Search Results (30)

Reliable short-term wind power forecasting is crucial for smart grid stability. However, high-dimensional noise and stochastic fluctuations in wind sequences often degrade the accuracy of traditional forecasting models. Moreover, wind power time series typically exhibit asymmetric rising and decaying patterns, which further complicate accurate modeling. To address these challenges, this study proposes a hybrid intelligent system that integrates three components: data preprocessing, heterogeneous ensemble learning, and probabilistic interval forecasting. First, we build a multi-stage preprocessing workflow. Adaptive DBSCAN and Local Outlier Factor (LOF) remove spatial and density anomalies. Then multivariate variational mode decomposition (MVMD) synchronously separates multi-scale oscillatory patterns while preserving cross-channel correlations and frequency-domain symmetry across input variables. SHAP analysis quantifies feature importance, ensuring interpretability. The selected features are fed into a heterogeneous ensemble model consisting of Transformer, BPNN, ELM, XGBoost, and QRLSTM, which collectively capture multi-scale temporal dependencies and diverse data patterns. The ensemble weights are dynamically optimized by a modified multi-objective dragonfly algorithm (MMODA) that balances forecast accuracy and stability. Based on this ensemble, we apply MMODA to tune kernel density estimation for generating high-quality forecast intervals, maximizing coverage while minimizing interval width. Experiments on two wind farms in Shandong show that our MMODA-optimized ensemble reduces mean absolute percentage error by about 44.7% compared to single models, and ablations confirm that MVMD preprocessing adds a further 10.7% reduction. The proposed system provides an interpretable and reliable decision-support tool for sustainable grid operations. Full article

The stable and accurate output of the inertial measurement unit array (IMU) of a micro-electro-mechanical system (MEMS) is the key to ensuring the data fusion of the MEMS IMU array. However, due to the large number of MEMS IMUs contained in the MEMS IMU array, it is susceptible to interference and has difficulty avoiding failures. The output of the MEMS IMU contains noise, outliers, and other related errors, which can seriously lead to low fault detection and isolation accuracy in the MEMS IMU. In this study, a new method of fault detection and isolation based on multivariate variational mode decomposition (MVMD), a whale optimization algorithm (WOA), and a generalized likelihood test (GLT) is proposed, which is called WOA-MVMD-GLT. Firstly, a multi-index fitness function WOA is proposed to optimize the parameters of MVMD. Secondly, MVMD is used to extract the features of the MEMS IMU’s signals. Finally, a GLT is used to construct a fault detection function and a fault isolation function to detect and isolate the faults of gyroscopes and accelerometers. The experimental results show that the method proposed in this paper can significantly reduce the false alarm rate and false isolation rate. Full article

The high penetration of photovoltaic and wind power introduces strong non-stationarity and multi-scale fluctuations into power system load profiles, challenging the accuracy of short-term load forecasting (STLF). To address this, we propose a hybrid forecasting framework, IMVMD-XLSTM, which synergistically integrates an optimized multivariate decomposition with an advanced neural network. First, to address the critical issue that MVMD performance is highly sensitive to its parameter settings, which impacts decomposition quality, a multi-strategy Improved Fruit Fly Optimization Algorithm (IFOA) is developed to task-oriented adaptively tune the key parameters of MVMD, forming an Improved MVMD (IMVMD). This optimization aims to ensure decomposition stability and maximize the relevance for the subsequent forecasting task. Second, to fully leverage the characteristics of the frequency-aligned, multi-channel sub-sequences generated by IMVMD, an Extended LSTM (XLSTM) network is designed. Its serially arranged BisLSTM and mLSTM units are specifically tailored to capture the bidirectional long-term dependencies within each stable sub-sequence and the complex high-dimensional interactions across the aligned sub-sequences, respectively. Evaluated on 15 min resolution data from the Austrian grid, the proposed IMVMD-XLSTM framework achieves a day-ahead forecasting Mean Absolute Percentage Error (MAPE) of 2.45% (±1.41%). This study provides a verifiable and effective solution that couples data-adaptive signal processing with a purpose-built neural architecture to enhance forecasting reliability in renewable-rich power systems. Full article

Accurate wind power forecasting is critical for enhancing the operational efficiency and stability of electrical power grids. Conventional single-variable signal decomposition forecasting methods ignore the coupling relationship between wind power and multiple meteorological data, thus limiting prediction accuracy. This study proposes an accurate and fast short-term wind power prediction approach based on series-core fusion technology considering multiple meteorological data. In the data preprocessing stage, the multivariate variational mode decomposition (MVMD) algorithm decomposes wind power and meteorological variables into the same predefined number of frequency-aligned intrinsic mode functions (IMFs), thereby enhancing feature representation and improving forecasting accuracy via a more comprehensive and detailed dataset representation. During the training stage, the series-core fused time series (SOFTS) model establishes the connection among wind power channel and other meteorological variable channels for each IMF, achieving fast convergence through its streamlined and parallel structure. In the forecasting stage, the final wind power prediction is generated by the reconstruction of all IMFs. Furthermore, we conducted a comprehensive performance evaluation by comparing the proposed MVMD-SOFTS model with eight alternative models, including the CNN model, the TCN model, the LSTM model, the GRU model, the Transformer model, the SOFTS model, the CEEMDAN-SOFTS model, and the VMD-SOFTS model. The results indicate that MVMD-SOFTS outperformed all other models, demonstrating its effectiveness in capturing the multifaceted relationships in wind power forecasting. Full article

Field verification of contact-type ultrasonic sensors enables rapid evaluation of their sensitivity performance, thereby ensuring the accuracy of partial discharge (PD) ultrasonic monitoring results. However, during the verification process, both the standard sensor and the sensor under testing are inevitably affected by ambient noise when receiving verification signals, which can result in significant errors in the verification outcome. To address this issue, a noise suppression method is proposed in this study, which integrates multivariate variational mode decomposition (MVMD) optimized by an improved particle swarm optimization (IPSO) algorithm with a hyperbolic tangent-modulated exponential decay wavelet thresholding technique. First, the IPSO algorithm is employed to automatically optimize the parameters of MVMD. Then, the dominant components of the verification signal are selected based on the energy entropy of each decomposed mode. Subsequently, a novel wavelet threshold function incorporating hyperbolic tangent modulation and exponential decay is constructed and combined with an improved thresholding strategy to denoise the residual noise in the dominant components. Finally, a verification platform based on a real-type transformer is established. Both simulated and measured signals are denoised and subjected to sensitivity verification using the proposed method. Comparative analysis with noise-affected verification results demonstrates that the proposed method effectively suppresses noise in the verification signals and improves the accuracy of the sensitivity verification. Full article

The Electric Vehicle (EV) industry is developing rapidly, and EVs are becoming an increasingly important choice for the future of transportation. Therefore, accurately forecasting the electricity demand for EVs is crucial. This paper presents a hybrid deep learning model for EV charging load prediction based on Multivariate Variational Mode Decomposition (MVMD), Improved Artemisinin Optimization algorithm (IAO), and Deep Representation Learning Extreme Learning Machines (DrELMs). Firstly, MVMD decomposes the original data into several modal components. Secondly, IAO optimizes the hyperparameters of the DrELM model. Finally, the trained IAO-DrELM model predicts multiple modal components following MVMD decomposition to obtain the final predictions. Experimental results show that the proposed model outperforms eight other models, achieving the lowest Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) error values and the highest Coefficient of Determination (R²) value. Full article

Gas disasters in coal mines are the principal constraint on safe operations; accordingly, accurate gas time-series forecasting and real-time fluctuation monitoring are essential for prevention and early warning. A method termed Decomposition-Enhanced Cross-Graph Forecasting and Anomaly Finding is proposed. The Multi-Variate Variational Mode Decomposition (MVMD) algorithm is refined by integrating wavelet denoising with an Entropy Weight Method (EWM) multi-index scheme (seven indicators, including SNR and PSNR; weight-solver error ≤ 0.001, defined as the maximum absolute change between successive weight vectors in the entropy-weight iteration). Through this optimisation, the decomposition parameters are selected as K = 4 (modes) and $\alpha$ = 1000, yielding effective noise reduction on 83,970 multi-channel records from longwall faces; after joint denoising, SSIM reaches 0.9849, representing an improvement of 0.5%–18.7% over standalone wavelet denoising. An interpretable Cross Interaction Refinement Graph Neural Network (CrossGNN) is then constructed. Shapley analysis is employed to quantify feature contributions; the m1t2 gas component attains a SHAP value of 0.025, which is 5.8× that of the wind-speed sensor. For multi-timestep prediction (T0–T2), the model achieves MAE = 0.008705754 and MSE = 0.000242083, which are 8.7% and 12.7% lower, respectively, than those of STGNN and MTGNN. For fluctuation detection, Pruned Exact Linear Time (PELT) with minimum segment length L_min = 58 is combined with a circular block bootstrap test to identify sudden-growth and high-fluctuation segments while controlling FDR = 0.10. Hasse diagrams are further used to elucidate dominance relations among components (e.g., m3t3, the third decomposed component of the T2 gas sensor). Field data analyses substantiate the effectiveness of the approach and provide technical guidance for the intellectualisation of coal-mine safety management. Full article

The increasing reliance on renewable energy sources, such as photovoltaic (PV) systems, is pivotal for achieving sustainable development and addressing global energy challenges. However, short-term power forecasting for distributed PV systems often faces accuracy limitations, hindering their efficient grid integration. To address this, a novel hybrid prediction model is proposed, combining multivariate variational mode decomposition (MVMD) with a gated recurrent unit (GRU) network, an attention mechanism (ATT), and an enhanced vector weighted average algorithm (cINFO). The MVMD first decomposes historical data to reduce volatility. The INFO algorithm is then improved by integrating the crested porcupine optimizer (CPO), forming the cINFO algorithm to optimize GRU-ATT hyperparameters. An attention mechanism is incorporated to accentuate key influencing factors. The model was evaluated using the DKASC Alice Springs dataset. Results demonstrate high predictive accuracy, with mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²) values of 0.0249, 0.0693, and 99.79%, respectively, under sunny conditions, significantly outperforming benchmark models. This confirms the model’s feasibility and superiority for short-term PV power forecasting. Full article

Accurate and efficient short-term load forecasting is crucial for the secure and stable operation and scheduling of power grids. Addressing the inability of traditional Transformer-based prediction models to capture symmetric correlations between different feature sequences and their susceptibility to multi-scale feature influences, this paper proposes a short-term power distribution network load forecasting model based on an enhanced Komodo Mlipir Algorithm (KMA)—Multivariate Variational Mode Decomposition (MVMD)-Crossformer. Initially, the KMA is enhanced with chaotic mapping and temporal variation inertia weighting, which strengthens the symmetric exploration of the solution space. This enhanced KMA is integrated into the parameter optimization of the MVMD algorithm, facilitating the decomposition of distribution network load sequences into multiple Intrinsic Mode Function (IMF) components with symmetric periodic characteristics across different time scales. Subsequently, the Multi-variable Rapid Maximum Information Coefficient (MVRapidMIC) algorithm is employed to extract features with strong symmetric correlations to the load from weather and date characteristics, reducing redundancy while preserving key symmetric associations. Finally, a power distribution network short-term load forecasting model based on the Crossformer is constructed. Through the symmetric Dimension Segmentation (DSW) embedding layer and the Two-Stage Attention (TSA) mechanism layer with bidirectional symmetric correlation capture, the model effectively captures symmetric dependencies between different feature sequences, leading to the final load prediction outcome. Experimental results on the real power distribution network dataset show that: the Root Mean Square Error (RMSE) of the proposed model is as low as 14.7597 MW, the Mean Absolute Error (MAE) is 13.9728 MW, the Mean Absolute Percentage Error (MAPE) reaches 4.89%, and the coefficient of determination (R²) is as high as 0.9942. Full article

Background/Objectives: Epilepsy is a neurological disorder that severely impacts patients’ quality of life. In clinical practice, specific pharmacological and surgical interventions are tailored to distinct seizure types. The identification of the epileptogenic zone enables the implementation of surgical procedures and neuromodulation therapies. Consequently, accurate classification of seizure types and precise determination of focal epileptic signals are critical to provide clinicians with essential diagnostic insights for optimizing therapeutic strategies. Traditional machine learning approaches are constrained in their efficacy due to limited capability in autonomously extracting features. Methods: This study proposes a novel deep learning framework integrating temporal and spatial information extraction to address this limitation. Multivariate variational mode decomposition (MVMD) is employed to maintain inter-channel mode alignment during the decomposition of multi-channel epileptic signals, ensuring the synchronization of time–frequency characteristics across channels and effectively mitigating mode mixing and mode mismatch issues. Results: The Bern–Barcelona database is employed to classify focal epileptic signals, with the proposed framework achieving an accuracy of 98.85%, a sensitivity of 98.75%, and a specificity of 98.95%. For multi-class seizure type classification, the TUSZ database is utilized. Subject-dependent experiments yield an accuracy of 96.17% with a weighted F1-score of 0.962. Meanwhile, subject-independent experiments attain an accuracy of 87.97% and a weighted F1-score of 0.884. Conclusions: The proposed framework effectively integrates temporal and spatial domain information derived from multi-channel epileptic signals, thereby significantly enhancing the algorithm’s classification performance. The performance on unseen patients demonstrates robust generalization capability, indicating the potential clinical applicability in assisting neurologists with epileptic signal classification. Full article

Motor imagery (MI) is a widely used paradigm in brain–computer interface (BCI) systems, with applications in rehabilitation and neuroscience. In this study, magnetoencephalography (MEG) signals were employed to analyze MI and other mental imagery tasks. MEG provides high spatial resolution, facilitating the classification of imagery-related signals. This study aims to enhance the classification of motor and cognitive imagery (CI) tasks using a public MEG dataset including four distinct tasks: imagining the movement of hands (H) or feet (F), performing arithmetic subtraction (S), and forming words (W). MEG signals were decomposed using five signal-decomposition methods: Empirical Wavelet Transform (EWT), Maximal Overlap Discrete Wavelet Transform (MODWT), Empirical Mode Decomposition (EMD), Variational Mode Decomposition (VMD), and Multivariate Variational Mode Decomposition (MVMD). Feature extraction was performed using the Common Spatial Patterns (CSP), with t-test-based feature selection. Subsequently, commonly used machine learning algorithms were employed to classify MI and CI tasks. The results indicate that MVMD and MODWT achieved the highest accuracies when combined with the Artificial Neural Networks. MVMD yielded superior performances in (H and W: 79.2%; F and S: 75.8%; and F and W: 73.8%) tasks. MODWT achieved high accuracies in the H and W (75.9%) and F and W (76.3%) tasks. Overall, motor and non-motor pairs (H and W, F and W) yielded higher accuracy than the cognitive pair (W and S). Full article

With the swift evolution of renewable energy technologies, the design and optimization of microgrids have emerged as vital components for fostering energy transition and promoting sustainable development. This study presents a bi-level capacity optimization model for microgrids, integrating wind–solar generation with hybrid electric–hydrogen energy storage systems to simultaneously enhance economic efficiency and system stability. The outer layer minimizes the annual total cost through the application of an Improved Beluga Whale Optimization (IBWO) algorithm, which is enhanced by strategies including the reverse elitism strategy, horizontal and vertical crossover operations, and a whirlwind scavenging strategy to improve performance. The inner layer builds on the optimized results from the outer layer, employing a Multivariable Variational Mode Decomposition (MVMD) algorithm to regulate the power output of the energy storage system. By integrating electric–hydrogen hybrid storage technology, the inner layer effectively mitigates power fluctuations. Furthermore, this study designs a modal decomposition-based charging and discharging scheduling strategy to ensures the system’s continuous and stable operation. Simulations performed on MATLAB 2018b and CPLEX 12.8 platforms indicate that the proposed dual-layer model decreases annual total expenses by 27.5% compared to a single-layer model while keeping grid-connected power variations within 10% of the installed capacity. This research provides innovative perspectives on microgrid optimization design and offers substantial technical support for ensuring stability and economic efficiency in intricate operational settings. Full article

Fault location technology is crucial for enhancing the efficiency of fault maintenance and ensuring the safety of the power supply in small current grounding systems. To address the challenge that traditional single-end positioning methods experience when identifying the reflected wave head and that the adaptability of wave head calibration methods is typically limited, a single-end location method of modulus wave velocity differences based on marine predator algorithm optimized multivariate variational mode decomposition (MVMD) and morphological gradient is proposed. Firstly, the minimum comprehensive entropy kurtosis ratio is used as the fitness function, and the marine predator algorithm is used to realize the automatic optimization of the mode number and penalty factor of the multivariate variational mode decomposition. Therefore, with the goal of decomposing the traveling wave characteristic signals with the most significant traveling wave characteristic information and the lowest noise component, the line-mode traveling wave and the zero-mode traveling wave are accurately decomposed. Secondly, the intrinsic mode function component with the smallest entropy kurtosis ratio is selected as the line-mode traveling wave characteristic signal and the zero-mode traveling wave characteristic signal, respectively, and the arrival time of the wave head is accurately calibrated by combining the morphological gradient value. Finally, the fault distance is calculated by the modulus wave velocity difference location formula and compared with the variational mode decomposition-Teager energy operator (VMD-TEO) method and the empirical mode decomposition _first-order difference method. The results show that the proposed method has the highest accuracy of positioning results, and the algorithm time is significantly reduced compared with the VMD-TEO method, and it has strong adaptability to different line types of faults, different fault initial conditions, and noise interference. Full article

Wind turbine planetary gearboxes have complex structures and operating environments, which makes it difficult to extract fault features effectively. In addition, it is difficult to achieve efficient fault diagnosis. To improve the efficiency of feature extraction and fault diagnosis, a fault diagnosis method based on improved multivariate variational mode decomposition (IMVMD) and ensemble refined composite multivariate multiscale dispersion entropy (ERCmvMDE) with multi-channel vibration data is proposed. Firstly, the IMVMD is proposed to obtain the optimal parameters of the MVMD, which would make the MVMD more effective. Secondly, the ERCmvMDE is proposed to extract rich and effective feature information. Finally, the fault diagnosis of the planetary gearbox is achieved using the least squares support vector machine (LSSVM) with features consisting of ERCmvMDE. Simulations and experimental studies indicate that the proposed method performs feature extraction well and obtains higher fault diagnosis accuracy. Full article

Partial discharge (PD) detection plays an important role in online condition monitoring of electrical equipment and power cables. However, the noise of PD measurement will significantly reduce the performance of the detection algorithm. In this paper, we focus on the study of a PD noise reduction algorithm based on improved singular value decomposition (SVD) and multivariate variational mode decomposition (MVMD) for white Gaussian noise (WGN) and periodic narrowband interference signal noise. The specific noise reduction algorithm is divided into three noise reduction processes: The first noise reduction completes the suppression of narrowband interference in the noisy PD signal by the SVD algorithm with the guidance signal. The guidance signal is composed of a sinusoidal signal of the accurately estimated narrowband interference frequency component, and the amplitude is twice the maximum amplitude of the noisy PD signal. The second noise reduction decomposes the noisy PD signal after filtering the narrowband interference signal into k optimal intrinsic mode function by the MVMD after parameter optimization. By calculating the kurtosis value of each intrinsic mode function, it is determined whether it is the PD dominant component or the noise dominant component, and the noise dominant component is subjected to 3σ filtering to obtain the reconstructed PD signal. The third noise reduction uses a new wavelet threshold algorithm to denoise the reconstructed PD signal to obtain the denoised PD signal. The overall noise reduction algorithm proposed in this paper is compared with some existing methods. The results show that this method has a good effect on reducing the noise of PD signals measured in simulation and field. Full article