Accurate Performance Prediction Research Articles

Respiratory Motion Prediction with Empirical Mode Decomposition-Based Random Vector Functional Link

The precise prediction of tumor motion for radiotherapy has proven challenging due to the non-stationary nature of respiration-induced motion, frequently accompanied by unpredictable irregularities. Despite the availability of numerous prediction methods for respiratory motion prediction, the prediction errors they generate often suffer from large prediction horizons, intra-trace variabilities, and irregularities. To overcome these challenges, we have employed a hybrid method, which combines empirical mode decomposition (EMD) and random vector functional link (RVFL), referred to as EMD-RVFL. In the initial stage, EMD is used to decompose respiratory motion into interpretable intrinsic mode functions (IMFs) and residue. Subsequently, the RVFL network is trained for each obtained IMF and residue. Finally, the prediction results of all the IMFs and residue are summed up to obtain the final predicted output. We validated this proposed method on the benchmark datasets of 304 respiratory motion traces obtained from 31 patients for various prediction lengths, which are equivalent to the latencies of radiotherapy systems. In direct comparison with existing prediction techniques, our hybrid architecture consistently delivers a robust and highly accurate prediction performance. This proof-of-concept study indicates that the proposed approach is feasible and has the potential to improve the accuracy and effectiveness of radiotherapy treatment.

Predicting optical properties of different photonic crystal fibers from 2D structural images using convolutional neural network and transfer learning

An efficient and accurate joint neural network has been established to predict the optical properties of different photonic crystal fibers using two-dimensional structural images. The input variables of this network are structural images derived from the two-dimensional material refractive index distribution of the fiber cross-section. The structural images have greater flexibility and facilitate generalization research and transfer learning testing on various types of optical fibers. The generalization properties of this neural network for other photonic crystal fibers with different lattice arrangements have been investigated, and the corresponding transfer learning method is also proposed. With this transfer learning method, only a small amount of data is required to train and update the parameter weights of the last fully connected hidden layers. As a result, efficient and accurate prediction performance can be achieved for other photonic crystal fibers with different lattice arrangements. The proposed joint neural network and the transfer learning method are flexible and efficient, which provide new approaches for more flexible optimization and reverse design of optical fiber structures in the two-dimensional parameter space.

Multi-Objective Prediction of the Sound Insulation Performance of a Vehicle Body System Using Multiple Kernel Learning–Support Vector Regression

The sound insulation performance of an electric vehicle’s body system serves as a critical metric for evaluating the noise, vibration, and harshness (NVH) quality of the vehicle. The accurate and efficient prediction of sound insulation performance is foundational for undertaking noise reduction design and optimization. Current engineering practices predominantly rely on Computer-Aided Engineering (CAE) methodologies to address this challenge. However, inherent shortcomings such as low modeling efficiency and difficulty in ensuring prediction accuracy often characterize these approaches. In an effort to overcome these limitations, we propose a decomposition framework for predicting the sound insulation performance of the electric vehicle body system. This framework is established based on a comprehensive analysis of the noise transmission paths within the system. Subsequently, the support vector regression (SVR) method is introduced to construct a machine learning model specifically designed for predicting the sound insulation performance of the body system. This approach aims to mitigate the inherent weaknesses associated with the conventional CAE processes using a ‘data-driven’ paradigm. Furthermore, the Multiple Kernel Learning (MKL) method is used to enhance the processing efficacy of the SVR model. The proposed method is validated using practical application and testing on a specific electric vehicle. The results demonstrate commendable performance in terms of prediction accuracy and robustness. This research contributes to advancing the field by presenting a more effective and reliable approach to predicting the sound insulation performance of electric vehicle body systems, offering valuable insights for noise reduction strategies and optimization efforts in the automotive industry.

Creep-Fatigue Life Evaluation for Grade 91 Steels with Various Origins and Service Histories

Grade 91 steel is widely used in the boilers and piping of thermal power plants. There has been significant research interest in understanding the variations in creep characteristics among different heats of this steel for effective plant management. In recent years, thermal power plants have been subjected to frequent load changes and startup/shutdown to adjust power supply and demand and stabilize frequencies. These operational shifts have raised concerns regarding the potential for creep-fatigue damage in high-temperature components. Therefore, this research focuses on creep-fatigue properties of Grade 91 steel and their predictability. Tensile, creep, strain-controlled fatigue, and strain-controlled creep-fatigue tests were performed on six Grade 91 steels with different heats and/or histories, and the characteristics in each test were compared. As a result, the variations in creep-fatigue life among the materials were found to be correlated with the difference in creep characteristics and stress level during stress relaxation. Furthermore, the study involved a comparative assessment of the predictive performance of creep-fatigue life using five different approaches: time fraction, classical ductility exhaustion, modified ductility exhaustion, energy-based, and hybrid approaches. Among these approaches, the hybrid approach, based on inelastic strain energy density at fracture formulated as a function of inelastic strain rate, exhibited the most accurate predictive performance.

MSRMNet: Multi-scale skip residual and multi-mixed features network for salient object detection

The current models for the salient object detection (SOD) have made remarkable progress through multi-scale feature fusion strategies. However, the existing models have large deviations in the detection of different scales, and the target boundaries of the prediction images are still blurred. In this paper, we propose a new model addressing these issues using a transformer backbone to capture multiple feature layers. The model uses multi-scale skip residual connections during encoding to improve the accuracy of the model’s predicted object position and edge pixel information. Furthermore, to extract richer multi-scale semantic information, we perform multiple mixed feature operations in the decoding stage. In addition, we add the structure similarity index measure (SSIM) function with coefficients in the loss function to enhance the accurate prediction performance of the boundaries. Experiments demonstrate that our algorithm achieves state-of-the-art results on five public datasets, and improves the performance metrics of the existing SOD tasks. Codes and results are available at: https://github.com/xxwudi508/MSRMNet.

Prediction of antibiotic sorption in soil with machine learning and analysis of global antibiotic resistance risk

Although the sorption of antibiotics in soil has been extensively studied, their spatial distribution patterns and sorption mechanisms still need to be clarified, which hinders the assessment of antibiotic resistance risk. In this study, machine learning was employed to develop the models for predicting the soil sorption behavior of three classes of antibiotics (sulfonamides, tetracyclines, and fluoroquinolones) in 255 soils with 2203 data points. The optimal independent models obtained an accurate predictive performance with R2 of 0.942 to 0.977 and RMSE of 0.051 to 0.210 on test sets compared to combined models. Besides, a global map of the antibiotic sorption capacity of soil predicted with the optimal models revealed that the sorption potential of fluoroquinolones was the highest, followed by tetracyclines and sulfonamides. Additionally, 14.3% of regions had higher antibiotic sorption potential, mainly in East and South Asia, Central Siberia, Western Europe, South America, and Central North America. Moreover, a risk index calculated with the antibiotic sorption capacity of soil and population density indicated that about 3.6% of soils worldwide have a high risk of resistance, especially in South and East Asia with high population densities. This work has significant implications for assessing the antibiotic contamination potential and resistance risk.

Deep learning power grid project cost prediction under low-carbon background

Abstract Under the background of low-carbon power system developing towards cleaner, more efficient and more economical direction, accurate prediction of power grid project cost is very important for the construction of power grid project. In order to improve the accuracy of power grid project cost prediction, a power grid project cost prediction method based on deep learning is proposed. First, for the complex and nonlinear features of the line engineering cost data, the XGBoost model is used to analyze the line engineering cost data. Feature selection and data dimension reduction are carried out through the importance ordering of the features analyzed. Then, the engineering cost integration model is established based on the XGBoost model and Stacking. The cost analysis of power grid transmission project shows that the integrated model has better generalization performance and higher prediction accuracy, and can accurately predict the line cost level.

Numerical simulation of corroded circular hollow section steel columns: A corrosion evolution approach

This study introduces a numerical simulation method for corroded circular hollow section steel columns, utilising a newly developed corrosion evolution model. This model was formulated by characterising the corrosion morphology and calibrating parameters throughout the entire corrosion process. An interpolation method was implemented to estimate the number of corrosion pits, based on experimentally measured corrosion ratios. Consequently, this allowed for the numerical prediction of the time-varying corrosion morphologies. Finite element (FE) models, incorporating this corrosion evolution model, were constructed. These corroded column models underwent validation through comparison with experimental findings. To further establish the effectiveness of the proposed FE models in predicting the structural behaviour of corroded members, FE models were also developed using the traditional uniform thickness reduction approach for comparative analysis. The results revealed that the proposed FE models for corroded structures offer a more accurate prediction of mechanical performance, particularly in instances of severe corrosion damage.

An integrated grey-box model for accurate ship engine performance prediction under varying speed and environmental conditions

The development of ship engine fault diagnosis has led to an increased interest in predicting marine engine performance under various environmental and operating conditions. However, predicting engine performance using a single model is limited due to the various characteristics of ship engines depending on speed and environmental conditions. To address this issue, we propose a grey box model (GBM)-based ship engine performance prediction framework that combines the white box model and black box model (BBM) appropriately for both low- and high-speed operating conditions. The application of data preprocessing techniques, such as clustering and cleaning, under specific engine and environmental conditions, combined with dimensionality reduction techniques (partial least square and principal component) and the use of WBM/BBM models under classified speed conditions, makes the proposed framework accessible to real-world operators through data-driven approaches and domain knowledge. We demonstrate that the proposed framework improves the robustness, accuracy, and efficiency of engine performance predictions by considering the characteristics of each speed in real-world navigation data, compared to using single models.

A hybrid data driven framework considering feature extraction for battery state of health estimation and remaining useful life prediction

Battery life prediction is of great significance to the safe operation, and reduces the maintenance costs. This paper proposes a hybrid framework considering feature extraction to achieve more accurate and stable life prediction performance of the battery. By feature extraction, eight features are obtained to fed into the life prediction model. The hybrid framework combines variational mode decomposition, the multi-kernel support vector regression model and the improved sparrow search algorithm to solve the problem of data backward, uneven distribution of high-dimensional feature space and the local escape ability, respectively. Better parameters of the estimation model are obtained by introducing the elite chaotic opposition-learning strategy and adaptive weights to optimize the sparrow search algorithm. The algorithm can improve the local escape ability and convergence performance and find the global optimum. The comparison is conducted by dataset from National Aeronautics and Space Administration which shows that the proposed framework has a more accurate and stable prediction performance. Compared with other algorithms, the SOH estimation accuracy of the proposed algorithm is improved by 0.16%–1.67%. With the advance of the start point, the RUL prediction accuracy of the proposed algorithm does not change much.

The influence of viscous behavior and static shear stress on the cyclic strengths of plastic soil: a numerical study

An accurate understanding of the cyclic behavior of clays and plastic silts is important for system performance predictions during earthquake loading. This paper presents the results of a numerical investigation into the individual and combined influences of static shear stress and viscous strength gain on the cyclic resistance of clays and plastic silts. Using the viscoplastic constitutive model PM4SiltR implemented in the finite difference program FLAC 8.1, the cyclic behaviors of the plastic soils were simulated using single-element cyclic direct simple shear simulations. A parametric analysis was performed with different combinations of viscous strength gains and static shear stresses. The effects of static shear stress and viscous strength gain varied under monotonic and cyclic loading conditions. Numerical findings suggest empirical correlations developed using scant laboratory data may not accurately predict the reduction of cyclic strengths with increasing static shear stress. Furthermore, sizable magnitudes of monotonic viscous strength gains only produced a marginal increase in cyclic strengths. The findings from this study highlight the need for future experimental laboratory testing to validate the numerical findings, to improve the accuracy of performance predictions of geosystems constructed with clays and plastic silts during and following earthquake loading.

Construction of Prediction Model of Foodborne Disease Outbreaks and Its Trend Prediction - Guizhou Province, China, 2023-2025.

Foodborne diseases pose a significant public health concern globally. This study aims to analyze the correlation between disease prevalence and climatic conditions, forecast the pattern of foodborne disease outbreaks, and offer insights for effective prevention and control strategies and optimizing health resource allocation policies in Guizhou Province. This study utilized the χ2 test and four comprehensive prediction models to analyze foodborne disease outbreaks recorded in the Guizhou Foodborne Disease Outbreak system between 2012 and 2022. The best-performing model was chosen to forecast the trend of foodborne disease outbreaks in Guizhou Province, 2023-2025. Significant variations were observed in the incidence of foodborne disease outbreaks in Guizhou Province concerning various meteorological factors (all P≤0.05). Among all models, the SARIMA-ARIMAX combined model demonstrated the most accurate predictive performance (RMSE: Prophet model=67.645, SARIMA model=3.953, ARIMAX model=26.544, SARIMA-ARIMAX model=26.196; MAPE: Prophet model=42.357%, SARIMA model=37.740%, ARIMAX model=15.289%, SARIMA-ARIMAX model=13.961%). The analysis indicates that foodborne disease outbreaks in Guizhou Province demonstrate distinct seasonal patterns. It is recommended to concentrate prevention efforts during peak periods. The SARIMA-ARIMAX hybrid model enhances the precision of monthly forecasts for foodborne disease outbreaks, offering valuable insights for future prevention and control strategies.

Accurate Prediction of Electrochemical Degradation Trajectory for Lithium‐Ion Battery Using Self‐Discharge

Accurate prediction of battery performance is crucial for timely battery health management. However, it is challenging to forecast precisely battery’s performance due to its intricate degradation mechanisms and variability in the degradation rates. To overcome the challenges, we employed an artificial intelligence (AI)‐driven approach. By training an indicator that reflects well structural degradation of a battery (self‐discharge; SD), a model could predict battery performance metrics with a high accuracy compared to models using direct indicators (e.g., capacity). In a comparative analysis, the self‐discharge model with the couple of bidirectional‐long–short term memory demonstrates outstanding prediction accuracy with a mean absolute percentage error of 0.39% for capacity retention (CR) prediction and a root mean square error of 13.2 cycles for remaining useful life prediction. These findings underscore the significance of incorporating indicators reflecting the internal electrode health of batteries for accurate lifespan prediction.

Research on Acoustic Control of Coupled Vibration System of Transducers Using Acoustic Surface and Topological Defect Structures

How to regulate the sound waves in the coupled vibration system of complex power ultrasonic transducers and design high-performance transducer systems has always been an urgent problem in the field of power ultrasound. Research has found that introducing various defects within the transducer system can improve the performance of the transducer coupled vibration system to a certain extent. However, the drawbacks of high loss, narrow frequency band, and sensitivity to structural parameters limit the further practical application of defect type phononic crystal transducer coupled vibration systems.<br>In order to improve the limitations of the coupled vibration system of defect type phononic crystal transducers, effectively reduce energy loss, and improve the efficiency of energy transmission, this paper introduces a topological defect structure with energy localization effect and a sound surface structure with high energy transmission efficiency into the coupled vibration system of the transducer. In this study, the acoustic surface structure and topological defect structure were used to excite defect states with energy localization effects and high energy transmission efficiency surface states, effectively regulating the vibration of the transducer coupled vibration system, and constructing a transducer coupled vibration system with high quality factor, low loss, and high energy transmission efficiency. By flexibly designing the geometric size parameters of the acoustic surface structure and defects, the vibration of the transducer coupled vibration system can be effectively controlled, thereby meeting the different functional requirements of the transducer coupled vibration system.<br>However, due to the excessive design parameters of surface structure and topological defect structure, the complexity of the design will be multiplied, greatly reducing the success rate of the design. Therefore, this study uses data analysis technology to establish a performance prediction model for the transducer coupled vibration system, in order to achieve accurate prediction of system performance and change the shortcomings of low design efficiency and low success rate brought by traditional empirical trial and error methods.<br>In order to verify the effectiveness of the research, the paper simulated and experimentally processed the coupled vibration system of the transducer. The simulation and experimental results indicate that the acoustic surface structure and topological defect structure can effectively regulate sound waves to improve the performance of the transducer coupled vibration system.

Research and comparison of pavement performance prediction based on neural networks and fusion transformer architecture

<abstract> <p>The decision-making process for pavement maintenance from a scientific perspective is based on accurate predictions of pavement performance. To improve the rationality of pavement performance indicators, comprehensive consideration of various influencing factors is necessary. To this end, four typical pavement performance indicators (i.e., Rutting Depth, International Roughness Index, Longitudinal Cracking, and Alligator Cracking) were predicted using the Long Term Pavement Performance (LTPP) database. Two types of data, i.e., local input variables and global input variables, were selected, and S-ANN and L-ANN models were constructed using a fully connected neural network. A comparative analysis of the predictive outcomes reveals the superior optimization of the L-ANN model. Subsequently, by incorporating structures such as self-attention mechanism, a novel predictive approach based on the Transformer architecture was proposed. The objective is to devise a more accurate predictive methodology for pavement performance indices, with the goal of guiding pavement maintenance and management efforts. Experimental results indicate that, through comparative analysis of three quantitative evaluation metrics (root mean square error, mean absolute error, coefficient of determination), along with visual scatter plots, the predictive model employing the fused Transformer architecture demonstrates higher robustness and accuracy within the domain of pavement performance prediction when compared to the L-ANN model. This outcome substantiates the efficacy and superiority of the model in terms of predictive performance, establishing it as a reliable tool for accurately reflecting the evolution of asphalt pavement performance. Furthermore, it furnishes a theoretical reference for determining optimal preventive maintenance timing for pavements.</p> </abstract>

Improving Student Performance Prediction Through Feature Selection: Insights from ‘Offee’ Assessment Data during the Covid-19 Pandemic

Post-pandemic student performance prediction has gained considerable attention within the academic community. Educational institutions worldwide have adopted blended learning approaches for delivering education and assessments. In this study, we harnessed data from the ‘Offee’ assessment platform based in Mumbai, India, spanning from September 2020 to October 2022. This dataset allows us to analyze the real impact of the Covid-19 pandemic on examinations.To tackle the challenges posed by high-dimensional data, we employed feature selection techniques to retain only the most significant features for predicting student performance. Specifically, we assessed the effectiveness of two decision tree-based methods, J48 classifier and Random Forest, in conjunction with the ranker search method using wrapper subset evaluation. The resulting feature set was then utilized to train and test a Support Vector Machine model for predicting student performance.Our findings reveal that both J48 and Random Forest feature selection methods yield impressive precision accuracy rates for student performance prediction, achieving 93.14% and 86.24%, respectively. In contrast, using the dataset without feature selection resulted in lower precision accuracy, standing at 79.9%, and consumed more time during model training and development.In summary, this study underscores the significance of feature selection in enhancing the accuracy of student performance prediction compared to utilizing the dataset without such feature curation.

Maximizing blue energy: the role of ion partitioning in nanochannel systems.

This study describes a numerical analysis on blue energy generation using a charged nanochannel with an integrated pH-sensitive polyelectrolyte layer (PEL), considering ion partitioning effects due to permittivity differences. The mathematical model for ionic and fluidic transport is solved using the finite element method, and the model validation is performed against existing theoretical and experimental results. The study investigates the influence of electrolyte concentration, permittivity ratio, and salt types (KCl, BeCl2, AlCl3) on the energy conversion process. The findings illustrate the substantial role of ion partitioning in modulating ionic concentration and potential fields, thereby affecting current profiles and energy conversion efficiencies. Remarkably, overlooking ion partitioning leads to significant overestimations of power density, highlighting the necessity of this consideration for accurate device performance predictions. This work introduces a promising configuration that achieves higher power densities, paving the way for the next generation of efficient energy-harvesting devices. The findings offer valuable insights into the development of state-of-the-art blue energy harvesting nanofluidic devices, advancing sustainable energy production.

Research on Performance Prediction Method Based on Gaussian Process Regression

Utilizing performance prediction models to predict students' graduation outcomes can offer crucial data support for academic early warning systems in higher education institutions, potentially becoming an essential tool for enhancing teaching quality. Therefore, in order to build a more accurate performance prediction model, a performance prediction method based on Gaussian process regression is proposed, and a series number of random experiments are carried out on the real performance data of seven majors such as broadcast and television directing major in a university to verify the effectiveness and feasibility of the method. The experimental results show that the proposed method has higher prediction accuracy and stability, and can provide effective reference for improving teaching quality.

Quality-Driven Regularization for Deep Learning Networks and Its Application to Industrial Soft Sensors.

The growth of data collection in industrial processes has led to a renewed emphasis on the development of data-driven soft sensors. A key step in building an accurate, reliable soft sensor is feature representation. Deep networks have shown great ability to learn hierarchical data features using unsupervised pretraining and supervised fine-tuning. For typical deep networks like stacked auto-encoder (SAE), the pretraining stage is unsupervised, in which some important information related to quality variables may be discarded. In this article, a new quality-driven regularization (QR) is proposed for deep networks to learn quality-related features from industrial process data. Specifically, a QR-based SAE (QR-SAE) is developed, which changes the loss function to control the weights of the different input variables. By choosing an appropriate inductive bias for the weight matrix, the model provides quality-relevant information for predictive modeling. Finally, the proposed QR-SAE is used to predict the quality of a real industrial hydrocracking process. Comparative experiments show that QR-SAE can extract quality-related features and achieve accurate prediction performance.

A Simplified Chemical Reactor Network Approach for Aeroengine Combustion Chamber Modeling and Preliminary Design

In a time when low emission solutions and technologies are of utmost importance regarding the sustainability of the aviation sector, this publication introduces a reduced-order physics-based model for combustion chambers of aeroengines, which is capable of reliably producing accurate pollutant emission and combustion efficiency estimations. The burner is subdivided into three volumes, with each represented by a single perfectly stirred reactor, thereby resulting in a simplified three-element serial chemical reactor network configuration, reducing complexity, and promoting the generality and ease of use of the model, without requiring the proprietary engine information needed by other such models. A tuning method is proposed to circumvent the limitations of its simplified configuration and the lack of detailed geometric data for combustors in literature. In contrast to most similar frameworks, this also provides the model with the ability to simultaneously predict the combustion efficiency and all pollutant emissions of interest (NOx, CO and unburnt hydrocarbons) more effectively by means of implementing a detailed chemical kinetics model. Validation against three correlation methods and actual aeroengine configurations demonstrates accurate performance and emission trend predictions. Integrated within two distinct combustion chamber low-emission preliminary design processes, the proposed model evaluates each new design, thereby displaying the ability to be employed in terms of optimizing a combustor’s overall performance given its sensitivity to geometric changes. Overall, the proposed model proves its worth as a reliable and valuable tool for use towards a greener future in aviation.