Predictive maintenance (PdM), a widely used approach for improving reliability, safety, and cost-efficiency in industrial operations, relies on advanced analytics and data-driven insights to detect incipient failures and optimize system performance. While conventional machine learning (ML) techniques are widely applied in PdM, they often struggle with noisy, high-dimensional sensor data. Recent progress in quantum machine learning (QML) offers potentially useful directions for improving fault diagnosis and predictive accuracy. This motivates a systematic literature review that assesses QML applications in PdM, examines technical and practical challenges shaping their development, and identifies opportunities for future research and industrial adoption. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, we screened 238 records and finalized 18 empirical studies published between 2015 and 2025 across five major digital libraries. Our synthesis indicates that QML-for-PdM studies primarily use quantum kernel methods and shallow variational hybrid models, typically employing angle-based encoding, controlled-Z (CZ) entanglement, and circuit depth ≤ 5 . Reported results suggest performance advantages of QML over classical baselines in curated settings, though the supporting evidence remains concentrated in highly controlled, few-qubit experimental environments. However, reported performance degrades under positive–unlabeled noise, over-parameterization, and unmitigated hardware noise. Overall, this review provides an evidence-based assessment of QML-based predictive maintenance by synthesizing reported benefits, practical constraints, and priority directions for future work.
Predictive maintenance (PdM), a widely used approach for improving reliability, safety, and cost-efficiency in industrial operations, relies on advanced analytics and data-driven insights to detect incipient failures and optimize system performance. While conventional machine learning (ML) techniques are widely applied in PdM, they often struggle with noisy, high-dimensional sensor data. Recent progress in quantum machine learning (QML) offers potentially useful directions for improving fault diagnosis and predictive accuracy. This motivates a systematic literature review that assesses QML applications in PdM, examines technical and practical challenges shaping their development, and identifies opportunities for future research and industrial adoption. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, we screened 238 records and finalized 18 empirical studies published between 2015 and 2025 across five major digital libraries. Our synthesis indicates that QML-for-PdM studies primarily use quantum kernel methods and shallow variational hybrid models, typically employing angle-based encoding, controlled-Z (CZ) entanglement, and circuit depth ≤ 5 . Reported results suggest performance advantages of QML over classical baselines in curated settings, though the supporting evidence remains concentrated in highly controlled, few-qubit experimental environments. However, reported performance degrades under positive–unlabeled noise, over-parameterization, and unmitigated hardware noise. Overall, this review provides an evidence-based assessment of QML-based predictive maintenance by synthesizing reported benefits, practical constraints, and priority directions for future work.
Quantum Machine Learning (QML) has become an important research area in recent years due to its potential to overcome the computational bottlenecks faced by classical machine learning methods. In this study, only SCI/SCI-Expanded journal articles published between 2023 and 2025 and accepted as early access for 2026 are considered, and 30 such articles are systematically examined to provide a comprehensive assessment of the current state of QML methods. The reviewed literature covers variational quantum circuits, quantum kernel methods, hybrid quantum–classical models, quantum annealing approaches, federated QML architectures, data encoding strategies, and adversarial robustness analyses. The findings indicate that QML models can exhibit stronger representational capacity and higher generalization performance compared to classical methods, particularly on high-dimensional, noisy, or small sample datasets. Reported results in domains such as healthcare, chemistry, energy systems, cybersecurity, blockchain, and finance reveal the diversity of QML applications and its interdisciplinary potential. Nevertheless, the limited qubit capacity of current NISQ hardware, constraints on circuit depth, and noise-related issues remain fundamental factors that restrict the scalability of QML models. This study synthesizes methodological trends, identifies open research problems, and proposes a directional roadmap for future QML research focused on hardware-aware circuit design, efficient data encoding schemes, and robust learning frameworks.
The rapid digitalization of manufacturing systems has led to the widespread adoption of Industrial Internet of Things (IIoT) networks, enabling real-time monitoring, data-driven optimization, and intelligent automation. A critical application within this paradigm is predictive maintenance, which aims to anticipate equipment failures before they occur, thereby reducing downtime, operational costs, and safety risks. However, traditional machine learning approaches for predictive maintenance and anomaly detection often struggle with high-dimensional sensor data, complex nonlinear relationships, and scalability constraints in large industrial environments. This paper explores the emerging role of Quantum Machine Learning (QML) as a novel computational framework for enhancing predictive maintenance and anomaly detection in smart manufacturing systems. By leveraging quantum principles such as superposition and quantum-enhanced feature spaces, QML algorithms offer new possibilities for processing complex industrial data more efficiently and accurately. The study examines hybrid quantum–classical models for fault prediction, early anomaly detection, and pattern recognition in IIoT networks, highlighting their potential advantages over classical methods. Challenges related to hardware limitations, data encoding, and industrial deployment are also discussed, providing a balanced perspective on the feasibility and future impact of quantum-enhanced intelligence in smart manufacturing.
Predictive maintenance (PdM) functions as a proven industrial 4.0 element which enables organizations to detect issues ahead of time while minimizing system downtimes and improving their maintenance procedures. The predictive maintenance success of Random Forest (RF), Gradient Boosting Machines (GBM) and Deep Neural Networks (DNNs) remains limited by their high computational costs and feature selection inefficiencies and difficulties in scaling for real-time industrial applications. New Quantum Machine Learning (QML) advancements manage to improve predictions through quantum superposition methods alongside kernel transformations and entanglement mechanics for better efficiency. The research introduces Q-PdM methodology that combines QSVM with VQC and Q-DNN for device failure detection in industrial systems through predictive maintenance. The research introduces Q-CBAM as a metric that enables financial feasibility evaluation of quantum-enhanced PdM models. The methodology demonstrates superior performance when implemented with AI4I 2020 Predictive Maintenance Dataset because it surpasses traditional prediction methods in all operational aspects including accuracy rates, processing speed and operational expense reduction. This research validates the Q-DNN model because it delivers 96.2% accuracy alongside 93.5% cost-benefit efficiency however its quantum models minimize computation demands and speed up inference time to suit industrial IoT real-time environments. The presented study enables a key connection between theoretical quantum machine learning research and industrial predictive maintenance practice leading to future quantum-driven monitoring systems for industries.
Recent advances in Quantum Machine Learning (QML) bring together Quantum Computing and Machine Learning with the aim of enhancing the advantages of Machine Learning to solve problems efficiently. The properties of quantum systems (superposition, entanglement, etc.) to represent multiple states of information at once, QML can potentially offer significant advantages when solving complex high-dimensional (multidimensional) computational problems. This paper reviews the current state-of-art regarding QML in general through an organized compilation and assessment of selected studies recently published in scientific literature that were found via large electronic library catalogs based on peer-reviewed sources according to algorithms used, optimization approaches employed, and areas of applied study. This review provides comparative analyses of each selected studies for purposes of identifying major trends in QML research/practice as well as opportunities for methodological improvements and challenges still existing within QML. Finally, this review presents an overview of Quantum Computing and Quantum Data Encoding Principles utilized to translate Classical Data into Quantum States as a high-level evaluation of several popular Quantum Learning Algorithms (e.g., Quantum Neural Networks, Quantum Support Machines, and Variational Quantum Circuit). The survey describes the optimization strategies such as gradient based techniques, Bayesian Optimization and evolutionary techniques being used to improve the stability of the quantum machine learning (QML) training process. Then, it provides examples of application areas for such QML, where healthcare analytics, environmental modelling, manufacturing optimization and analysis of biologic data are included. The comparative review of the recent academic research has identified several limitations and challenges regarding the use of QML that researchers. Although QML is believed to be capable of solving complex computational problems, issues such as noise in hardware, limited numbers of qubits and scalability present significant challenges for researchers working with this type of machine learning application. Overall, it appears that this survey provides a broad overview of contemporary developments and future trends for developing high-performance quantum learning systems.
Quantum Machine Learning (QML) has emerged as a promising interdisciplinary paradigm that integrates quantum computing and machine learning to address limitations of classical approaches in processing complex high-dimensional heterogeneous and imbalanced medical data. This study presents a systematic literature review of QML applications in healthcare based on 94 primary studies published between 2020 and April 2025. The review follows Kitchenham’s guidelines and the PRISMA framework to ensure rigor transparency and reproducibility. Seven research questions were formulated to examine publication trends sources datasets topics quantum model categories algorithms methods and evaluation metrics. Findings reveal a sharp increase in publication activity after 2023 indicating growing academic interest in healthcare-oriented QML. Medical imaging datasets were most frequently used followed by signal-based and tabular datasets with 86.5% of studies relying on public data. Hybrid classical-quantum approaches including CNN-QSVM Quantum Neural Networks and Variational Quantum Classifiers were dominant because they combine classical feature extraction with quantum-enhanced learning. However most studies were conducted in simulation environments rather than real hardware reflecting NISQ limitations including noise decoherence limited qubits and circuit depth constraints. Many results used small curated or imbalanced datasets raising concerns regarding generalizability reproducibility and clinical validity. Although numerous studies reported high accuracy standardized evaluation protocols external validation and uncertainty assessment remain limited. Overall QML in healthcare remains exploratory with substantial potential but significant barriers. This review highlights progress gaps and future directions emphasizing clinically representative datasets robust benchmarking interpretable noise-resilient models and real-hardware implementation to support trustworthy deployment in healthcare systems worldwide settings today.
The economic value of predictive maintenance (PdM) for industrial IoT machinery is undeniable, as unplanned equipment downtime is estimated to cost industries USD 50 billion a year worldwide. Deep learning techniques have achieved good fault classification results on benchmark datasets, but they are not robust enough to cope with noise in industrial environments, are computationally intensive for use at the edge, and are unable to make good use of the capabilities of quantum computing. In this paper, a new hybrid network, called QEML-Net (Quantum-Enhanced Machine Learning Network), is proposed to combine the ResNet-50 deep residual network with Convolutional Block Attention Modules (CBAM), variational quantum feature enhancement, and a compound hybrid loss function, for efficient fault diagnosis. The framework features a 6-layer, 4-qubit Parameterized Quantum Circuit (PQC) with angle encoding and linear CNOT entanglement that is implemented using PennyLane. Experiments were performed on six harmonized datasets from public PdM which have 57164 samples across eight unified fault categories. The framework was validated with the help of Bayesian hyperparameter optimization, 5-fold stratified cross-validation, ablation studies, and statistical testing. By optimizing the deployment on the edges, QEML-Net got 97.3% accuracy, 96.9% macro-F1 score, AUC of 0.988, and real-time inference performance with 19ms latency and 52FPS throughput on the benchmark dataset. The statistical analysis revealed significant improvement when compared to other methods (p < 0.001). Even when evaluated cross-dataset without fine-tuning, good generalization was achieved with an accuracy of 92.8–94.6%. The results reveal the advantages of combining the quantum variational circuits with deep learning to enhance the classification accuracy, interpretability, and deployment efficiency for the fault diagnosis of industrial IoT.