ANN-based Prediction Research Articles

Mechanical performance and ANN-based prediction of Co-Cr dental alloys with gyroid cellular structures produced by LPBF technology

Gyroid structures exhibit significant potential in the fields of lightweight structural design, heat transfer, energy absorption, and biological applications. The use of gyroid for implants in dentistry is currently not sufficiently widespread. The research encompasses design, compression testing, cellular investigation using a digital microscope, and the application of artificial neural networks (ANNs) using data gained from the compression test. The ANN study and the test phase in which gyroid geometries are addressed by dental three-point bending tests are novel in this field. In the field of dentistry, this study compares the usability of five distinct gyroid design characteristics, including one model without a gyroid structure. During the testing, we found that the m1 model had an average maximum strength of 600 N, while the m3 model achieved 230 N. The remaining models achieved an approximate strength of 200 N. In the mechanical performance evaluation of the samples, a 40% weight reduction was achieved. An ANN model has been developed to predict the force experienced by gyroid structures under certain deformations depending on the infill ratio. This model was trained with data obtained from a three-point bending test. Using grid search and Monte Carlo cross-validation, the optimal multilayer perceptron structure was determined to have 12 neurons in the hidden layer, a mini-batch size of 8, and a learning rate of 0.0001. The Adam optimization algorithm was used to train the ANN model, which was constructed using the TensorFlow library. Evaluation metrics were used to test the model’s performance, and the results showed strong generalization capability and high accuracy with coefficient of determination ( R2) of 0.997, mean squared error (MSE) of 3.337E-05 kN2, root mean square error of (RMSE) 0.005777 kN, and mean absolute error (MAE) of 0.003633 kN on the test dataset.

Sustainable mortar into paver block using agricultural waste ash and recycled glass: ANN-based prediction of mechanical properties

Sustainable mortar into paver block using agricultural waste ash and recycled glass: ANN-based prediction of mechanical properties

Comparison of electricity savings in community units through ESS and PV generation using ANN-based prediction model under Korean climatic conditions

Comparison of electricity savings in community units through ESS and PV generation using ANN-based prediction model under Korean climatic conditions

Study on GA–ANN-Based Prediction of Paving Time of Cement-Stabilized Layer above Ultra-High-Filled Subgrade

In mountainous areas, high-filled subgrade often experiences significant post-construction settlement. Prematurely paving the cement-stabilized gravel layer on an unstable subgrade can easily lead to subsequent cracking. To accurately predict the settlement of high-filled subgrade and determine the appropriate timing for paving the cement-stabilized layer, this study proposes a subgrade settlement prediction method combining an Artificial Neural Network (ANN) with a Genetic Algorithm (GA). Using monitoring data from a high-filled subgrade on a highway in Hunan Province, China, a GA–ANN model was established to predict settlement curves. The predicted data from the GA–ANN model were compared with measured data and ANN predictions to validate the advantages of using GA–ANN for subgrade settlement prediction. The results indicate that the GA–ANN model significantly outperforms the ANN model due to GA’s ability to provide more reasonable weight biases for ANN through global search optimization. Predictions of settlement data beyond 50 days using both ANN and GA–ANN showed that the GA–ANN prediction curve closely matched the measured curve, with a basic deviation within ±3 mm. In contrast, ANN’s prediction error gradually increased to over 5 mm as the observation time increased, with predicted values lower than measured values, leading to an overly optimistic estimation of early settlement convergence. Based on the predicted data and settlement standards, the estimated timing for laying the stabilized layer was determined. During the laying process, no cracking was observed in the stabilized layer. The project has been in operation for six months, with the road surface in good condition. This study provides a valuable reference for the laying of stabilized layers on similar high-filled and ultra-high-filled subgrades.

Artificial neural network prediction of transverse modulus in humid conditions for randomly distributed unidirectional fibre reinforced composites: A micromechanics approach

This paper proposes an innovative micromechanics-based artificial neural network (ANN) method to efficiently investigate the transverse modulus of unidirectional fibre/epoxy composites under humid conditions. In this research, a novel approach is developed to establish relations between the geometrical, mechanical, and environmental properties of the microstructure and the material’s performance under transverse tension. A framework is developed to artificially generate periodic representative volume elements (RVEs) while taking into account the interphase region between fibre and matrix. The RVEs are analysed by the finite element method to obtain the transverse moduli of composites. Two-point correlation functions and principal component analysis techniques are applied to extract and compress statistical information from microstructure images. A database establishment framework is developed to create three batches of data with 1000, 2000, and 3000 sizes. An ANN-based prediction framework is developed by integrating 10-fold cross-validation and Bayesian optimisation to optimise the neural network architecture and establish an efficient structure-property linkage under the influence of humid conditions. The prediction results demonstrate the efficiency of ANN in mapping microstructural data to an effective transverse modulus. A parametric study by ANN reveals the role of microstructure geometrical features and humid environmental parameters on the transverse performance of the composite.

Performance Prediction and Heating Parameter Optimization of Organic-Rich Shale In Situ Conversion Based on Numerical Simulation and Artificial Intelligence Algorithms.

In situ conversion technology is a green and effective way to realize the development of organic-rich shale. Supercritical CO2 can be used as a good heating medium for shale in situ conversion. Numerical simulation is an important means to explore the shale in situ conversion process, but it requires a lot of time and computational cost for in situ conversion simulation under different working conditions. Therefore, a computational framework for rapid prediction of shale in situ conversion development performance and heating parameter optimization is proposed by coupling artificial neural network (ANN) and particle swarm optimization (PSO). The results indicated that kerogen pyrolysis and hydrocarbon product release mainly occurred within 2 years of shale in situ conversion. The production curves of pyrolysis hydrocarbon obviously slowed after in situ conversion for 2 years. The database was constructed by a large number of in situ conversion simulations, and Pearson correlation analysis and the random forest method were adopted to obtain seven main controlling factors affecting reservoir temperature and hydrocarbon production. The determination coefficient of the obtained ANN-based prediction models is higher than 97%, and the mean square error (MSE) is lower than 0.3%. The basic reservoir case can choose to inject 350-450 °C supercritical CO2 (Sc-CO2) fluid with a rate of 600 m3/day to obtain a more promising development effect. The heating parameter optimization for three typical reservoir cases using PSO was performed, and reasonable injection temperature and injection rate were obtained. It realized accurate development prediction and rapid heating parameter optimization, which helps the effective application of shale in situ conversion development design.

Flow characteristics, ANN-based prediction, 3D processing map, and interface microstructure of titanium/stainless steel bimetallic composite

To investigate the hot deformation characteristics, workability, and interfacial microstructure of the titanium/steel bimetallic composite, hot compression simulations were carried out on the TA1/SUS430 composite within the temperatures of 750 °C–1050 °C, accompanied by strain rates spanning from 0.01 s⁻1–10 s⁻1. The hyperbolic sine Arrhenius constitutive equation and back-propagation artificial neural network (BP-ANN) model for flow stresses of this bimetallic composite were developed. 2D and 3D hot processing maps were established to study processability. The results revealed the calculated average activation energy (Q) was 277.9671 kJ/mol. The BP-ANN model demonstrated higher prediction accuracy than the Arrhenius model, with a correlation coefficient (R2) of 0.99947. As the strain increases, the area of the unstable region in the processing map expands, and the failure mode is characterized by the formation of microcracks at the bonded interface. Interfacial exfoliation manifested under elevated temperature and high strain rate deformation conditions. High power dissipation (η) values were observed within the processing parameters of 875°C–950 °C/0.01 s−1-0.03 s−1. The bimetal exhibited superior deformation coordination at low strain rates. TiC predominantly constituted the interface products at lower temperatures, while at higher temperatures, phases containing both Fe and Ti dominated. Furthermore, the deformed steel stratum manifested a pronounced cubic orientation <001>//CD and a less dominant recrystallized γ orientation. This γ texture attenuated progressively with increased deformation temperatures, while the strain rate has less impact.

ANN-based prediction models for green water events around a FPSO in irregular waves

The green water problem has been a critical concern for the safety of offshore structures in extreme environmental conditions. However, accurately predicting the green water events using the conventional diffraction analysis method is challenging, primarily due to the highly nonlinear physics of the green water phenomenon. In this study, a novel methodology for the prediction green water events is proposed by integrating the linear diffraction method integrated with deep learning techniques. The proposed methodology is designed as a screening tool to predict the occurrence of green water events in terms of relative wave motions around the hull. In the proposed model, a linear prediction model is employed to account for the dominant physics of ship hydrodynamics and wave mechanics, while the ANN model is introduced to complement its nonlinear effects. First, the prediction performance was compared between the linear model and the ANN-based models for the peak value of relative wave motion. The ANN-based prediction model significantly reduced the prediction error of the linear prediction model. Moreover, the ANN model based on the time series itself shows a higher predictive performance than the ANN model using features extracted from the time series. Next, the predictive performance of the ANN model was analyzed when applied to different wave conditions. It was found that the prediction error greatly decreased even for different wave conditions. Finally, the screening performances of the prediction models are investigated. The ANN-based prediction model was found to be a more effective screening tool than the linear prediction model in terms of screening quality index.

Automated mapping of regolith units with support vector machine and artificial neural network using data from Landsat-8 OLI, ALOS PALSAR DEM, and Sentinel-1A radar images: the case of the Sissingué Gold Project, Northern Côte d’Ivoire

ABSTRACT The Sissingué Gold Project is in Northern Côte d’Ivoire and part of the southern extension, a large peneplain of the landscape in South Mali. The area has experienced extensive weathering and erosion over a long time, resulting in a widespread and complex regolith cover. This diverse and vast regolith cover poses considerable difficulties for exploration. To overcome this problem, we adopted mapping of regolith units using machine learning (ML) with support vector machine (SVM) and artificial neural network (ANN) algorithms. The main objectives were to (1) make the predictive regolith map of the study region using these algorithms with data obtained from Landsat-8 operational land imager, Advanced Land Observing Satellite Phased Array Type L-Band Synthetic Aperture Radar digital elevation model and Sentinel-1A; (2) show the method of pre-processing and processing the required data and (3) develop the regolith landform unit (RLU) map from the predictive regolith map and collected data based on the Relict – Erosional – Depositional model. Tests using the SVM and ANN algorithms showed that both ML tools could accurately map regolith landforms. An innovative method of optimizing data using parameters is presented. The results showed that ANN outperformed SVM with an overall accuracy of 87.01% and a kappa coefficient of 0.84, whereas the corresponding values for SVM were 86.69% and 0.84, respectively. However, the validation data obtained from SVM-based prediction exhibited a better score than that of validation data obtained from ANN-based prediction. The Sentinel-1A radar band combined with Landsat-8 data reduced the vegetation-masking effect and improved the classification results. The RLUs of this area are composed primarily of relicts at 24.91%, including lateritic residuum and soil, depositional material at 36.39% with exotic sediments and ferrierite and the remaining 38.7% of erosional material made of saprolite, colluvial fragments, and mottled zones on flanks.

Design, implementation and performance prediction of profiled steel sheet-mixed aggregate recycled concrete hollow composite slab

Profiled steel sheet-mixed aggregate recycled concrete composite slabs are widely studied and applied in engineering applications by virtue of their good durability and recyclability. As an alternative to concrete composite slabs, concrete hollow composite slabs that can reduce their self-weight are also attracting people’s attention. However, the internal holes will increase the risk of collapse and shear failure of the concrete composite slabs. In order to reduce the risk and ensure the flexural performance of the concrete hollow composite slabs, this paper designs the recycled concrete hollow composite slabs with PVC pipes. A full-scale experiment is carried out on five open-mouth profiled steel sheet-mixed aggregate recycled concrete hollow composite slab specimens, to explore the influence of whether the bottom of the plate is reinforced, the thickness of the concrete surface layer and the hollow size on the working performance of the composite slabs. In order to predict the mechanical performance of the proposed hollow composite slabs, a prediction model based on artificial neural network (ANN) consisting of several sub-ANN modules is established. Moreover, according to the priority of the factors affecting the mechanical performance of composite slabs, a decision tree is designed to select appropriate testing sub-ANN module and thus improve the testing accuracy. Predicted results and experimental results are given to validate the feasibility and effectiveness of the developed ANN-based prediction framework for the mechanical performance prediction of composite slabs.

Publisher Correction: ANN-based prediction of cone tip resistance with Tabu-Search optimization for geotechnical engineering applications

Publisher Correction: ANN-based prediction of cone tip resistance with Tabu-Search optimization for geotechnical engineering applications

Analysis and ANN-based prediction of wind effects on twisted skyscrapers

Analysis and ANN-based prediction of wind effects on twisted skyscrapers

ANN-based prediction of ammonia nitrogen for wastewater discharge indicators under carbon neutral trend

IntroductionWith the rapid development of society and urbanization, greenhouse gas emissions have increased, leading to environmental problems such as global warming. The rise in urban water consumption has also resulted in increased sewage discharge, exacerbating freshwater scarcity and water pollution. Understanding the current status and spatial distribution of greenhouse gas emissions in China's sewage treatment industry is crucial for emission reduction measures and controlling ammonia nitrogen pollution.MethodsThis study comprehensively investigates greenhouse gas emissions from sewage treatment plants, analyzing influencing factors and predicting future spatial and temporal distributions. The uncertainty of ammonia nitrogen emissions is calculated using the IPCC's error propagation method, considering uncertainty ranges of variables. Additionally, an artificial neural network is employed to predict ammonia nitrogen content in sewage discharge, aiming to prevent excessive levels in wastewater.Results and discussionThe proposed model outperforms others with an R-Squared score of 0.926, demonstrating its superior accuracy in predicting ammonia content in wastewater. These findings contribute to better emission reduction strategies and control of ammonia nitrogen emissions. This model can effectively prevent excessive ammonia nitrogen content in discharged wastewater, contributing to water pollution control. In conclusion, this study highlights the importance of understanding greenhouse gas emissions from sewage treatment plants and their impact on water pollution. The research provides valuable insights into emission reduction measures, emission prediction, and technological innovations suitable for China's specific conditions. By effectively managing ammonia nitrogen emissions and adopting the proposed predictive model, the goals of carbon neutrality and environmental sustainability can be better achieved.

Optimal Design of Flow Control Fins for a Small Container Ship Based on Machine Learning

In this study, the optimal design of flow control fins (FCFs) for a container ship was carried out via a machine learning approach. The conventional design practice for the FCF relied on simulation-based performance evaluation, which demands a large amount of analysis time. Instead of computational fluid dynamics (CFD)-based prediction, artificial neural network (ANN)-based prediction was attempted. Prior to the machine learning process, the wake distribution data were collected systematically via CFD. Based on the collected data, the wake distributions and resistance performance dependent on varying the fin positions were learned using the ANN, and the optimal fin position was selected with relevant optimization techniques. When multi-objective optimization was employed, it was found that both wake distributions and resistance performance were improved in a practically applicable timeframe. The current process is superior to conventional simulation-based optimization in terms of speed. From the viewpoint of prediction accuracy, in this study, ANN-based prediction was found to be equally accurate as CFD-based prediction. Thus, the results can provide a novel and reliable design methodology for the optimal design of ship appendages.

ANN-based prediction of cone tip resistance with Tabu-Search optimization for geotechnical engineering applications

ANN-based prediction of cone tip resistance with Tabu-Search optimization for geotechnical engineering applications

Developing a computational toolbased on an artificial neural network for predicting and optimizing propolis oil, an important natural product for drug discovery.

Propolis is a promising natural product that has been extensively researched and studied for its potential health and medical benefits. The lack of requisite high oil-containing propolis and existing variation in the quality and quantity of essential oil within agro-climatic regions pose a problem in the commercialization of essential oil. As a result, the current study was carried out to optimize and estimate the essential oil yield of propolis. The essential oil data of 62 propolis samples from ten agro-climatic areas of Odisha, as well as an investigation of their soil and environmental parameters, were used to construct an artificial neural network (ANN) based prediction model. The influential predictors were determined using Garson's algorithm. To understand how the variables interact and to determine the optimum value of each variable for the greatest response, the response surface curves were plotted. The results revealed that the most suited model was multilayer-feed-forward neural networks with an R2 value of 0.93. According to the model, altitude was found to have a very strong influence on response, followed by phosphorous & maximum average temperature. This research shows that using an ANN-based prediction model with a response surface methodology technique to estimate oil yield at a new site and maximize propolis oil yield at a specific site by adjusting variable parameters is a viable commercial option. To our knowledge, this is the first report on the development of a model to optimize and estimate the essential oil yield of propolis.

Artificial Neural Network and Response Surface-Based Combined Approach to Optimize the Oil Content of Ocimum basilicum var. thyrsiflora (Thai Basil).

Ocimum basilicum var. thyrsiflora is valuable for its medicinal properties. The barriers to the commercialization of essential oil are the lack of requisite high oil-containing genotypes and variations in the quantity and quality of essential oils in different geographic areas. Thai basil's essential oil content is significantly influenced by soil and environmental factors. To optimize and predict the essential oil yield of Thai basil in various agroclimatic regions, the current study was conducted. The 93 datasets used to construct the model were collected from samples taken across 10 different agroclimatic regions of Odisha. Climate variables, soil parameters, and oil content were used to train the Artificial Neural Network (ANN) model. The outcome showed that a multilayer feed-forward neural network with an R squared value of 0.95 was the most suitable model. To understand how the variables interact and to determine the optimum value of each variable for the greatest response, the response surface curves were plotted. Garson's algorithm was used to discover the influential predictors. Soil potassium content was found to have a very strong influence on responses, followed by maximum relative humidity and average rainfall, respectively. The study reveals that by adjusting the changeable parameters for high commercial significance, the ANN-based prediction model with the response surface methodology technique is a new and promising way to estimate the oil yield at a new site and maximize the essential oil yield at a particular region. To our knowledge, this is the first report on an ANN-based prediction model for Ocimum basilicum var. thyrsiflora.

ANN for design and fabrication of ENi-P-nano TiO2 coatings on AH36 steel

Designing optimal ENi-P-nano TiO2 with higher surface hardness is time-consuming and expensive. Thus, this study is aims to develop the optimal optimiser-based ANN model to forcast Vickers hardness for newer process parametric combinations and find the ideal combination before manufacture. Consequently, three ANN model were devised using ADAM, AdaMax, and RMSprop optimisers with identical data set for training and testing. mean Squared Error (MSE) and R 2 values were used to compare and assess their performance. Rectified Linear Unit (ReLU) is used to provide nonlinearity to the neural network's output since the activation function affects ANN model performance. The study also highlights hyperparameter setting's impact on optimiser performance. The ADAM-based ANN model was determined as optimal design through comparing the predicted and experimental Vickers hardness for the unknown combinations using Taguchi DOE. In addition, FESEM and XRD micrographs confirmed the optimal coating's morphology and phases. This study results shown the compatibility of utilising ANN-based prediction models for ENi-P-nanoTiO2 coating design and prediction, however future research much incoporates more process parameters and their level ranges.

SBLMD–ANN–MOPSO-based hybrid approach for determining optimum parameter in CNC milling

Chatter is a type of self-excited vibration that expresses variations in frequency and energy dispersion during the milling process and invariably results in poor part quality and a lower material removal rate. An efficacious chatter detection approach is necessary to anticipate the chatter's nascent stage. Feature extraction is an important step in identifying chatter. In this paper, an efficient PF-based multi-mode signal processing method, i.e., Spline-Based Local Mean Decomposition (SBLMD), has been used to decompose the experimentally acquired sound signals into a series of PFs and then, selected PFs have been used to reconstruct the new chatter signal, which is rich in information. Further, two three-layer ANN-based prediction models are established to predict the CI and MRR. Three process-related variables, such as tool speed, feed speed, and cut depth, have been used to develop ANN models. Statistical comparisons have been conducted to obtain the optimal training algorithm and have found that the LM-based training algorithm was the best among the five other training algorithms. For the estimates of CI and MRR, the neurons in the hidden layer are optimized at 5 and 7 with the least mean squared errors (MSE), respectively. After applying MOPSO to ANN-based prediction models, the MOPSO-optimized ANNs are very sensitive to optimizing input layers. The optimal ranges for the Cut Depth (CD), Feed Speed (FS) and Tool Speed (TS) are 1.56–1.77 mm, 77–97 mm/min, and 2380–2880 rpm, respectively.

Comparing Artificial Neural Networks with Multiple Linear Regression for Forecasting Heavy Metal Content

This paper adopts two modeling tools, namely, multiple linear regression (MLR) and artificial neural networks (ANNs), to predict the concentrations of heavy metals (zinc, boron, and manganese) in surface waters of the Oued Inaouen watershed flowing towards Inaouen, using a set of physical-chemical parameters. XLStat was employed to perform multiple linear and nonlinear regressions, and Statista 10 was chosen to construct neural networks for modeling and prediction. The effectiveness of the ANN- and MLR-based stochastic models was assessed by the determination coefficient (R²), the sum squared error (SSE) and a review of fit graphs. The results demonstrate the value of ANNs for prediction modeling. Drawing on supervised learning and back propagation, the ANN-based prediction models adopt an architecture of [18-15-1] for zinc, [18-11-1] for manganese, and [18-8-1] for boron, and perform effectively with a single cached layer. It was found that the MLR-based prediction models are substantially less accurate than those based on the ANNs. In addition, the physical-chemical parameters being investigated are nonlinearly correlated with the levels of heavy metals in the surface waters of the Oued Inaouen watershed flowing towards Inaouen.