, practical application of the information obtained about the above conclusions and the regularities of changes in technical properties of recyclables solves the identified scientific and practical problem of expanding the base of theoretical and practical data on technical parameters of various compositions of industrial and household SCW with an increase in efficiency of the process of fuel briquette manufacture.…”

Section: Analysis Of the Results Of The Experimental Study Of The mentioning

confidence: 99%

“…At the same time, the issue of strength of final briquettes and the influence of pressing on them is not touched upon, especially for the case of using raw materials with a variable morphological and granulometric composition. The need to assess particle size distribution in solid waste is considered in [17]. The particle size distribution in such waste as polymers, sawdust, unsorted residues, etc.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Improving the efficiency of equipment and technology of waste briquetting

Bondarenko

Kutniashenko

Toporov

et al. 2020

EEJET

View full text Add to dashboard Cite

Section: Analysis Of the Results Of The Experimental Study Of The mentioning

confidence: 99%

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Improving the efficiency of equipment and technology of waste briquetting

Bondarenko

Kutniashenko

Toporov

et al. 2020

EEJET

View full text Add to dashboard Cite

“…Viczek et al 2021b), indicating that the element is well distributed in the waste material. This is likely to result from the broad range of applications of titanium dioxide (TiO 2 ), which is present in most white or brightly tinted items, including paints, plastics, fibers, paper or cardboard, enamels, or ceramics (Holleman et al 2007).…”

Section: Rsvs For Different Elementsmentioning

confidence: 99%

“…Overall, the results show that a correlation between material composition and element concentration is recognizable, which might allow calculating chemical parameters based on information from, e.g., an NIR sorter combined with a model for sensor-based particle size determination. The latter was investigated on single particles in a mixed commercial waste stream by Kandlbauer et al (2020). This combination could enable the evaluation of chemical properties without the expensive and time-consuming act of sampling, sample preparation, and chemical analysis since the information regarding material and particle size from NIR sorters and sensor-based particle size determination models could be evaluated, while the material is still in the treatment process (in-line analytics).…”

Section: Study Limitationsmentioning

confidence: 99%

Sampling and analysis of coarsely shredded mixed commercial waste. Part II: particle size-dependent element determination

Viczek

Kandlbauer

Khodier

et al. 2021

Int. J. Environ. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

In contemporary waste management, sampling of waste is essential whenever a specific parameter needs to be determined. Although sensor-based continuous analysis methods are being developed and enhanced, many parameters still require conventional analytics. Therefore, sampling procedures that provide representative samples of waste streams and enable sufficiently accurate analysis results are crucial. While Part I estimated the relative sampling variabilities for material classes in a replication experiment, Part II focuses on relative sampling variabilities for 30 chemical elements and the lower heating value of the same samples, i.e., 10 composite samples screened to yield 9 particle size classes (< 5 mm–400 mm). Variabilities < 20% were achieved for 39% of element-particle size class combinations but ranged up to 203.5%. When calculated for the original composite samples, variabilities < 20% were found for 57% of the analysis parameters. High variabilities were observed for elements that are expectedly subject to high constitutional heterogeneity. Besides depending on the element, relative sampling variabilities were found to depend on particle size and the mass of the particle size fraction in the sample. Furthermore, Part I and Part II results were combined, and the correlations between material composition and element concentrations in the particle size classes were interpreted and discussed. For interpretation purposes, log-ratios were calculated from the material compositions. They were used to build a regression model predicting element concentration based on material composition only. In most cases, a prediction accuracy of ± 20% of the expected value was reached, implying that a mathematical relationship exists.

show abstract

“…image descriptors, to find image signatures (feature vectors), auto-correlation, circular filters and granulometry (a set of morphological filters at different scales). Kandlbauer et al [8] analysed individual waste particle images with a set of image transformations to detect particles and a regression model to estimate sizes. Zhang et al [9] and Dunnu et al [10] used dimensionless coefficients, e.g.…”

Section: Related Workmentioning

confidence: 99%

Particle Size Estimation in Mixed Commercial Waste Images Using Deep Learning

Kittiworapanya¹,

Pasupa²,

Auer³

2021

Preprint

View full text Add to dashboard Cite

<div>This work was presented at the 10th Joint Symposium on Computational Intelligence (JSCI10), organized by the IEEE-CIS Thailand Chapter, that aims to support research students and young researchers, to create a place enabling participants to share and discuss on their research prior to publishing their works. The event was open to all researchers who want to broaden their knowledge in the field of computational intelligence.<br></div><div><br></div><div>We assessed several state-of-the-art deep learning algorithms and computer vision techniques for estimating the particle size of mixed commercial waste from images. In waste management, the first step is often coarse shredding, using the particle size to set up the shredder machine. The difficulty is separating the waste particles in an image, which can not be performed well. This work focused on estimating size by using the texture from the input image, captured at a fixed height from the camera lens to the ground. We found that EfficientNet achieved the best performance of 0.72 on F1-Score and 75.89% on accuracy.<br></div>

show abstract

Sensor-based Particle Size Determination of Shredded Mixed Commercial Waste based on two-dimensional Images

Cited by 13 publications

References 19 publications

Improving the efficiency of equipment and technology of waste briquetting

Improving the efficiency of equipment and technology of waste briquetting

Sampling and analysis of coarsely shredded mixed commercial waste. Part II: particle size-dependent element determination

Particle Size Estimation in Mixed Commercial Waste Images Using Deep Learning

Contact Info

Product

Resources

About