Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Engineering Applications of Artificial Intelligence

Dynamic quantum annealing optimized quantum neural networks for remaining useful lifetime prediction

Manoranjan Gandhudi, G. R. Gangadharan

Published Jan 13, 2026• 1 citation
Publisher
DOI
10.1016/j.engappai.2026.113856

Related papers

Harnessing Quantum Computing for Telecommunication Optimization: A Journey from Quantum Annealing to Quantum Neural Networks

Zsolt Tabi

•Sep 4, 2025•0 citations

Optimizing quantum annealing schedules with Monte Carlo tree search enhanced with neural networks

Yuqin Chen, Yu Chen, Chee‐Kong Lee +2 more

arXiv:2004.02836•Nature Machine Intelligence•Mar 14, 2022•50 citations

Spiking neural network dynamic system modeling for computation of quantum annealing and its convergence analysis

Chenhui Zhao, Zenan Huang, Donghui Guo

Quantum Information Processing•Feb 1, 2021•6 citations

Quantum Annealing for Real-World Machine Learning Applications

Rajdeep Kumar Nath, Himanshu Thapliyal, Travis S. Humble

Springer eBooks•Aug 7, 2023•4 citations

Quantum Annealing Enhanced Reinforcement Learning for Accurate Remaining Useful Lifetime Prediction

Manoranjan Gandhudi, Arunkumar V., G. R. Anil +1 more

Remaining useful life (RUL) estimation is central to predictive maintenance, where an unplanned failure can cost far more than the asset itself. Statistical degradation models miss the strong nonlinearity of real systems, and data-driven models often converge to suboptimal solutions in high-dimensional, non-convex search spaces. We propose a Quantum Annealing enhanced Q-Learning (QAQL) framework that couples the sampling behaviour of quantum annealing with the sequential decision making of Q-learning. Each Q-value update is encoded as a small quadratic unconstrained binary optimization (QUBO) whose ground state is the greedy action; rather than acting as a deterministic optimizer, the annealer returns a distribution over near-optimal actions across many reads, and this stochastic action selection supplies the exploration that curbs premature convergence on nonlinear degradation trajectories. The QUBO is solved on the D-Wave Advantage system using minor embedding, with the annealer woven into the reinforcement-learning loop rather than bolted on after training. We validate QAQL on two public benchmarks: the NASA C-MAPSS turbofan engine datasets and a device-fleet predictive maintenance dataset. Averaged over many independent runs and across six error metrics, QAQL outperforms the classical and quantum baselines considered in this study, with statistically significant improvements. The results indicate that quantum annealing is a usable, not merely theoretical, optimizer inside a reinforcement-learning loop for industrial predictive-maintenance applications.

arXiv:2606.18503•Jun 16, 2026•1 citation

Designing a Quantum Annealing-Based Method for Optimizing Backpropagation Neural Networks in Greenhouse Gas Emissions Prediction

Wahyu Hidayat, Nur Ulfa Maulidevi, Kridanto Surendro

Greenhouse gas emissions prediction, whether at a macroscopic scale or through building energy demand, commonly employs Backpropagation Neural Network (BPNN) models. These models often encounter issues like extended training durations and difficulties in configuring the optimal number of hidden layers and neurons. Achieving a balance between the complexity of the model and its ability to generalize effectively is essential for creating models that are both efficient and effective. Current approaches to optimizing BPNN structures predominantly utilize classical optimization techniques, often focusing on either the number of hidden layers or the number of neurons. In this paper, we propose a conceptual framework that leverages quantum annealing to optimize BPNN models for GHG emissions prediction. The method is structured in three stages: (1) optimizing the number of hidden layers, (2) optimizing the number of neurons in each layer, and (3) performing neuron pruning optimization. This study focuses on the theoretical design and methodology of the proposed approach, emphasizing its potential to integrate classical and quantum computing paradigms to achieve superior optimization outcomes.

International Conference on Software and Computer Applications (ICSCA)•Feb 20, 2025•2 citations
Remaining useful life (RUL) estimation is central to predictive maintenance, where an unplanned failure can cost far more than the asset itself. Statistical degradation models miss the strong nonlinearity of real systems, and data-driven models often converge to suboptimal solutions in high-dimensional, non-convex search spaces. We propose a Quantum Annealing enhanced Q-Learning (QAQL) framework that couples the sampling behaviour of quantum annealing with the sequential decision making of Q-learning. Each Q-value update is encoded as a small quadratic unconstrained binary optimization (QUBO) whose ground state is the greedy action; rather than acting as a deterministic optimizer, the annealer returns a distribution over near-optimal actions across many reads, and this stochastic action selection supplies the exploration that curbs premature convergence on nonlinear degradation trajectories. The QUBO is solved on the D-Wave Advantage system using minor embedding, with the annealer woven into the reinforcement-learning loop rather than bolted on after training. We validate QAQL on two public benchmarks: the NASA C-MAPSS turbofan engine datasets and a device-fleet predictive maintenance dataset. Averaged over many independent runs and across six error metrics, QAQL outperforms the classical and quantum baselines considered in this study, with statistically significant improvements. The results indicate that quantum annealing is a usable, not merely theoretical, optimizer inside a reinforcement-learning loop for industrial predictive-maintenance applications.
Greenhouse gas emissions prediction, whether at a macroscopic scale or through building energy demand, commonly employs Backpropagation Neural Network (BPNN) models. These models often encounter issues like extended training durations and difficulties in configuring the optimal number of hidden layers and neurons. Achieving a balance between the complexity of the model and its ability to generalize effectively is essential for creating models that are both efficient and effective. Current approaches to optimizing BPNN structures predominantly utilize classical optimization techniques, often focusing on either the number of hidden layers or the number of neurons. In this paper, we propose a conceptual framework that leverages quantum annealing to optimize BPNN models for GHG emissions prediction. The method is structured in three stages: (1) optimizing the number of hidden layers, (2) optimizing the number of neurons in each layer, and (3) performing neuron pruning optimization. This study focuses on the theoretical design and methodology of the proposed approach, emphasizing its potential to integrate classical and quantum computing paradigms to achieve superior optimization outcomes.