National Power (United Kingdom)

Accurate and continuous measurement of key process variables in modern coal-fired power plants is critical, yet challenging due to ”concept drift” induced by flexible operating regimes. Frequent start-ups, shutdowns, and rapid load changes introduce complex, variable, and unknown operating conditions, which degrade the performance and adaptability of conventional soft-sensing instruments. To address this measurement problem, this paper proposes a novel soft-sensing model with high accuracy and robust tracking capabilities: the Tracking Structured State Space Sequence Model (TS4). The TS4 architecture is composed of three key innovations for superior measurement performance. First, a Probabilistic Structured State Space Sequence (PS4) model is developed to establish a highly accurate baseline measurement under stable conditions and provide probabilistic uncertainty quantification. Second, a lightweight Probabilistic Kernel Recursive Least Squares (PKRLS) algorithm with a forgetting factor is derived, enabling the soft sensor to rapidly adapt to new operating conditions through online updates. Finally, a dynamic posterior weight updating strategy is designed to intelligently fuse the deep representation of PS4 with the online tracking ability of PKRLS, creating a single, robust measurement model. The proposed soft sensor was validated on operational data from a large-scale coal-fired power plant for the task of power generation measurement. Compared to various baseline models, the TS4-based instrument demonstrates significantly improved measurement accuracy and superior capability in tracking dynamic operating conditions, proving its value for enabling intelligent, safe, and efficient plant operations.

Aiming at the phenomenon that photovoltaic (PV) arrays may be partially shaded due to external influences, resulting in several power peaks in power-voltage (P-V) graph and making it difficult to find the maximum power point (MPP) accurately. In this paper, an improved sparrow search algorithm (ISSA) method is proposed to improve stability and speed of finding MPP. The conventional sparrow search algorithm (CSSA) has drawbacks of slow convergence speed and poor robustness. ISSA method makes the initial positions of the population more uniform by introducing the Tent chaos mapping. Introduce a position update strategy to optimize the positions of discoverers, followers and guards to improve the global search ability. The introduction of the random perturbation strategy in the iteration increases the perturbation during the iteration process of the population, thereby enhancing the ability of algorithm to jump out of the local optimal value and accelerating convergence. Finally, the model results in MATLAB show that compared with CSSA method, the duty cycle fluctuation of the ISSA method is smaller, with a reduction of 74.32%, making the photovoltaic output power more stable. In addition, the ISSA method significantly improves convergence speed, reducing the convergence time by 61.39%. This indicates that ISSA method has better stability and faster speed.

Abstract Offshore wind energy generation has a key role in reducing reliance on fossil fuels and mitigating climate change. However, it also has the potential to negatively impact the environment, including seabird populations. Quantifying and minimising impacts of wind projects on seabirds is necessary for ensuring compliance with environmental legislation and safeguarding populations. However, the timescales and complexity involved in assessment processes can limit the extent to which estimates can be leveraged towards balancing environmental impact and energy generation. OCcAM is a simple, user-friendly and transparent industry-developed tool allowing rapid assessment of impacts on seabirds from offshore wind developments. Mortality rates of five seabird species are estimated using two UK industry-standard models: the Band collision risk model which predicts fatal collisions with turbine blades, and the matrix-based displacement approach that predicts mortalities associated with distributional responses to the presence of a wind farm. The tool supports simultaneous analysis of up to three input parameter sets and predictions can be expressed as a percentage of a focal population. OCcAM allows auditable analyses to be run quickly and easily with no requirement for specific technical expertise, making it accessible to all stakeholders. It presents a variety of opportunities to facilitate ornithological assessment at strategic to project-specific scales. Here we demonstrate three potential applications of OCcAM: (1) predicting the cumulative impact of Scottish offshore wind farms upon protected seabird populations, (2) updating fatality estimates calculated for worst-case consented values using as-built input parameters and (3) optioneering of project design parameters relative to seabird risk.

River water level detection is accomplished by sensors. However, the bending of the river channel, width changes, riverbed morphology and other factors result in errors in the water level images monitored by the sensors, which in turn affects the accuracy of small-scale feature mapping. For this reason, this paper proposes a river water level AI detection method based on image segmentation processing. The river water level image is preprocessed by mean filtering and histogram equalization to remove noise and enhance contrast. The Retinex defogging algorithm is utilized to further improve the image quality. An image segmentation model based on L1-[Formula: see text]L2 regularity is constructed, and the image segmentation is realized by solving DCA and ADMM algorithms. In the traditional YOLOv5 network structure, the meso-scale and large-scale feature mappings are fused into the small-scale feature mapping by weighted summation to enhance the spatial information, detail information and semantic information transfer capability of the small-scale feature mapping, and the water level detection is carried out based on the improved YOLOv5. The experimental results show that when the method in this paper deals with different backgrounds, light and reflection images, the segmented accurate distinction between the river water level region and other background regions has obvious boundaries. The accuracy of water level detection is always around 98%, and the recall rate is always above 96%, which is practical.

Empowering vulnerable communities through a local culture-based approach has not yet gained prominence in the formulation of corporate social responsibility (CSR) program design, despite its substantial potential to create sustainable social impact.This research aims to examine the social impact of the Maengket Program initiated by PT PLN Indonesia Power UBP Kamojang UP PLTP Lahendong on vulnerable communities in North Sulawesi.Using a descriptive qualitative approach through in-depth interviews, FGDs, and documentation analysis, and analyzed through the Miles and Huberman model within a qualitative social impact assessment framework, the findings reveal a positive impact in three key dimensions: psychosocial transformation through increased environmental awareness, strengthening social capital through community cohesion, and indirect economic benefits through productive activities based on culture.In addition, this program strengthens the relationship between companies and communities through the integration of local cultural values into CSR strategies.This study underscores the need to mainstream cultural empowerment models in both development policies and corporate sustainability strategies to promote inclusive and contextual development.

With the increasingly stringent environmental regulations on air pollutant emission standards for thermal power plants, the importance of wet flue gas desulfurization (WFGD) technology in reducing sulfur dioxide emissions has become increasingly prominent. However, for the complex nonlinear desulfurization process, the traditional PID control has poor adaptability to operating conditions. To solve this problem, a time-delay process control strategy based on uncertainty and disturbance estimator (UDE) and state observer is proposed in this paper. In this method, the state observer is used to solve the problem that some states are difficult to measure directly, and then the uncertain disturbance estimator is used to compensate the unknown disturbance and unmodeled dynamics in the operation of the system, which effectively improves the control quality of the wet desulfurization system for complex operating conditions.

Methods based on deep learning have significantly advanced network intrusion detection systems (NIDS). However, they face critical challenges such as insufficient labeled data and difficulties in distinguishing normal traffic from anomalies. Existing methods often fail to capture both spatial and temporal dependencies effectively in complex network traffic. To overcome these limitations, we propose a novel hybrid spatiotemporal network that integrates Multi-Scale Convolutional Neural Networks (MSCNN) for spatial feature extraction and Multi-Layer Fusion Long Short-Term Memory Networks (MLFLSTM) for temporal modeling, enabling dual non-linear representations of both spatial and temporal dimensions. This innovation enables our method to better handle the complexity of network traffic, compared to conventional methods that focus only on either spatial or temporal features. Additionally, we introduce Focal Loss (FL) to address the class imbalance issue caused by imbalanced network traffic, improving detection performance for rare anomalies, a challenge that existing methods often overlook. By incorporating Bootstrap Your Own Latent (BYOL) selfsupervised learning, we enable the model to effectively learn from limited labeled data, making it more scalable and robust compared to traditional supervised learning methods. Experimental results on the CICIDS2017 dataset, which includes various network attack scenarios, demonstrate the effectiveness of our approach, showing superior performance in detecting both common and rare network anomalies compared to existing methods.

We previously identified Paenibacillus species in the cerebrospinal fluid of 44% of infants presenting for neurosurgical evaluation with findings consistent with postinfectious hydrocephalus (PIH) in Eastern Uganda. Here we sought to compare outcomes among hydrocephalic infants with and without Paenibacillus detection at the time of hydrocephalus surgery. In a prospective observational study, 78 infants with PIH who underwent a cerebrospinal fluid (CSF) diversion prior to 90 days of age had a positive CSF polymerase chain reaction result for Paenibacillus species (PP), and 111 had a negative result (PN). The primary outcome was diversion failure-free survival defined as being alive without diversion failure at last patient contact. Secondary outcomes included overall survival and diversion success. After a median follow-up period of 35.7 months, the primary outcome was observed in 42 PP patients (54%) and in 76 PN patients (68%) (adjusted hazard ratio (aHR), 2.45; 95% confidence interval [CI], 1.42 to 4.22; P=0.001). PP patients who underwent endoscopic diversion had the worst primary event rate (aHR, 6.47; 95% CI, 2.40 to 17.42; P<0.001). Death from any cause occurred in 16 PP patients (20%) and 9 PN patients (8%) (aHR, 3.47; 95% CI, 1.44 to 8.37; P=0.006). Diversion failure occurred in 28 PP patients (36%) and in 29 PN patients (26%) (aHR, 2.24; 95% CI, 1.31 to 3.85; P=0.003). In this study, Paenibacillus detection in the CSF at the time of hydrocephalus surgery was associated with a significantly increased rate of the composite of diversion failure or death, death, and diversion failure, and was particularly increased for patients who had an endoscopic diversion.