Back Propagation Neural Network Model Research Articles

Probabilistic solution of non-linear random ship roll motion by data-driven method

In this paper, a data-driven method is employed to investigate the probability density function (PDF) of nonlinear stochastic ship roll motion. The mathematical model of ship roll motion comprises a linear term with cubic damping and a nonlinear restoring moment represented as an odd-degree polynomial up to the fifth order. The data-driven method integrates maximum entropy, the pseudo-inverse algorithm, and a backpropagation (BP) neural network to obtain the PDF. The process begins with simulating data for the nonlinear stochastic system, followed by dimensional analysis to identify dimensionless parameter clusters. Optimization algorithms are then employed to solve for the coefficients, leading to the development of a BP neural network model trained to predict the PDF across various system characteristics and excitation intensities. The method's effectiveness is validated with Monte Carlo simulations, demonstrating high accuracy and reduced sensitivity to parameter variations.

Quantitative predictions of protein and total flavonoids content in Tartary and common buckwheat using near-infrared spectroscopy and chemometrics

A rapid method was developed for determining the total flavonoid and protein content in Tartary buckwheat by employing near-infrared spectroscopy (NIRS) and various machine learning algorithms, including partial least squares regression (PLSR), support vector regression (SVR), and backpropagation neural network (BPNN). The RAW-SPA-CV-SVR model exhibited superior predictive accuracy for both Tartary and common buckwheat, with a high coefficient of determination (R2p = 0.9811) and a root mean squared error of prediction (RMSEP = 0.1071) for flavonoids, outperforming both PLSR and BPNN models. Additionally, the MMN-SPA-PSO-SVR model demonstrated exceptional performance in predicting protein content (R2p = 0.9247, RMSEP = 0.3906), enhancing the effectiveness of the MMN preprocessing technique for preserving the original data distribution. These findings indicate that the proposed methodology could efficiently assess buckwheat adulteration analysis. It can also provide new insights for the development of a promising method for quantifying food adulteration and controlling food quality.

An intelligent mix design system for sustainable concrete containing multi-source recycled aggregate

The source complexity of recycled aggregate (RA) generally leads to significant fluctuations in the aggregate quality, which brings difficulties in the mix design of the recycled aggregate concrete (RAC). In this study, machine-learning models were developed to predict the cubic compressive strength by collecting mix proportions data including aggregate properties. Then a carbon emission model considering carbon sequestration was established. Based on these models, optimization algorithms were employed to obtain the optimal mix proportions. The results indicate that the backpropagation neural network model optimized by genetic algorithms (GABP) demonstrates the best predictive capability. Furthermore, the GABP model exhibits the highest sensitivity towards cement strength and water absorption of recycled coarse aggregate (RCA). In addition, single-objective optimization achieves a carbon reduction of 61.8–68.4 %. In dual-objective optimization, when the optimized mix proportions exhibit a low level of carbon intensity, the cubic compressive strength of RAC exceeds 50 MPa. This suggests that more efficient and valuable utilization of RA in concrete can be achieved after mix proportion optimization.

Artificial Neural Network-driven Optimization of Fe3O4 Nanoparticles/PVDF Macrospheres in Fenton-like System for Methylene Blue Degradation

Efficient degradation of industrial dyes remains a critical challenge in environmental engineering. This study introduces a novel Fe3O4 nanoparticles/PVDF macrospheres in a Fenton-like system, optimized using an Artificial Neural Network (ANN) for the degradation of Methylene Blue (MB). A feedforward backpropagation neural network model to optimize and predict the performance of this advanced oxidation process under various operational conditions. The model was trained, validated, and tested with robust datasets, demonstrating high predictive accuracy and generalization capability. The Mean Square Error (MSE) and Root Mean Square Error (RMSE) during testing were 0.0200 and 0.1414, respectively, indicating precise predictions. The coefficient of determination (R²) and correlation coefficient (R) were exceptionally high at 0.9744 and 0.9871, affirming the model's ability to capture the underlying dynamics of the degradation process effectively. The ANN-driven approach not only enhanced the efficiency of the MB degradation process but also provided significant insights into the scalability and applicability of the Fe3O4/PVDF system for practical water treatment solutions. This study underscores the potential of integrating advanced machine learning techniques with chemical engineering processes to achieve sustainable and efficient environmental management solutions, particularly for the treatment of recalcitrant wastewater contaminants.

Medical information management system based on multi-source heterogeneous big data

ABSTRACT This study aims to provide a medical information management system using multi-source heterogeneous big data to improve medical service quality and efficiency, with a motivation on its potential in medical insurance DRG payment. The system framework uses Back Propagation Neural Network (BPNN) technology to efficiently process and analyze multi-source medical data. Comparative experiments and parameter adjustments evaluated the system’s performance. Results show that the BPNN model achieved excellent accuracy (92.5%), recall (93%), and F1 value (92.8%) on the test data set, outperforming other models such as PSO(88%), CNN(89%), and RNN(90%). The system’s response speed was also significantly improved, with an average response time of 0.38 seconds, compared to 0.89 seconds for traditional systems. A 72-hour stability test confirmed the system’s reliability and ability to meet user needs. The proposed system demonstrates improved performance and user experience, making it a promising solution for medical information management and DRG payment applications.

The surrogate model for short-term extreme response prediction based on ANN and Kriging algorithm

Numerical simulation is a common method for calculating the short-term extreme response of floating offshore wind turbines (FOWTs). However, it requires significant computational resources. This study presents a dynamic response database for a 5MW semi-submersible FOWT under complex environmental conditions, including wind speed, effective wave height, and wave spectral peak period, using a numerical model. The peak over threshold (POT) method can be used to obtain the parametric database of short-term extreme responses, which includes the short-term extreme response distribution parameters for four responses: float surge, mooring tension, outward bending moment at the leaf root surface (OoPBM) and tower base pitching moment (TBPM). And the parameter database is applied to train models such as the Genetic Algorithm optimization Back Propagation neural network (GA-BP) and Kriging algorithm models. The research indicates that a correlation can be established between environmental conditions and short-term extreme response parameters using two algorithms. The accuracy of surrogate model prediction for some parameters can be improved by grouping the data based on wind speed and training separately. Additionally, selecting the appropriate surrogate model for each parameter separately can improve the accuracy of short-term extreme response prediction.

Towards laryngeal cancer diagnosis using Dandelion Optimizer Algorithm with ensemble learning on biomedical throat region images

Laryngeal cancer exhibits a notable global health burden, with later-stage detection contributing to a low mortality rate. Laryngeal cancer diagnosis on throat region images is a pivotal application of computer vision (CV) and medical image diagnoses in the medical sector. It includes detecting and analysing abnormal or cancerous tissue from the larynx, an integral part of the vocal and respiratory systems. The computer-aided system makes use of artificial intelligence (AI) through deep learning (DL) and machine learning (ML) models, including convolution neural networks (CNN), for automated disease diagnoses and detection. Various DL and ML approaches are executed to categorize the extraction feature as healthy and cancerous tissues. This article introduces an automated Laryngeal Cancer Diagnosis using the Dandelion Optimizer Algorithm with Ensemble Learning (LCD-DOAEL) method on Biomedical Throat Region Image. The LCD-DOAEL method aims to investigate the images of the throat region for the presence of laryngeal cancer. In the LCD-DOAEL method, the Gaussian filtering (GF) approach is applied to eliminate the noise in the biomedical images. Besides, the complex and intrinsic feature patterns can be extracted by the MobileNetv2 model. Meanwhile, the DOA model carries out the hyperparameter selection of MobileNetV2 architecture. Finally, the ensemble of three classifiers such as bidirectional long short-term memory (BiLSTM), regularized extreme learning machine (ELM), and backpropagation neural network (BPNN) models, are utilized for the classification process. A comprehensive set of simulations is conducted on the biomedical image dataset to highlight the efficient performance of the LCD-DOAEL technique. The comparison analysis of the LCD-DOAEL method exhibited a superior accuracy outcome of 97.54% over other existing techniques.

Sectoral recommendation system for medium term investment using technical indicators

Stocks of different companies are generally categorized into various industrial sectors based on the domain they operate. Individual stock prices are much more difficult to predict, and an investment bears a significant risk of unanticipated failure while thematic investment allows diversification within a sector and hence avoids the risk of failure of a single stock. In thematic investment, a user identifies one or more industrial sectors based on thematic preference and then distributes the corpus among various stocks from those sectors. If sectors are chosen wisely then it is possible to have a positive return even with the sudden downfall of some stock. To identify the sectors that will yield a positive return in the medium term, we have selected ten technical indicators (TI), and designed backpropagation neural networks (BPNN) with scaled conjugate gradient learning. We have evaluated the BPNN models with 12 sectoral index price history from NSE and achieved a comparable accuracy of 81.05% in prediction. In the next step, we have predicted sectoral index movement for one month to six months in the future, and based on the predicted gains we ranked the sectors. Based on the given investment horizon, top-k(=4) sectors are recommended to an investor. We validated our strategy on NSE sectoral data and achieved a recommendation accuracy of 87.5%.

Comparison of five methods for improving the accuracy of SRTM3 DEM and TanDEM-X DEM in the Qinghai-Tibet Plateau using ICESat-2 data

ABSTRACT The accuracy of digital elevation models (DEMs) is crucial for practical applications in complex terrain. In this study, various correction models were employed to evaluate and correct the 90 m SRTM3 DEM and TanDEM-X DEM data in the Qinghai-Tibet Plateau region. A simple and universal three-dimensional data co-registration method was utilized for horizontal alignment. The study demonstrated a significant reduction in horizontal discrepancies between datasets after data co-registration. By comparing the performance of five different correction methods, it was found that the RF model exhibited excellent accuracy and robustness, making it particularly suitable for applications that require high precision. The XGB and BPNN models offer a good balance between accuracy and time efficiency, making them suitable for research scenarios that are less sensitive to precision requirements. In contrast, the MLR and IDW methods performed poorly and are not recommended for high-precision applications. Furthermore, the corrected DEMs showed improved resistance to the influence of high slopes, enhancing their applicability in complex terrain areas. This study provides an important reference for the correction of high-quality DEMs in the Qinghai-Tibet Plateau region and offers valuable insights for DEM research in similar areas.

Research on the prediction of tar potential and maceral recognition based on artificial neural network: A case study of tar-rich coal from north Shaanxi, China

The high tar yield of tar-rich coal is ascribable to the complex interplay and coupling effects among various factors, which pose a significant challenge to its tar yield prediction owing to its intricate formation mechanism. This study employed artificial neural networks to predict the tar potential and maceral recognition considering the case of tar-rich coal in northern Shaanxi Province. A deep neural network model based on the U-Net architecture was utilised for high-precision quantitative analysis of macerals. In addition, traditional instrumental analyses were conducted to acquire fundamental coal quality parameters, such as industrial analysis, elemental analysis, and tar yield data. Subsequently, key features closely related to tar yield were carefully selected through correlation analysis. Finally, multiple statistical regression (MSR), backpropagation neural networks (BPNN), and convolutional neural networks (CNNs) were employed to construct a tar yield prediction model. Experimental results revealed that the hydrogen-rich feature parameters (Vad, Hd, and V) in tar-rich coal exhibited the most pronounced influence on tar yield. In terms of maceral recognition, U-Net performed exceptionally well, achieving an average accuracy of 72.16%, with the prediction accuracy for the four main macerals (vitrinite, inertinite, carbonate minerals, and sulfide minerals) surpassing 90.00%. With respect to the tar yield prediction, the neural network predictive models surpassed the MSR predictive models in terms of performance. Both the BPNN and CNN prediction models had a coefficient of determination greater than or equal to 0.95, especially for the Group CNN prediction model optimised by group convolution, which had a coefficient of determination as high as 0.98, an average absolute error as low as 0.18%, and a root mean square error of only 0.24%. The application of neural networks in deciphering the maceral and tar-producing characteristics of tar-rich coal can significantly enhance the associated analytical efficiency and precision.

Estimation of winter wheat LAI based on color indices and texture features of RGB images taken by UAV.

Leaf area index (LAI) is an important indicator for assessing plant growth and development, and is also closely related to photosynthesis in plants. The realization of rapid accurate estimation of crop LAI plays an important role in guiding farmland production. In study, the UAV-RGB technology was used to estimate LAI based on 65 winter wheat varieties at different fertility periods, the wheat varieties including farm varieties, main cultivars, new lines, core germplasm and foreign varieties. Color indices (CIs) and texture features were extracted from RGB images to determine their quantitative link to LAI. The results revealed that among the extracted image features, LAI exhibited a significant positive correlation with CIs (r = 0.801), whereas there was a significant negative correlation with texture features (r = -0.783). Furthermore, the visible atmospheric resistance index, the green-red vegetation index, the modified green-red vegetation index in the CIs, and the mean in the texture features demonstrated a strong correlation with the LAI with r > 0.8. With reference to the model input variables, the backpropagation neural network (BPNN) model of LAI based on the CIs and texture features (R2 = 0.730, RMSE = 0.691, RPD = 1.927) outperformed other models constructed by individual variables. This study offers a theoretical basis and technical reference for precise monitor on winter wheat LAI based on consumer-level UAVs. The BPNN model, incorporating CIs and texture features, proved to be superior in estimating LAI, and offered a reliable method for monitoring the growth of winter wheat. © 2024 Society of Chemical Industry.

Real-Time Prediction of Oil-Type Gas Emissions in Coal-Oil-Gas Coexistence Mines.

Oil-type gas disasters are a frequently occurring concern in coal-oil-gas coexistence mines. In order to actively predict the volume of oil-type gas emissions from floor rocks, this study presents an investigative methodology to forecast the geological conditions of floor rocks in front of the roadway face by utilizing the Direct Current (DC) method. The assessment of electrical resistance in rock formations, which is widely employed for identifying geological characteristics, serves as the basis for proposing a geological anomaly index derived from rock resistivity. This index effectively characterizes the stability of rock strata, providing an indirect evaluation of fracture development. As a real-time geological detection index for floor rocks that are 100 m ahead of the roadway face, it enhances predictive capabilities. Moreover, when combined with parameters such as floor rock thickness and permeability, the paper presents simulations of oil-type gas emissions under varying geological conditions. Subsequently, an adaptive optimization of the Back Propagation (BP) neural network is achieved through the Genetic Algorithm Back Propagation Neural Network (GA-BP) model to evaluate the quantity of oil-type gas emissions in roadways. This advanced real-time prediction method is applied in Huangling coal mining to predict the oil-type gas emissions from the floor rocks in the excavation roadway area. The results show consistency with field monitoring outcomes, confirming the accuracy of the predictive model. In conclusion, this advanced real-time prediction technique enables continuous monitoring and real-time forecasting of oil-type gas emissions in front of roadways. This capability facilitates the implementation of specific measures for pre-extraction in gas disaster prevention and control, thereby ensuring the safety of coal mine production. Moreover, the versatility of this advanced real-time prediction method extends to early warnings of rock mass instability-related disasters. Through a comprehensive understanding of subsurface conditions, continuous monitoring of changes, and the application of predictive models, timely actions can be taken to reduce risks and uphold safety standards.

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.

Multi-stage damage identification method for PC structures based on machine learning driven by piezoelectric singular feature

Efficient and accurate damage identification methods are great significant for ensuring the structural safety. This study proposes a multi-stage damage identification method for prestressed concrete (PC) structures based on machine learning driven by piezoelectric singular feature to improve the identification accuracy. This method extracts the singular value vector in the piezoelectric signal as the damage feature by multi-layer wavelet packet transform and singular value decomposition. The singular value vectors are put into the improved back propagation neural network (BPNN) model to achieve complete damage identification. This method is verified by analyzing the piezoelectric signals collected by PZT patches based on the static load failure test. The results show that the amplitude and energy of the signal gradually decreases and the frequency subject gradually develops from high frequency to low frequency with the development of damage. The extracted singular values effectively retain the main information of the piezoelectric signal as damage feature. The peak singular value decreases from fast to slow with the development of damage, which finally tends to be stable. The improved BPNN model has strong flexibility and adaptability, which enhances its ability of damage identification. The proposed method can achieve high-precision damage identification using piezoelectric signals, which has great application potential in the field of damage identification for PC structures.

Research on the Development Height Prediction Model of Water-Conduction Fracture Zones under Conditions of Extremely Thin Coal Seam Mining

Addressing the difficult problem of predicting the height of water-conducting fracture zones in shallow and thin coal seams, a prediction model of water-conduction fracture zones based on a backpropagation (BP) neural network was developed by integrating theoretical analysis, field measurements, and algorithmic advancements. Firstly, through overburden migration analysis and correlation tests, the height index system of the water-conducting fracture zone was determined. This system includes mining height, buried depth, dip angle, working face width, and overburden rock lithology, with five groups of characteristic parameters. Then, 35 pairs of minefield-measured data were collected to establish the measured height data set of the water-conducting fracture zone. Secondly, a BP neural network prediction model and a traditional support vector regression (SVR) prediction model were constructed based on a Pytorch framework, and the models were trained and tested by selecting data sets. Thirdly, the optimal prediction model was determined by comparing the model with the empirical model and multiple regression model of mining regulations for coal pillar maintenance and pressure in buildings, water bodies, railways, and main shafts. Finally, a typical mine was selected for application to verify the suitability of the optimal model. The results show that: (1) the predicted value of the neural network model is consistent with the change trend of the measured value, which accords with the theoretical law; (2) compared with traditional forecasting methods, the error of the BP neural network prediction model is stable and the prediction effect is the best; (3) dropout can effectively mitigate mitigation training overfitting, achieve regularization, and improve prediction accuracy; (4) the field application further verified that the BP neural network model is the best for predicting the height of water-conducting fracture zones of extremely thin coal seams, and the research results can provide technical guidance for similar fragile coal seams.

Prediction model of moisture content in spray drying of ceramic slurry based on IMFO-BPNN

The final particle moisture content of ceramic slurry spray drying affects the processing, product quality, and process energy consumption. While the real-time moisture content determination is very difficult for spray drying process due to nonlinear, severe lag, interference factors, and complexity of the systems, the high temperature, high humidity drying environment and short drying process. In current work, an improved moth optimization (IMFO) algorithm combined with backpropagation neural network (BPNN) was proposed to predict the moisture content of ceramic slurry particles during spray drying. The performance of the model is trained and tested. Results demonstrate that IMFO has better convergence ability and speed compared to other algorithms such as particle swarm optimization (PSO) and gravitational search algorithm (GSA). The IMFO-BPNN model achieves a MAE of 0.0293, RMSE of 0.0383, and R2 value of 0.9113, outperforming the prediction performance of BPNN and MFO-BPNN models. The absolute error rate of the IMFO-BPNN model (0–5%) is lower compared to BPNN (5–10%) and MFO-BPNN model (>10%), showcasing superior accuracy in predicting moisture content. This mathematical model established in the study provides an efficient, accurate, and nondestructive method for predicting the drying endpoint of ceramic slurry spray drying.

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.

Volatilization of benzene on soil surface under different factors: evaluation and modeling

The volatilization of volatile organic compounds following a leakage event is a crucial mechanism that influences their migration and transformation in the soil. It is noteworthy that this process is intricately shaped by soil properties and environmental factors, exhibiting highly complex nonlinear relationships. However, there is currently no reliable mathematical model to predict the nonlinear relationship. To address this gap, the study conducted dynamic experiments considering various factors, including particle size, organic matter content, temperature, wind speed and moisture content. The volatilization rate (k\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$k$$\\end{document}), an important parameter in volatilization kinetics reflecting the speed of volatilization, was calculated by first-order kinetic principle. Finally, an innovative approach was introduced using a Back Propagation Neural Network (BPNN) model for prediction. The findings indicate that wind speed exerts the most significant impact on the volatilization rate of benzene among the examined factors. The application of BPNN demonstrates the model's accuracy in simulating benzene volatilization rates under diverse conditions. The results of K-fold cross-validation alleviate concerns of potential over-prediction, affirming the reliability of the constructed model. This research introduces a novel methodology for predicting volatilization parameters in real-world scenarios.

Few shot intelligent assessment method for compaction quality of earthwork considering uncertainty

Current practices lack reliable models for continuously assessing compaction quality from limited data, which hinders effective compaction quality control and the acceptance of earthwork. Using material source parameters as inputs for assessment models makes it infeasible to achieve a real-time assessment of the compaction quality in earthwork. These issues have hindered the popularization of emerging intelligent compaction (IC) and intelligent rolling compaction (IRC) technologies. Therefore, this study addresses the need for small-sample training by introducing an uncertainty-based multi-population genetic algorithm fused with a backpropagation neural network model (UB-MPGA-BP), enabling the real-time intelligent assessment of compaction quality based on few-shot learning. In case studies involving high- and low-liquid limit silts, existing models trained on large datasets were notably inadequate for small-sample evaluation tasks. However, the proposed method not only performed well in silt cases but also exhibited high performance in rockfill materials. The analysis revealed that in small-sample scenarios without reliance on material source parameters, the proposed method has the advantages of real-time accuracy, generalization, few-shot data-driven, and simple input parameters, which enable the rapid assessment of compaction quality. The model can potentially facilitate IC/IRC applications in other engineering practices.

Vibration analysis of Ti-SiC composite airfoil blade based on machine learning

In this study, machine learning (ML) methods are integrated with Rayleigh-Ritz method and first-order shear deformation theory (FSDT) to predict the vibration properties of Ti-SiC fiber-reinforced composite airfoil blade. The natural vibration characteristics of airfoil blade are largely determined by various geometric and material parameters, which leads to the high computational cost of numerical methods. Therefore, the low-cost ML models in conjunction with Ti-SiC fiber-reinforced composite material is developed to replace traditional numerical methods in order to predict the vibration characteristics of airfoil blade. Random Forest (RF), Gradient Boosting Decision Tree (GBDT) and Back Propagation (BP) neural network models are utilized to compare the predicted results with existing data. Among these models, the BP neural network demonstrates superior performance. Additionally, the SHapley Additive exPlanation (SHAP) method is utilized to elucidate BP neural network model, facilitating the prioritization of input features. This approach offers a feasible auxiliary solution for investigating the vibration characteristics of airfoil blade.