A convolutional neural network (cnn)-based classification of rotary machine vibration and acoustic signals

Acoustic signal - based misfire detection in internal combustion engines using machine learning techniques

Rotatory Machine Fault Detection Using CNNs on Spectrogram Signal Data

Rotary machines are vital in industrial and electrical systems, and prompt defect detection is crucial to prevent operational failures and financial losses. This article presents a framework using a Convolutional Neural Network (CNN) for defect detection via spectrogram images derived from simulated voltage, current, and load signals of rotary machines. The dataset, generated using MATLAB simulations and accessible on Kaggle, comprises spectrograms depicting normal operation and three fault conditions: $10 \Omega, 30 \Omega$, and $60 \Omega$. The CNN model proficiently extracts time-frequency characteristics from the spectrograms, attaining an overall classification accuracy of 96.3%, with precision, recall, and F1-scores continuously above 95% across all fault categories. The findings illustrate the model’s capacity to identify nuanced differences in machine behavior resulting from varying fault resistances. In contrast to traditional vibration- and signal-based techniques, the proposed method offers a resilient, non-invasive, and automated alternative for monitoring the state of rotary machines, facilitating predictive maintenance and mitigating the risk of unforeseen breakdowns. This research highlights the efficacy of integrating deep learning with spectrogram analysis for precise industrial problem identification.

Neural network-supported vibration analysis of turbomachinery for early fault prediction

A new hybrid deep learning architecture, combining one-dimensional convolutional neural networks (1D-CNN) with bidirectional long short-term memory (BiLSTM) networks to the problem of automatic detection and early forecasting of mechanical faults based on raw vibration signals is suggested.

Intelligent Side-Channel Acoustic–Vibration-Based Monitoring for Additive Manufacturing of Smart Composites Using Deep Learning

Reliable in situ monitoring is essential for the improvement of process supervision, quality assurance, and machine-state recognition in additive manufacturing of smart composite systems. This study presents a non-invasive acoustic–vibration side-channel monitoring framework for identifying FDM printing cases using experimental recordings from two printers, Bambu Lab A1 mini and Bambu Lab P1P. Four representative printing cases were investigated: simple key, hard key, two keys, and retraction test. Raw acoustic and vibration signals were converted into interval-level statistical features, including six acoustic descriptors and 18 vibration descriptors extracted from the X, Y, and Z axes. A baseline deep neural network (DNN) and an enhanced residual attention deep neural network (RA-DNN) were implemented under acoustic-only, vibration-only, and fused acoustic–vibration input conditions using stratified five-fold cross-validation. The fused acoustic–vibration features achieved the best performance, with the RA-DNN reaching 96.75% accuracy, 96.91% precision, 96.75% recall, and 96.70% F1-score for the A1 mini, and 98.19% accuracy, 98.25% precision, 98.19% recall, and 98.18% F1-score for the P1P. These results indicate that acoustic–vibration side-channel signals can provide effective process signatures for intelligent and quality-aware FDM monitoring.

Feature extraction and recognition based on distributed optical fiber network vibration signals

Phase-sensitive optical time-domain reflectometry (Φ-OTDR) offers advantages such as a simple structure, multi-point vibration localization, and long-distance disturbance detection in optical fiber networks. However, accurately distinguishing diverse environmental vibration events remains challenging. In this study, experiments were conducted using a distributed optical fiber vibration sensing system. Seven common types of environmental vibration events were simulated, and the corresponding signals were collected. Ten time-domain and frequency-domain features were extracted to construct a 10-dimensional feature vector for model training and classification. An improved decision tree optimal ensemble (IDTOE) method was introduced to optimize the random forest model, resulting in the proposed IDTOE-RF classifier. Model performance was evaluated using confusion matrices, accuracy, recall, and F1-score. The IDTOE-RF model outperformed the conventional random forest and support vector machine (SVM) models, achieving an average recognition accuracy of 93.46%, which was 3.84 percentage points higher than that of the conventional random forest model. The proposed method demonstrates good statistical stability and practical applicability for perimeter security monitoring.

Non-destructive identification of moldy pear core using acoustic vibration analysis and dual-channel deep feature fusion