Yi Yang

Accurate lithium-ion battery capacity prediction is critical for reliable battery management. However, measured capacity sequences contain slowly varying evolution, local oscillations, and short-term fluctuations, which makes direct raw-sequence prediction difficult. This study proposes an ICEEMDAN-guided fine-grained VMD and frequency-specific TCN–LR framework, named IFVMD-FSTLR. ICEEMDAN first performs coarse separation, retaining the residual as a slowly varying low-frequency component and aggregating the remaining oscillatory components. VMD then refines the aggregated component into compact higher-frequency modes. These components are treated as signal-scale representations rather than direct indicators of specific electrochemical mechanisms. Guided by the reconstruction-error analysis, TCN is used to model the refined higher-frequency components, while linear regression is used for the smoother low-frequency component. The final prediction is obtained by summing the component-wise forecasts. Experiments on the NASA and CALCE datasets are independently repeated five times, with mean ± standard deviation used to characterize result variability. The RMSE, MAE, and MRE are below 0.0033 Ah, 0.0026 Ah, and 0.18% on NASA, and below 0.0044 Ah, 0.0033 Ah, and 0.62% on CALCE, respectively. Overall, IFVMD-FSTLR achieves lower average errors in most evaluated cases.

The induction motor serves as the core power component in new energy vehicle drive systems. Any malfunction of the drive motor will directly undermine the operational reliability of the vehicle, potentially leading to drive system failures or, in severe cases, significant safety hazards endangering the lives of drivers and passengers. To address the issue of faint fault signatures within motor current signals, an image-based fault characterization method synergized empirical mode decomposition (EMD) with modified symmetrized dot pattern (MSDP) was proposed. Subsequently, a dedicated convolutional neural network (CNN) architecture with automated image feature extraction capabilities was engineered to classify motor health conditions, including healthy operation, bearing fault, and rotor broken bar. Finally, the efficiency and precision of the EMD-MSDP-CNN model for induction motor fault diagnosis were validated through experimental data, demonstrating a robust average diagnostic accuracy of 93.21% across diverse fault scenarios under multiple operating conditions.

Data augmentation and generation are popular solutions for the problem of imbalanced and insufficient data. Aiming to conduct cross-domain data generation, this article proposes a physics-guided data generation framework, termed “digital block printing (DBP).” Its core idea is to use the “Digital Printing Plate” constructed from the simulation data as a reference, and use the “Data Printer” trained with source-domain experimental data to generate synthetic data with a similar distribution to the target-domain experimental data. For a specific case, conditional-diffusion-based vibration signal generation is conducted in this article, with the target-domain data simulated by a phenomenological model as the “Digital Printing Plate,” and the diffusion model trained by source-domain experimental data as the “Data Printer.” The result shows that the method proposed in this article can generate experiment-like synthetic data, which processes both the frequency-domain characteristics similar to the target-domain simulation data, and time-domain characteristics similar to the source-domain experimental data.

Rotating machinery plays a critical role in industrial systems, and effective anomaly detection and assessment are indispensable for ensuring operational safety and reliability. However, the performance of existing methods is often constrained by the difficulty in acquiring fault samples—such samples are typically scarce during the initial operational phase of equipment. To address this challenge, this paper proposes a novel anomaly detection and evaluation framework based on Data-Accumulation-Aware Generative Adversarial Networks (DAA-GANs) and similarity estimation. The core innovation of this framework lies in its adaptability across different data accumulation stages. During the early operational phase dominated by normal samples, only normal data is used to train the DAA-GAN to establish a baseline detector. As fault data gradually accumulates, the detection threshold undergoes adaptive adjustment through collaborative optimization of normal and abnormal samples, thereby enhancing the detector’s generalization capability. Upon amassing annotated fault samples of varying severity, the framework assesses anomaly severity by analyzing the similarity between test outputs of unknown samples and known fault samples. The framework is validated through two case studies: a fault simulation model for a torque-splitting transmission system and the publicly available Case Western Reserve University (CWRU) bearing dataset. In the simulation case, the detection accuracy reaches 100% for the gear tooth breakage levels. On the CWRU dataset, the proposed method achieves an overall average detection accuracy of 99.83% across three operating speeds (1730/1750/1772 rpm), and the similarity-based assessment provides consistent severity identification. These results demonstrate that the proposed framework can support reliable anomaly detection and severity assessments under progressive data accumulation.

Envelope analysis, one of the most widely used methods in the field of rotating machinery fault diagnosis, aims to approximate fault impact characteristics by analyzing the envelope of the filtered signal in the demodulation band. The demodulation band is essentially the carrier frequency band and the resonant frequency band of the mechanical system. However, since the resonant frequencies of different mechanical components vary and are often unknown, accurately identifying the carrier frequency band becomes the most significant challenge in the envelope analysis process. Currently, the mainstream research approach involves the use of various metrics to evaluate the band with the most fault information and then performing envelope analysis on this band. Although these methods have shown effectiveness in practical applications, they still have notable limitations. For example, when faults occur simultaneously in different bearings and gears, existing methods can identify only one carrier frequency band, and the identified bands often lack consistency across the same set of test data. To address these issues, this paper proposes a novel demodulation band selection method that can efficiently and accurately identify all faults when signals from multiple faulty components coexist. This method has been evaluated through bearing fault simulations and case studies, and its performance outperforms traditional methods such as spectral kurtosis and Autogram. It can effectively extract the characteristic spectra of all faulty components under multi-resonance conditions, demonstrating excellent anti-interference capability and efficiency advantages. Therefore, it holds significant engineering value in improving the accuracy of fault diagnosis.

Planetary gearbox serves as a key transmission component in planetary ball screw actuator systems. Under the action of alternating loads, the stress concentration locations of the planet carrier in actuators with planetary gear trains are prone to fatigue cracks, which can lead to catastrophic system breakdowns. However, due to the complex vibration transmission path and the interference of uninterested vibration components, the characteristic modulation signal is ambiguous, so it is challenging to diagnose this fault. Therefore, this paper proposes a new fault diagnosis method. Firstly, a vibration signal model is established to accurately characterize the amplitude and phase modulation effects caused by cracked carriers, providing theoretical guidance for fault feature identification. Subsequently, three novel sideband evaluators of the modulation signal bispectrum (MSB) and their parameter selection ranges are proposed to efficiently locate the optimal fault-related bifrequency signatures and reduce computational cost, leveraging the effects identified by the model. Finally, a novel health indicator, the mean absolute root value (MARV), is used to monitor the state of the planet carrier. The effectiveness of this method is verified by experiments on the planetary gearbox test rig. The results show that the robustness of the amplitude and phase modulation effect of the cracked carrier in the low-frequency band is significantly higher than that in the high-frequency band, and the initial carrier crack can be accurately identified using this phenomenon under different operating conditions. This study provides a reliable solution for the condition monitoring and health management of the actuation system, which is helpful to improve the safety and reliability of operation.

In practical applications, intelligent diagnostic methods for actuator-integrated gearboxes in industrial driving systems encounter challenges such as the scarcity of fault samples and variable operating conditions, which undermine diagnostic accuracy. This paper introduces a multi-layer feature fusion meta-learning (MLFFML) approach to address fault diagnosis problems in cross-condition scenarios with class imbalance. First, meta-training is performed to develop a mature fault diagnosis model on the source domain, obtaining cross-domain meta-knowledge; subsequently, meta-testing is conducted on the target domain, extracting meta-features from limited fault samples and abundant healthy samples to rapidly adjust model parameters. For data augmentation, this paper proposes a frequency-domain weighted mixing (FWM) method that preserves the physical plausibility of signals while enhancing sample diversity. Regarding the feature extractor, this paper integrates shallow and deep features by replacing the first layer of the feature extraction module with a dual-stream wavelet convolution block (DWCB), which transforms actuator vibration or acoustic signals into the time-frequency space to flexibly capture fault characteristics and fuses information from both amplitude and phase aspects; following the convolutional network, an encoder layer of the Transformer network is incorporated, containing multi-head self-attention mechanisms and feedforward neural networks to comprehensively consider dependencies among different channel features, thereby achieving a larger receptive field compared to other methods for actuation system monitoring. Furthermore, this paper experimentally investigates cross-modal scenarios where vibration signals exist in the source domain while only acoustic signals are available in the target domain, specifically validating the approach on industrial actuator assemblies.