QSVM-RQNN: Low-Qubit Recurrent Quantum Similarity Learning for Condition Monitoring and Fault Classification

Abstract

In the Noisy Intermediate-Scale Quantum (NISQ) era, limited qubit availability and hardware noise constrain the practical deployment of quantum machine learning (QML). Existing quantum neural network (QNN) and quantum convolutional neural network (QCNN) architectures often require increasing quantum resources as the input dimension grows, limiting scalability on near-term devices. We propose QSVM-RQNN, a low-qubit framework integrating centroid-based Quantum Support Vector Machine (QSVM) similarity learning with Recurrent Quantum Neural Networks (RQNNs) for fault classification. The framework reduces the feature space using principal component analysis (PCA), partitions the reduced representation into sequential timesteps, and processes them using a compact three-qubit recurrent quantum architecture with shared parameters. Two complementary variants are developed: QSVM-RQNN-V1 performs class-conditioned joint quantum encoding of input and centroid segments, whereas QSVM-RQNN-V2 performs recurrent learning over timestep-wise quantum similarity representations. Experimental evaluation on multiple fault diagnosis datasets shows competitive and, in several cases, state-of-the-art performance compared with QSVM, QNN, QCNN, QSVM-QNN, QSVM-QCNN, and RQNN models. The proposed architectures provide favorable performance-efficiency trade-offs, improved recall, and enhanced fault detection on highly imbalanced datasets. These results demonstrate that integrating centroid-based quantum similarity learning with low-qubit recurrent representation learning provides an effective and scalable approach to condition monitoring and fault classification on resource-constrained NISQ devices.

Why dimensional analysis works: general classification of self-similarity based on scale-invariance
Hirokazu Maruoka
arXiv4 Nov 2026PreprintCC BY 4.0Full textStatistical & nonlinear physicsarXiv
Cluster-based Structural Similarity for Dataset Visualization and Data Selection for Machine Learning Interatomic Potentials
Yuto Iwasaki, Miguel A. Caro
arXiv30 Sep 2026PreprintarXiv licenceFull textCondensed matterarXiv
Real-Time Monitoring of MHD Liquid Metal Flows with Shallow Recurrent Decoders
Claudio Scardino, Stefano Riva, Carolina Introini +4
arXiv28 Aug 2026PreprintCC BY-SA 4.0Full textComputational physics Fluid dynamicsarXiv
When Similarity Is Interaction-Driven: Quantum Kernels for Regime-Sensitive Learning
Hanqiu Peng, Jianlong Lu, Ying Chen
arXiv6 Oct 2026PreprintCC BY-NC-SA 4.0Full textQuantum physics & quantum informationarXiv
Learning-Induced Dynamical Transition in Recurrent Neural Networks
Varun Vaidya
arXiv16 Sep 2026PreprintCC BY 4.0Full textCondensed matter Statistical & nonlinear physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{patel2026qsvmrqnn,
  title = {{QSVM-RQNN: Low-Qubit Recurrent Quantum Similarity Learning for Condition Monitoring and Fault Classification}},
  author = {Amit S. Patel and Himanshu R. Patel and Bikash K. Behera and Pranav Mehta and David Bassir and Ganshyam G. Tejani},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2608.09652},
  eprint = {2608.09652},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.09652},
  note = {CC BY-NC-ND 4.0},
}

RIS

TY  - UNPB
TI  - QSVM-RQNN: Low-Qubit Recurrent Quantum Similarity Learning for Condition Monitoring and Fault Classification
AU  - Amit S. Patel
AU  - Himanshu R. Patel
AU  - Bikash K. Behera
AU  - Pranav Mehta
AU  - David Bassir
AU  - Ganshyam G. Tejani
PY  - 2026
DA  - 2026/10/27
PB  - arXiv
DO  - 10.48550/arxiv.2608.09652
UR  - https://arxiv.org/abs/2608.09652
AB  - In the Noisy Intermediate-Scale Quantum (NISQ) era, limited qubit availability and hardware noise constrain the practical deployment of quantum machine learning (QML). Existing quantum neural network (QNN) and quantum convolutional neural network (QCNN) architectures often require increasing quantum resources as the input dimension grows, limiting scalability on near-term devices. We propose QSVM-RQNN, a low-qubit framework integrating centroid-based Quantum Support Vector Machine (QSVM) similarity learning with Recurrent Quantum Neural Networks (RQNNs) for fault classification. The framework reduces the feature space using principal component analysis (PCA), partitions the reduced representation into sequential timesteps, and processes them using a compact three-qubit recurrent quantum architecture with shared parameters. Two complementary variants are developed: QSVM-RQNN-V1 performs class-conditioned joint quantum encoding of input and centroid segments, whereas QSVM-RQNN-V2 performs recurrent learning over timestep-wise quantum similarity representations. Experimental evaluation on multiple fault diagnosis datasets shows competitive and, in several cases, state-of-the-art performance compared with QSVM, QNN, QCNN, QSVM-QNN, QSVM-QCNN, and RQNN models. The proposed architectures provide favorable performance-efficiency trade-offs, improved recall, and enhanced fault detection on highly imbalanced datasets. These results demonstrate that integrating centroid-based quantum similarity learning with low-qubit recurrent representation learning provides an effective and scalable approach to condition monitoring and fault classification on resource-constrained NISQ devices.
ER  -

Abstract

Related

Cite