Search Results (23,587)

Hybrid modeling techniques are increasingly important for improving predictive accuracy and control in biomanufacturing, particularly in data-limited conditions. This study develops and experimentally validates a hybrid deep learning model predictive control (MPC) framework for recombinant P. pastoris fed-batch fermentations. Bayesian optimization and grid search techniques were employed to identify the best-performing hybrid model architecture: an LSTM layer with 2 hidden units followed by a fully connected layer with 8 nodes and ReLU activation. This design balanced accuracy (NRMSE 4.93%) and computational efficiency (AICc 998). This architecture was adapted to a new, smaller dataset of bacteriophage Qβ coat protein production using transfer learning, yielding strong predictive performance with low validation (3.53%) and test (5.61%) losses. Finally, the hybrid model was integrated into a novel MPC system and experimentally validated, demonstrating robust real-time substrate feed control in a way that allows it to maintain specific target growth rates. The system achieved predictive accuracies of 6.51% for biomass and 14.65% for product estimation, with an average tracking error of 10.64%. In summary, this work establishes a robust, adaptable, and efficient hybrid modeling framework for MPC in P. pastoris bioprocesses. By integrating automated architecture searching, transfer learning, and MPC, the approach offers a practical and generalizable solution for real-time control and supports scalable digital twin deployment in industrial biotechnology. Full article

To combat the catastrophic effects of climate change, the usage of renewable energy sources (RESs) has increased dramatically in recent years. The main drivers of the increase in solar photovoltaic (PV) system grid integrations in recent years have been lowering energy costs and pollution. Active and reactive powers are controlled by a proportional–integral controller, whereas energy storage batteries improve the quality of energy by storing both current and voltage, which have an impact on steady-state error. Since traditional controllers are unable to maximize the energy output of solar systems, artificial intelligence (AI) is essential for enhancing the energy generation of PV systems under a variety of climatic conditions. Nevertheless, variations in the weather can have an impact on how well photovoltaic systems function. This paper presents an intelligent power management controller (IPMC) for obtaining power management with load and electric-vehicle applications. The architecture combines the solar PV, battery with electric-vehicle load, and grid system. Initially, the PV architecture is utilized to generate power from the irradiance. The generated power is utilized to compensate for the required load demand on the grid side. The remaining PV power generated is utilized to charge the batteries of electric vehicles. The power management of the PV is obtained by considering the proposed control strategy. The power management controller is a combination of the twisting sliding-mode controller (TSMC) and Modified Pufferfish Optimization Algorithm (MPOA). The proposed method is implemented, and the application results are matched with the Mountain Gazelle Optimizer (MSO) and Beluga Whale Optimization (BWO) Algorithm by evaluating the PV power output, EV power, battery-power and battery-energy utilization, grid power, and grid price to show the merits of the proposed work. Full article

The Internet of Things (IoT) holds transformative potential in fields such as power grid optimization, defense networks, and healthcare. However, the constrained processing capacities and resource limitations of IoT networks make them especially susceptible to cyber threats. This study addresses the problem of detecting intrusions in IoT environments by evaluating the performance of deep learning (DL) models under different data and algorithmic conditions. We conducted a comparative analysis of three widely used DL models—Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Bidirectional LSTM (biLSTM)—across four benchmark IoT intrusion detection datasets: BoTIoT, CiCIoT, ToNIoT, and WUSTL-IIoT-2021. Each model was assessed under balanced and imbalanced dataset configurations and evaluated using three loss functions (cross-entropy, focal loss, and dual focal loss). By analyzing model efficacy across these datasets, we highlight the importance of generalizability and adaptability to varied data characteristics that are essential for real-world applications. The results demonstrate that the CNN trained using the cross-entropy loss function consistently outperforms the other models, particularly on balanced datasets. On the other hand, LSTM and biLSTM show strong potential in temporal modeling, but their performance is highly dependent on the characteristics of the dataset. By analyzing the performance of multiple DL models under diverse datasets, this research provides actionable insights for developing secure, interpretable IoT systems that can meet the challenges of designing a secure IoT system. Full article

This study introduces an enhanced Intrusion Detection System (IDS) framework for Denial-of-Service (DoS) attacks, utilizing network traffic inter-arrival time (IAT) analysis. By examining the timing between packets and other statistical features, we detected patterns of malicious activity, allowing early and effective DoS threat mitigation. We generate real DoS traffic, including normal, Internet Control Message Protocol (ICMP), Smurf attack, and Transmission Control Protocol (TCP) classes, and develop nine predictive algorithms, combining traditional machine learning and advanced deep learning techniques with optimization methods, including the synthetic minority sampling technique (SMOTE) and grid search (GS). Our findings reveal that while traditional machine learning achieved moderate accuracy, it struggled with imbalanced datasets. In contrast, Deep Neural Network (DNN) models showed significant improvements with optimization, with DNN combined with GS (DNN-GS) reaching 89% accuracy. However, we also used Recurrent Neural Networks (RNNs) combined with SMOTE and GS (RNN-SMOTE-GS), which emerged as the best-performing with a precision of 97%, demonstrating the effectiveness of combining SMOTE and GS and highlighting the critical role of advanced optimization techniques in enhancing the detection capabilities of IDS models for the accurate classification of various types of network traffic and attacks. Full article

As power grids continue to expand in scale, the occurrence of cascading failures within them can lead to significant economic losses. Therefore, assessing the criticality of grid nodes is crucial for ensuring the secure and stable operation of power systems and for mitigating losses when cascading failures occur. The classical Local Link Similarity (LLS) algorithm in complex networks evaluates the importance of network nodes from a neighborhood topology perspective, but it suffers from issues such as the excessive weighting of node degrees and the neglect of electrical parameters. Based on the classical algorithm, this paper first develops the Improved Local Link Similarity (ILLS) algorithm by substituting alternative similarity metrics and comparatively evaluating their performance. Building upon the ILLS, we then propose the Electrical LLS (ELLS) algorithm by integrating node power flow and electrical coupling connectivity as multiplicative factors, with optimal combinations determined via simulation experiments. Compared to classical approaches, ELLS demonstrates superior adaptability to power grid contexts and delivers enhanced accuracy in power system node importance assessments. These algorithms are applied to rank the node importance in the IEEE 300-bus system. Their performance is evaluated using the loss-of-load-size metric, comparing ELLS, ILLS, and the classical algorithm. The results demonstrate that under the loss-of-load-size metric, the ELLS algorithm achieves approximately 25% higher accuracy compared to both the ILLS and the classical algorithm, validating its effectiveness. Full article

The energy sector uses artificial intelligence (AI) as a crucial instrument to achieve environmental sustainability targets by improving resource efficiency and decreasing emissions while minimizing waste production. This paper establishes an industry-specific executive playbook that guides energy sector leaders by implementing AI technologies for sustainability management with approaches suitable for industrial needs. The playbook provides an industry-specific framework along with strategies and AI-based solutions to help organizations overcome their sustainability challenges. Predictive analytics combined with smart grid management implemented through AI applications produced 15% less energy waste and reduced carbon emissions by 20% according to industry pilot project data. AI has proven its transformative capabilities by optimizing energy consumption while detecting inefficiencies to create both operational improvements and cost savings. The real-time monitoring capabilities of AI systems help companies meet strict environmental regulations and international climate goals by optimizing resource use and waste reduction, supporting circular economy practices for sustainable operations and enduring profitability. Leaders can establish impactful technology-based sustainability initiatives through the playbook which addresses the energy sector requirements for corporate goals and regulatory standards. Full article

A rather novel approach for delivery of inertia-like grid services through energy storage devices is described and validated by physical experiments and on-site measurements. In this approach, denoted “amplified inertia response”, an actual inertial response from a grid-connected synchronous machine is amplified. This inertia emulation approach is contrasted by what is called synthetic inertia, which uses a frequency-locked loop in order to extract the grid frequency. The synthetic inertia faces the usual input signal filtering challenges if the signal-to-noise ratio is low. The amplified inertia controller avoids the input filtering since it only amplifies the natural inertial response from a synchronous machine. However, rotor angle oscillations lead to filtering requirements of the amplified version as well, but on the output signal of the controller. Experimental comparisons are conducted both on the measurement output from the physical experiments in a microgrid and on analysis based on input from on-site measurements from a 55 MVA hydropower generator connected to the Nordic grid. In the specific cases compared, we observe that the amplified inertia version is the better method for smaller power systems, with large frequency fluctuations. On the other hand, the synthetic inertia method is the better in larger power systems as compared to the amplification of the inertial response from a real production unit. Full article

This study analyzes the feasibility of energy mixes composed of different shares of various types of power generation units, including photovoltaic (PV) and wind farms, hydropower, fossil fuel-based plants, and nuclear power. The analysis uses the concept of Energy Return on Investment (EROI), which is considered the most reliable indicator for comparing different technologies as it measures the energy required rather than monetary costs needed to build and operate each technology. Literature-based EROI values for individual generation technologies were used, along with the minimum EROI thresholds for the entire energy mix that are necessary to sustain developed societies and a high quality of life. The results show that, depending on the assumed minimum EROI value, which ranges from 10 to 30, the maximum share of intermittent renewable energy sources (IRESs), such as PV and wind farms, in the system cannot exceed 90% or 60%, respectively. It is important to emphasize that this EROI-based analysis does not account for power grid stability, which currently can only be maintained by the inertia of large synchronous generators. Therefore, the scenario with a 90% IRES share should be regarded as purely theoretical. Full article

Beef fat injection technology, used to enhance the perceived quality of lower-grade meat, often results in artificially marbled beef that mimics the visual traits of Wagyu, characterized by dense fat distribution. This practice, driven by the high cost of Wagyu and the affordability of fat-injected beef, has led to the proliferation of mislabeled “Wagyu-grade” products sold at premium prices, posing potential food safety risks such as allergen exposure or consumption of unverified additives, which can adversely affect consumer health. Addressing this, this study introduces a smart sensing system integrated with handheld mobile devices, enabling consumers to capture beef images during purchase for real-time health-focused assessment. The system analyzes surface texture and color, transmitting data to a server for classification to determine if the beef is artificially marbled, thus supporting informed dietary choices and reducing health risks. Images are processed by applying a region of interest (ROI) mask to remove background noise, followed by partitioning into grid blocks. Local binary pattern (LBP) texture features and RGB color features are extracted from these blocks to characterize surface properties of three beef types (Wagyu, regular, and fat-injected). A support vector machine (SVM) model classifies the blocks, with the final image classification determined via majority voting. Experimental results reveal that the system achieves a recall rate of 95.00% for fat-injected beef, a misjudgment rate of 1.67% for non-fat-injected beef, a correct classification rate (CR) of 93.89%, and an F1-score of 95.80%, demonstrating its potential as a human-centered healthcare tool for ensuring food safety and transparency. Full article

The urgent demand for sustainable energy solutions in the face of climate change and resource depletion has catalyzed a global shift toward cleaner energy production and more efficient storage technologies. Lithium-ion batteries (LIBs), as the cornerstone of modern portable electronics, electric vehicles, and grid-scale storage systems, are continually evolving to meet the growing performance requirements. In this dynamic context, two-dimensional (2D) materials have emerged as highly promising candidates for use in electrodes due to their layered structure, tunable electronic properties, and high theoretical capacity. Among 2D materials, molybdenum disulfide (MoS₂) has gained increasing attention as a promising low-dimensional candidate for LIB anode applications. This review provides a comprehensive yet concise overview of recent advances in the application of MoS₂ in LIB electrodes, with particular attention to its unique electrochemical behavior at the nanoscale. We critically examine the interplay between structural features, charge-storage mechanisms, and performance metrics—chiefly the specific capacity, rate capability, and cycling stability. Furthermore, we discuss current challenges, primarily poor intrinsic conductivity and volume fluctuations, and highlight innovative strategies aimed at overcoming these limitations, such as through nanostructuring, composite formation, and surface engineering. By shedding light on the opportunities and hurdles in this rapidly progressing field, this work offers a forward-looking perspective on the role of MoS₂ in the next generation of high-performance LIBs. Full article

Bupleurum scorzonerifolium Willd. is a perennial herbaceous plant of the genus Bupleurum in the Apiaceae family. Also known as red Bupleurum, it is mainly distributed in Northeast China, North China and other regions and is a commonly used medicinal plant. It is difficult for the wild plant resources of Bupleurum scorzonerifolium Willd. to meet the market demand. In artificial cultivation, there are problems such as a low yield per plant, low quality, weakened stress resistance and variety degradation. The contents of bioactive components and metabolites in traditional Chinese medicinal materials vary significantly across different growth years. The growth duration directly impacts their quality and clinical efficacy. Therefore, determining the optimal growth period is one of the crucial factors in ensuring the quality of traditional Chinese medicinal materials. In this study, Gas Chromatography–Mass Spectrometry (GC-MS) and High-performance liquid chromatography (HPLC) were comprehensively applied to analyze the metabolically differential substances in different parts of Bupleurum scorzonerifolium Willd. By comparing the compositions and content differences of chemical components in different growth years and different parts, the chemical components with significant differences were accurately screened out. In order to further explore the dynamic change characteristics and internal laws of metabolites, a metabolic network was constructed for a visual analysis and, finally, to see the optimal growth years of Bupleurum scorzonerifolium Willd. This result showed that with the accumulation of the growth cycle, the height, root width, fresh mass and saikosaponins content of Bupleurum scorzonerifolium Willd. increased year by year. Except for sodium and calcium elements in the main shoot, the other elements were significantly reduced. In addition, 59 primary metabolites were identified by GC-MS, with the accumulation of the growth cycle, the contents of organic acids, sugars, alcohols and amino acids gradually decreased, while the contents of alkyl, glycosides and other substances gradually increased. There were 53 positive correlations and 18 negative correlations in the triennial Bupleurum scorzonerifolium Willd. grid, all of which were positively correlated with saikosaponins. Therefore, the triennial Bupleurum scorzonerifolium Willd. was considered to be the suitable growth year. It not only provided a new idea and method for the quality evaluation of Bupleurum scorzonerifolium Willd., but also provided a scientific basis for the quality control of Chinese herbs. Full article

Battery-swapping stations (BSSs) are pivotal for supplying energy to electric heavy-duty trucks. However, their operations face challenges in accurate demand forecasting for battery-swapping and fair revenue allocation. This study proposes an optimization strategy for the economic operation of BSSs that optimizes revenue allocation and load balancing to enhance financial viability and grid stability. First, factors including geographical environment, traffic conditions, and truck characteristics are incorporated to simulate swapping behaviors, supporting the construction of an accurate demand-forecasting model. Second, an optimization problem is formulated to maximize the weighted difference between BSS revenue and squared load deviations. An economic operations strategy is proposed based on an adaptive Shapley value. It enables precise evaluation of differentiated member contributions through dynamic adjustment of bias weights in revenue allocation for a strategy that aligns with the interests of multiple stakeholders and market dynamics. Simulation results validate the superior performance of the proposed algorithm in revenue maximization, peak shaving, and valley filling. Full article

This study presents community-specific modeling approaches for simulating power injection from photovoltaic and wind energy systems in a German metropolitan region. Developed within the EMN_SIM project and based on openly accessible datasets, the methods are broadly transferable across Germany. For PV, a cluster-based model groups systems by geographic and technical characteristics, using real weather data to reduce computational effort. Validation against measured specific yields shows strong agreement, confirming energetic accuracy. The wind model operates on a per-turbine basis, integrating technical specifications, land use, and high-resolution wind data. Energetic validation indicates good consistency with Bavarian reference values, while power-based comparisons with selected turbines show reasonable correlation, subject to expected limitations in wind data resolution. The resulting high-resolution generation profiles reveal spatial and temporal patterns valuable for grid planning and targeted policy design. While further validation with additional measurement data could enhance model precision, the current results already offer a robust foundation for urban energy system analyses and future grid integration studies. Full article

With a potentially increasing share of the electricity grid relying on wind to provide generating capacity and energy, there is an expanding global need for historically accurate, spatiotemporally continuous, high-resolution wind data. Conventional downscaling methods for generating these data based on numerical weather prediction have a high computational burden and require extensive tuning for historical accuracy. In this work, we present a novel deep learning-based spatiotemporal downscaling method using generative adversarial networks (GANs) for generating historically accurate high-resolution wind resource data from the European Centre for Medium-Range Weather Forecasting Reanalysis version 5 data (ERA5). In contrast to previous approaches, which used coarsened high-resolution data as low-resolution training data, we use true low-resolution simulation outputs. We show that by training a GAN model with ERA5 as the low-resolution input and Wind Integration National Dataset Toolkit (WTK) data as the high-resolution target, we achieved results comparable in historical accuracy and spatiotemporal variability to conventional dynamical downscaling. This GAN-based downscaling method additionally reduces computational costs over dynamical downscaling by two orders of magnitude. We applied this approach to downscale 30 km, hourly ERA5 data to 2 km, 5 min wind data for January 2000 through December 2023 at multiple hub heights over Ukraine, Moldova, and part of Romania. With WTK coverage limited to North America from 2007–2013, this is a significant spatiotemporal generalization. The geographic extent centered on Ukraine was motivated by stakeholders and energy-planning needs to rebuild the Ukrainian power grid in a decentralized manner. This 24-year data record is the first member of the super-resolution for renewable energy resource data with wind from the reanalysis data dataset (Sup3rWind). Full article

Rolling bearings are indispensable but also the most fault-prone components of rotating machinery, typically used in fields such as industrial aircraft, production workshops, and manufacturing. They encounter diverse mechanical stresses, such as vibration and friction during operation, which may lead to wear and fatigue cracks. From this standpoint, the present study combined a 1-D convolutional neural network (1-D CNN) with a long short-term memory (LSTM) algorithm for classifying different ball-bearing health conditions. A physics-guided method that adopts fault characteristics frequencies was used to calculate an optimal input size (sample length). Moreover, grid search was utilized to optimize (1) the number of epochs, (2) batch size, and (3) dropout ratio and further enhance the efficacy of the proposed 1-D CNN-LSTM network. Therefore, an attempt was made to reduce epistemic uncertainty that arises due to not knowing the best possible hyper-parameter configuration. Ultimately, the effectiveness of the physics-guided optimized 1-D CNN-LSTM was tested by comparing its performance with other state-of-the-art models. The findings revealed that the average accuracies could be enhanced by up to 20.717% with the help of the proposed approach after testing it on two benchmark datasets. Full article