In pursuit of advancing fault diagnosis in electromechanical systems, this research focusses on vibration analysis through innovative techniques. The study unfolds in a structured manner, beginning with an introduction that situates the research question in a broader context, emphasising the critical role of fault diagnosis. Subsequently, the methods section offers a concise summary of the primary techniques employed, highlighting the utilisation of short-time Fourier transform (STFT) and continuous wavelet transform (CWT) for extracting time–frequency components from the signal. The results section succinctly summarises the main findings of the article, showcasing the results of features extraction by CWT and subsequently utilising a convolutional neural network (CNN) for fault diagnosis. The proposed method, named CWTx6-CNN, was compared with the STFTx6-CNN method of the previous stage of the investigation. Visual insights into the time–frequency characteristics of the inertial measurement unit (IMU) data are presented for various operational classes, offering a clear representation of fault-related features. Finally, the conclusion section underscores the advantages of the suggested method, particularly the concentration of single-frequency components for enhanced fault representation. The research demonstrates commendable classification performance, highlighting the efficiency of the suggested approach in real-time scenarios of fault analysis in less than 50 ms. Calculation by CWT with a complex Morlet wavelet of six time–frequency images and combining them into a single colour image took less than 35 ms. In this study, interpretability techniques have been employed to address the imperative need for transparency in intricate neural network models, particularly in the context of the case presented. Notably, techniques such as Grad-CAM (gradient-weighted class activation mapping), occlusion, and LIME (locally interpretable model-agnostic explanation) have proven instrumental in elucidating the inner workings of the model. Through a comparative analysis of the proposed CWTx6-CNN method and the reference STFTx6-CNN method, the application of interpretability techniques, including Grad-CAM, occlusion, and LIME, has played a pivotal role in revealing the distinctive spectral representations of these methodologies.

This paper is dedicated to the motion control system of a multimass mechanism with occurring resonances and variable moment of inertia. The proposed concept of control structure for such mechanism consists of a filter damping higher resonance frequencies and an adaptive speed controller. The filter has properly selected fixed characteristics giving a compromised filtering effect in a range of resonance frequency variation, caused by the variable moment of inertia. The used neural adaptive controller realizes active damping of lower resonance frequencies, which are not eliminated by the resonance filter. This original concept is compared with a more complex solution, treated as a reference, which contains an offline-tuned resonance filter together with an offline-adjusted PI-two degrees of freedom controller. Good speed control dynamic properties of the proposed concept in comparison with the reference complex solution are proven by laboratory results.

The article describes mathematical model of multi-mass electric drive system with flexible connection. Mechanical part was modeled as one-, two- and multi-mass. System with rigid, flexible and damping connection was considered. Model was shown in form of the equations of motion, state space and transfer function.

Modern industrial process and household equipment more often use direct drives. According to European policy, Industry 4.0 and new Industry 5.0 need to undertake the effort required to ensure a sustainable, human-centric, and resilient European industry. One of the main problems of rotating machines is mechanical vibrations that can limit the lifetime of the final product or the machine in which they are applied. Therefore, analysis of vibration in electrical drives is crucial for appropriate maintenance of the machine. The present article undertakes an analysis of vibration measured at the laboratory stand with multiple dominant frequencies in the range 50–500 Hz. The fast Fourier transform (FFT) gives information about the frequency component without its time localisation. While the solution made available by the short-time Fourier transform (STFT) is able to overcome the problem of FFT, it still has limitations, particularly in terms of there being a lacuna in time and frequency localisation; accordingly, the need is felt for other methods that can give a good localisation in time and frequency. In the article, the continuous wavelet transform (CWT) was investigated, which requires selection of the wavelet function (kernel of transformation). The complex Morlet wavelet was selected with description of its central frequency and bandwidth. CWT and STFT time-frequency localisation capabilities were compared to investigate data registered from the direct-drive laboratory stand. CWT gives better frequency localisation than STFT even for the same frequency resolution. Vibration frequencies with near-locations were separated in CWT and STFT joined them into one wide pick. To ensure a good extraction of frequency features in electric drive systems, the author, based on analysing the results of the present study, recommends that CWT with complex Morlet wavelet be used instead of STFT.

Accurate vibration classification using inertial measurement unit (IMU) data is critical for various applications such as condition monitoring and fault diagnosis. This study proposes a novel convolutional neural network (CNN) based approach, the IMU6DoF-SST-CNN in six variants, for robust vibration classification. The method utilizes Fourier synchrosqueezed transform (FSST) and wavelet synchrosqueezed transform (WSST) for time-frequency analysis, effectively capturing the temporal and spectral characteristics of the vibration data. Additionally, was used the IMU6DoF-SST-CNN to explore three different fusion strategies for sensor data to combine information from the IMU’s multiple axes, allowing the CNN to learn from complementary information across various axes. The efficacy of the proposed method was validated using three datasets. The first dataset consisted of constant fan velocity data (three classes: idle, normal operation, and fault) at 200 Hz. The second dataset contained variable fan velocity data (also with three classes: normal operation, fault 1, and fault 2) at 2000 Hz. Finally, a third dataset of Case Western Reserve University (CWRU) comprised bearing fault data with thirteen classes, sampled at 12 kHz. The proposed method achieved a perfect validation accuracy for the investigated vibration classification task. While all variants of the method achieved high accuracy, a trade-off between training speed and image generation efficiency was observed. Furthermore, FSST demonstrated superior localization capabilities compared to traditional methods like continuous wavelet transform (CWT) and short-time Fourier transform (STFT), as confirmed by image representations and interpretability analysis. This improved localization allows the CNN to effectively capture transient features associated with faults, leading to more accurate vibration classification. Overall, this study presents a promising and efficient approach for vibration classification using IMU data with the proposed IMU6DoF-SST-CNN method. The best result was obtained for IMU6DoF-SST-CNN with FSST and sensor-type fusion.

Accurate and timely fault detection is crucial for ensuring the smooth operation and longevity of rotating machinery. This study explores the effectiveness of image-based approaches for machine fault diagnosis using data from a 6DOF IMU (Inertial Measurement Unit) sensor. Three novel methods are proposed. The IMU6DoF-Time2GrayscaleGrid-CNN method converts the time series sensor data into a single grayscale image, leveraging the efficiency of a grayscale representation and the power of convolutional neural networks (CNNs) for feature extraction. The IMU6DoF-Time2RGBbyType-CNN method utilizes RGB images. The IMU6DoF-Time2RGBbyAxis-CNN method employs an RGB image where each channel corresponds to a specific axis (X, Y, Z) of the sensor data. This axis-aligned representation potentially allows the CNN to learn the relationships between movements along different axes. The performance of all three methods is evaluated through extensive training and testing on a dataset containing various operational states (idle, normal, fault). All methods achieve high accuracy in classifying these states. While the grayscale method offers the fastest training convergence, the RGB-based methods might provide additional insights. The interpretability of the models is also explored using Grad-CAM visualizations. This research demonstrates the potential of image-based approaches with CNNs for robust and interpretable machine fault diagnosis using sensor data.