In this article, we propose a data-driven remanufacturability evaluation method for the waste parts considering uncertainty. First, the remanufacturing cost and remanufacturing profit functions based on the Taguchi quality concept are established. Subsequently, the back propagation neural network is applied for the parameter estimation to deal with the multivariable, uncertain, and nonlinear effects of remanufacturing machining. Moreover, the improved particle swarm optimization algorithm is used to efficiently optimize the remanufacturing value for waste parts. This article develops the remanufacturability evaluation model of waste parts considering remanufacturing processing capacity and quality loss. Through a case study of waste crankshafts, we show a particular application of the proposed data-driven remanufacturability evaluation method. This article provides a new and effective tool for remanufacturing production management and could assist both practitioners and policymakers in developing practical lean remanufacturing methods, promoting the sustainable development of the remanufacturing industry.
Stored only when both papers are in the corpus — 51 citations exist upstream.
Imported from OpenAlex (CC0) — nothing here is generated.