Prediction of municipal solid waste generation: an investigation of the effect of clustering techniques and parameters on ANFIS model performance.

The present waste-management system in most developing countries are insufficient to combat the challenge of increasing rate of solid waste generation. Accurate prediction of waste generated through modelling approach will help to overcome the challenge of deficient-planning of sustainable waste-management. In modelling the complexity within a system, a paradigm-shift from classical-model to artificial intelligent model has been necessitated. Previous researches which used Adaptive Neuro-Fuzzy Inference System (ANFIS) for waste generation forecast did not investigate the effect of clustering-techniques and parameters on the performance of the model despite its significance in achieving accurate prediction. This study therefore investigates the impact of the parameters of three clustering-technique namely: Fuzzy c-means (FCM), Grid-Partitioning (GP) and Subtractive-Clustering (SC) on the performance of the ANFIS model in predicting waste generation using South Africa as a case study. Socio-economic and demographic provincial-data for the period 2008-2016 were used as input-variables and provincial waste quantities as output-variable. ANFIS model clustered with GP using triangular input membership-function (tri-MF) and a linear type output membership-function (ANFIS-GP1) is the optimal model with Mean Absolute Percentage Error (MAPE), Mean Absolute Deviation (MAD), Root Mean Square Error (RMSE) and Correlation Co-efficient (R2) values of 12.6727, 0.6940, 1.2372 and 0.9392 respectively. Based on the result in this study, ANFIS-GP with a triangular membership-function is recommended for modelling waste generation. The tool presented in this study can be utilized for the national repository of waste generation data by the South Africa Waste Information Centre (SAWIC) in South Africa and in other developing countries.

Environmental impact assessment of the current, emerging, and alternative waste management systems using life cycle assessment tools: a case study of Johannesburg, South Africa.

Proper information regarding the performance of waste management systems from an environmental perspective is significant to sustainable waste management decisions and planning toward the selection of the least impactful treatment options. However, little is known about the environmental impacts of the different waste management options in South Africa. This study is therefore aimed at using the life cycle assessment tool to assess the environmental impact of the current, emerging, and alternative waste management systems in South Africa, using the city of Johannesburg as a case study. This assessment involves a comparative analysis of the unit processes of waste management and the different waste management scenarios comprising two or more unit processes from an environmental view. The lifecycle boundary consists of unit processes: waste collection and transportation (WC&T), material recycling facilities (MRF), composting, incineration, and landfilling. Four scenarios developed for the assessment are S1 (WC&T, MRF, and landfilling without energy recovery), S2 (WC&T, MRF, composting, and landfilling with energy recovery), S3 (WC&T and incineration), and S4 (WC&T, MRF, composting, and incineration). Based on the result of this study, MRF is the most environmentally beneficial unit operation while landfill without energy recovery is the most impactful unit operation. The result further revealed that no scenario had the best performance across all the impact categories. However, S3 can be considered as the most environmentally friendly option owing to its lowest impact in most of the impact categories. S3 has the lowest global warming potential (GWP) of 33.19 × 106 kgCO2eq, ozone depletion potential (ODP) of 0.563 kgCFC-11e, and photochemical ozone depletion potential (PODP) of 679.46 kgC2H2eq. Also, S4 can be regarded as the most impactful option owing to its highest contributions to PODP of 1044 kgC2H2eq, acidification potential (AP) of 892073.8 kgSO2eq, and eutrophication potential (EP) of 51292.98 MaxPO4-3eq. The result of this study will be found helpful in creating a complete impression of the environmental performance of waste management systems in Johannesburg, South Africa which will aid sustainable planning and decisions by the concerned sector.

Application of artificial neural networks for predicting the physical composition of municipal solid waste: An assessment of the impact of seasonal variation.

Sustainable planning of waste management is contingent on reliable data on waste characteristics and their variation across the seasons owing to the consequential environmental impact of such variation. Traditional waste characterization techniques in most developing countries are time-consuming and expensive; hence the need to address the issue from a modelling approach arises. In modelling the complexity within the system, a paradigm shift from the classical models to the intelligent models has been observed. The application of artificial intelligence models in waste management is gaining traction; however its application in predicting the physical composition of waste is still lacking. This study aims at investigating the optimal combinations of network architecture, training algorithm and activation functions that accurately predict the fraction of physical waste streams from meteorological parameters using artificial neural networks. The city of Johannesburg was used as a case study. Maximum temperature, minimum temperature, wind speed and humidity were used as input variables to predict the percentage composition of organic, paper, plastics and textile waste streams. Several sub-models were stimulated with combination of nine training algorithms and four activation functions in each single hidden layer topology with a range of 1-15 neurons. Performance metrics used to evaluate the accuracy of the system are, root mean square error, mean absolute deviation, mean absolute percentage error and correlation coefficient (R). Optimal architectures in the order of input layer-number of neurons in the hidden layer-output layer for predicting organic, paper, plastics and textile waste were 4-10-1, 4-14-1, 4-5-1 and 4-8-1 with R-values of 0.916, 0.862, 0.834 and 0.826, respectively at the testing phase. The result of the study verifies that waste composition prediction can be done in a single hidden-layer satisfactorily.

Comprehensive data on the mechanical properties and biodegradation profile of polylactide composites developed for hard tissue repairs.

Polylactide (PLA), a biopolymer, was reinforced with three fillers (two organic reinforcements and one inorganic filler). The processing technique used to fabricate the composites was the melt-blending technique. The composites and the unreinforced PLA were subjected to microhardness, compression and biodegradation characterisations. Data obtained are presented in this article as raw data. Data from microhardness and compression tests were used to predict the fracture toughness. The biodegradation of the composites was also examined, and the data obtained reported in this article. The data presented in this article allow for a comprehensive understanding of the mechanical behaviour and the biodegradation profile of three composites of PLA with respect to their applications as biodegradable implants. It also helps in the selection of fillers for biopolymers such as PLA.

Data on microhardness and structural analysis of friction stir spot welded lap joints of AA5083-H116.

Friction stir spot welding (FSSW) was established to compete reasonably with the reverting, bolting, adhesive bonding as well as resistance spot welding (RSW) which have been used in the past for lap joining in automobile, aerospace, marine, railways, defence and shipbuilding industries. The use of these ancient and conventional joining techniques had led to increasing material cost, installation labour, and additional weight in the aircraft, shipbuilding, and other areas of applications. All these are disadvantages that can be overcome using FSSW. This research work carried out friction stir spot welding on 5058-H116 aluminium alloy by employing rotational speed in the step of 300 rpm ranges from 600 rpm to 1200 rpm with a no travel speed. It was noted that the dwell times were in the step of 5 s varying from 5 s to 15 s while the tool plunge rate was maintained at 30 mm/min. In this dataset, a cylindrical tapered rotating H13 Hot-working steel tool was used with a probe length of 5 mm and probe diameter of 6 mm, it has a shoulder diameter of 18 mm. The tool penetration depth (plunge) was maintained at 0.2 mm and the tool tilt angle at 2°. Structural integrity was carried out using Rigaku ultima IV multifunctional X-ray diffractometer (XRD) with a scan voltage of 40 kV and scan current of 30 mA. This was used to determine crystallite sizes, peak intensity, d-spacing, full width at half maximum intensity (FWHM) of the diffraction peak. TH713 digital microhardness equipment with diamond indenter was used for microhardness data acquisition following ASTM E92-82 standard test. The average Vickers hardness data values at different zones of the spot-welds were captured and presented.

Data showing the effects of disc milling time on the composition and morphological transformation of (α+ß) titanium alloy (Ti-6Al-2Sn-2Mo-2Cr-2Zr-0.25Si) grade.

In powder metallurgy, dry mechanical milling process is an effective technique employed in the reduction of solid materials into the desired size in the fabrication of materials or components from metal powders for various applications. However, the milling operation introduces changes in the size and shape as well as the elemental or chemical composition of the milled substance. These changes introduced after milling requires critical analyses as the performance and efficiency of fabricated components depend so much on the size, shape and chemical composition of the powders. In this data, the effects of vibratory disc milling on the morphological transformation and elemental composition of titanium alloy powder were observed and analyzed by Scanning Electron Microscopy (SEM) and Energy Dispersive Spectroscopy (EDS). The as received titanium alloy powder was subjected to dry mechanical milling machine rated 380V/50Hz at 940 rpm. Milling time of 2, 4, 6, 8 and 10 mins were adopted in this data collection. SEM and EDS analyses revealed that milling transformed the spherical shaped powders into plate-like shapes. This deformation in the shape of the powder increased with increase in milling time. Also, the oxygen content of the powder fluctuated as the milling time increased.