Intelligent Monitoring Research Articles

Triglyceride-glucose index is associated with all-cause mortality in critically ill patients with alcohol use disorder: a retrospective cohort study

BackgroundThe relationship between Triglyceride-glucose (TyG) index and clinical outcomes in patients with alcohol use disorder (AUD) is unclear. The aim of this study was to evaluate the association between TyG index and all-cause mortality in critically ill patients with AUD.MethodsWe used data from the multi-parameter intelligent monitoring in intensive care IV (MIMIC-IV) database. The patients were equally divided into quartiles. Kaplan–Meier curves were used for survival analysis. The primary endpoint of the study was 28-day mortality, followed by 1-year mortality. We used Cox proportional hazard models to assess the relationship between TyG index and all-cause mortality at different endpoints.ResultsA total of 537 AUD patients were included. Using TyG value as a continuous variable (HR 1.460, 95% CI 1.121–1.903, p = 0.005) and categorical variable (HR 1.447–3.477 from Q2 to Q4, with Q1 as reference), elevated TyG value was significantly associated with increased 28-day mortality. TyG was positively associated with 1-year mortality in AUD patients with an HR of 1.295 (95% CI 1.011–1.659, p = 0.041).ConclusionTyG index is positively associated with different clinical outcomes of critically ill AUD patients.

An investigation on energy-saving scheduling algorithm of wireless monitoring sensors in oil and gas pipeline networks

With the rapid development of the oil and gas industry, monitoring the safety and efficiency of pipeline networks has become particularly important. In this context, Wireless Sensor Networks (WSNs) are widely used for monitoring oil and gas pipelines due to their flexible deployment and cost-effectiveness. However, since sensor nodes typically rely on limited battery power, extending the network’s lifecycle and improving energy utilization efficiency have become focal points of research. Therefore, this paper proposes an energy-saving scheduling algorithm based on transformer networks, aimed at optimizing energy consumption and data transmission efficiency of wireless monitoring sensors in oil and gas pipelines. Firstly, this study designs a deep learning-based Transformer model that learns from historical data on energy consumption patterns and environmental variables to predict the energy and data transmission needs of each sensor node. Secondly, based on the prediction results, this algorithm employs a dynamic scheduling strategy that automatically adjusts the sensor’s operational mode and communication frequency according to the node’s energy status and task urgency. Additionally, we have validated the effectiveness of the proposed algorithm through field tests and simulation experiments. According to the experimental results, our model has higher efficiency in energy saving. Compared with Convolutional Neural Networks, Recurrent Neural Networks and Graph Neural Networks, the total energy consumption of sensor networks under the model scheduling in this paper was reduced by 6.7%, 33.4% and 26.3%, respectively. Our algorithms improve the energy efficiency and stability of the monitoring system and provide important technical support for future intelligent pipeline monitoring systems. We hope this paper will inspire future scientific research in this field.

Internet of Things-Driven Precision in Fish Farming: A Deep Dive into Automated Temperature, Oxygen, and pH Regulation

The research introduces a revolutionary Internet of Things (IoT)-based system for fish farming, designed to significantly enhance efficiency and cost-effectiveness. By integrating the NodeMcu12E ESP8266 microcontroller, this system automates the management of critical water quality parameters such as pH, temperature, and oxygen levels, essential for fostering optimal fish growth conditions and minimizing mortality rates. The core of this innovation lies in its intelligent monitoring and control mechanism, which not only supports accelerated fish development but also ensures the robustness of the farming process through automated adjustments whenever the monitored parameters deviate from desired thresholds. This smart fish farming solution features an Arduino IoT cloud-based framework, offering a user-friendly web interface that enables fish farmers to remotely monitor and manage their operations from any global location. This aspect of the system emphasizes the importance of efficient information management and the transformation of sensor data into actionable insights, thereby reducing the need for constant human oversight and significantly increasing operational reliability. The autonomous functionality of the system is a key highlight, designed to persist in adjusting the environmental conditions within the fish farm until the optimal parameters are restored. This capability greatly diminishes the risks associated with manual monitoring and adjustments, allowing even those with limited expertise in aquaculture to achieve high levels of production efficiency and sustainability. By leveraging data-driven technologies and IoT innovations, this study not only addresses the immediate needs of the fish farming industry but also contributes to solving the broader global challenge of protein production. It presents a scalable and accessible approach to modern aquaculture, empowering stakeholders to maximize output and minimize risks associated with fish farming, thereby paving the way for a more sustainable and efficient future in the global food supply.

Intelligent Structural Health Monitoring and Noncontact Measurement Method of Small Reservoir Dams Using UAV Photogrammetry and Anomaly Detection

Intelligent Structural Health Monitoring and Noncontact Measurement Method of Small Reservoir Dams Using UAV Photogrammetry and Anomaly Detection

Intelligent monitoring and quantitative evaluation of fire risk in subway construction: Integration of multi- source data fusion, FTA, and deep learning

Due to their long, winding passages and poor visibility, subway systems are highly susceptible to rapid smoke spread during fires, risking substantial casualties. This paper examines the causes of fire risks in subways, compiling a comprehensive list of risk factors and using fault tree analysis (FTA) to underscore the importance of fire monitoring systems in the causal chains of subway construction fires. To improve the speed, accuracy, and responsiveness of fire detection in subway construction, this study introduces a novel fire monitoring system incorporating wireless sensor networks, edge computing, multi-source data fusion, and deep neural networks. The system employs a multi-wireless sensor network (M-WSN) for transmitting monitoring data, using Long Short-Term Memory (LSTM) for time series prediction of sensor data, followed by deep belief network (DBN) for fusing multi-source data to identify fire risks. It also includes a gas diffusion model and a weighted windy-centroid localization algorithm (W-CLA) to develop a fire source localization algorithm suitable for windy conditions. Furthermore, an improved framework is established for assessing fire risks in subway construction. Practical applications demonstrate that this system not only extends the range of data collection, achieves 100% accuracy in fire risk identification, and maintains a key fire risk indicator prediction error (RMSE) of 3.34 with fire source localization errors under 0.4 m, but also effectively enhances the system's capability for rapid detection, accurate risk identification, and precise source localization.

Intelligent Lost Circulation Monitoring Method Based on Data Augmentation and Temporal Models

Deep and offshore drilling operations face complex geological formations, uncertain formation pressures, and narrow safety density windows, making them susceptible to lost circulation risks. To address these challenges, this paper introduces an innovative, intelligent lost circulation monitoring model that incorporates geological lithology information. This model not only utilizes real-time drilling parameters, but also encodes geological information such as rock type as inputs to the model. By combining these key lithological features, the model can comprehensively assess wellbore stability and reduce the lost circulation risks. In this paper, the Conditional Tabular Generative adversarial network (CTGAN) model is used to enhance the data of small-sample risk data, which can effectively expand the data distribution space and improve the performance of the model. This paper conducts a comparative analysis of intelligent monitoring results using artificial neural networks (ANNs), long short-term memory (LSTM), and temporal convolutional networks (TCNs). The results show that the TCN achieves an identification accuracy of 93.7%. Furthermore, the analysis reveals that the inclusion of lithology information significantly enhances the model’s performance, resulting in a 7.1% increase in accuracy. The false alarm rate of the model can be reduced by 10.2%, considering the fluctuation of the logging curve caused by the on/off condition of the pump. This indicates that the introduction of lithology information and the condition of the pump on−off provide advantages in monitoring and identifying lost circulation risks, enabling a more precise assessment of wellbore stability and a reduction in lost circulation incidents. The method of lost circulation monitoring proposed in this paper provides an important safety guarantee for the oil drilling industry.

Self-management in young and middle-aged patients with hypertension: a systematic review and meta-synthesis of qualitative studies

BackgroundThere has been a sharp increase in the prevalence of hypertension in young and middle-aged people at high risk of the disease. Despite the fact that good self-management can be effective in controlling blood pressure, patients do not perform well in this area, resulting in poor blood pressure control. It is therefore particularly important to gain a thorough understanding of patients’ attitudes to self-management and the factors that influence them. The aim of this study was to synthesise the qualitative research on attitudes, motivations and challenges of self-management in young and middle-aged hypertensive patients, to analyse the synthesised results using the COM-B model and to propose appropriate improvement actions.MethodsFrom the time of construction until May 2023, the system searched PubMed, Web of Science, ProQuest, Embase, MEDLINE, CINAHL, PsyCINFO and CNKI databases. The analyses were carried out using a thematic synthesis approach to summarise the key findings. The findings were then mapped and analysed using the COM-B model.ResultsA total of 11 studies were included, involving 250 patients between the ages of 18 and 64. Four themes with ten sub-themes were identified: Poor disease recognition (low disease perception, fuzzy disease knowledge); Barriers to doctor-patient interactions (short communication time, unmet knowledge needs, incomplete guidance for disease management); Living in a hostile environment (heavy workload, lack of companionship, ignorance of families); Expectations for a healthy body (responsibility of family roles, witness the cruelty of illness). Analysis of the composite results based on the COM-B model showed that low disease perceptions, barriers to doctor-patient interactions and life circumstances with enemies on all sides were the main challenges faced by young and middle-aged hypertensive patients, whereas the expectation of a healthy body was a motivation to promote self-management of blood pressure in patients.ConclusionsThis study shows that family responsibilities are a particular motivator for self-management in young and middle-aged hypertensive patients. In response to the problems they face, we believe that meeting patients’ knowledge needs, improving healthcare professionals’ communication skills and valuing the role of community hospitals are effective ways to promote patient self-management. In the future, telemedicine, mobile healthcare and intelligent monitoring devices will provide a solution to reduce the burden on medical resources.Systematic review registrationPROSPERO CRD42018100810.

Intelligent monitoring of marine vessel dynamics based on data mining

This study explores vessel navigation's universal characteristics and individual anomaly behavior from dispatch to destination. With the help of information technology, it introduces big data and machine learning technologies into the work of vessel traffic management and conducts statistical analysis and monitoring studies of vessel behavior from a data-driven perspective. The study was conducted by modeling vessel speed, position, course, and other navigational characteristics behavior through comprehensive statistical analysis of vessel AIS, radar, and VTS data. The study was based on the monitoring methods for anomalous behavior of vessel speed, position, and heading inconsistencies with the expected behavior identified by the model.

Application of digital twin technology in monitoring system of pump turbine

The advent of advanced productive forces has catalyzed the ongoing evolution of intelligent and digital technologies within the pump-turbine sector. The integration of digital technologies has not only enhanced production efficiency but also facilitated intelligent operation management, offering novel solutions for pump-turbine design and operation, thereby accelerating the digital transformation in fluid machinery. This study first established the theoretical framework of the digital twin system for pump-turbines, followed by the development of a mathematical model and the construction of a twin virtual model utilizing Proper Orthogonal Decomposition (POD) reduction theory. The model’s accuracy was validated through real-time pressure pulsation data, and exploratory investigations into cavitation prediction were subsequently carried out. To enable the visualization of the digital twin system, this study incorporated Open3D (Three-dimensional computer graphics tools) point cloud technology, effectively rendering the state cloud map of the pump-turbine. Finally, by synthesizing the proposed theories and technologies, the digital twin system’s visualization and monitoring for pump-turbines were successfully implemented through the Unity3D simulation platform. This study offers novel insights into intelligent monitoring and prediction of pump-turbines, holding significant implications for the modernization and intelligent advancement of the hydropower industry.

Design of intelligent remote monitoring and diagnosis system for equipment

Design of intelligent remote monitoring and diagnosis system for equipment

AVA-YOLO: image-based multiscale feature fusion enhanced perception model for snow avalanche detection

Abstract The global climate change has led to frequent occurrences of snow avalanche disasters. However, the significant variations in scale and shape during the avalanche process, and complex background imagery pose significant challenges to automated detection efforts. There is an urgent need to combine advanced deep learning technology to research automatic detection and recognition of avalanches in the field. In this paper, a novel deep learning model based on YOLOv8 improved multi-scale detection called AVA-YOLO is proposed to solve this problem. In AVA-YOLO, a key component, AKA (AKConv Combined Attention) module was designed and developed. This module combines the deformable convolutional properties of AKConv with the state-of-the-art self-attention module Exponential Moving Average, aiming to better perceive the feature map information of different shaped avalanches and to enhance the global relevance, thus improving the utilization of the information. Secondly, a new multi-scale sensing network structure was designed by increasing the number of detection heads to four and introducing the AKA module into the key positions of the network, while the association between model layers was newly designed to enhance the fusion of shallow and deep information to improve the detection accuracy. Experimental results demonstrated the effectiveness of AVA-YOLO, achieving 95.7% mAP50 and 75.6% mAP50:95 detection accuracies, as well as an F1 score of 0.92. Finally, a number of experiments were conducted to demonstrate the superior performance of the proposed model in comparison to other versions of YOLO, which will further exploit the potential of webcams as an underutilized technical capability in snow avalanche intelligence and portable monitoring.

Intelligent Condition Monitoring of Multiple Thermal Degradation of IGBT Modules Based on Case Temperature Matrix

Intelligent Condition Monitoring of Multiple Thermal Degradation of IGBT Modules Based on Case Temperature Matrix

Well control technology and digital intelligent management practice in Zhaodong Oilfield

Abstract Zhao-dong Oilfield is an offshore cooperation project in the mode of “international operation and PetroChina control”, adheres to the principle of “safety and environmental protection first, equal emphasis on production and efficiency”, practices the well control management concept of the whole life cycle, and consolidates the foundation of well control management by continuously optimizing the system and system, adheres to the integrated design of geology and engineering to control the source risk, implements fine trajectory control and anti-collision management to control the process risk, and The digital and intelligent production monitoring system is applied to control dynamic risks and realize the safe, efficient and sustainable development of Zhao-dong Oilfield.

Hydro-steel structure digital twins: Application in structural health monitoring and maintenance of large-scale reservoir

In the context of frequent accidents during hydro-steel structures (HSS) operations due to harsh environments and extended service conditions, a novel approach is proposed to reduce the frequency of structural failure incidents and ensure safe and reliable operation. The approach begins with introducing a comprehensive DT modeling framework. Subsequently, detailed DT modeling and DT-based SHM methods are developed. Finally, a platform with perception, interaction, analysis, and decision-making for intelligent health monitoring and maintenance of HSS is constructed and validated in China’s large-scale reservoir project, Luhun Reservoir. The platform includes functions of condition monitoring, fault feature recognition, health status assessment, and maintenance strategies optimization. The integration of DT technology has led to significant improvements in health monitoring and maintenance quality, which includes data collection, model optimization, comprehensive evaluation, and decision-making. This approach has also demonstrated its effectiveness by reducing the operation and maintenance response time and enhancing the overall efficiency and reliability.

Advanced unconditional signal processing model for cross-section contour reconstruction using multi-channel measurements

In mechanical engineering the standard method to assess the geometric tolerances of rotational parts is by analysing parts’ rotational motion in relation to the measuring system. Traditional tolerance compliance measurement models are conditional signal processing models that require pre-defined contour parameters of measured sections. However, due to part diversity and complexity, pre-determining and pre-setting the section parameters before each measurement process is very time-consuming and, in some cases, unachievable. To address this challenge, this paper proposes a universal unconditional signal processing model, which uses multi-channel measurements for cross-section contour reconstruction that operates without predefined section parameters. This model can handle multi-point measurement signals and accurately estimate the contour shape and engineering center coordinates of measured sections through circumferential Fourier expansion and an approximated signal-contour transform matrix. An efficient iterative algorithm then reconstructs the contour and precisely locates the engineering center. The computational accuracy and robustness of the proposed model have been confirmed through rigorous theoretical analysis and comprehensive experimental validation. Due to its inherent unconditional advantage, the proposed signal processing model can achieve intelligent monitoring of rotational parts throughout their entire life, which not only adapts and remains stable across a wide variety of cross-section types but also significantly improves measurement efficiency, ensuring precise and accurate results.

High-performance triboelectric nanogenerator with aminated barium titanate composite nanoparticles for early Parkinson’s disease diagnosis

High dielectric constant nanoparticles into polymer matrices have attracted much attention because this process can improve the nanofriction generator performance. However, the dispersion of the developed materials remains a challenge. In this paper, we present a novel high-performance nanofriction generator (FBT-TENG) based on composite nanoparticles of Amino-functionalized barium titanate and functionalized graphite oxide (FGO/ABTO) with Polyimide (PI) as substrate, which can be used as a sensor for intelligent monitoring systems. Specifically, we introduced amino groups on the surface of barium titanate to improve its dispersion in the PI solution, and the dual effect composite with functionalized graphite oxide improved the TENG performance of the PI film. Due to the FGO/ABTO synergy, the FBT-TENG can generate high output voltages, currents and power densities of 75 V, 13 µA and 4.6 W/m2, respectively, which is a 9 times increase in power density compared to the original PI film. FBT-TENG is capable of powering capacitors. In addition, the FBT-TENG can be used as a sensor to build an early Parkinson’s disease detection system, which provides a more convenient option for the early diagnosis of Parkinson’s patients and has the potential for a wide range of medical applications.

Digital Twin Model Study of Piping Acoustic Induced Vibration Risk

Abstract The research and calibration of digital twin models are crucial for developing an intelligent monitoring system for pipeline acoustic induced vibration. This study addresses the rapid assessment of acoustic induced vibration risks during the design stage using a digital twin model. First, the likelihood of failure (LOF) due to acoustic induced vibration was calculated based on EI guideline, providing a quantitative risk assessment. Concurrently, numerical simulations were conducted to validate these results. The findings show a high consistency between the two methods, indicating their complementary and validating roles. Therefore, the integrated use of methods based on EI guidelines and numerical simulation provides robust technical support for early-stage assessment of acoustic induced vibration risk in pipeline design, enhancing both accuracy and reliability of the evaluation, and laying a solid foundation for pipeline design and safety assurance.

Advanced design of target-driven self-powered sensor assisted by cascade catalytic strategy

In this work, a self-powered microsensor platform based on enzyme biofuel cells (EBFCs) was developed for intelligent monitoring of disease markers miRNA-451. The cascade catalysis system constructed by using the strategy of enzyme-like ZIF-8 nanocapsule incorporation with biological enzymes, which could simultaneously take into account the specificity of biological enzymes and the high activity of nano-enzymes, significantly promoted the electron transfer between glucose and the bio-anode surface, and improved the sensitivity and stability of the sensing system. Meanwhile, the target-triggered hybridisation chain reaction (HCR) amplification strategy to achieve exponential signal amplification based on accurate recognition, and jointly improve the detection sensitivity. As expected, the micro-sensor platform has a wide linear range of 0.5-1.0 fmol/L with a low limit of detection (LOD) of 0.13 fmol/L (S/N=3) and exhibits excellent selectivity, reproducibility and stability in interference assays under optimal detection conditions. The designed self-powered system is simple to construct, easy to transport and the data transmission mode is intelligent and controllable, which is expected to be used in basic biochemical research, clinical diagnosis and environmental monitoring.

Позиции Республики Корея и Японии по институционализации военно-политического сотрудничества в Азиатско-Тихоокеанском регионе

The article analyzes the current stance of the Republic of Korea (ROK) and Japan on the institutionalization of defense cooperation in the Asia-Pacific region, provides the assessment of the prospects for the US-ROK-Japan triangle institutionalization, as well as the assessment of the prospects for the possible accession of Japan and South Korea to the AUKUS agreement. Drawing from the strategic documents of Tokyo and Seoul in the field of security, as well as joint statements and other official information materials of the United States and its partners in the Asia-Pacific region, the author comes to the conclusion that the announced "Trilateral Security Cooperation Framework" of the United States – South Korea – Japan will be poorly formalized, and the main area of cooperation within this framework will be the exchange of intelligence data and monitoring of the military activity of the DPRK. The Memorandum of Cooperation concluded in July 2024 has primarily an ideological significance and is intended to create a precedent for formalizing military cooperation in a trilateral format. The potential entry of the ROK and Japan into AUKUS also has its problems. Through the license-free AUKUS arms trade ecosystem, Japan potentially can be able to develop its own defense industry and gain a foothold as an arms exporter. On the contrary, for South Korea, which is already an established exporter of military equipment and weapons, this would be a potential risk and the possibility of losing its acquired positions in Australia and other markets. Nevertheless, the prospect for both parties joining AUKUS is real, and cooperation within this multilateral format can also be of a weakly formalized nature, reduced to work on a number of joint projects, mainly in high-tech areas with the ultimate goal of developing common technological and legal standards.

Data Analysis and Algorithm Innovation in Power System IntelligentMonitoring and Early Warning Technology

Data analysis and algorithm innovation play a pivotal role in enhancing power system intelligent monitoring and early warning technology. With the increasing complexity of modern power grids, the integration of advanced data analytics enables real-time monitoring, fault detection, and predictive maintenance. By leveraging machine learning algorithms, anomaly detection techniques, and big data analytics, power systems can efficiently identify potential risks and failures before they escalate into serious issues. These innovations not only improve grid reliability and resilience but also optimize resource utilization. Early warning mechanisms based on intelligent algorithms provide timely alerts, allowing for preventive measures that ensure the stability and safety of the power network. This approach fosters a smarter, more adaptive power infrastructure capable of meeting growing energy demands while minimizing downtime and disruptions.This paper presents a comprehensive investigation into the development and efficacy of an intelligent early warning system for power systems. Leveraging machine learning algorithms, IoT sensors, and cloud computing frameworks, the system aims to enhance real-time monitoring capabilities and facilitate proactive intervention and maintenance. Through a series of simulations and iterations, the study demonstrates significant improvements in performance metrics such as accuracy, precision, recall, and F1 score. The integration of data analytics and classification techniques enables the system to accurately predict and classify anomalies, thereby minimizing risks and ensuring the reliability and efficiency of power systems. Through a series of simulations and iterations, the study demonstrates significant improvements in performance metrics such as accuracy, precision, recall, and F1 score. Specifically, the system achieves an average accuracy of 95%, precision of 92%, recall of 94%, and F1 score of 92% across multiple iterations. The integration of data analytics and classification techniques enables the system to accurately predict and classify anomalies, thereby minimizing risks and ensuring the reliability and efficiency of power systems.