Elsevier

Waste Management

Volume 50, April 2016, Pages 222-233
Waste Management

How to improve WEEE management? Novel approach in mobile collection with application of artificial intelligence

https://doi.org/10.1016/j.wasman.2016.02.033Get rights and content

Highlights

  • Innovative method of WEEE mobile collection is proposed.

  • We have included residents’ satisfaction of collection WEEE on requested time.

  • Fuzzy logic and genetic algorithms have been applied in optimisation of vehicle routes.

  • The model is fully parametric and can be easily adapted for collecting companies’ demand.

Abstract

In global demand of improvement of electrical and electronic waste management systems, stakeholders look for effective collection systems that generate minimal costs. In this study we propose a novel model for application in mobile collection schemes - on demand that waste be taken back from household residents. This type of the waste equipment collection is comfortable for residents as they can indicate day and time windows for the take-back. Collecting companies are interested in lowering operational costs required for service. This lowering includes selection of a sufficient number of vehicles and employees, and then minimising the routes’ length in order to achieve savings in fuel consumption, and lowering of emissions. In the proposed model we use a genetic algorithm for optimisation of the route length and number of vehicles and fuzzy logic for representation of the household residents’ satisfaction on the take-back service provided by collection companies. Also, modern communication channels like websites or mobile phone applications can be used to send the waste equipment take-back request from the household, so it has the potential to be developed in future applications. The operation of the model has been presented in the case study of a city in southern Poland. The results can be useful for collecting companies and software producers for preparation of new applications to be used in waste collection.

Introduction

One of the most important types of household waste is electrical and electronic equipment (WEEE). Such items contain a variety of materials that are easily recycled like metals, plastics, or glass (Huisman and Magalini, 2007, Oguchi et al., 2012). There are also some hazardous substances, which cause major environmental and health problems (Bogaert et al., 2008). Regarding the disposal of hazardous components and substances, WEEE management systems have been introduced in developed and developing countries (Ongondo et al., 2010). In the European Union (EU) the new Directive on WEEE requires higher levels of collection 65% of the total mass of the equipment placed on the market (POM) as an average of the three preceding years (European Commission, 2012). This requirement is to be achieved by 2019. However in 2012 in the majority of the EU members, the collection rate was below 50% and average for the entire EU was 38% (Eurostat, 2014).

There are many factors that contribute to collection rates. They depend on reverse logistics and attitudes of end users towards disposing of unwanted electrical and electronic equipment. Waste collection companies should prepare schedules for WEEE take-back and for the location of containers or the drop off places. Also they should inform the residents about the container location or the collection schedule. However, it is up to end users when and where they dispose of the broken and unwanted equipment. The WEEE regulations are designed to minimise the negative impact on the natural environment. Therefore the collection should be provided by legal companies, and the waste should be transported to treatment facilities where disassembly operations of discarded WEEE items are in compliance with environmental standards. Improper disposal of the obsolete equipment by end users, e.g. together with municipal waste or at scrap points poses a threat for the contamination of the natural environment (Wang et al., 2011, Saphores et al., 2012). One more factor to consider is vehicle emissions. Inefficient collections’ schedules and allocation of more vehicles than is required leads to an increase of emissions (Salhofer et al., 2007).

We would like to propose a variant of a mobile collection – on demand. This system could be widely used by collection companies. The advantage of this approach to the residents is twofold: ease and convenience, which plays a significant role in choosing a method of waste disposal. A collection vehicle makes a stop at a residence and the old equipment is carried out by the company’s employees. In order to schedule a pick up, the resident has a choice of a wide variety of readily available communication channels via telephone, website, or mobile apps.

A concept of this type of collection builds in a punctuality factor of the take-back resulting in positive feedback.

To encourage household residents to dispose of WEEE properly and to prepare optimised collection schedules, we propose an innovative program based on a multi-criteria collection model. This approach will use fuzzy logic – to measure the satisfaction of the residents depending on an average delay and maximum delay of waste collection and vehicle routing problem with time windows (VRPTW). The genetic algorithm will be used as the heuristic approach to optimize the route length of WEEE collection vehicles.

In this approach, the optimal number of vehicles, route length, and satisfaction of the residents in the take-back of the waste equipment are calculated. These attributes are necessary to cut collection costs. On demand collection system will be an important step in efforts to increase WEEE collection levels.

Section snippets

Collection type characteristics

Collection methods of WEEE can vary depending on requirements of environmental law. In the EU, collection types are described in the WEEE Directive (European Commission, 2012), and similar methods are used in other countries (Dwivedy et al., 2015).

The main types of collection can be classified as either stationary or mobile. The stationary model requires containers placed close to residential neighbourhoods or at municipal collection centres. Once the containers are filled, they are hauled off

Model description

Collections from households are scheduled by residents. The customer satisfaction level is described in Helgesen (2006). If the collection of unwanted equipment is punctual, it enhances a resident’s satisfaction. In this model heavy equipment is removed by the collecting company’s staff. If that service is satisfactory, residents promote it through the word of mouth (Zeithaml, 2000).

Therefore in this model we propose to measure the satisfaction of the residents based on an average delay and

Case study – WEEE collection on demand in Tychy, Poland

The operation of this model is presented in a case study of WEEE take-back in a suburb of Tychy, a city in the Silesian region of Poland. The calculations are based on simulation of calls from the residents that correspond to real conditions of the equipment possession in the households and life span of the equipment. The population of the entire city is 130,000. In the suburb used for calculations the majority of residents live in flats.

There are 10,811 of households and about 40,000 citizens.

Discussion and conclusions

WEEE treatment and processing after collection gives the possibility of recycling of almost all materials used in that kind of equipment, and of minimising the negative impacts on the natural environment and human health.

To achieve all these benefits efficient collection of WEEE is necessary. We have seen the development of communication channels, especially websites or mobile phone apps that enable finding the nearest waste collection sites (eSCHROT, 2015, Ewaste App, 2015). However most of

References (57)

  • R.J. Kuo et al.

    Hybrid particle swarm optimization with genetic algorithm for solving capacitated vehicle routing problem with fuzzy demand – a case study on garbage collection system

    Appl. Math. Comput.

    (2012)
  • H.C.W. Lau et al.

    A fuzzy guided multi-objective evolutionary algorithm model for solving transportation problem

    Expert Syst. Appl.

    (2009)
  • S. Liu et al.

    An effective genetic algorithm for the fleet size and mix vehicle routing problems

    Transport. Res. Part E: Logist. Transport. Rev.

    (2009)
  • E.H. Mamdani

    Advances in the linguistic synthesis of fuzzy controllers

    Int. J. Man-Mach. Stud.

    (1976)
  • N. Milovantseva et al.

    E-waste bans and U.S. households’ preferences for disposing of their e-waste

    J. Environ. Manage.

    (2013)
  • B. Mota et al.

    Towards supply chain sustainability: economic, environmental and social design and planning

    J. Clean. Prod.

    (2015)
  • M. Oguchi et al.

    Fate of metals contained in waste electrical and electronic equipment in a municipal waste treatment process

    Waste Manage.

    (2012)
  • A. Pires et al.

    Solid waste management in European countries: a review of systems analysis techniques

    J. Environ. Manage.

    (2011)
  • B.H. Robinson

    E-waste: an assessment of global production and environmental impacts

    Sci. Total Environ.

    (2009)
  • S. Salhofer et al.

    The ecological relevance of transport in waste disposal systems in Western Europe

    Waste Manage.

    (2007)
  • J.-D.M. Saphores et al.

    Willingness to engage in a pro-environmental behavior: an analysis of e-waste recycling based on a national survey of U.S. households

    Resour. Conserv. Recycl.

    (2012)
  • L. Shi et al.

    Flexible planning using fuzzy description logics: theory and application

    Appl. Soft Comput.

    (2009)
  • Q. Song et al.

    Residents’ behaviors, attitudes, and willingness to pay for recycling e-waste in Macau

    J. Environ. Manage.

    (2012)
  • A.S. Tasan et al.

    A genetic algorithm based approach to vehicle routing problem with simultaneous pick-up and deliveries

    Comput. Ind. Eng.

    (2012)
  • Z. Ursani et al.

    Localized genetic algorithm for vehicle routing problem with time windows

    Appl. Soft Comput.

    (2011)
  • Z. Wang et al.

    Willingness and behavior towards e-waste recycling for residents in Beijing city, China

    J. Clean. Prod.

    (2011)
  • R. Widmer et al.

    Global perspectives on e-waste

    Environ. Impact Assess. Rev.

    (2005)
  • C.-H. Yeh et al.

    Sustainable planning of e-waste recycling activities using fuzzy multicriteria decision making

    J. Clean. Prod.

    (2013)
  • Cited by (74)

    • Transitions toward sustainable E-waste management plans

      2023, Global E-waste Management Strategies and Future Implications
    • Artificial intelligence applications for sustainable solid waste management practices in Australia: A systematic review

      2022, Science of the Total Environment
      Citation Excerpt :

      Unorganised collection schedules and insufficient allocation of trucks result in unnecessary delays and traffic congestions, in addition to increasing the operating costs. As a result, the development and implementation of new solutions for AI based smart waste collection are also being adopted, although smart waste collection technology is still evolving (Abdallah et al., 2020; Popa et al., 2017; Krol et al., 2016). A review of the literature shows that a few studies have examined the adoption of AI based model in solid waste collection (see Table 3).

    View all citing articles on Scopus
    View full text