Quantum-Enhanced and Machine Learning Framework for High-Accuracy Fatigue Life Prediction and Structural Analysis of Connecting Rod
TL;DR
Fatigue assessment revealed that AA-7075 operates above its endurance limit, whereas 42CrMo4 alloy steel provides an infinite-life performance and is therefore recommended and the integration of quantum-inspired optimization and deep neural networks has demonstrated improved predictive accuracy compared with that of conventional simulation approaches.
Abstract
The connecting rod is a critical mechanical component that transmits reciprocating motion from the piston to rotational motion in the crankshaft. Although connecting rods are traditionally manufactured from aluminum alloys, titanium alloys, or alloy steels, the demand for higher power-to-weight ratios has motivated the exploration of alternative materials supported by advanced computational validation methods. This study proposes a multilayer optimization framework for identifying the most suitable material for the connecting rod of a 110 cc four-stroke petrol engine. The component was modelled in Pro/ENGINEER, and high-fidelity Finite Element Analysis (FEA) was performed in ANSYS to evaluate the von Mises stress, total strain, and displacement under tensile and compressive loading. A deep neural network (DNN), trained on 1,500 FEA-generated samples, was employed as a fast surrogate model, whereas a Takagi–Sugeno fuzzy inference system was used for the multi-criteria material ranking. A quantum-inspired optimization layer, implemented as a Quantum Approximate Optimization Algorithm (QAOA) executed on the IBM Qiskit Aer state-vector simulator, was used to search the multidimensional design space of alloy candidates and cost-to-performance ratios. The fatigue life was quantified using the Basquin stress–life relation with Goodman's mean stress correction and Miner's linear damage accumulation rule. The DNN surrogate reproduced the FEA results with R2 = 0.987, RMSE = 2.41 MPa, and MAPE = 0.71% for stress prediction, outperforming the Random Forest and XGBoost baselines. Fatigue assessment revealed that AA-7075 operates above its endurance limit (fatigue safety factor 0.78), whereas 42CrMo4 alloy steel provides an infinite-life performance (fatigue safety factor 1.97) and is therefore recommended. The integration of quantum-inspired optimization and deep neural networks has demonstrated improved predictive accuracy compared with that of conventional simulation approaches.