Development of an artificial neural network for identification of used button cell batteries

点击翻译按钮获取中文摘要

Alkaline batteries in all shapes and sizes are used in many applications and comprise 78% of all batteries soldinto the Canadian market every year. Alkaline (non-rechargeable) and Lithium-Ion (rechargeable) batteriescontain Zinc and rare Earth metals such as Lithium, Cadmium, and Nickel. If these batteries are recycledresponsibly, they will provide new sources for fertilizing agricultural fields, save energy and resources, protectthe environment, and divert waste from landfills.However, considering the volume and variety of waste batteries, automated systems require the ability to sortby chemistry in order to ensure proper recycling. Sorting results in better control over environmental outcomesas separated battery types can be processed by the best specialty recyclers using technology designed forrecycling of specific battery chemistries.In this feasibility study project, we will investigate different ways to employ new technologies for improvingthe efficiency and productivity of household batteries recycling. The core of our study will be to develop areliable method for identifying different types of used button cell batteries using machine vision and ArtificialNeural Networks (ANNs).