The occurrence of multiple faults is a practical problem in the bearings of rotating machines, and early diagnosis of such issues in an intelligent manner is vital in the era of industry 4.0. The present work investigated various combinations of bearing faults, including dual and multiple fault conditions. Two prevalent fault diagnosis methods were employed: vibration monitoring using time-frequency scalograms extracted through Continuous Wavelet Transform (CWT) and a non-invasive Infrared Thermography (IRT). A 2-D Convolutional Neural Network (CNN) was used to classify various combinations of fault conditions through automated feature extraction. The proposed methodology was validated at two constant speed conditions of 19 Hz and 29 Hz and continuously accelerated and decelerated speed conditions in the range of 19 Hz - 29 Hz. Adequate accuracy was achieved in both dual and multiple fault conditions in the case of vibration-based fault diagnosis, with a range of 99.39 % to 99.97 %. Meanwhile, in the case of proposed IRT-based fault diagnosis, 100 % classification accuracy was achieved for dual and multiple faults in all conditions. These results signify the robustness and reliability of the proposed methodology for dual and multiple fault diagnosis in bearings at constant and varying speed conditions.
16 June 2023 in IEEE Transactions on Industry Applications
Rotating machines frequently undergo various faults causing increased maintenance and operation costs. To minimize these costs, effective and intelligent methods are thus required. Different sensor modalities reflecting various faults should continuously be monitored and interpreted to enable these methods. In this work, two sensor modalities, Infrared Thermography (IRT), and vibration are used complementary to form a multi-sensor fault diagnosis system. This system is used to diagnose the three most occurring faults: misalignment, unbalance, and rotor disk eccentricity, as single, dual, and multi-faults in a rotating mechanical system. The high feature processing capabilities of a Deep Convolutional Neural Network (DCNN) and the high predictive capabilities of a Support Vector Machine (SVM) are combined along with the potential dimensionality reduction using Principal Component Analysis (PCA). The results show that the proposed method is robust and signifies its reliability towards the effective diagnosis of considered faults. Further, IRT-based fault diagnosis outperforms the vibration-based classification in all working conditions.
Bearing is one of the core components of any rotating machine, and its failure is widespread. This reason drives continuous monitoring and detecting bearing faults during machine operation to warn operators and prevent unforeseen damage. This paper proposes an intelligent Passive Thermography (PTG) based fault diagnosis technique for detection of bearing faults using Convolutional Neural Network (CNN) with Transfer Learning (TL) under varying working conditions. The validation of the proposed method has been done on three different datasets; bearing test rig dataset has been taken as a source domain data while Induction Motor (IM), and Machine Fault Simulator (MFS) datasets have been taken as target domain data. The proposed method enables and speeds up the training process of CNN towards accurate adaptation for fault diagnosis approach in the escalated time frame. The experimental results demonstrated that the suggested approach could successfully learn transferable characteristics from the source domain model, which can cope with the issue of limited availability of training data required for the target domain. The classification accuracy on the target domain dataset were varied in the range of 89 -95.4 % in the case of the IM dataset and 96.5-97.5% in the case of the MFS dataset. Moreover, it shows the benefits of the suggested method, which may be utilized as an effective non-invasive diagnostic tool for rotating machines to avoid unexpected system shutdowns.
Electric Vehicles (EVs) have grown in universality in recent years due to their specific advantages such as zero emissions, low noise, and remarkable efficiency. Moreover, these vehicles, especially two-wheelers becoming an integrated part of the present transport system, and their safe operation must be considered for a successful run under practical operating conditions. In the present work, a two-wheeler EV simulator is designed and developed to perform experimental simulations on different pragmatic operating conditions at the laboratory level. Moreover, A Convolutional Neural Network (CNN) steered with Wavelet Synchrosqueezing Transform (WSST) based scalograms is proposed for fault identification in an electric-two wheeler. Firstly, raw vibration signatures are acquired from the in-wheel Brushless Direct Current (BLDC) hub motor and mid-drive Switched Reluctance Motor (SRM). Thereafter, these signatures are decomposed and transformed into time-frequency representation using WSST. Then, a CNN model is used for further identification and classification of the various bearing defects in EV motors. The experimental findings showed that the suggested method could successfully diagnose the various bearing faults under the mentioned working conditions. In both in-wheel BLDC hub motor and mid-drive SRM, the maximum achieved classification accuracies are 97.14 % and 97.78 % in the case of the full-speed condition. It is evident from the obtained results that recommended approach can be used as an effective diagnostic tool for electric-two wheelers in order to prevent unforeseen vehicle motor breakdown.
24 December 2025 in Engineering Applications of Artificial Intelligence