Search Results (137)

This paper presents a comparative study of data-driven modeling approaches for vanadium redox flow batteries (VRFBs), utilizing Multiple Linear Regression (MLR) and Random Forest (RF) algorithms. Experimental voltage–capacity datasets from a 1 kW/1 kWh VRFB system were digitized, processed, and used for model training, validation, and testing. The MLR model, built using eight optimized features, achieved a mean error (ME) of 0.0204 V, a residual sum of squares (RSS) of 8.87, and a root mean squared error (RMSE) of 0.1796 V on the test data, demonstrating high predictive performance in stationary operating regions. However, it exhibited limited accuracy during dynamic transitions. Optimized through out-of-bag (OOB) error minimization, the Random Forest model achieved a training RMSE of 0.093 V and a test RMSE of 0.110 V, significantly outperforming MLR in capturing dynamic behavior while maintaining comparable performance in steady-state regions. The accuracy remained high even at lower current densities. Feature importance analysis and partial dependence plots (PDPs) confirmed the dominance of current-related features and SOC dynamics in influencing VRFB terminal voltage. Overall, the Random Forest model offers superior accuracy and robustness, making it highly suitable for real-time VRFB system monitoring, control, and digital twin integration. This study highlights the potential of combining machine learning algorithms with electrochemical domain knowledge to enhance battery system modeling for future energy storage applications. Full article

Time series data are fundamental for analyzing temporal dynamics and patterns, enabling researchers and practitioners to model, forecast, and support decision-making across a wide range of domains, such as finance, climate science, environmental studies, and signal processing. In the context of high-dimensional time series, the Vector Autoregressive model (VAR) is widely used, wherein each variable is modeled as a linear combination of lagged values of all variables in the system. However, the traditional VAR framework relies on the assumption of stationarity, which states that the autoregressive coefficients remain constant over time. Unfortunately, this assumption often fails in practice, especially in systems subject to structural breaks or evolving temporal dynamics. The Time-Varying Vector Autoregressive (TV-VAR) model has been developed to address this limitation, allowing model parameters to vary over time and thereby offering greater flexibility in capturing non-stationary behavior. In this study, we propose an enhanced modeling approach for the TV-VAR framework by incorporating minimization solvers in generalized additive models and one-sided kernel smoothing techniques. The effectiveness of the proposed methodology is assessed using simulations based on non-homogeneous Markov chains, accompanied by a detailed discussion of its advantages and limitations. Finally, we illustrate the practical utility of our approach using an application to real-world financial data. Full article

The integration of renewable energy sources, battery energy storage, and electric vehicles into industrial systems unlocks new opportunities for reducing emissions and improving sustainability. However, the coordination and management of these new technologies also pose new challenges due to complex interactions. This paper proposes a methodology for designing a holistic energy management system, based on advanced digital twins and optimization techniques, to minimize the cost of supplying industry loads and electric vehicles using local renewable energy sources, second-life battery energy storage systems, and grid power. The digital twins represent and forecast the principal energy assets, providing variables necessary for optimizers, such as photovoltaic generation, the state of charge and state of health of electric vehicles and stationary batteries, and industry power demand. Furthermore, a two-layer optimization framework based on mixed-integer linear programming is proposed. The optimization aims to minimize the cost of purchased energy from the grid, local second-life battery operation, and electric vehicle fleet charging. The paper details the mathematical fundamentals behind digital twins and optimizers. Finally, a real-world case study is used to demonstrate the operation of the proposed approach within the context of the waste collection and management industry. The study confirms the effectiveness of digital twins for forecasting and performance analysis in complex energy systems. Furthermore, the optimization strategies reduce the operational costs by 1.3%, compared to the actual industry procedure, resulting in daily savings of EUR 24.2 through the efficient scheduling of electric vehicle fleet charging. Full article

The linear pseudo-measurements filter is adapted for use in a stochastic observation system with random time delays between the arrival of observations and the actual state of a moving object. The observation model is characterized by limited prior knowledge of the measurement errors distribution, specified only by its first two moments. Furthermore, the proposed model allows for a multiplicative dependence of errors on the state of the moving object. The filter incorporates direction angles and range measurements generated by several independent measurement complexes. As a practical application, the method is used for tracking an autonomous underwater vehicle moving toward a stationary target. The vehicle’s velocity is influenced by continuous random disturbances and periodic abrupt changes. Observations are performed by two stationary acoustic beacons. Full article

With the growing demand for global energy transition, integrated energy systems (IESs) have emerged as a key pathway for sustainable development due to their deep coupling of multi-energy flows. Accurate load forecasting is crucial for IES optimization and scheduling, yet conventional methods struggle with complex spatio-temporal correlations and long-term dependencies. This study proposes ST-ScaleFusion, a multi-scale time–frequency complementary hybrid model to enhance comprehensive energy load forecasting accuracy. The model features three core modules: a multi-scale decomposition hybrid module for fine-grained extraction of multi-time-scale features via hierarchical down-sampling and seasonal-trend decoupling; a frequency domain interpolation forecasting (FI) module using complex linear projection for amplitude-phase joint modeling to capture long-term patterns and suppress noise; and an FI sub-module extending series length via frequency domain interpolation to adapt to non-stationary loads. Experiments on 2021–2023 multi-energy load and meteorological data from the Arizona State University Tempe campus show that ST-ScaleFusion achieves 24 h forecasting MAE values of 667.67 kW for electric load, 1073.93 kW/h for cooling load, and 85.73 kW for heating load, outperforming models like TimesNet and TSMixer. Robust in long-step (96 h) forecasting, it reduces MAE by 30% compared to conventional methods, offering an efficient tool for real-time IES scheduling and risk decision-making. Full article

This study establishes a novel mathematical framework for stochastic maintenance optimization in production systems by integrating Markov decision processes (MDPs) with convex programming theory. We develop a Z-transformation-based dual-space decomposition method to reconstruct MDPs into a solvable linear programming form, resolving the inherent instability of traditional models caused by uncertain initial conditions and non-stationary state transitions. The proposed approach introduces three mathematical innovations: (i) a spectral clustering mechanism that reduces state-space dimensionality while preserving Markovian properties, (ii) a Lagrangian dual formulation with adaptive penalty functions to handle operational constraints, and (iii) a warm start algorithm accelerating convergence in high-dimensional convex optimization. Theoretical analysis proves that the derived policy achieves stability in probabilistic transitions through martingale convergence arguments, demonstrating structural invariance to initial distributions. Experimental validations on production processes reveal that our model reduces long-term maintenance costs by 36.17% compared to Monte Carlo simulations (1500 vs. 2350 average cost) and improves computational efficiency by 14.29% over Q-learning methods. Sensitivity analyses confirm robustness across Weibull-distributed failure regimes (shape parameter $\beta \in$ [1.2, 4.8]) and varying resource constraints. Full article

The magnetic field of the Sun is formed by the mechanism of hydromagnetic dynamo. In this mechanism, the flow of the conducting medium (plasma) of the convective zone generates a magnetic field, and this field corrects the flow using the Lorentz force, creating feedback. An important role in dynamo is played by memory (hereditary), when a change in the current state of a physical system depends on its states in the past. Taking these effects into account may provide a more accurate description of the generation of the Sun’s magnetic field. This paper generalizes classical dynamo models by including hereditary feedback effects. The feedback parameters such as the presence or absence of delay, delay duration, and memory duration are additional degrees of freedom. This can provide more diverse dynamic modes compared to classical memoryless models. The proposed model is based on the kinematic dynamo problem, where the large-scale velocity field is predetermined. The field in the model is represented as a linear combination of two stationary predetermined modes with time-dependent amplitudes. For these amplitudes, equations are obtained based on the kinematic dynamo equations. The model includes two generators of a large-scale magnetic field. In the first, the field is generated due to large-scale flow of the medium. The second generator has a turbulent nature; in it, generation occurs due to the nonlinear interaction of small-scale pulsations of the magnetic field and velocity. Memory in the system under study is implemented in the form of feedback distributed over all past states of the system. The feedback is represented by an integral term of the type of convolution of a quadratic form of phase variables with a kernel of a fairly general form. The quadratic form models the influence of the Lorentz force. This integral term describes the turbulent generator quenching. Mathematically, this model is written with a system of integro-differential equations for amplitudes of modes. The model was applied to a real space object, namely, the solar dynamo. The model representation of the Sun’s velocity field was constructed based on helioseismological data. Free field decay modes were chosen as components of the magnetic field. The work considered cases when hereditary feedback with the system arose instantly or with a delay. The simulation results showed that the model under study reproduces dynamic modes characteristic of the solar dynamo, if there is a delay in the feedback. Full article

Accurate prediction of tool wear plays a vital role in improving machining quality in intelligent manufacturing. However, traditional Gaussian Process Regression (GPR) models are constrained by linear assumptions, while conventional filtering algorithms struggle in noisy environments with low signal-to-noise ratios. To address these challenges, this paper presents an innovative tool wear prediction method that integrates a nonlinear mean function and a multi-kernel function-optimized GPR model combined with an LSTM-enhanced particle filter algorithm. The approach incorporates the LSTM network into the state transition model, utilizing its strong time-series feature extraction capabilities to dynamically adjust particle weight distributions, significantly enhancing the accuracy of state estimation. Experimental results demonstrate that the proposed method reduces the mean absolute error (MAE) by 47.6% and improves the signal-to-noise ratio by 15.4% compared to traditional filtering approaches. By incorporating a nonlinear mean function based on machining parameters, the method effectively models the coupling relationships between cutting depth, spindle speed, feed rate, and wear, leading to a 31.09% reduction in MAE and a 42.61% reduction in RMSE compared to traditional linear models. The kernel function design employs a composite strategy using a Gaussian kernel and a 5/2 Matern kernel, achieving a balanced approach that captures both data smoothness and abrupt changes. This results in a 58.7% reduction in MAE and a 64.5% reduction in RMSE. This study successfully tackles key challenges in tool wear monitoring, such as noise suppression, nonlinear modeling, and non-stationary data handling, providing an efficient and stable solution for tool condition monitoring in complex manufacturing environments. Full article

Background/Objectives: The implementation of artificial intelligence-based systems for disease detection using biomedical signals is challenging due to the limited availability of training data. This paper deals with the generation of synthetic EEG signals using deep learning-based models, to be used in future research for training Parkinson’s disease detection systems. Methods: Linear models, such as AR, MA, and ARMA, are often inadequate due to the inherent non-linearity of time series. To overcome this drawback, long short-term memory (LSTM) networks are proposed to learn long-term dependencies in non-linear EEG time series and subsequently generate synthetic signals to enhance the training of detection systems. To learn the forward and backward time dependencies in the EEG signals, a Bidirectional LSTM model has been implemented. The LSTM model was trained on the UC San Diego Resting State EEG Dataset, which includes samples from two groups: individuals with Parkinson’s disease and a healthy control group. Results: To determine the optimal number of cells in the model, we evaluated the mean squared error (MSE) and cross-correlation between the original and synthetic signals. This method was also applied to select the length of the hidden state vector. The number of hidden cells was set to 14, and the length of the hidden state vector for each cell was fixed at 4. Increasing these values did not improve MSE or cross-correlation and unnecessarily increased computational complexity. The proposed model’s performance was evaluated using the mean-squared error (MSE), Pearson’s correlation coefficient, and the power spectra of the synthetic and original signals, demonstrating the suitability of the proposed method for this application. Conclusions: The proposed model was compared to Autoregressive Moving Average (ARMA) models, demonstrating superior performance. This confirms that deep learning-based models, such as LSTM, are strong alternatives to statistical models like ARMA for handling non-linear, multifrequency, and non-stationary signals. Full article

Understanding human cortical neurodynamics is increasingly important, as highlighted by the European Innovation Council, which prioritises tools for measuring and stimulating brain activity. Unravelling how cytoarchitecture, morphology, and connectivity shape neurodynamics is essential for developing technologies that target specific brain regions. Given the dynamic and non-stationary nature of neural interactions, there is an urgent need for non-linear signal analysis methods, in addition to the linear ones, to track local neurodynamics and differentiate cortical parcels. Here, we explore linear and non-linear methods using data from a public stereotactic intracranial EEG (sEEG) dataset, focusing on the superior temporal gyrus (STG), postcentral gyrus (postCG), and precentral gyrus (preCG) in 55 subjects during resting-state wakefulness. For this study, we used a linear Power Spectral Density (PSD) estimate and three non-linear measures: the Higuchi fractal dimension (HFD), a one-dimensional convolutional neural network (1D-CNN), and a one-shot learning model. The PSD was able to distinguish the regions in α, β, and γ frequency bands. The HFD showed a tendency of a higher value in the preCG than in the postCG, and both were higher in the STG. The 1D-CNN showed promise in identifying cortical parcels, with an 85% accuracy for the training set, although performance in the test phase indicates that further refinement is needed to integrate dynamic neural electrical activity patterns into neural networks for suitable classification. Full article

Linear tight-binding models with long-range interactions and small-world geometry have a broad energy spectrum in the nearest neighbor coupling limit, while the spectrum becomes narrow in the fully connected limit due to the emergence of flat bands. A transition to a Wigner-like density of states appears at a low fraction of long-range bonds. Adding nonlinearity to the model introduces correlations among the stationary states, while multiple new states are generated as a result of the nonlinearity. In this work, we study the effect of band correlations on the local density of states for small-world networks as a function of the number of long-range bonds. We find that close to the nearest neighbor limit, the onset of correlations shifts the nonlinear density of states towards the band edge of the spectrum. Close to the opposite limit of the fully connected model, the band collapses in the band center, accompanied by a large increase in the new states induced by the nonlinearity. While in both limits the effect of correlations is to flatten the band, close to the mean field fully connected limit, the states are correlated and generally have distinct localized features. These effects may have implications for the dynamics of electrons in two-dimensional moiré structures and the onset of superconductivity in these systems. Full article

In recent decades, with the acceleration of industrialization and urbanization, the contradiction between resource development and environmental protection has become more and more prominent. Scientific simulation of the spatial and temporal correlation between habitat quality (HQ) and habitat fragmentation at a suitable scale is of great significance for maintaining the stability of regional ecosystems and achieving high-quality development. This study took the West Qinling Mountains as an example, where, firstly, the appropriate grid scale was determined based on the spatial stability of HQ, and the evolution characteristics of HQ were analyzed from 2000 to 2020 based on the InVEST model and GeoDa software. Secondly, the habitat fragmentation process was simulated from three characteristic dimensions of habitat area, habitat shape, and habitat distribution. Finally, the GWR model was used to explore the correlation mechanism between habitat fragmentation and HQ. The results showed the following: (1) The 3 km grid scale was a suitable scale for HQ evaluation and analysis in the West Qinling Mountains, and the scale effect was consistent across years. (2) The degree of HQ was at a higher level, where, from 2000 to 2020, it showed a decreasing trend, with a clear phenomenon of bipolar sharpening. The spatial distribution showed a pattern of “high in the west and low in the east, low in the north and high in the south”, and exhibited obvious spatial double clustering characteristics. (3) The degree of habitat fragmentation was at a medium level, where, from 2000 to 2020, it showed a increasing trend, with a clear bipolar contraction state. The spatial distribution showed a pattern of “high in the east and low in the west, high in the north and low in the south”, and the overall spatial distribution was retained with the change in time scale. (4) The effects of habitat fragmentation on HQ showed significant spatial and temporal non-stationary with a non-linear negative correlation. From 2000 to 2020, the degree of negative effect gradually increased, and the staggered distribution of forest, unused land, and water might offset the negative impact of unused land on HQ. The results could provide scientific evidence for the optimization of ecological patterns and ecological prevention and control in the West Qinling Mountains. Full article

This paper examined the cyclical patterns of mergers and acquisitions (M&A) in the global water sector from 1982 to 2024, with a focus on both linear and nonlinear dynamics in M&A waves. Through a univariate analysis using ARFIMA models, we found that the data exhibited stationary behavior, meaning that in response to an exogenous shock, the series is likely to revert to its original trend over time. Additionally, the non-parametric Brock, Dechert, and Scheinkman (BDS) test revealed the complex and irregular nature of M&A cycles within the sector. To account for this complexity, we applied the Markov-switching dynamic regression (MS-DR) model, which shows that once the industry enters a high-activity regime, it tends to persist in this state for extended periods. This suggests that external shocks or trends—such as regulatory reforms or global water scarcity concerns—are key drivers that trigger and sustain waves of M&A activity in the sector. Full article

Unmanned underground articulated dump trucks (UADTs) are an important direction for the coal mining industry to vigorously promote automation and intelligence. Among these, tracking and controlling the motion trajectory is the key weak link. This paper presents a kinematic analysis of the stationary turning process of UADTs. Then, a posture state model for articulated trucks is established. The objective is to optimize the control method and further improve trajectory tracking accuracy. Based on the advantages and disadvantages of the feedback linearization control (FLC) method, a sliding mode control method based on the Ackermann formula (ASMC) and integral type switch gain (ISMC) are proposed. Finally, hardware-in-the-loop simulation verifies the superiority and tracking quality of the controller. The results show that the ASMC controller can control the lateral position deviation, course angle deviation, and curvature deviation around 10 cm, 0.04 rad, and 0.08 m⁻¹ in the hardware-in-the-loop simulation environment. The ISMC controller can control the lateral position deviation, course angle deviation, and curvature deviation near 8 cm, 0.01 rad, and 0.02 m⁻¹, and can also effectively control the jitter problem. Each deviation is stabilized within 10 s. This provides a reference for the development of trajectory tracking strategies for articulated vehicles. Full article

Commonly used methods for identifying modal parameters under environmental excitations assume that the unknown environmental input is a stationary white noise sequence. For large-scale civil structures, actual environmental excitations, such as wind gusts and impact loads, cannot usually meet this condition, and exhibit obvious non-stationary and non-white-noise characteristics. The theoretical basis of the stochastic subspace method is the state-space equation in the time domain, while the state-space equation of the system is only applicable to linear systems. Therefore, under non-smooth excitation, this paper proposes a stochastic subspace method based on RDT. Firstly, this paper uses the random decrement technique of non-stationary excitation to obtain the free attenuation response of the response signal, and then uses the stochastic subspace identification (SSI) method to identify the modal parameters. This not only improves the signal-to-noise ratio of the signal, but also improves the computational efficiency significantly. A non-stationary excitation is applied to the spatial grid structure model, and the RDT-SSI method is used to identify the modal parameters. The identification results show that the proposed method can solve the problem of identifying structural modal parameters under non-stationary excitation. This method is applied to the actual health monitoring of stadium grids, and can also obtain better identification results in frequency, damping ratio, and vibration mode, while also significantly improving computational efficiency. Full article