An official website of the United States government
Early identification of rotating machinery faults is crucial to avoid catastrophic failures upon installation. Contact-based vibration acquisition approaches are traditionally used for the purpose of machine health monitoring and end-of-line quality control. In complex working conditions, it can be difficult to perform an accurate accelerometer based vibration test. Acoustic signals (sound pressure and particle velocity) also contain important information about the operating state of mechanical equipment and can be used to detect different faults. A deep learning approach, namely one-dimensional Convolution Neural Networks (1D-CNN) can directly process raw time signals thereby eliminating the human dependance on fault feature extraction. An experimental research study is conducted to test the proposed 1D-CNN methodology on three different electric motor faults. The results from the study indicate that the fault detection performance from the new acoustic-based method is very effective and thus can be a good replacement to the conventional accelerometer-based methods for detection and diagnosis of mechanical faults in electric motors.
more »
« less
This content will become publicly available on May 31, 2026
Vector based acoustic sensing for mechanical fault classification through convolutional neural networks
Many industries are keenly interested in detecting and classifying faults before systems are sent to the customer or fail in use. A common approach is measuring the vibration of the machine and then using a classifier to check whether a fault is present. However, this process is difficult to automate because accelerometers are applied to the unit under test and are sometimes difficult to install and maintain due to complicated surface conditions. Accurate contact-based sensing is difficult when trying to check each rotating machinery assembly product during end-of-line quality control examinations or when evaluating the machine health of pre-installed rotating machinery. A deep learning-based fault classification system using both scalar and vector acoustic signals is a promising alternative that can replace the traditional error-prone, contact-based methods. Acoustic sound pressure and particle velocity measurements capture the directional fault signature of the mechanical defects in electric motors, and a one-dimensional convolutional neural networks (1D-CNNs) approach is proposed to process raw sensing data and eliminate the need for manual feature extraction. An experimental case study is performed to test the proposed 1D-CNN based fault classification on three different mechanically faulty electric motors across a variety of speeds. The results from acoustic pressure and particle velocity signals are compared against those from accelerometer signals. The experimental study confirms the feasibility of the proposed 1D-CNN on acoustic signals to be an excellent replacement for contact-based methods when assessing and classifying the machine fault condition. © 2025 Institute of Noise Control Engineering.
more »
« less
- Award ID(s):
- 2529773
- PAR ID:
- 10655981
- Publisher / Repository:
- Institute of Noise Control Engineering
- Date Published:
- Journal Name:
- Noise Control Engineering Journal
- Volume:
- 73
- Issue:
- 3
- ISSN:
- 0736-2501
- Page Range / eLocation ID:
- 303 to 320
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Machine learning can predict the timing and magnitude of laboratory earthquakes using statistics of acoustic emissions. The evolution of acoustic energy is critical for lab earthquake prediction; however, the connections between acoustic energy and fault zone processes leading to failure are poorly understood. Here, we document in detail the temporal evolution of acoustic energy during the laboratory seismic cycle. We report on friction experiments for a range of shearing velocities, normal stresses, and granular particle sizes. Acoustic emission data are recorded continuously throughout shear using broadband piezo‐ceramic sensors. The coseismic acoustic energy release scales directly with stress drop and is consistent with concepts of frictional contact mechanics and time‐dependent fault healing. Experiments conducted with larger grains (10.5 μm) show that the temporal evolution of acoustic energy scales directly with fault slip rate. In particular, the acoustic energy is low when the fault is locked and increases to a maximum during coseismic failure. Data from traditional slide‐hold‐slide friction tests confirm that acoustic energy release is closely linked to fault slip rate. Furthermore, variations in the true contact area of fault zone particles play a key role in the generation of acoustic energy. Our data show that acoustic radiation is related primarily to breaking/sliding of frictional contact junctions, which suggests that machine learning‐based laboratory earthquake prediction derives from frictional weakening processes that begin very early in the seismic cycle and well before macroscopic failure.more » « less
-
Humpback whale behavior, population distribution and structure can be inferred from long term underwater passive acoustic monitoring of their vocalizations. Here we develop automatic approaches for classifying humpback whale vocalizations into the two categories of song and non-song, employing machine learning techniques. The vocalization behavior of humpback whales was monitored over instantaneous vast areas of the Gulf of Maine using a large aperture coherent hydrophone array system via the passive ocean acoustic waveguide remote sensing technique over multiple diel cycles in Fall 2006. We use wavelet signal denoising and coherent array processing to enhance the signal-to-noise ratio. To build features vector for every time sequence of the beamformed signals, we employ Bag of Words approach to time-frequency features. Finally, we apply Support Vector Machine (SVM), Neural Networks, and Naive Bayes to classify the acoustic data and compare their performances. Best results are obtained using Mel Frequency Cepstrum Coefficient (MFCC) features and SVM which leads to 94% accuracy and 72.73% F1-score for humpback whale song versus non-song vocalization classification, showing effectiveness of the proposed approach for real-time classification at sea.more » « less
-
Not AvailablePose measurement and contact realization for soft robots are important but are also challenging to perform. In this article, a new approach is proposed which uses light transmission through the bore of the robot to sense its pose. By combining optical signals with inertial measurement units and pressure signals, along with governing models and machine learning algorithms, this sensing approach allows us to measure the pose of the soft robot in free space. It also allows the applied machine learning algorithm to estimate the robot configuration during contact events, predicting the location, direction, and magnitude of the contact force by learning from prior contact data in a training phase. The sensing devices used are affordable and widely available so that the robot can be mass-produced. Experimental results show that the proposed sensing system successfully estimates these quantities with good accuracy.more » « less
-
BLDC motors are widely employed in various applications because of their high efficiency, reliability, and long operational life. For BLDC motors, any electric malfunctions in the commutation signal creation with or without Hall sensors can lead to unexpected vibrations, crashes, and accidents according to application areas. Therefore, fast detection and diagnosis of these faults are crucial for the reliable operation of BLDC motor drive systems. In this paper, a unique approach has been explored for developing fault signatures to detect commutation signal faults accurately and rapidly in the BLDC motor drive system under highly dynamic loads. After the fault detection, a commutation signal is indirectly reconstructed based on healthy commutation signals to continuously drive the motor drive system to avoid serious electrical and mechanical issues due to the faults. The proposed approach and feasibility of the method have been verified both by simulation and experimental studies. The results of the proposed method will significantly improve the accuracy of the commutation signal fault detection and eventually enhance the reliability of the BLDC motor drive.more » « less
