Real-time Model Research Articles

Signal recognition and prediction system based on random forest model

To accurately predict the occurrence of rock bursts during deep coal mining and ensure the safe and efficient operation of coal mines, a signal recognition and prediction system based on the Random Forest model is proposed. This system utilizes electromagnetic radiation (EMR) and acoustic emission (AE) signal data, employing feature extraction and point biserial correlation analysis to screen out the most relevant feature parameters. A Random Forest binary classification model is constructed to identify interference signals. Subsequently, by introducing new features such as moving average slope and exponentially weighted moving average (EWMA), a time series analysis of precursor feature signals is conducted. A real-time warning model based on the Random Forest algorithm is developed, dynamically calculating the probability of precursor feature signal occurrence by integrating historical data and real-time data changes. This approach improves the accuracy and recall rate of signal recognition and prediction, providing reliable data support for mine safety management.

Enhancing real-time urban drainage network modeling through Crossformer algorithm and online continual learning

This study presents an innovative approach to real-time modeling of urban drainage networks, leveraging a highly accurate coupled one- and two-dimensional hydrodynamic model to generate a training dataset for node water levels. By employing global states inferred from monitoring points as model inputs, this study overcomes the limitations imposed by the scarcity of monitoring data and the challenge of capturing all node levels. The Crossformer algorithm, which simultaneously accounts for correlation at both temporal and feature scales, is applied to enhance the precision of simultaneous water level predictions across the network. Comparative analysis of different prediction patterns reveals that extending predictions based on a high-accuracy infrastructure offers more benefits than direct modifications to the algorithm's structure. In addition, this paper pioneered the application of online continuous learning concepts to update the prediction model in real time, achieving a balanced integration of measured and simulated data. Consequently, this paper establishes a complete monitoring-predicting-updating real-time simulation system for urban drainage networks.

Kinodynamic Model-Based UAV Trajectory Optimization for Wireless Communication Support of Internet of Vehicles in Smart Cities

Unmanned aerial vehicles (UAVs) are utilized for wireless communication support of Internet of Intelligent Vehicles (IoVs). Intelligent vehicles (IVs) need vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) wireless communication for real-time perception knowledge exchange and dynamic environment modeling for safe autonomous driving and mission accomplishment. UAVs autonomously navigate through dense urban areas to provide aerial line-of-sight (LoS) communication links for IoVs. Real-time UAV trajectory design is required for minimum energy consumption and maximum channel performance. However, this is multidisciplinary research including (1) dynamic-aware kinematic (kinodynamic) planning by considering UAVs’ motion and nonholonomic constraints; (2) channel modeling and channel performance improvement in future wireless networks (i.e., beyond 5G and 6G) that are limited to beamforming to LoS links with the aid of reconfigurable intelligent surfaces (RISs); and (3) real-time obstacle-free crash avoidance 3D trajectory optimization in dense urban areas by modeling obstacles and LoS paths in convex programming. Modeling and solving this multilateral problem in real-time are computationally prohibitive unless extensive computational and overhead processing costs are imposed. To pave the path for computationally efficient yet feasible real-time trajectory optimization, this paper presents UAV kinodynamic modeling. Then, it proposes a convex trajectory optimization problem with the developed linear kinodynamic models. The optimality and smoothness of the trajectory optimization problem are improved by utilizing model predictive control and quadratic state feedback control. Simulation results are provided to validate the methodology.

A Study on Air Quality Analysis and the Impact of Pollutants and Climatic Factors

The study analyses how pollutants such as Particulate Matter, Sulphur dioxide, Nitrogen Oxides, Ozone, Benzene, Carbon Monoxide, Ammonia and weather conditions impact the Air Quality Index (AQI).Methods like Multiple Regression and Logistic Regression are used to examine the effects of pollutants (PM2.5, NO2, SO2) and weather factors (temperature, humidity) on AQI. The data type to be collected here will be secondary data from Kaggle.The sample size collected was 8000+, methodology used is descriptive research. The findings show that pollutants and climate factors significantly affect air quality, with recommendations for real-time monitoring, predictive modeling, and stricter regulations to improve air quality.

A semi-empirical model for online real-time control of NOX generation in diesel engines

Diesel NOX emission control is the main control content of diesel engines. Real-time high-precision NOX emission prediction model is the basic guarantee for (1) Diesel combustion management, (2) SCR after-treatment control, (3) OBD system. Existing models that rely exclusively on physical processes or data-driven artificial intelligence models fail to meet real-time requirements, while MAP look-up table-based models are poorly adapted and require extensive experiments for calibration. In this study, a new semi-empirical model for NOX emission prediction was developed, and the variables of the model were identified as exhaust temperature, engine speed, injected fuel mass flow rate, air intake mass flow rate, and exhaust oxygen mass flow rate, taking into account the mechanism of NOX generation in diesel engines as well as the requirement of real-time and direct measurability of the variables for on-line control. The influence of each variable on NOX was analyzed, the model structure of the NOX prediction model was determined, and the parameters of the prediction model were identified by least squares. The model is applied to real operating vehicles for validation and compared with a previous semiempirical model taken from the literature, and the results show that the overall accuracy of the proposed model is improved. Finally, the effect of variable uncertainty on the proposed model was assessed and it was found that the relative uncertainty in predicting NOX emissions ranged between 0 and 8% for sensor accuracies of [Formula: see text] and [Formula: see text] for exhaust temperature and intake air mass flow, respectively, suggesting that the sensor accuracy has a significant effect on the uncertainty of the model.

Hierarchical MPC-based authority allocation strategy for human–machine shared vehicles considering human–machine conflict

The uncertainty of driver behavior is an important factor affecting the safety of human–machine co-driving vehicles. Traditional rule-based models often fail to capture the nonlinear and complex characteristics of human steering behavior. To overcome this, we propose a data network-driven approach utilizing gated recurrent unit (GRU) neural networks to accurately predict driver steering behavior. The GRU-based driver model is integrated with vehicle dynamics to construct a control-oriented driver–vehicle model. Considering that human–machine conflict may cause vehicle instability, an exponential function combining proportional–integral–derivative is proposed to quantify the human–machine conflict level based on steering difference. To reasonably allocate human–computer permissions based on human–machine interaction, a hierarchical authority allocation framework is proposed. The upper layer provides a reference authority allocation via an exponential function, while the lower layer employs a real-time model predictive control (MPC) optimizer to track this reference, ensuring optimal vehicle path tracking and stability. The proposed system’s effectiveness is validated through driver-in-the-loop testing, demonstrating significant improvements in safety and performance. The results show that in the human–machine conflict scenario, the proposed authority allocation strategy can still ensure the path tracking and safety of the vehicle.

Real-time hazard assessment of maize based on the chilling injury process —— Using a standard curve to establish a daily cumulative assessment method

Cold damage caused by low temperatures is known as chilling injury (CI), and it has consistently been one of the primary meteorological disasters affecting maize. With ongoing global climate change, the issue of chilling injury is becoming more prominent, exhibiting new characteristics and presenting new challenges. Consequently, understanding the disaster process and conducting a more refined real-time chilling injury identification have become significant challenges. In this study, we divided maize planting areas into seven maturity types based on the accumulated temperature, constructed a standard curve of the daily accumulated temperature from 1991 to 2020, proposed real-time identification indicators based on the CI process, and developed a real-time CI hazard assessment model. The results indicated that the model can capture independent CI events and rapidly determine the location, intensity, duration and scope of CIs, thereby providing a basis for accurately understanding the impact of chilling injury and taking timely countermeasures. The combination of accumulated temperature standard curves for seven maturity types of maize and the CI curve was used to construct the CI daily scale identification indicator, ΔEAT. Judgment thresholds for the CI identification indicators at various maturity levels were obtained by correlating them with historical disaster data. The frequency and intensity of maize CI gradually increased from the extremely late-maturing zone to the extremely early-maturing zone, with the seeding and emergence periods being the peak periods for CI. The spatiotemporal evolution characteristics of the three different degrees of CI events in 1992, 2004, and 2017 were consistent with the historical disaster records. Northeastern Inner Mongolia and most of Heilongjiang were found to be high-hazard areas for maize CIs. The constructed daily CI identification indicators can accurately and rapidly identify maize CIs, providing practical and targeted guidance for combating these injuries.

Machine learning-based rainfall forecasting in real-time optimal operation of urban drainage systems

This paper presents a rainfall forecast-based real-time optimal operation model of urban drainage systems (UDSs) investigating the role of rainfall forecasts in predictive real-time operation of UDSs. Two rainfall forecast models, namely long short-term memory (LSTM) and optimized-by-PSO (particle swarm optimization) support vector regression, are linked to an integrated simulation–optimization model. For any given operation policies, the rainfall-runoff stormwater management model (SWMM) simulates the urban system’s operation under flooding conditions in which the operation policies are optimized by the metaheuristic harmony search (HS) optimizer. The objective function of the HS algorithm is minimizing flood volumes at control points. The presented approach is therefore a dynamic predictive real-time operation (PRTOP) model that continuously updates rainfall forecasts and operational decisions during flood events. The performance of the developed forecast-based integrated SWMM-HS simulation–optimization modeling framework is tested through its application in a real urban system case study located in Tehran, Iran. Results demonstrate that a notable reduction in flood volume (11.8%) is achieved by using the LSTM-driven rainfall forecasts in the proposed PRTOP model compared to a reactive real-time operation (RTOP) model not utilizing rainfall forecasts.

Lightweight medical image segmentation network with multi-scale feature-guided fusion

In the field of computer-aided medical diagnosis, it is crucial to adapt medical image segmentation to limited computing resources. There is tremendous value in developing accurate, real-time vision processing models that require minimal computational resources. When building lightweight models, there is always a trade-off between computational cost and segmentation performance. Performance often suffers when applying models to meet resource-constrained scenarios characterized by computation, memory, or storage constraints. This remains an ongoing challenge. This paper proposes a lightweight network for medical image segmentation. It introduces a lightweight transformer, proposes a simplified core feature extraction network to capture more semantic information, and builds a multi-scale feature interaction guidance framework. The fusion module embedded in this framework is designed to address spatial and channel complexities. Through the multi-scale feature interaction guidance framework and fusion module, the proposed network achieves robust semantic information extraction from low-resolution feature maps and rich spatial information retrieval from high-resolution feature maps while ensuring segmentation performance. This significantly reduces the parameter requirements for maintaining deep features within the network, resulting in faster inference and reduced floating-point operations (FLOPs) and parameter counts. Experimental results on ISIC2017 and ISIC2018 datasets confirm the effectiveness of the proposed network in medical image segmentation tasks. For instance, on the ISIC2017 dataset, the proposed network achieved a segmentation accuracy of 82.33 % mIoU, and a speed of 71.26 FPS on 256 × 256 images using a GeForce GTX 3090 GPU. Furthermore, the proposed network is tremendously lightweight, containing only 0.524M parameters. The corresponding source codes are available at https://github.com/CurbUni/LMIS-lightweight-network.

An early warning method of pipeline leakage monitoring with limited leakage samples

Aiming at the problems of low computational efficiency of the real-time transient model (RTTM), and training difficulty of data-driven models with small leakage samples in existing pipeline leakage monitoring methods, this paper proposes a novel pipeline leakage detection model (Multiple Regression Modeling of Real-time Transients, MR-RTTM) based on the fusion of real-time transient mechanism model and data-driven inference. Firstly, the real-time transient mechanism model of pipelines is derived based on the Bernoulli equation, and the required eigenvalues and label values of the data-driven model are determined to achieve the integration of the mechanism and the data-driven model. Secondly, MR-RTTM is constructed by applying the data of pipelines in normal working conditions and combining with the multiple regression algorithm to fit the real-time transient mechanism model of pipelines. An optimal threshold interval selection method of the model is also proposed based on the probability of detection (POD) and the probability of false call (POFC). Experiments show that MR-RTTM can detect pipeline leakage by arranging common pressure and flow rate sensors in the pipeline inlets and outlets, and the minimum detectable leakage is 1 % with an acceptable interval of 80 %∼100 % for POD and 0 ∼ 10 % for POFC, and the leakage discrimination rate is up to 100 %.

Real-time predictive control assessment of low-water head hydropower station considering power generation and flood discharge

In the real-time operation of cascade reservoirs, when the discharge flow of the upstream power station changes frequently, the downstream power station with a low head and small storage capacity has to adjust the gate or turbine frequently to keep the water level safe. This paper proposes a real-time optimal scheduling model based on model predictive control theory(MPC), considering the interaction between power generation and flood discharge. Firstly, the correlation analysis is carried out between the outflow of the Zhentouba hydropower station(ZTB) and the inflow of the Shaping II Hydropower Station(SP), and the spatio-temporal hydraulic connection between the ZTB and SP is obtained. The fuzzy relationship between tail water level and discharge flow is accurately described using numerical simulation, considering the interaction between power generation and discharge. Secondly, based on the precise description of inflow and outflow, a high-precision water level rolling prediction model is constructed using the water balance principle. Finally, based on the MPC, the real-time control model of SP is constructed. The results show that the water level process is steadier, with fewer gate adjustments. Compared with the observed number of gate adjustments in 2020, the number of reservoir gate adjustments after model optimization is reduced by 73.26%. It improves the operation efficiency and safety of the hydropower station and provides a guidance basis for the optimal operation of the SP.

Real Time Prediction and Modelling of Power Grid System Stability and Load Balancing

Abstract The extensive geographical distribution of the power system determines its highly complex structure. The system includes key components such as generators, substations, transmission and distribution grids, and users. This system has characteristics such as nonlinearity, time-varying, and parameter uncertainty. Power system stability is inherently linked to its regular operational performance. This article uses Simulink models to simulate the working state of generators and circuit breakers during faults. Under the conditions of a synchronous generator with a rated power of 350MW, a voltage of 10.5KV, a three-phase parallel RLC load rated voltage of 115KV, and a power consumption of 300MW, when a short occurs on line, the speed and relative angle of the generator tend to a fixed value, and the system remains stable. When a fault occurs in the circuit within 0.1 seconds, the circuit breaker will cut off the faulty line within 0.6 seconds. Avoiding the occurrence of oscillations and unstable states in typical dynamic systems.

Kalman filter-driven state observer for thermal error compensation in machine tool digital twins

Sustainable reduction of thermal errors during production is the key challenge in modern high-precision manufacturing. Numerical compensation models provide an energy-efficient solution, but in the case of data-driven models, high-quality experimental data must be time-consuming and expensive to produce, negatively impacting overall productivity. Furthermore, robustness concerns arise in the case of new operating conditions, which were not contained in the training data. This paper presents a novel use of a Kalman filter together with model order reduced finite element models to observe the entire thermal state, which allows the subsequent solution of the mechanical model and computation of the thermal errors in real-time without requiring any training data but instead purely based on the physical system model. The effectiveness of this approach is evaluated using experiments on a thermal test bench with 16 out of 40 temperature sensors employed for observation and demonstrated on a 5-axis machine tool (MT) with 13 out of 25 temperature sensors used. Due to the combination of the reduced order model and Kalman filter these 13 temperature sensors are sufficient to represent a MT mesh of more than 350’000 elements. The entire temperature profile of the thermal test bench is reconstructed to achieve a root mean square error (RMSE) of the unobserved temperature sensors of only 2.7 °C, which accounts for more than 83% of all temperature variations and 1.3 °C for the 5-axis MT. For the thermal error of the thermal test bench, the RMSE could be reduced from 67.4μm to 33.3μm, corresponding to a reduction of 52.7 %. This could be achieved without the need for experimental data for model calibration, in a real-time capable physics-based model.

Integrated real-time dispatch of power and gas systems

The integrated operation of the electricity and gas systems has attracted the attention of many researchers due to the ever-increasing interdependency between the two systems. In this paper, a novel framework for the real-time rolling dispatch of the integrated system is presented, targeting to attain the economically optimal and technically secure gas system real-time operation through the control of the available flexibility procured by various resources. A decoupled day-ahead scheduling is initially executed to determine unit commitment and gas linepack target decisions, which are then utilized as inputs to the proposed integrated real-time dispatch model. Intra-day gas system control is executed in a hierarchical procedure through the deployment of four control actions from various inter-system flexibility providers. The presented analysis illustrates that, based on the selection of control parameters, the activation of flexibility resources from both systems can be steered in such a way as to alleviate linepack deviations, even in cases of severely limited scheduled gas supply. The proposed control framework is tested on the Greek power and gas systems, providing significant insights regarding the activation of the control actions for the real-time gas system balancing in different look-ahead horizons.

TCT-206 Real-Time Predictive Modeling for Deployment of Transcatheter Aortic Valve Prostheses Using a Novel Reduced Order Model-Driven Computational Framework

TCT-206 Real-Time Predictive Modeling for Deployment of Transcatheter Aortic Valve Prostheses Using a Novel Reduced Order Model-Driven Computational Framework

Decision-making method of managed pressure drilling based on real-time calculation and analysis models

Abstract As petroleum exploration and development extend towards marginal, deep, and unconventional resources, drilling challenges such as narrow density windows and high wellbore control risks become increasingly prominent. Managed pressure drilling (MPD) proves effective in reducing drilling operational difficulties and well control risks in narrow safe-density window formations. However, existing MPD systems have limited capabilities for real-time calculation and analysis in the absence of downhole pressure measurement data, hindering accurate guidance for real-time calculation, analysis, and control decision recommendations in both conventional and precise MPD operations.Therefore, based on on-site engineering logging, real-time data from MPD operations, a branch decision tree was established to automatically determine the operational conditions of MPD. This achieved real-time identification of 11 drilling conditions. Starting from the characteristics of two-phase fluid flow in the annulus, coupling wellbore pressure and formation fluid invasion, a predictive model for annular pressure distribution during MPD was established. This model facilitated the calculation, determination, and recommendation of the pre-control value for wellhead backpressure. Building upon theoretical research, a MPD calculation, analysis, and control decision system was developed. Field testing and validation indicated that the system could simulate and analyze wellbore pressure and wellhead backpressure values, automatically identify drilling conditions and downhole complexities. The average error between the calculated and measured values of the standpipe pressure was 1.88%. The accuracy of the predicted wellhead backpressure values based on safe operating conditions compared to the actual controlled values reached 89.8%. This system achieved real-time calculation, analysis, and control decision-making based on real-time engineering parameters, enhancing the reliability and timeliness of wellhead backpressure control in MPD operations. It effectively guided conventional MPD operations and improved the capabilities and intelligence level of precision MPD operations after process optimization.

A real-time phase transition modeling of supercritical steam cycle and load variation rate enhancement of thermal power plants under deep peak shaving

The ambitious green revolution to renewable energy sources in global power grids necessitates massive integration of solar and wind energy, which involves intermittent and unpredictable challenges. Thermal power plants are crucial in stabilizing the grid and addressing these challenges through flexibility reformation including deep peak shaving and frequent load variations since the unsteady state energy transfer and thermal dynamics during combustion and heat transformation in thermodynamic processes vary significantly. These conditions lead to issues such as furnace instability and latent heat of phase transition. This study introduces a novel approach to modeling phase transitions of supercritical steam cycle, and investigatesthe length, position, temperature, and energy transfer of the working medium and components under normal and low operational states. Conducting and analyzing the thermal feasible region associating the security of components and working medium this study establishes a control strategy for dynamic heat transfer to reduce component degradation effects andenhance load variation rate under flexible operations. Simulation model of a supercritical power unit based on the proposed method demonstrates an accuracy of 97.94%. Results from the optimal approach in maximizing load variation rate show the effectiveness and achieve 1.2%p.e./min most under transition process.

Emotion recognition based on a limited number of multimodal physiological signals channels

Emotion constitutes a higher-order cognitive process, moreover, physiological signals can offer a more objective and realistically reflection of human emotional state. Electroencephalograph (EEG) signals, controlled by the central nervous system, are highly sensitive to emotional state fluctuations. Current research primarily focuses on recognizing emotions through feature extraction from multi-channel EEG signals. However, the acquisition of multi-channel EEG signals is hindered by difficulties acquiring from hair occlusion. The objective of this study is to construct a real-time physiological-emotion recognition model based on 2-channel EEG signals from the forehead without hair occlusion combined with 3-channel peripheral physiological (PPS) signals, employing signal preprocessing, feature extraction, feature normalization, and the ensemble learning algorithm Light Gradient Boosting Machine (LightGBM). In this paper, thirty participants sequentially viewed fourteen virtual reality (VR) scenes, rated for valence and arousal using the Self-Assessment Manikin (SAM) scale after each scene. The 2-channel EEG signals and 3-channel PPS signals were recorded synchronously from forehead by VR Head-Mounted Displays (HMD) Bio Pad developed in our research center. Our proposed model achieved median accuracy of 89.68% for valence, 90.11% for arousal in binary classification, and 84.93% for four classification of emotion recognition based on the collected samples. Furthermore, verification result of the proposed method on a public database (DEAP) achieved accuracy of 84.03%, 84.37%, and 72.23% on valence, arousal, and four classification, respectively. The proposed physiological-emotion recognition model, utilizing a limited number of multimodal physiological signals channels from wearable devices, demonstrates higher accuracy compared with the results in some literature, suggesting its potential for real-time implementation due to limited signal channels and low runtime.

Personalized Health Management Strategies Based on Deep Reinforcement Learning in the Network Environment

In order to study the optimal personalized motion push target, the author proposes a personalized health managementstrategy based on deep reinforcement learning in the network environment. Firstly, the research problem is defined, and a real-time interactive personalized motion target decision-making model is constructed; Subsequently, in response to the uncertain characteristics of user behavior in the problem, a deep reinforcement learning algorithm was adopted, combined with the departure strategy temporal difference learning method and neural network nonlinear fitting method, in order to learn strategies from user historical data; Finally, the effectiveness of the proposed method was validated using a real dataset from Fitbit. The research results indicate that personalized motion goal push services based on deep reinforcement learning can help users cultivate a healthy lifestyle and improve their personal health management level by analyzing user behavior data in real-time, providing scientific guidance and timely incentives.

Real-time adaptive model of mainstream parameters for aircraft engines based on OSELM-EKF

Gas path parameters play a crucial role in the health management of aeroengines, which are usually generated from the nonlinear component-level model. However, risks of stability and substantial time consumption confine online applications of conventional models. This paper proposes a mainstream parameter model that exclusively involves rotating components using fewer gas path parameters, including an adaptive strategy based on an online sequential extreme learning machine and an extended Kalman filter. The mainstream parameter model is designed in a linear parameter-varying form with a non-iterative smooth state-switching mechanism and enables real-time operation by simplifying the component complexity. Besides, some sensor measurements are employed to update rotor speeds, thus eliminating the need for derivative computations. Neural networks are introduced in compressor component calculations. Additionally, the extended Kalman filter is developed to estimate health parameters to tune the system equation residuals, and the learning machine is applied to compensate for rotating components’ pressure ratios under different degradation magnitudes. Finally, systematic tests are carried out to evaluate the computation accuracy and fast capabilities of the mainstream parameter adaptive model in various scenarios. Simulations demonstrate the proposed methodology's superiority over traditional adaptive correction schemes.