Kriging Method-Based Return Prediction of Waste Electrical and Electronic Equipment in Reverse Logistics

Abstract

In reverse logistics, the accurate prediction of waste electrical and electronic equipment (WEEE) return amount is of great significance to guide electronic enterprises to formulate a reasonable recycling plan, remanufacturing production plan and inventory plan. However, due to the uncertainty of WEEE return, it is a challenge to accurately predict the WEEE return amount of recycling sites. Differently from the existing research methods aiming at the spatial correlation of the recycling amount of recycling sites, a spatial mathematical model based on Kriging method is proposed by this paper to predict the return amount of WEEE in reverse logistics. Based on the second-order randomness of the return amount, the spatial structure of the return amount of the recycling network is analyzed. According to the principle of unbiased prediction and minimum variance, the Kriging space mathematical model of WEEE return amount is derived, and the calculation process of three variograms is given. The results of Monte Carlo simulation and the case study on J company in Shanghai show that it is effective to utilize the Kriging method-based spatial mathematical model to predict the WEEE return of reverse logistics and analyze the spatial correlation structure of each recycling site. The proposed model can accurately predict the WEEE return amounts of unknown sites as well as those of the whole area through the known site data, which provides a novel analysis method and theoretical basis for the prediction of reverse logistics return amount.

Simulation of Electronic Waste Reverse Chains for the Sao Paulo Circular Economy: An Artificial Intelligence-Based Approach for Economic and Environmental Optimizations

“…The model considers economic efficiency and environmental impacts in decision-making, and environmental impacts are evaluated in terms of carbon emissions. Lv and Du [29] developed a simulation based on the Kriging method to predict the amount of WEEE returned in reverse logistics in China. The proposed model can accurately predict the amounts of WEEE returned from unknown locations, as well as those from the entire area, through data from the known location, which is important for compliance with environmental legislation.…”

“…Some studies combined simulation and artificial intelligence techniques, as was found in the nonlinear gray Bernoulli model with the convolution integral NBGMC that was improved by Particle Swarm Optimization in Duman et al [28], as well as in the multi-objective models that were computed using the two-phase fuzzy compromise approach developed by Tosarkani et al [6]. In addition, Lv and Du used the Kriging method [29], whereas Moslehi et al [30] used a multi-objective stochastic model and a bi-objective mixed-integer programming model under certain uncertainties. An approach using system dynamics and a mixed-integer nonlinear programming model was utilized by Llerena-Riascos et al [4], and a convolutional neural network-based quality prediction and closed-loop control method was used by Zhang et al [31].…”

“…In this regard, the studies that presented an environmental assessment-listed in Table 1-only offered a quantification in percentage using data extracted from the computer simulation. These studies generally emphasized the reduction of WEEE disposal in landfills and the reduction of CO 2 , such as in Gamberini et al [24]; Achilles et al [21]; Achilles et al [22]; Assavapokee and Wongthatsanekorn [20]; Shokohyar and Mansour [25]; Yu and Solvang [23]; Bal and Satoglu [15]; Elia et al [16]; Duman et al [28]; Tosarkani et al 2020 [6]; Llerena-Riascos et al 2021 [4]; Lv and Du [29]; Moslehi et al [30]; and Guo and Zhong [5]. From this, the second gap identified was that no research evaluated the reduction of environmental impacts in the abiotic, biotic, and water dimensions using the Material Intensity Factor (MIF), which is a relevant tool for global assessment of the minimization of environmental impacts, not just using percentage data.…”

“…The fourth aspect analyzed in the research was the country of application of computer techniques for optimization of the WEEE reverse chains. Five surveys were carried out in China by Dat et al [26], Qiang and Zhou [13], Yu and Solvang [23], Lv and Du [29], and Guo and Zhong [5]; three surveys were conducted in Greece by Achillas et al [12], Achillas et al [21], and Achillas et al [22]; three in Türkiye by Ayvaz et al [27], Kilic et al [14], and Bal and Satoglu [15]; two in Italy by Gamberini et al [24] and Elia et al [16]; two the USA by Assavapokee and Wongthatsanekorn [20], and Duman et al [28]; two in Iran by Shokohyar and Mansour [25], and Moslehi et al [30]; and one study in each of the following countries: Spain, by Mar-Ortiz et al [17]; Portugal, by Gomes et al [18]; Germany, by Alumur et al [19]; Canada, by Tosarkani et al [6]; Colombia, by Llerena-Riascos et al [4]; and Belgium, by Zhang et al [31]. Thus, the fourth research gap was the lack of studies carried out in Brazil, mainly in Sao Paulo, on the use of simulation and artificial intelligence for economic and environmental optimization of the reverse WEEE network, considering manufacturers, waste managers, collection points, and recyclers.…”

Prediction of WEEE Recycling in China Based on an Improved Grey Prediction Model

“…Liu et al [22] proposed a new model for estimating appliance usage and e-waste generation at the 1 km × 1 km grid-level by combining geographic information systems (GIS) and material flow analysis (MFA). Lv et al [9] proposed a kriging-based spatial mathematical model for WEEE recycling based on the spatial structure of the recycling network. Wang et al [23] proposed a multi-source data hybrid method based on quarterly sales data, survey data, and Internet data to estimate the amount of e-waste generated for domestic electrical storage water heaters (DESWH), namely the SMK-GDSGM (1,1)-MSA method, which can deal with seasonal trend features hidden in time series in e-waste forecast modeling.…”