Employing Deep Learning for Predicting Remanufacturing Costs of EOL Products

Remanufacturing cost prediction is conducive to visually judging the remanufacturability of end-of-life (EOL) products from economic perspective. However, due to the randomness, non-linearity of remanufacturing cost and the lack of sufficient data samples. The general method for predicting the remanufacturing cost of EOL products is very low precision. The approach is based on historical remanufacturing cost data to build a model for prediction. First of all, the remanufacturing cost of individual EOL product is arranged as a time series in reprocessing order. The long short term memory (LSTM) deep learning structure is used to predict the cost. The ADAM optimization is also applied to enhance the performance of the LSTM Model, where a combination of two gradient descent methodologies, momentum and a weighted average of the gradients is used to make the algorithm converge towards the minima in a faster pace. It has been shown that the proposed approach attains higher accuracy compared to existing work.