# Circular saw blade wear status prediction based on generative adversarial network and CNN-LSTM model

## TL;DR

This paper proposes a new method using GAN and CNN-LSTM to accurately predict circular saw blade wear during spent fuel assembly cutting.

## Contribution

A novel GAN and CNN-LSTM model is introduced to improve wear prediction accuracy in complex cutting conditions.

## Key findings

- A GAN optimized with PCC expanded data samples to 2100, addressing small sample size issues.
- The CNN-LSTM model achieved 100% accuracy in identifying wear status, outperforming LSTM and RBFNN models.
- The method improves safety and efficiency in spent fuel assembly cutting under complex conditions.

## Abstract

Monitoring the status of circular saw blades is an effective measure to ensure the production efficiency and safety of spent fuel assembly cutting. However, the prediction of wear during the cutting of stainless steel shells of spent fuel assemblies by circular saw blades is not entirely accurate in complicated working conditions. The main challenges include deficiency of data acquisition, signal features extracting complex process, and insufficient robustness of models. To enhance the precision of forecasting consequence, a circular saw blade wear prediction method combining generative adversarial network (GAN) and CNN-LSTM models is proposed. The main fault types during the cutting of stainless steel shells by circular saw blades should be identified in advance, and vibration signals of each fault state is able to be collected then. The collected data is supposed to be preprocessed through sampling overlapping, single-layer wavelet transform denoising, and normalization. GAN optimized by the Pearson correlation coefficient (PCC) has been utilized aiming to expand the data volume of each fault state to 300 samples and resulting in a total data volume of 2100 samples; A CNN-LSTM model based on dual feature fusion has been established to identify the wear status of circular saw blades, achieving an accuracy rate of 100%, higher than Long Short-Term Memory (LSTM) neural networks (86.2%) and Radial Basis Function Neural Networks (RBFNNs) (94.9%). This study effectively solves the problem of small sample sizes for circular saw blade wear data, and provides an efficient and accurate method for circular saw blade wear identification under complex working conditions, which has important practical significance for improving the safety and efficiency of spent fuel assembly cutting.