Aug 2026· International journal of computer information systems and industrial management applications· Vol 18, pp. 393-404· 0 citations
TL;DR
An end-to-end predictive maintenance system is proposed for high stress mechanical drivetrain and rotating machinery and the architecture proposed combines an industrial Internet of Things edge sensory network and hybrid machine learning and deep learning pipelines.
Abstract
It is widely recognized that modern industrial automation depends on real time condition monitoring of the equipment in order to avoid catastrophic failure and ensure that maintenance resources are used in the most efficient manner while minimising unscheduled downtime. In this research paper, an end-to-end predictive maintenance system is proposed for high stress mechanical drivetrain and rotating machinery. The architecture proposed combines an industrial Internet of Things (IoT) edge sensory network and hybrid machine learning and deep learning pipelines. These data include multi-modal sensor telemetry, including tri-axial vibration profiles, acoustic emissions, thermal imaging data, operational load metrics and electrical motor current signatures, all acquired at high sampling rates continuously. Advanced Wavelet Packet Decomposition and fast empirical mode extraction are used to remove signal artifacts and high frequency noise. These statistical, temporal and spectral attributes are reduced to a few-dimensional vector each and each is individually judged by a predictive suite of models including Random Forest regressors, Extreme Gradient Boosting (XGBoost), Support Vector Machines, Long Short-Term Memory (LSTM) recurrent networks, and Deep Residual Convolutional Neural Networks (ResNet-1D). Experimental validations conducted on standard bearing and gear testbeds prove the accuracy of optimized hybrid CNN-LSTM model in multi-class fault classification of 99.14% and Root Mean Square Error (RMSE) in Remaining Useful Life (RUL) prediction of 4.18 operating cycles. The edge-to-cloud telemetry infrastructure has been proven to provide an inference latency of less than 12 milliseconds per monitoring window, making real-time autonomous prognostics feasible in Industry 4.0 applications.
This research proposes an AI-driven, edge-based system for electric motor health monitoring and predictive maintenance using multi-sensor data, and achieves low latency, reduced bandwidth usage, and fast on-site decision-making using TinyML, an edge AI framework.
F. Haruna, M. Abdulraheem, I. O. Durotoye et al.· SPE Nigeria Annual Internati...· 0 citations
Unplanned failures of induction motors impose serious operational and financial penalties on industrial facilities, yet the fault signatures that precede such failures are detectable well in advance through careful sensor instrumentation and data-driven analysis. This paper presents an end-to-end Internet-of-Things (IoT) predictive maintenance scheme based on two off-the-shelf sensors: a DS18B20 one-wire digital thermometer and 2 piezo vibration sensor modules, with an ESP32 edge device for running the full machine learning pipeline offline, independent from any cloud services. Four operating scenarios are considered: healthy condition, BPFO (bearing outer race fault), misaligned shaft, and rotor imbalance. Based on 1-second sampling intervals, 17 descriptors are derived, including statistics in the time domain, Fourier harmonic peaks, energy ratios between different frequency bands, and temperature gradients measured across all sensors. A dual-stage feature selection method using mutual information (MI) score and Random Forest mean decrease impurity (MDI) ranking reduces the number of features to the 10 most relevant descriptors, reducing the computational complexity by 41% at the expense of 5.6% F1-macro. On a balanced 600-sample synthetic dataset, the resulting Random Forest classifier attains 87.3% hold-out accuracy, 91.0±1.9% five-fold cross-validation accuracy, and a macro area-under-the-ROC-curve of 0.980. End-to-end inference takes just 39 ms on the ESP32, easily meeting the 200 ms requirement for real-time alerting.
Akash Mastud, Dhiraj Vaidya, Azaroddin Sayyed et al.· International Conference on...· 0 citations
An Industrial Internet of Things (IIoT)-based Predictive Maintenance System that integrates smart sensors, edge computing, cloud analytics, artificial intelligence, and digital twin technology is proposed that contributes to the development of intelligent and self-optimizing industrial environments aligned with Industry 4.0 objectives.
Gajula Prasad Gajula Prasad, Bolloju Divya Sri Bolloju Divya Sri, Dr B Ramprasad Dr B Ramprasad· International Journal of Sci...· 0 citations
As predictive maintenance transitions from the data-centric paradigm of Industry 4.0 to the sustainable, human-centric framework of Industry 5.0, diagnosing servo motor conditions faces the dual challenges of data scarcity and a profound lack of labeled fault samples. To address this cold-start problem, we present a pseudo-supervised machine learning framework evaluated on a custom five-channel dataset comprising 199 servo motor telemetry samples (current, voltage, temperature, humidity, and vibration). The methodology integrates hard structural partitioning (k-means) and soft posterior confidence estimation (Gaussian Mixture Models) to characterize operating modes without prior annotation. Concurrently, an Isolation Forest model quantifies anomaly intensity and establishes a dynamic quantile-based threshold. A critical innovation of this research is the deterministic risk mapping derived from engineering priors; it defines the "high-risk" (abnormal) state by inversely weighting the physical safety margins of the sensors. This mechanism strictly maps unsupervised clusters to binary pseudo-labels. These labels are subsequently used to supervise downstream discriminators (Random Forest and Support Vector Machine). The final online diagnostic outputs a score-level fusion of the classifier probability and the GMM posterior, gated by the anomaly threshold. Quantitative evaluation demonstrates that the Random Forest model achieved a perfect F1 score of 1.000, while the comparative SVM yielded an F1 score of 0.997, proving the framework to be a robust, interpretable, and highly accurate solution for cold-start industrial health monitoring.
A Composite Health Index (CHI) is developed to transform multi-motor sensor data into an interpretable machine-level degradation indicator and is used to train ensemble machine learning models including Random Forest, Extra Trees, and XGBoost.
Ahmet Pişmişoğlu, Erkan Caner Ozkat, M. Konar· Eksploatacja I Niezawodnosc-...· 0 citations
