Regression Neural Network Research Articles

Development of an efficient design optimization strategy for thick-walled cylinders treated with combinations of autofrettage, shrink-fit and wire-winding processes

Shrink-fit, wire-winding, and autofrettage processes are commonly utilized to enhance fatigue strength and durability of thick-walled cylinders across various mechanical applications. In this study, a novel practical design optimization methodology has been developed to determine the optimal configuration of a thick-walled cylinder, incorporating different combinations of shrink-fit, wire-winding, and autofrettage techniques. The objective is to identify the optimal layer thickness, shrink-fit interference, conventional autofrettage pressure, and reverse autofrettage pressure, if applicable, to maximize the compressive residual stress and minimize the tensile residual stress, thereby extending fatigue lifetime of the cylinder. First, different configurations of thick-walled cylinders, subjected to various combinations of reinforcement processes, are identified. A dataset of residual hoop stress profiles through the cylinder thickness is subsequently generated for these configurations based on the same manufacturing process. Neural network regression is effectively utilized to construct a single fitting function for the residual hoop stress profiles. A parametric study is performed to determine the optimal training functions, activation functions, and hyperparameters, achieving a remarkable agreement with the dataset, indicated by a coefficient of determination of over 0.97. A combination of Genetic Algorithm and Sequential Quadratic Programming algorithms is utilized to determine the accurate optimal values. Fatigue life analysis is subsequently conducted to estimate the fatigue lifetime of the optimal configuration. Results suggest that the optimal configuration, involving conventional autofrettage of the inner layer followed by shrink-fitting with a virgin layer and wire-winding the entire assembly, achieves a maximum fatigue life of 88 × 10⁶ cycles under cyclic pressure load of 300 MPa.

Study on sporty exhaust sound of economical vehicle under acceleration

Exhaust sound quality is an important part of vehicle performance. In this paper, the sporty exhaust sound quality of an economical vehicle equipped with a 4-cylinder and 4-stroke engine is evaluated, analyzed, and improved under acceleration. Firstly, a sporty feeling evaluation method with engine speed divided is proposed, and the influence of exhaust sound order components on sporty exhaust sound is analyzed. The results show that while the A-weighted sound pressure level (ASPL) of Order 2 is lower and the ASPLs of Orders 4 and 6 are higher, the exhaust sound is sportier. Then, a hybrid predicted model of vehicle sporty exhaust sound under acceleration is established based on convolutional neural network (CNN) and support vector regression (SVR) algorithm. The relative errors between the predicted results of CNN-SVR hybrid model and the subjective evaluation results are limited within 2%, which indicates that the CNN-SVR hybrid prediction model achieves a high accuracy in assessing the sporty feeling of exhaust sound. Finally, considering the frequency ranges corresponding with the above order components under the practical accelerating condition, a strategy is proposed to enhance the sporty feeling of exhaust sound by reducing the sound energy within 100 Hz and increasing the sound energy within 100–450 Hz. Based on this strategy, a muffler with different structure is selected and installed on the economical vehicle, and the sporty feeling of exhaust sound is 0.63 points higher than before.

Optimizing stock market volatility predictions based on the SMVF-ANP approach

The stock market is considered one of the most complicated financial systems, comprising several components or inventories, whose prices vary substantially over time. Bursaries include revealing market tendencies over time. All investors in the stock market aim to maximize profits and reduce the associated risks. Stock currency forecasts are a significant financial concern that is being handled even more closely. In recent years, various neural network and hybrid models have surpassed classic linear and non-linear techniques to produce reliable prediction outcomes. This study investigates the efficacy of dynamic and effective stock market forecasting using neural network models. This study examines market transmission mechanisms and assesses the predicted links between multiple financial and economic factors. A stock market volatility and artificial network prediction (SMVF–ANP) approach is presented. The models analyzed included a multi-layer perceptron (MLP), dynamic artificial neural network, and generalized autoregressive conditional heteroscedasticity to extract additional input variables. The results reveal that the trade strategies led by the classification models yield superior risk-adjusted returns compared to the buy-and-hold approach and those led by the neural network and linear regression model-level estimate predictions. The numerical results show that the proposed SMVF-ANP method achieved a high performance ratio of 94.1%, an enhanced prediction ratio of 98.4%, a high stock market volatility rate of 96.7%, a reduced mean square percentage error ratio of 16.3%, a probability rate of 32.7%, an increased efficiency rate of 96.9%, and an accuracy ratio of 97.2% compared to other methods.

Confinement strength prediction of corroded rectangular concrete columns using BP neural networks and support vector regression

The application of machine learning in predicting the mechanical performance of reinforced concrete columns subjected to reinforcement corrosion was investigated in this study. Traditional models, often relying on empirical formulas or simplified assumptions, are known to struggle in capturing all variables and relationships in complex problems, leading to inadequate prediction accuracy. Through theoretical analysis, the confinement effect of stirrups on core concrete and its performance deterioration caused by reinforcement corrosion were determined. To improve the prediction accuracy and generalization ability, the error Back Propagation Neural Network (BPNN) and Support Vector Regression (SVR) models were employed. Parameter effects in the BPNN model were interpreted using the SHapley Additive exPlanations (SHAP) and compared with traditional parameter sensitivity analyses. The investigation indicates that the machine learning models have a high degree of fit and low error levels, particularly within the training set. After analyzing using the SHAP approach, it is found that the corrosion ratio of the stirrup and longitudinal reinforcement have a significant effect on the confinement strength of the concrete, whereas the effects of the stirrup configuration and size effect are negligible, which is different from conventional parametric sensitivity analysis. As to the stability analysis of model predictions, the SVR model shows lower volatility and higher prediction stability compared with the BPNN model, despite the latter occasionally providing superior generalization ability. This research underscores the significant advantages offered by machine learning models in addressing longstanding challenges associated with strength prediction, and thus presents new perspectives for future study.

Prediction Of Student Achievement Using Artificial Neural Network And Support Vector Regression At SMK TELKOM Lampung

The analysis of student performance is crucial in vocational schools because it helps identify the challenges students face in preparing themselves for the workforce. By integrating data mining techniques such as Artificial Neural Networks (ANN), educators can enhance their understanding of factors that improve student learning outcomes. An artificial neural network (ANN) is composed of interconnected artificial neurons that can learn from input data and make complex predictions, including academic achievements. The structure and function of the human brain inspire ANN. This study compares the effec- tiveness of the artificial neural network (ANN) method with other methodologies, such as support vector regression (SVR), to predict student achievement at SMK Telkom Lampung. Primary data collected from SMK Telkom Lampung includes 4939 examples with 550 cases, 26 features, and 4 meta-attributes. Performance evaluation involves metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2). The coefficient of determination (R2) value of the Neural Network at 0.001 is higher than the R2 value of SVR, which reaches -0.036. Research find- ings indicate that the Artificial Neural Network model slightly outperforms the Support Vector Regression model, with lower prediction error rates and better ability to explain data variability.

Prediction of flash flood peak discharge in hilly areas with ungauged basins based on machine learning

ABSTRACT Peak discharge is an essential element of hydrological forecasting. Due to rapid outbreaks of flash floods in hilly areas and the lack of measured data, the fast and accurate estimation of peak discharge is crucial for flash flood hazard management. Three machine learning algorithms were applied to estimate peak discharge; this estimation was compared with the results of hydrological–hydraulic models, and the results were verified with measured watershed data. In this paper, 10 hydrological and geomorphological parameters were selected to predict the flood peak discharge in 103 watersheds in Taiyi Mountain North District. The results show that the particle swarm optimization backpropagation (PSO-BP) neural network model outperforms the BP neural network and random forest regression in prediction performance. PSO-BP has a lower mean absolute error (2.51%), root mean square error (3.74%), and mean absolute percentage error (2.74%) than the other models, which indicates that PSO-BP has high prediction accuracy. Importance analysis revealed that rainfall, early impact rainfall, catchment area, and rain intensity are the key input parameters of PSO-BP. The proposed method was confirmed to be a fast and relatively accurate algorithm for estimating the peak discharge of flash floods in ungauged basins.

Enhancing Fermentation Process Monitoring through Data-Driven Modeling and Synthetic Time Series Generation.

Soft sensors based on deep learning regression models are promising approaches to predict real-time fermentation process quality measurements. However, experimental datasets are generally sparse and may contain outliers or corrupted data. This leads to insufficient model prediction performance. Therefore, datasets with a fully distributed solution space are required that enable effective exploration during model training. In this study, the robustness and predictive capability of the underlying model of a soft sensor was improved by generating synthetic datasets for training. The monitoring of intensified ethanol fermentation is used as a case study. Variational autoencoders were employed to create synthetic datasets, which were then combined with original datasets (experimental) to train neural network regression models. These models were tested on original versus augmented datasets to assess prediction improvements. Using the augmented datasets, the soft sensor predictive capability improved by 34%, and variability was reduced by 82%, based on R2 scores. The proposed method offers significant time and cost savings for dataset generation for the deep learning modeling of ethanol fermentation and can be easily adapted to other fermentation processes. This work contributes to the advancement of soft sensor technology, providing practical solutions for enhancing reliability and robustness in large-scale production.

Mathematical optimization of multilinear and artificial neural network regressions for mineral composition of different tea types infusions

The objective of this study was to investigate the change in mineral composition depending on tea variety, tea concentration, and steeping time. Four different tea varieties, black Ceylon (BC), black Turkish (BT), green Ceylon (GC), and green Turkish (GT), were used to produce teas at concentrations of 1, 2, and 3%, respectively. These teas were produced using 7 different steeping times: 2, 5, 10, 20, 30, 45, and 60 min. It was also aimed to optimize the regression equations utilizing these factors to identify parameters conducive to maximizing Zn, K, Cu, Mg, Ca, Na, and Fe levels; minimizing Al content, and maintaining Mn level at 5.3 mg/L. The optimal conditions for achieving a Mn content of 5.3 mg/L in black Turkish tea entailed steeping at a concentration of 1.94% for 11.4 min. Variations in K and Mg levels across teas were inconsistent with those observed for other minerals, whereas variations in Al, Cu, Fe, Mn, Na, and Zn levels exhibited a close relationship. Overall, mineral levels in tea can be predicted through regression analysis, and by mathematically optimizing the resultant equations, the requisite conditions for tea production can be determined to achieve maximum, minimum, or target mineral values.

Improved mapping of heavy metals in agricultural soils using machine learning augmented with spatial regionalization indices

The accurate spatial mapping of heavy metal levels in agricultural soils is crucial for environmental management and food security. However, the inherent limitations of traditional interpolation methods and emerging machine-learning techniques restrict their spatial prediction accuracy. This study aimed to refine the spatial prediction of heavy metal distributions in Guangxi, China, by integrating machine learning models and spatial regionalization indices (SRIs). The results demonstrated that random forest (RF) models incorporating SRIs outperformed artificial neural network and support vector regression models, achieving R2 values exceeding 0.96 for eight heavy metals on the test data. Hierarchical clustering for feature selection further improved the model performance. The optimized RF models accurately predicted the heavy metal distributions in agricultural soils across the province, revealing higher levels in the central-western regions and lower levels in the north and south. Notably, the models identified that 25.78 % of agricultural soils constitute hotspots with multiple co-occurring heavy metals, and over 6.41 million people are exposed to excessive soil heavy metal levels. Our findings provide valuable insights for the development of targeted strategies for soil pollution control and agricultural soil management to safeguard food security and public health.

Regularity analysis of resilient modulus for hot-mix asphalt with large temperature fluctuations

To evaluate the regularity of resilient modulus for hot-mix asphalt (HMA) under large temperature fluctuations, back propagation (BP) neural network technology was used to analyze the continuous change of HMA resilient modulus. Firstly, based on the abundant data, the training model of HMA resilient modulus was established by using BP neural network technology. Subsequently, BP neural network prediction and regression analysis were performed, and the prediction model of HMA resilient modulus at different temperatures (−50 °C to 60 °C) was obtained, which fully considered multi-factor and nonlinearity. Finally, the fitted theoretical model can be used to evaluate the HMA performance under the condition of large temperature fluctuations, and the rationality of theoretical model was verified by taking Harbin region as an example. It was found that the relationship between HMA resilient modulus and temperatures can be described by inverse tangent function. And the key parameters of theoretical model can be used to evaluate the continuous change characteristics of HMA resilient modulus with large temperature fluctuations. The results can further improve the HMA performance evaluation system and have certain theoretical value.

Active control vibrations of aircraft wings under dynamic loading: Introducing PSO-GWO algorithm to predict dynamical information

This study presents an innovative approach to mitigate vibrations induced by external shock on composite structures through the application of an intelligent controller. Leveraging the first-order shear deformation panel theory, a sophisticated controller scheme is developed, integrating methodologies such as the differential quadrature approach and Laplace transform. Furthermore, deep neural network (DNN) and support vector regression (SVR) techniques are employed to enhance prediction accuracy and control efficiency. Additionally, two optimized hybrid models are proposed, incorporating Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO) algorithms, to further refine the controller's performance. The proposed methodology aims to address the challenges associated with vibrations in composite structures by providing a comprehensive and adaptive control solution. By utilizing advanced optimization algorithms and machine learning techniques, the controller can effectively adapt to dynamic changes in external shock conditions, thereby minimizing vibrations and ensuring structural integrity. The integration of ANN and SVR enhances the controller's predictive capabilities, enabling it to anticipate and respond to varying shock scenarios with precision. Through theoretical analysis and numerical simulations, the effectiveness of the proposed intelligent controller is demonstrated in reducing vibrations and enhancing the structural stability of composite systems. The optimized hybrid models, employing PSO and GWO algorithms, further improve the controller's performance by fine-tuning its parameters for optimal control efficiency. Overall, this research contributes to the development of robust control strategies for mitigating vibrations in composite structures subjected to external shock, with potential applications in aerospace, automotive, and civil engineering industries.

Predicting the Risk of Severity and Readmission in Patients with Heart Failure in Indonesia: A Machine Learning Approach.

In Indonesia, the poor prognosis and high hospital readmission rates of patients with heart failure (HF) have yet to receive focused attention. However, machine learning (ML) approaches can help to mitigate these problems. We aimed to determine which ML models best predicted HF severity and hospital readmissions and could be used in a patient self-monitoring mobile application. In a retrospective cohort study, we collected the data of patients admitted with HF to the Siloam Diagram Heart Center in 2020, 2021, and 2022. Data was analyzed using the Orange data mining classification method. ML support algorithms, including artificial neural network (ANN), random forest, gradient boosting, Naïve Bayes, tree-based models, and logistic regression were used to predict HF severity and hospital readmissions. The performance of these models was evaluated using the area under the curve (AUC), accuracy, and F1-scores. Of the 543 patients with HF, 3 (0.56%) were excluded due to death on admission. Hospital readmission occurred in 138 patients (25.6%). Of the six algorithms tested, ANN showed the best performance in predicting both HF severity (AUC = 1.000, accuracy = 0.998, F1-score = 0.998) and readmission for HF (AUC = 0.998, accuracy = 0.975, F1-score = 0.972). Other studies have shown variable results for the best algorithm to predict hospital readmission in patients with HF. The ANN algorithm performed best in predicting HF severity and hospital readmissions and will be integrated into a mobile application for patient self-monitoring to prevent readmissions.

Estimation of citrus leaves’ nitrogen content by multispectral unmanned aerial vehicle remote sensing based on semi-supervised twin neural network regression

Estimation of citrus leaves’ nitrogen content by multispectral unmanned aerial vehicle remote sensing based on semi-supervised twin neural network regression

Toward Machine-Learning-Accelerated Design of All-Dielectric Magnetophotonic Nanostructures.

All-dielectric magnetophotonic nanostructures are promising for integrated nanophotonic devices with high resolution and sensitivity, but their design requires computationally demanding electromagnetic simulations evaluated through trial and error. In this paper, we propose a machine-learning approach to accelerate the design of these nanostructures. Using a data set of 12 170 samples containing four geometric parameters of the nanostructure and the incidence wavelength, trained neural network and polynomial regression algorithms were capable of predicting the amplitude of the transverse magneto-optical Kerr effect (TMOKE) within a time frame of 10-3 s and mean square error below 4.2%. With this approach, one can readily identify nanostructures suitable for sensing at ultralow analyte concentrations in aqueous solutions. As a proof of principle, we used the machine-learning models to determine the sensitivity (S = |Δθres/Δna|) of a nanophotonic grating, which is competitive with state-of-the-art systems and exhibits a figure of merit of 672 RIU-1. Furthermore, researchers can use the predictions of TMOKE peaks generated by the algorithms to assess the suitability for experimental setups, adding a layer of utility to the machine-learning methodology.

Enhanced lithium‐ion battery state‐of‐charge estimation for Electric Vehicles using the AOA‐DNN approach

AbstractElectric vehicles (EVs) battery management systems (BMSs) rely on exact state of charge (SoC) estimations to guarantee efficient and safe operation. Lithium‐ion batteries (LIBs) are favored for EVs due to their extended lifespan, high energy density, and minimal self‐discharge and high voltage. To address these issues, this research propose a LIB SoC prediction based on an actual BMS in EVs. The main objective is improving SoC of LIB. The proposed hybrid strategy is the combined performance of both the dynamic neural networks (DNN) and arithmetic optimization algorithm (AOA). Commonly it is named as DNN‐AOA technique. The SoC of Lithium‐ion batteries are predicted using the DNN approach. The proposed AOA is used to optimize the weight parameter of DNN to enhance prediction accuracy and reliability. By then, the operational MATLAB platform has adopted the proposed framework, and existing procedures are used to compute its execution. The proposed method demonstrates superior existing like Bayesian network (DBN), random vector functional link neural network (RVFLNN) and Gaussian progress regression (GPR). The proposed method yields a lower error value of 0.1 and a higher accuracy value of 98% compared with other existing methods.

Origami single-end capacitive sensing for continuous shape estimation of morphing structures

In this work, we propose a novel single-end morphing capacitive sensing method for shape tracking, FxC, by combining Folding origami structures and Capacitive sensing to detect the morphing structural motions using state-of-the-art sensing circuits and deep learning. It was observed through embedding areas of origami structures with conductive materials as single-end capacitive sensing patches, that the sensor signals change coherently with the motion of the structure. Different from other origami capacitors where the origami structures are used in adjusting the thickness of the dielectric layer of double-plate capacitors, FxC uses only a single conductive plate per channel, and the origami structure directly changes the geometry of the conductive plate. We examined the operation principle of morphing single-end capacitors through 3D geometry simulation combined with physics theoretical deduction, which deduced similar behavior as observed in experimentation. Then a software pipeline was developed to use the sensor signals to reconstruct the dynamic structural geometry through data-driven deep neural network regression of geometric primitives extracted from vision tracking. We created multiple folding patterns to validate our approach, based on folding patterns including Accordion, Chevron, Sunray and V-Fold patterns with different layouts of capacitive sensors using paper-based and textile-based materials. Experimentation results show that the geometry primitives predicted from the capacitive signals have a strong correlation with the visual ground truth with R-squared value of up to 95% and tracking error of 6.5 mm for patches. The simulation and machine learning constitute two-way information exchange between the sensing signals and structural geometry. By embedding part of the origami surface with morphing single-end capacitive sensors, FxC presents a unique solution that leverages both the mechanical properties of origami and sensing properties of capacitive sensing.

Neural network integrated with symbolic regression for multiaxial fatigue life prediction

In the realm of structural engineering, accurately predicting multiaxial fatigue life presents a formidable challenge, stemming from the complex interplay of stress and strain across multiple directions. This research introduces the Symbolic Regression-Neural Network (SR-NN) framework, a novel integration of symbolic regression-derived expressions with neural networks aimed at enhancing predictive accuracy in this field. Initiated by selecting salient features through SHAP-informed Recursive Feature Elimination, our approach effectively minimized dimensionality while pinpointing key feature groups. Symbolic regression, newly applied to guide neural network training in the prediction of alloy material fatigue life, facilitated the generation of meaningful expressions that describe the fatigue processes. These expressions were incorporated into the network’s loss function alongside MSE loss, refining the model’s learning dynamics. Our proposed SR-NN framework demonstrated substantial improvements over traditional models in rigorous testing, notably reducing MSE by 55.4% compared to RF and 45% against SVM models, underscoring the potential of merging symbolic regression with machine learning to tackle the inherent variability and complexity of fatigue behavior across diverse materials and loading conditions. This study highlights the transformative impact of symbolic regression in improving the interpretability and accuracy of predictive models within structural engineering.

Predicting the remaining life of oil pipeline circumferential welds based on hybrid machine learning-based methods

Circumferential welds are often considered critical junctions in oil pipelines. Considering that the failure of circumferential welds in pipelines can lead to economic losses and environmental pollution, timely maintenance of these welds is crucial, which requires accurately estimating the remaining life of welds. This paper proposes a comprehensive framework with hybrid machine learning-based methods for circumferential welds remaining life prediction. A backpropagation (BP) neural network is developed to identify circumferential welds with abnormal detection levels related to cracking defects. Then, another BP neural network and support vector regression are utilized to establish a time-series-based model for predicting the remaining life of circumferential welds. The model is then optimized for accuracy using a stacking method. The proposed methods are applied to real data from a pipeline, and the results indicate that the optimal model for abnormal circumferential weld detection achieves a training set accuracy of 99.44 %, a test set accuracy of 99.71 %, a recall rate of 0.97, and an F1 score of 0.98. The optimal prediction model for the remaining life of circumferential welds has root mean square errors of 1.36, 3.28, and 0.67. The research results demonstrate that the models have high accuracy and good performance.

Adaptive machine learning surrogate based multiobjective optimization for scavenging residual saltwater behind subsurface dams

High-fidelity physically based groundwater flow and solute transport models have been limited for seawater intrusion remediation design because of computationally intensive evolutionary algorithms. Data-driven machine learning approaches are promising to substitute expensive-cost groundwater numerical models within optimization due to computing efficiency. However, machine learning surrogates may accumulate error of forecasting and thereby result in infeasible optimal solutions. To achieve desired fidelity level, this study proposes a novel adaptive machine learning surrogate based multiobjective optimization method for coastal aquifer desalination. An adaptive modeling algorithm is newly introduced to iteratively retrain poorly-performed machine learning models and enhance predicting accuracy. The method is demonstrated to seek optimal extraction and injection strategies for scavenging residual saltwater trapped in an upstream aquifer behind a subsurface dam. Two conflicting objectives of minimizing the total extraction-injection rate and maximizing saltwater removal effectiveness are considered. Three machine learning models including artificial neural network (ANN), Gaussian process (GP) and response surface regression model (RSR) are developed to replace a high-fidelity seawater intrusion model for predicting chloride concentration and salinity mass. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is employed to derive Pareto fronts. Pareto optimal solutions obtained from machine learning models are compared against those from the seawater intrusion model. Results indicate that the developed machine learning models do not only have strong predicting capability, but also maintain good quality of Pareto optimal solutions, while achieving substantial computational saving up to 95%. Especially, the adaptively retrained RSR model inhibits error accumulation of forecasting and accelerates correct convergence to the true Pareto front. The proposed method is found superior performance in accurate convergence, widely-spread diversity as well as high computing efficiency than conventional methods.

Applying Artificial Intelligence Constructing a Prediction Model Related to Environmental Hormones and Breast Cancer Incidence.

Breast cancer is the second leading cause of death in the world and the age of diagnosis is younger and younger. The research is aimed to make a prediction model related to environmental hormones and breast cancer incidence. First, we analyzed lab data to figure out the risk factor of breast cancer. By using Chi-square, Neural network and logistic regression, we find out that Lead, Copper, Zinc, Mercury, Chromium, Chloramphenicol, Sulfonamides, Penicillin and metabolites of phthalates MEP, MBHP related to incidence of breast cancer. These risk factors will be verified by questionnaire of daily habit survey of breast cancer patients. We will establish the relationship between breast cancer and environmental hormones and make public attention to risks of environmental hormones.