Uncertainty Aware Functional Behavior Prediction and Material Fatigue Assessment for Circular Factory

2026-06-03

AI Summary

This study addresses the challenge of accurately assessing the reuse feasibility of returned products in circular manufacturing, where heterogeneous conditions impede reliable evaluation. The authors propose an integrated reliability workflow that synergistically combines functional behavior prediction with material fatigue analysis. Specifically, a convolutional encoder extracts force-torque loading patterns, while an LSTM network predicts Gaussian distributions for nine functional variables. Concurrently, finite element stress reconstruction is coupled with S–N/Miner’s rule (augmented by Haibach correction) and Paris’ law to evaluate output shaft fatigue. A streaming replay algorithm then fuses functional, material, and system-level reliability trajectories. This approach represents the first uncertainty-aware co-integration of functional forecasting and component-level fatigue assessment. Experimental results demonstrate an average accuracy of 0.9652 for the nine output variables within a 2% tolerance, with R² values of 0.9750 and 0.9924 for drive current and rotational speed, respectively, confirming its efficacy and reliability calibration capability for precision reuse decisions.

Abstract

Returned products in circular factories re-enter production with heterogeneous degradation states, usage histories, and remaining capability. Reuse cannot be decided from the current inspection alone, because future function fulfillment and component integrity may evolve differently under the next service scenario. Existing PHM approaches support degradation prediction, but often target fixed operating conditions or isolated component benchmarks, while material-fatigue assessment is rarely linked to system-level functional prognosis. This paper addresses this gap for an angle grinder by combining uncertainty-aware functional prediction with component-level fatigue assessment in an instance-specific reliability workflow. The proposed framework combines the current tool state with recent force--torque usage windows. A convolutional encoder extracts loading patterns from spindle forces and shaft torque, and an LSTM backbone predicts nine functional variables as Gaussian mean and variance estimates. In parallel, the same loading history is translated into output-shaft fatigue information through finite-element-supported stress reconstruction, S--N/Miner damage evaluation with Haibach extension, and Paris-law crack-growth analysis. A streaming replay algorithm consolidates both branches into functional, material, and system reliability trajectories. Held-out tests show mean \(2\%\)-tolerance accuracy of 0.9652 across nine outputs. Thermal variables are predicted near-perfectly, while drive motor current and load speed remain the most demanding dynamic outputs, with \(R^2\) values of 0.9750 and 0.9924. Torque history is especially important for these variables, and the conventional LSTM outperforms GRU and xLSTM in the short-history setting. Reliability calibration is most informative for drive motor current, where predicted and observed exceedance probabilities ...

Problem

• circular factory
• functional behavior prediction
• material fatigue assessment
• uncertainty quantification
• reliability prognosis

Innovation

• uncertainty-aware prediction
• material fatigue assessment
• functional prognosis
• reliability calibration
• circular factory