Search Results (264)

Rapid urbanization has increasingly posed risks of inducing land subsidence in newly developed urban districts, posing growing threats to infrastructure safety. This study focuses on a selected rectangular area within the Shannan New District of Huainan City. Based on 94 Sentinel-1A images acquired from 2023 to 2025, the SBAS-InSAR technique was employed to obtain high-density spatiotemporal surface deformation data. The discrete monitoring points were mapped onto a 100 × 100 regular grid according to their spatial coordinates, with null-value cells retained. A spatial attention mechanism was then embedded into the Convolutional Long Short-Term Memory (ConvLSTM) network to construct a Spatial Attention–ConvLSTM (SA-ConvLSTM) model for spatiotemporal prediction, which was systematically compared with LSTM, CNN-LSTM (Convolutional Neural Network combined with Long Short-Term Memory), and standard ConvLSTM. The results demonstrate that SA-ConvLSTM achieves optimal prediction performance on the temporal hold-out test set, with a root mean square error of 2.09 mm and a coefficient of determination (R²) of 0.77. For subsidence hotspot identification, the intersection over union (IoU) reaches 0.56, and the F1-score reaches 0.72—substantially improving from 0.25 for standard ConvLSTM, confirming that the spatial attention mechanism effectively enhances the model’s capability to focus on key deformation areas. Rolling predictions of the deformation field for 2026 (12 time steps, each covering one Sentinel-1A acquisition interval of approximately 12 days) yield an estimated deformation trend ranging from −16.58 to 0.28 mm over the 12-step forecast period (approximately 144 days). This integrated framework provides a methodological reference for subsidence risk identification and mitigation in the Shannan New District. Full article

This study presents the development and validation of an intelligent error compensator based on Long Short-Term Memory (LSTM) recurrent neural networks for dynamic weighing systems in copper concentrate belt conveyors. Conventional weighing systems fail to capture nonlinear temporal dynamics, leading to measurement inaccuracies during container filling operations. The methodology comprised data acquisition from load cells, speed sensors, and inclinometers; systematic hyperparameter optimization; and evaluation using Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and coefficient of determination (R²). Hyperparameter optimization identified an optimal configuration with one LSTM layer (20 units, learning rate 0.001, window size 20 steps). Evaluation on an independent test set showed that the compensator reduced MAPE from 8.5% (uncompensated system) to 3.01%, representing a 64.6% improvement, and reduced RMSE from 12.3 to 4.2 tons (65.9% improvement), with an R² of 0.95. Feature importance analysis confirmed physical consistency, with load cell voltage as the dominant predictor (42%). These results demonstrate that LSTM-based compensation significantly enhances weighing accuracy. The study provides a replicable framework for industrial metrology modernization, contributing to sustainable mining operations through material loss reduction and logistics optimization. While the proposed model has been validated offline using historical data, its deployment in the live production environment remains pending. Full article

Data imputation has attracted considerable interest due to the importance of data quality, a key challenge in data science. Various statistical methods, and more recently machine learning techniques, have been developed to address the issue of missing values. In this study, we present an imputation method that integrates forecasting and backcasting using Long-Short-Term Memory (LSTM) architecture for predicting blocks of consecutive missing values. The proposed method was evaluated on a randomly generated absent group of data from a weather dataset. In this context, we assessed different hyperparameters using regression metrics. Initially, we trained and tested the models with varying data and sequence sizes on distinct units of missing data, subsequently applying the method to other units with specific data and sequence sizes. Additionally, we substituted the LSTM model with other machine learning algorithms applying, the same method, and we compared the results. Finally, we tested the method on missing blocks from a dataset obtained from the Digital Ocean Lab (DOL) weather station. Our findings indicate that this method effectively provides a reasonable estimation of missing values in time series datasets. Full article

Accurate state-of-health estimation of lithium-ion batteries under high-temperature conditions (40–50 °C) remains challenging because of accelerated electrochemical degradation and strongly nonlinear aging patterns. This paper presents a hybrid Ridge regression–convolutional bidirectional long short-term memory framework with a dual-level transfer learning strategy. A Ridge regression baseline first captures the global degradation trend, after which a convolutional bidirectional long short-term memory network learns the nonlinear residuals. For cross-battery adaptation, Ridge coefficients are transferred through prior-regularized regression, and the pre-trained network is fine-tuned using limited target-domain data. The method is validated on cycling datasets from three institutions, namely Tsinghua University, the University of Oxford, and Tongji University, covering 15 batteries under temperatures up to 50 °C. Four health-related features are extracted and adaptively denoised using locally weighted scatterplot smoothing. In single-battery extrapolation, the proposed method achieves a root mean square error as low as 0.0009 on cell B6 at 50 °C, outperforming random forest, long short-term memory, bidirectional long short-term memory, and Ridge regression by 91.1%, 88.6%, 87.7%, and 82.0%, respectively. A cross-battery ablation experiment showed that the dual-level transfer learning strategy reduced the root mean square error from approximately 0.009 to 0.0028, whereas increasing network complexity alone yielded only marginal improvement. A further hierarchical ablation showed that jointly adapting the Ridge prior and the residual network achieved a mean RMSE of 0.004325, representing reductions of 9.39%, 4.14%, and 6.92% relative to the no-adaptation, Ridge-only adaptation, and residual-network-only adaptation configurations, respectively. Full article

In this paper, we present LightBAL, an ultra-lightweight deep learning framework for real-time active cell balancing and onboard balancing control in electric vehicle (EV) battery management systems (BMSs). Although active cell balancing can improve battery utilisation and performance, applying deep learning-based balancing control strategies remains prohibitive in typical embeddable BMS platforms because of the computational complexity and inference latency of deep models. In response to this issue, we propose an AI-physics-informed controller that forecasts the voltage difference of a single cell, the SoC variation, and the optimal balancing current based on proportional feedback closed-loop (FCLL) control. The introduced framework exploits wavelet-based adaptive denoising, multi-scale hierarchical feature learning using a cooperative Principal Component Analysis (PCA) and autoencoder feature extraction technique, and a lightweight One-Dimensional Convolutional Neural Network (Conv1D) coupled with Bidirectional Long Short-Term Memory (BiLSTM) (Conv1D-BiLSTM). The implemented lightweight network is further trained by model compression methodologies such as knowledge distillation and 8-bit quantisation-aware training, aiming for efficient deployment on edge devices. Experimental validation on the multivariate battery time-series dataset demonstrates that LightBAL achieves an F1-score of 96.64%, a balancing efficiency of 94.30%, and a Mean Absolute Error (MAE) of 0.0379, outperforming methods based on conventional ANN, LSTM, and CNN. LightBAL without compression takes only 1.26 s to conclude on a PC workstation; the inference latency of the embedded light model is as low as 28.7 ms. In addition, hardware-in-the-loop (HIL) validation on the Raspberry Pi 4 platform indicates that the framework can fulfil real-time inference requirements under normal operating conditions, taking 28.7 ms per balancing process. Simulation shows that the proposed approach significantly decreases cumulative balancing energy loss by 12.4% across several driving cycle conditions. Full article

To address the limitations of static-obstacle-based route planning in forest fire missions, this study develops a three-dimensional route-planning method for fixed-wing unmanned aerial vehicles (UAVs) that accounts for time-varying fire and smoke threats, complex terrain, and flight-dynamics constraints. A cellular automaton models fire spread with wind, slope, fuel, and moisture effects, while a Gaussian plume model estimates smoke concentration. The resulting burning and high-concentration smoke cells are encoded as dynamic three-dimensional threat envelopes and local grid masks. A hierarchical proximal policy optimization (H-PPO) architecture then combines a high-level stateful long short-term memory (LSTM) policy for route-subgoal generation with a pretrained low-level flight controller that produces continuous throttle and control-surface commands in JSBSim. In 100 independent simulation tests, the complete H-PPO model achieved a 100% task success rate, a mean terrain clearance of 771.92 m, and an average online decision time of 1.290 ms. Compared with A* and RRT*, H-PPO provided higher task reliability, greater mean terrain clearance, and lower online computational cost. The results show that hierarchical temporal decision making improves safety-prioritized planning in evolving fire and smoke environments, although conservative avoidance increases route length and mission duration. Further real-world and flight-test validation is required. Full article

A fractional-order equivalent circuit model (FOECM) provides a compact and physically interpretable representation of the memory-dependent polarization behavior of lithium-ion batteries. Leveraging this property, a fractional order model-guided residual-correction framework is proposed for state-of-charge (SOC) estimation, in which the FOECM, unscented Kalman filter (UKF), and long short-term memory (LSTM) residual learner are integrated into a unified estimation chain rather than treated as separate modules. In this framework, the FOECM is parameterized using Dynamic Stress Test (DST) data and incorporated into the UKF to construct the FOECM + UKF estimator. The LSTM learns the history-dependent SOC residual from sequences of measured operating signals and FOECM + UKF SOC estimates, and its output is added to the UKF estimate without replacing the fractional-order physical model. The proposed hybrid estimator is trained and configured using the available DST, Supplemental Federal Test Procedure (US06), and Federal Urban Driving Schedule (FUDS) data, and is independently evaluated on the US06 and FUDS profiles of Cell 008. Compared with the FOECM + UKF estimator, the proposed hybrid estimator reduces the SOC root mean square error (RMSE) from 2.70% to 0.90% on US06 and from 2.93% to 1.20% on FUDS, with mean absolute error (MAE) values of 0.66% and 1.03%, respectively. These results demonstrate the effectiveness of coupling fractional-order memory modeling with sequence-based residual correction under the tested dynamic operating profiles. Full article

Precise prediction of voltage degradation is critical for the prognostics and health management of proton exchange membrane fuel cells (PEMFCs). The performance degradation of PEMFCs is governed by a complex coupling of multiple physicochemical mechanisms, including catalyst layer and proton exchange membrane degradation. Crucially, these internal degradation processes evolve across highly heterogeneous time scales, ranging from transient high-frequency fluctuations to low-frequency and long-term irreversible performance fade. Conventional predictive models, which typically rely on single-scale architectures or fixed receptive fields, are inherently ill-equipped to simultaneously decouple and capture these cross-scale temporal dynamics. To tackle this challenge, this paper innovatively proposes a multi-scale deep learning framework that integrates a multi-scale degradation trend perception module, a long short-term memory (LSTM)-based encoder–decoder architecture, and a multi-head attention mechanism. One-dimensional convolutional layers with different kernel sizes are employed to simultaneously extract local temporal features at multiple granularities, followed by the LSTM encoder–decoder to model long-range temporal dependencies, while the cross-attention mechanism dynamically allocates attention across the encoded context at each autoregressive decoding step. Experimental outcomes indicate that the proposed model realizes excellent predictive accuracy across five evaluation indices in comparison with standard baselines. In particular, the mean absolute percentage error (MAPE) reaches 1.6696%, and the maximum absolute percentage error (Max-APE) is strictly bounded within 5%, substantiating the reliability of the proposed framework for high precision and long-horizon health prognostics for PEMFCs. Full article

Perovskite solar cells (PSCs) have emerged as a disruptive photovoltaic technology for aerospace and extreme environment applications, driven by their substantial power-to-weight ratio and mechanical flexibility. However, continuous operation under harsh conditions, characterized by the AM0 spectrum, deep vacuum, extreme thermal cycling, and ionizing radiation, exposes the fundamental thermodynamic instability of traditional organic–inorganic hybrid perovskites. This comprehensive review systematically synthesizes 131 recent studies to provide a holistic framework for designing ultrastable, radiation-hardened PSCs. We critically examine the underlying degradation mechanisms, including vacuum-induced volatile desorption, UV-triggered halide segregation, and thermomechanical fracture at buried interfaces. To overcome these critical barriers, we highlight advanced engineering strategies: the transition to all-inorganic CsPbX₃ and lead-free double/chalcogenide perovskites (e.g., Cs₂SnI₆, CaHfS₃), the implementation of dopant-free inorganic transport layers coupled with self-assembled monolayers (SAMs) for cascade band alignment, and the integration of polymeric scaffolds for fracture energy toughening. Furthermore, we emphasize the imperative shift toward solvent-free vacuum deposition techniques (ALD, PLD). A distinctive focus of this review is the integration of Artificial Intelligence; specifically, we evaluate Deep Learning architectures, such as Long Short-Term Memory (LSTM) networks, for predictive State of Health (SOH) monitoring, underscoring the vital transition from simulated to empirical datasets. Finally, coupled with Material Flow Cost Accounting (MFCA), this review outlines a strategic roadmap for the commercialization and deployment of autonomous, self-diagnosing photovoltaic platforms in next-generation satellite and deep-space missions. Full article

A unifying theory of both human consciousness and memory is presented that is based on neuronal microtubules (MTs) being central to both, and different populations of pyramidal cells in neocortex and hippocampus being responsible for consciousness or memory. First, two quantum theories of consciousness are presented—the Orchestrated Objective Reduction (Orch OR) theory of Penrose/Hameroff and the Environmental-Induced Decoherence Theory (EID) theory of Neven. A Hybrid (MT/EID) theory is proposed in the context of “consciousness”-dedicated pyramidal cells in Layer V of the cerebral cortex. This MT/EID theory involves the MT vibrations of the Orch OR Theory, along with the continual superposition qubit (SPQ) formation and SPQ entanglement of the EID Theory to collectively induce SPQ formation/entanglement in Layer V of the cerebral cortex. Orch OR’s objective reduction (collapse of the waveform) is not included in this Hybrid theory because the system of SPQs themselves continuously collapses due to EID. For memory, it is proposed that Orch OR forms its basis with three specific modifications: (1) presenting “endogenous” radiofrequency (RF) vibrations generated by neuronal microtubules as forming a microtubule/RF wave “vibrational fabric” involving microtubular crystalline water cores, (2) refining Orch OR for memory by proposing SPQ formation for short-term memory and objective reduction of those qubits primarily in “memory-dedicated” pyramidal cells within cortical Layers II/III for long-term memory storage through “Quantum Darwinism” (SPQ/OR), and (3) integrating SPQ/OR with the ability of “externally” applied RF waves at 1 GHz to beneficially influence human memory through microtubule-enhancing mechanisms. It is proposed that a vibrational fabric consisting of MTs, RF waves, and generated photons provides the Photonic/RF-wave quantum coherence necessary for brain memory processing. Strong evidence for beneficial effects of exogenous RF wave treatment on memory is provided by a new bioengineered technology—Transcranial Radiofrequency Wave Treatment (TRFT; also known as TEMT). This evidence is presented in both pre-clinical and clinical studies involving normal and Alzheimer’s Disease (AD) transgenic mice, and AD patients bearing memory loss. In support of MT involvement in memory, TRFT would appear to be an ideal non-pharmacologic technology to beneficially modulate the microtubule/RF wave vibrational fabric—an intraneuronal fabric that may be at the deep core of human memory, and thus the key to Alzheimer’s Disease memory rescue. Full article

Accurate carbon price forecasting is essential for emission trading risk management and low-carbon investment decisions. In existing decomposition-prediction frameworks, secondary decomposition targets are typically selected based on statistical complexity rather than domain-informed causality, and standard Long Short-Term Memory (LSTM)-Transformer architectures discard the cell state that encodes long-term temporal memory. These limitations are particularly pronounced where energy-driven causal structures and regime-switching volatility coexist. This study proposes Causal State-driven Network (CaStNet), an intelligent forecasting framework with two core innovations. A Policy-Causality-guided Residual Secondary Decomposition (PCRSD) module replaces entropy-based criteria with Granger causality to select intrinsic mode functions (IMFs) exhibiting significant energy-carbon causal linkages for targeted variational mode decomposition (VMD). A Cell-State-Driven Dual-function Attention (CSDA) mechanism repurposes the LSTM cell state for simultaneously injecting long-term memory into the Transformer and employing the cell-state differential velocity as a volatility proxy to adaptively regulate Top-k attention sparsity. The Artificial Lemming Algorithm (ALA) globally co-optimizes decomposition dimensions and attention boundaries. A Shapley Additive exPlanations (SHAP)–Local Interpretable Model-agnostic Explanations (LIME) interpretability analysis reveals horizon-dependent driver transitions from short-term autoregressive momentum to long-term energy fundamentals, uncovering threshold nonlinearities in energy-carbon transmission channels. Validation on the Shanghai market (2013–2025) achieves point-forecast RMSE = 0.8326 and R² = 0.9777, outperforming all twelve benchmark models. Cross-market testing on the Hubei market yields R² = 0.9487, and expanding-window five-fold cross-validation on the Shanghai dataset yields mean R² = 0.9704, jointly confirming generalization robustness. Full article

Remote tele-rehabilitation requires objective pain assessment, but existing approaches fail in two distinct ways. Self-report scales such as the Visual Analog Scale and the Numeric Pain Rating Scale are easy to falsify, opening a special case of the Oracle problem in blockchain-based insurance. Cloud-based computer vision handles falsification but transmits raw biometric video off the patient’s device, violating privacy requirements. A decentralized Edge AI-Oracle architecture is proposed that combines MediaPipe Face Mesh landmark extraction with a recurrent classifier mapping Action-Unit feature sequences to a learned pain score aligned with the Prkachin and Solomon Pain Intensity scale. The recurrent cell is selected empirically across short-context (T = 2) and long-context (T = 120 frames at 24 fps) regimes, with a two-layer Long Short-Term Memory (LSTM) network adopted for deployment. Inference and Elliptic Curve Digital Signature Algorithm (ECDSA) signing run inside an ARM TrustZone Trusted Execution Environment (TEE). Biometric logs are stored off-chain on the InterPlanetary File System (IPFS). Smart contracts anchor results on-chain and open a 24 h optimistic verification window for an off-chain Watchtower auditor. On SynPAIN the LSTM reaches F1 = 0.683 on T = 120 video (leave-one-stratum-out), with a directional but non-significant advantage over Gated Recurrent Unit (GRU) (Wilcoxon p = 0.167). Cross-dataset validation on BioVid Heat Pain Database Part A (87 subjects, 174 paired observations, leave-one-subject-out) yields F1 = 0.519 for LSTM and 0.499 for GRU (Wilcoxon p = 0.549). A processor-only TEE surrogate benchmark estimates 1.96 ms (FP32) and 0.45 ms (INT8) inference latency at T = 120 with a 0.34 MB footprint and 707 µs ECDSA signing latency, leaving the INT8 inference latency more than an order of magnitude below the 33 ms per-frame budget. The dual-layer storage reduces gas costs by a factor of 23.4 (160,261 vs. 3,744,872 gas), corresponding to an illustrative mainnet cost of approximately 0.53 USD per submission at 1 gwei, rising to roughly 16 USD at a busier 30 gwei, and falling to approximately 0.005 USD on Arbitrum One (April 2026 reference parameters), so that continuous monitoring is economically practical on Layer-2. An adaptive-adversary analysis of the Watchtower shows that gross score tampering is detected at every usable operating threshold, whereas a rational adversary who inflates by less than the dispute threshold, or who shapes the injected score to fall just inside it, evades detection. Because the false-positive rate reaches zero only for $\mathsf{\delta }\gtrsim 0.15$, the protocol bounds rather than eliminates patient-side fraud and motivates a zero-knowledge proof-of-inference successor. The framework is architecturally and economically feasible as a cryptographically verifiable, privacy-preserving tele-rehabilitation substrate aligned with General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act (HIPAA) requirements through the Zero-Video Transmission principle, while remaining economically viable under post-Dencun mainnet and Layer-2 conditions. Recognition accuracy on real-world data and robustness to small-magnitude tampering remain limitations that the interchangeable recognition and audit components must improve before clinical deployment. Full article

The accurate estimation of lithium-ion battery state of health (SOH) is crucial for battery monitoring, safety, and degradation assessment; however, it remains challenging because of the nonlinear nature of battery degradation, measurement noise, and variability in the battery aging trajectory. This study aims to solve these problems by proposing a hybrid attention-based BiLSTM–RF model, which combines wavelet-based signal denoising, incremental capacity analysis (ICA)-based feature extraction, stacked Bidirectional Long Short-Term Memory (BiLSTM) networks, multi-head self-attention, principal component analysis (PCA)-based feature compression, and ensemble regression using a Random Forest (RF) model with adaptive weighted fusion. The proposed framework was tested on the NASA battery datasets (B0005, B0006, B0007 and B0018) and was further validated on the Oxford Battery Degradation Dataset using leave-one-battery-out cross validation conditions. Experimental results indicated that, in general, the proposed framework outperformed the evaluated benchmark models (CNN-LSTM, BiLSTM, and RF models) in terms of the prediction error, with a minimum RMSE value of 0.0229 for NASA battery B0007 and 0.0024 for Oxford Cell3. Ablation analysis also showed that the combination of wavelet denoising, PCA compression, temporal sequence learning and ensemble regression played a role in the overall SOH estimation performance. These results show that the proposed hybrid approach is effective and stable for SOH estimation in different battery degradation trajectories under the tested experimental conditions. Full article

This paper presents a forecasting and optimization framework for the control of a hybrid renewable energy system (HRES) integrating solar, wind, and biomass generation with lithium-ion batteries, electrolyzers, and fuel cells. A bidirectional long short-term memory (bi-LSTM) neural network model was applied for renewable generation and load forecasting, while the deep Q-network (DQN) and soft actor–critic (SAC) algorithms were used for real-time supervisory control of energy storage and hydrogen-based components. The HRES was formulated as a Markov decision process (MDP), where the agents optimize battery charging/discharging, electrolyzer activation, and fuel cell operation under dynamically changing operating conditions. Experimental results demonstrated that the SAC agent achieved more stable learning dynamics and superior operational performance compared to the DQN agent, maintaining an HRES energy imbalance below 0.5 MWh while reducing unnecessary component switching and improving overall system stability. The obtained results confirm the potential of deep reinforcement learning for adaptive and low-emission supervisory control of complex hybrid renewable energy systems. Full article

Long short-term memory (LSTM) networks demonstrate superior time-series feature extraction capabilities and have exhibited significant advantages in the soft sensing of key indicators in complex industrial processes. However, conventional LSTM networks rely solely on the output information from forward propagation through network units, neglecting the residual information between the LSTM cell outputs and the key indicators. Moreover, unidirectional LSTM networks fail to fully exploit the inherent bidirectional temporal dependencies in industrial data. These issues lead to excessive redundancy in the features learned by the network and suboptimal prediction efficiency. This paper proposes a novel dual residual-enhanced deep bidirectional LSTM (DResBiLSTM) framework that integrates bidirectional temporal modeling and dual residual learning for the soft sensing of key variables in complex industrial processes. Firstly, residual information derived from the discrepancy between previous network outputs and key indicators is introduced into the input of the traditional LSTM cell, thereby constructing a residual bidirectional LSTM (ResBiLSTM) network. Secondly, a deep neural architecture is established using residual structures to incorporate input variable residuals, enabling effective soft sensing of key industrial indicators. This framework simultaneously extracts and utilizes latent features characterized by nonlinearity and dynamics from both process and quality variables, significantly enhancing prediction performance. Finally, through both numerical simulations and experimental validations employing real-world operational data from the LaCe/PrNd solvent extraction process, the proposed method demonstrates superior predictive accuracy and better practical effectiveness compared to existing soft sensing approaches. Full article