Back-propagation Artificial Neural Network Research Articles

Laser-Induced Breakdown Spectroscopy and a Convolutional Neural Network Model for Predicting Total Iron Content in Iron Ores.

Laser-induced breakdown spectroscopy (LIBS) is a rapid method for detecting total iron (TFe) content in iron ores. However, accuracy and measurement error of univariate regression analysis in LIBS are limited due to factors such as laser energy fluctuations and spectral interference. To address this, multiple regression analysis and feature selection/extraction are needed to reduce redundant information, decrease the correlation between variables, and quantify the TFe content of iron ores accurately. Overall, 339 batches of iron ore samples from five countries were obtained from the ports of China during the discharging, and 2034 representative spectra were collected. A convolutional neural network (CNN) model for total iron content prediction in iron ores is established. The performance of variable importance random forest (VI-RF), variable importance back propagation artificial neural network (VI-BP-ANN), and CNN-assisted LIBS in predicting the TFe content of iron ores was compared. Coefficient of determination (R2), root mean square error (RMSE), mean relative error (MRE), and modeling time were selected for model evaluation. The result shows that variable importance significantly enhances the quantitative accuracy and reduces modeling time compared to traditional BP-ANN and RF models. Moreover, the CNN model outperformed manual feature selection methods (VI-BP-ANN and VI-RF), exhibiting the shortest modeling time, highest R2, lowest RMSE, and MRE. CNN model's unique characteristics, such as weight sharing and local connection, make it well suited for analyzing high-dimensional LIBS data in multivariate regression analysis. Our approach demonstrates the effectiveness of machine learning and deep learning approaches in improving the accuracy of LIBS for TFe content prediction in iron ores. CNN-assisted LIBS method holds great potential for practical applications in the mining industry.

Prediction acrylamide contents in fried dough twist based on the application of artificial neural network

Acrylamide forms through the reaction between reducing sugars and asparagine in the thermal processing of food. Detection measures like LC-MS, HPLC are time-consuming and costly, which inspired us to use back propagation-artificial neural networks (BP-ANN) based on a genetic algorithm to establish an acrylamide prediction model in fried dough twist. The effects of frying time and temperature on acrylamide contents, as well as the color difference and acid value at different time and temperature were determined. Acrylamide content was found significantly correlated with temperature (P < 0.01) and was correlated with acid value and color difference (P < 0.05). Thus, temperature, acid value, and the color difference were set as input layers, and acrylamide content was set as an output layer to establish a BP-ANN network prediction model. The weight and threshold values in the BP-ANN network prediction model were optimized with a multi-population genetic algorithm and the test data were set to obtain an optimized BP neural network predicting model. The results showed that the Levenberg-Marquardt back-propagation training algorithm of the BP-ANN model with 5 hidden layer neurons and 0.005 learning rate was the best predictive performance, which the correlation coefficients (R) of test and validation were 0.9640 and 0.8999, suggesting a good fitting and strong approximation ability. The BP-ANN model is expected to accurately predict the content of acrylamide in fried dough twist.

Long-term reproducibility improvement of LIBS quantitative analysis based on multi-period data fusion calibration method

Long-term reproducibility is one of the important problems that urgently need to be solved in the quantitative analysis of laser-induced breakdown spectroscopy (LIBS). In this work, a new calibration method based on multi-period data fusion was proposed. Under the same experimental equipment and parameters, LIBS data collected at different times were fused together to establish calibration models. The spectra of the same set of standard samples were collected once a day for 20 days, the spectral data from the first 10 days were used as the training set for the calibration model, and the data from the last 10 days were used as the test set. As a comparison, three types of calibration models of four elements (Mn, Ni, Cr, and V) were established, including the internal calibration model (IS-1) based on the data from first day, multi-period data fusion internal calibration model established using internal calibration (IS-10) and genetic algorithm based back-propagation artificial neural network (GA-BP-ANN) based on the data from first 10 days. The test set spectral data were used to verify the prediction effect of the above three models. It was found that the GA-BP-ANN models have the lowest average relative errors (ARE) and the average standard deviations (ASD). Therefore, the proposed multi-period data fusion GA-BP-ANN model provides a novel method for improving the reproducibility of LIBS long-term repeated measurement.

Finite Element Modeling and Artificial Neural Network Analyses on the Flexural Capacity of Concrete T-Beams Reinforced with Prestressed Carbon Fiber Reinforced Polymer Strands and Non-Prestressed Steel Rebars

The use of carbon fiber reinforced polymer (CFRP) strands as prestressed reinforcement in prestressed concrete (PC) structures offers an effective solution to the corrosion issues associated with prestressed steel strands. In this study, the flexural behavior of PC beams reinforced with prestressed CFRP strands and non-prestressed steel rebars was investigated using finite element modeling (FEM) and artificial neural network (ANN) methods. First, three-dimensional nonlinear FE models were developed. The FE results indicated that the predicted failure mode, load-deflection curve, and ultimate load agreed well with the previous test results. Variations in prestress level, concrete strength, and steel reinforcement ratio shifted the failure mode from concrete crushing to CFRP strand fracture. While the ultimate load generally increased with a higher prestressed level, an excessively high prestress level reduced the ultimate load due to premature fracture of CFRP strands. An increase in concrete strength and steel reinforcement ratio also contributed to a rise in the ultimate load. Subsequently, the verified FE models were utilized to create a database for training the back propagation ANN (BP-ANN) model. The ultimate moments of the experimental specimens were predicted using the trained model. The results showed the correlation coefficients for both the training and test datasets were approximately 0.99, and the maximum error between the predicted and test ultimate moments was around 8%, demonstrating that the BP-ANN method is an effective tool for accurately predicting the ultimate capacity of this type of PC beam.

Reliability-based multi-objective optimization design of composite patch repair structure using artificial neural networks

Due to the parameter differences and the existence of random factors, the performance of composite repair structure shows a large dispersion. In order to obtain stronger, lighter and more reliable repair structure, multi-objective optimization design of carbon fiber reinforced polymers (CFRP) laminate repair structure is investigated by combining the reliability theory, artificial neural networks and the genetic algorithm. First, a 3D simulation model of the composite laminate patch repair structures is established using the 3D Hashin criterion and the cohesive region model. Then, the Latin Hypercube sampling (LHS) method is used to realize the random sampling, and the strength proxy model of the repair structure is established by using Back-propagation artificial neural network, further a multi-objective optimization model with tensile strength, reliability and weight as objective functions is built considering the design parameters and the random parameters. Finally, NSGAⅡalgorithm is used to solve the multi-objective optimization problem, and a set of solutions on the Pareto front surface are obtained, also the optimal design parameters of the composite repair structure meets the requirements is obtained.

Strength prediction and optimization for microwave sintering of large-dimension lithium hydride ceramics: GA-BP-ANN modeling

Failure typically occurs during sintering due to high thermal stress and poor strength of LiH ceramics. The short sintering time has shown to be beneficial in preventing excessive grain growth and improving ceramic performance. In this study, we built a genetic algorithm back propagation artificial neural network (GA-BP-ANN) model to predict the strength margins under different work conditions. Sensitivity analysis showed that the thickness and end control time were the most relevant parameters for strength margins, and the GA-BP-ANN model demonstrated the most efficient sintering work condition for a given thickness. Through statistical analysis of the strength margin predicted by the GA-BP-ANN model, we found that the bilinear temperature control method expanded the range of safe sintering conditions by 30% compared to the linear temperature control method. The research results of this study may serve as a reference for the safe and efficient sintering of LiH ceramics.

Daily and seasonal variations of soil respiration from maize field under different water treatments in North China

AbstractTo further evaluate the effect of water stress on soil respiration (RS), reveal the influencing factors of daily and seasonal RS, and systematically evaluate and compare the sensibility of different machine learning algorithms (multiple nonlinear regression [MNR], support vector machine regression [SVR], backpropagation artificial neural network [BPNN]) to estimate RS from a maize field under water stress condition, the field experiments were conducted within a maize field in Inner Mongolia, China, during the entire 2019 growing season. Various levels of deficit irrigation were conducted in the vegetative, reproductive, and mature stages. Our research indicated that soil CO2 fluxes from 100% evapotranspiration treatment (Tr1) were significantly greater than various deficit irrigation treatments (Tr2, Tr3, Tr4) during each growth stage of summer maize. The cumulative soil CO2 fluxes of Tr2, Tr3, and Tr4 decreased 24.8%, 30.3%, and 43.7% compared with Tr1, respectively. We determined that the drivers affecting the daily RS were soil temperature at 5 cm depth (TS,5) and soil surface temperature (TSF), followed by water‐filled porosity (WFPS) at 5 cm depth, but no significant correlations were observed at 25 cm depths. TS,5 and TSF also performed similar correlation with seasonal RS with R greater than 0.753 among all water treatments, followed by chlorophyll content with R greater than 0.726. During the whole growing season, the BPNN model exhibited the best predicting result, and could explain the 60%–80% and 87.8% of the variations of RS at the daily and seasonal scales, with root mean square error of 48.7–100.9 mg m−2 h−1 and 91.5 mg m−2 h−1, respectively. The SVR and MNR models could estimate the 47.9%–57% and 39.9%–52.1% of the daily RS and 81.4% and 78.6% of the seasonal RS, respectively. Overall, our study indicated the machine learning algorithms could be successfully applied to estimate RS at daily and seasonal scales from a maize field under water stress condition.

Straw incorporation: A more effective coastal saline land reclamation approach to boost sunflower yield than straw mulching or burial

In coastal lands, soil salinity greatly impedes crops growth and severely affects the agricultural productivity. Returning the crop straw and residual to soil was considered an important land reclamation method; however, the approach of straw return varied, including mulching (SM), burial (SB), and incorporation (SI). This study aimed to determine which approach was most effective to ameliorate coastal saline land and boost crop yield. Field experiments were conducted under different straw amelioration treatments on dry farming sunflowers (Helianthus annuus Linn.) in Bohai coastal land of Northern China. The results indicated that SM and SB changed the soil salt profile and significantly reduced the topsoil (0–0.2 m) salt content mainly by their direct effects on soil water transport, with little impacts on soil structure changes. Differently, SI significantly increased 21.8 % soil organic carbon and 52.3 % soil mean weight diameter in straw incorporated layer. The improvement on soil aggregates and porosity reduced 24.1–38.9 % of topsoil salt content, by limiting soil salt accumulation and promoting salt leaching. Furthermore, SI significantly boosted the sunflower fine root (d< 1.0 mm) growth and resulted in the highest sunflower yield (4.7 t/ha in 2020 and 4.6 t/ha in 2021) among those straw treatments. Compared to SM and SB, the net revenues of two-years sunflower cultivation under SI were improved by 40.68 % and 31.22 %, respectively. Therefore, it concluded that straw incorporation was more effective to reclaim coastal saline soil than straw mulching or burial. In addition, a back propagation artificial neural network model was developed to predict the dynamic of sunflower yield. This outcome provides an insight into the management of coastal farmland by establishing an easily desalinized and fertile topsoil profile structure.

Non-Destructive Analysis for Machine-Picked Tea Leaf Composition Using Near-Infrared Spectroscopy Combined Chemometric Methods

This paper aimed to predict the mechanical composition of machine-picked fresh tea leaves (MPFTLs) using near-infrared spectroscopy (NIRS) rapidly and non-destructively. Samples of MPFTL with different mechanical composition ratios were collected and subjected to NIRS analysis. Subsequently, various preprocessing methods were employed to eliminate extraneous noise information. Next, characteristic spectral information was extracted using the backward interval partial least squares (biPLS) method, which was subsequently subjected to principal component analysis (PCA). Finally, a predictive model was constructed by applying the back propagation artificial neural network (BP-ANN) method, which was tested by external samples to assess its predictive efficacy, and the results were expressed as root mean square error and determination coefficient of prediction (Rp2). The optimal spectral pretreatment method was the following: (standard normal variate (SNV) + second derivative (SD)). Four characteristic spectral subintervals of ([2, 3, 7, 10]) were screened out, and the cumulative contribution rate of 95.20%, attributable to the first three principal components, was determined. When the tanh transfer function was applied to construct the BP-ANN-NIRS model, the results demonstrated optimal performance, exhibiting a root mean square error and a determination coefficient of prediction (Rp2) of 0.976 and 0.027, respectively. The absolute values of prediction deviation for all prediction set samples were found to be less than 0.04. The results of the best BP-ANN model for external samples were found to be in close agreement with those of the prediction set model. NIRS technology has successfully achieved the forecasting of the mechanical composition of machine-picked fresh tea leaves rapidly and accurately, providing a fair and convenient new method for purchasing fresh tea raw materials by machines, according to their quality, and promoting the sustainable high-quality and healthy development of the tea industry.

Magnetic sludge-derived biochar for Cu (II) removal: RSM-based preparation and BP artificial neural network adsorption modeling

Magnetic sludge-derived biochar (MSDB) was synthesized using response surface methodology (RSM) optimization, with sludge as the raw material and sodium pyrophosphate as the modifier. The structure and surface properties of MSDB were characterized using scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS), vibrating sample magnetometer (VSM), and Brunauer-Emmett-Teller (BET) analysis. These analyses revealed that MSDB is rich in functional groups and exhibits magnetic properties, facilitating the adsorption of Cu(II) via complexation and easy separation of MSDB through magnetic means. Batch adsorption experiments showed that under conditions of 25 °C and pH 3.0, with an MSDB dosage of 0.75 g L−1, a Cu(II) removal efficiency of 95.67 % was achieved. Thermodynamic studies demonstrated maximum adsorption capacities of 173.69 mg g−1 at 25 °C, 183.26 mg g−1 at 35 °C, and 197.96 mg g−1 at 45 °C. Additionally, the BP neural network model showed a high coefficient of determination (R2 = 0.9396) and a low mean squared error (MSE = 0.0268) in simulating the MSDB-Cu(II) adsorption process, confirming the robustness of the model in both data simulation and predictive accuracy. This method offers a promising approach for kinetic modeling and predicting adsorption behavior in related fields of study.

Machine learning prediction of microhardness and corrosion current density of Ni-Co alloys produced by scanning jet electrodeposition

ABSTRACT Scanning jet electrodeposition (SJE) is a promising method for electrodeposition. Integrated with automation and machine learning, intelligent electrodeposition can be achieved. In this study, a machine learning method was used to develop the relationship between the process parameters and properties of Ni-Co alloys produced by SJE. To evaluate the various models, the coefficient of determination (R 2), mean absolute percentage error (MAPE), and root mean square error (RMSE) were calculated as performance metrics. The multivariate nonlinear regression (MNR) model shows a higher R 2, lower MAPE and RMSE values, and better performance in both the training and testing sets, indicating superior approximation and prediction accuracies for microhardness. A back-propagation artificial neural network (BP-ANN) shows stable R 2 value of closest to 1, and the lowest MAPE and RMSE for corrosion current density and presents an exceptional generalisation ability. Finally, under the present experimental conditions, the highest microhardness and corresponding process parameters were determined using the MNR model, and the lowest corrosion current density was optimised using the BP-ANN model.

Exploring nanoparticle dynamics in binary chemical reactions within magnetized porous media: a computational analysis

Artificial Neural Networks are incredibly efficient at handling complicated and nonlinear mathematical problems, making them very useful for tackling these challenges. Artificial neural networks offer a special computational architecture that is extremely valuable in disciplines like biotechnology, biological computing, and computational fluid dynamics. The present work investigates the applicability of back-propagation artificial neural networks in conjunction with the Levenberg-Marquardt algorithm for evaluating heat transmission in hybrid nanofluids. This work focuses on the computational analysis of a MgO + GO/EG hybrid nanofluid’s steady mixed convection flow over an exponentially stretched sheet, considering multiple slip boundary conditions, thermal conductivity, heat generation, and thermal radiation. A nonlinear system of ordinary differential equations is produced from the basic associated partial differential system by performing the proper exponential similarities modifications. For generating benchmark datasets, the resulting ordinary differential equations are processed employing the bvp4c method. Considering benchmark datasets set aside for training (70%), testing (15%), and validation (15%), the Levenberg-Marquardt algorithm, which employs back-propagation in artificial neural networks, is implemented. The accuracy of the suggested strategy for handling nonlinear problems is verified utilizing mean squared error, error histograms, and regression analysis, which are all used to evaluate the methodology. Outstanding agreement is seen when ANN outputs are compared to numerical results. The flow properties, including temperature, velocity, and concentration profiles, are shown graphically and numerically. For practical purposes, it is therefore essential to analyze the flow and heat transfer in hybrid nanofluids over exponentially extending and shrinking surfaces under mixed convection and heat source scenarios. Hybrid nanofluid problems have a wide range of practical and industrial applications, such as medication delivery, manufacturing, microelectronics, nuclear plant cooling, and marine engineering.

Optimization model for mass casualty management system using qos-aware routing protocol and casualty triage prediction

Abstract Purpose Unexpected events, whether man-made or natural, cause significant distress and disorder. The number and magnitude of disasters and catastrophes have been rising globally in recent decades, according to historical data. Continued real-time monitoring of mass casualty along with the arrangement of needed medical resources to handle the mass casualty is required to reduce the mortality and morbidity rates. Methods Electronic tag-based casualty monitoring and machine learning-based Decision Support Systems are emerging as a more effective and proactive solution that provides continuous remote monitoring of patients. A novel framework based on Body-to-Body Network, Prediction model, and Genetic Algorithm-based medical resource optimization is proposed for the continuous monitoring of the mass casualty and medical resource allocation at the incident. The aim of this work is to give priority to the handling of critical casualties. Firstly, a Quality of Service and load-sensitive routing protocol for transmitting mass casualties' physiological parameters across a wireless network is proposed, with the critical casualty being emphasized. Secondly, the clinical seriousness degree of the mass casualty is predicted using Backpropagation Artificial Neural Network. Finally, an optimization model using a Genetic algorithm and queuing theory is proposed to find the required optimal number of medical resources to handle critical and non-critical casualties separately. Also, the proposed optimization model considers the predicted clinical level transition rates of the mass casualty. Results The performance and accuracy of the proposed framework are evaluated using the MIMIC-II dataset. The outcome demonstrates that the framework emphasizes critical casualty management. Furthermore, the framework allocates an adequate number of servers by incorporating the proposed routing protocol in comparison to the AODV protocol. Conclusion The inclusion of a prediction model in the framework aids in allocating an adequate number of servers by considering the predicted clinical deteriorating transition rates of casualties at a mass casualty incident. In terms of the estimated length of the casualty at the incident, the results suggest that incorporating a medical resource optimization model outperforms the non-optimal option.

Comparative Study of Back-Propagation Artificial Neural Network Models for Predicting Salinity Parameters Based on Spectroscopy Under Different Surface Conditions of Soda Saline–Alkali Soils

Comparative Study of Back-Propagation Artificial Neural Network Models for Predicting Salinity Parameters Based on Spectroscopy Under Different Surface Conditions of Soda Saline–Alkali Soils

Prediction of 3D printability and rheological properties of different pineapple gel formulations based on LF-NMR

In this study, a pineapple-starch-xanthan gum system was prepared using fresh pineapple juice, maize starch, and xanthan gum (XG). The feasibility of using low-field nuclear magnetic resonance (LF-NMR) to predict pineapple gels' rheological properties and printability was evaluated. Results indicated that as maize starch and XG increased, the gel transformed from unable to support printed models to a stable shape, eventually becoming too viscous for printing. Principal component analysis and Fisher discriminant analysis classified the gels into four categories based on their rheological properties, aligning with the actual printing results. Pearson correlation analysis showed a strong correlation between the LF-NMR parameters and the rheological properties of gels. The partial least squares (PLS) and back-propagation artificial neural network (BP-ANN) models constructed using the LF-NMR parameters can effectively predict the rheological properties of pineapple gels. Therefore, LF-NMR is a valuable, non-destructive method for quickly assessing pineapple gels' 3D printing suitability.

A Novel Neural Network Prediction Model for Mineral Content Based on the Data of Elemental Logging and Well Logging

The mineral content of shale plays an important role in the study of reservoir characteristics. Obtaining high-precision mineral content data from a simple and straightforward method is helpful for the study of reservoir properties. Due to the complex and varied elemental combination of minerals and the lithological diversity in different formations, there are limitations in the traditional statistical methods for predicting mineral content. In this study, a multi-source fusion dataset is constructed first using a detailed workflow to process multi-source data from elemental logging and conventional well logging from the Funing shale formations in China. A hybrid neural network model consisting of a back-propagation artificial neural network (BP-ANN) and gated recurrent unit (GRU) structure, with a custom constraint loss function, is developed to predict the mineral contents. The results show that the predictive performance of this hybrid multi-source model performs statistically significantly better than that of the BP-ANN and GRU models using single source data. In addition, the accuracy of the hybrid model is further improved by using the custom constraint loss function. This method provides high-resolution distributions of mineral content compared to the X-ray powder diffraction testing method. It will help enhance the understanding of the formation.

Design of Facial Expressions Recognition for Academic Presence By Using Backpropagation Artificial Neural Networks Based on Principal Components Analysis

There are 4,004 universities in Indonesia where each university needs data to find out student activities, one of which is through attendance. Some universities in Indonesia still use manual attendance systems and attendance systems through the website. This system has several obstacles that require solutions. Therefore, a more concise system is needed to assist students in filling in the attendance. This research aims to make a design to make academic presence for students by using neural network. There are many methods that can be used to create this system including using Principal Component Analysis (PCA) based on Backlpropagation Neural Network (BNN) because it can help the system perform faster and more accurately without losing important information. After carrying out a series of steps of algorithm designed for student attendance, we get the recognition of facial image expressions by using ANN Backpropagation and recognition of facial image expression with PCA.

Analysis and optimization of abrasive waterjet dressing parameters for surface texturing of diamond grinding wheels

With the development of ultra-precision machining technology, the grinding performance of diamond grinding wheels has put forward higher requirements. In this study, a new method of dressing diamond grinding wheels using abrasive waterjet (AWJ) technology is proposed to address the issues of workpiece damage and wheel clogging that occur when grinding difficult-to-machine materials with conventional diamond grinding wheels. The main process parameters were determined based on the theoretical model for dressing diamond grinding wheels using AWJ. The response surface methodology (RSM) and the backpropagation artificial neural network (BP-ANN) were employed to establish regression models between process parameters and microgroove characteristics. A comparison was performed to evaluate the prediction performance of both RSM and BP-ANN. The results indicated that both approaches BP-ANN and RSM are powerful tools for predicting microgroove characteristics. This work provides theoretical guidance for texturing diamond wheels surface.

Prediction of soil heavy metal content around mine tailings using multiple methods combined with transformed hyperspectral reflectance data

The extensive accumulation of tailings can potentially cause heavy metal contamination in the surrounding farmland soil. Accurately predicting the spatial distribution of heavy metals in farmland soil is crucial for assessing the potential environmental hazards of tailings.This study focuses on the spatial distribution and the quantitative prediction of heavy metals (chromium (Cr), vanadium (V), and copper (Cu)) in soils surrounding mine tailings using advanced spectral data analysis and multiple prediction models. The original hyperspectral reflectance data were processed using first-order differential (FD), second-order differential (SD), reciprocal logarithmic (LR), and continuum removal (CR) transformations to highlight the positions of characteristic bands. Multiple linear regression (MLR), stepwise linear regression (SLR), partial least squares regression (PLSR), random forest (RF), and back propagation artificial neural network (BP-ANN) models were used to establish inversion models for Cr, V, and Cu based on bands with high correlation coefficients. The performance of the inversion models was evaluated using the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and residual predictive deviation (RPD). The results indicate that the raw hyperspectral data from the measured soil exhibit a weak response to heavy metal content in the study area. However, applying FD, SD, and CR transformations significantly enhances the sensitivity of soil spectral data to heavy metal concentrations, facilitating subsequent modeling. Among these, the SD transformation is particularly beneficial for modeling the Cr and Cu elements in the soil. For the V element, the FD transformation yields data that are more suitable for modeling. Regarding the inversion models based on the measured spectral data, the BP-ANN model exhibited the best predictive performance. Specifically, when combined with SD spectral data, the BP-ANN achieved the highest predictive accuracy for Cu content (R² = 0.85, RPD = 2.12). The RF model demonstrated the next best performance, with its optimal inversion model also utilizing SD spectral data for predicting Cu content (R² = 0.76, RPD = 1.90). On the other hand, the MLR model exhibited the poorest performance and is unsuitable for predicting heavy metal content in the region using the measured spectral data. This study highlights the potential of spectral data in environmental monitoring and provides a technical reference for the inversion assessment and regulation of heavy metals in farmlands surrounding tailing sites.

Process optimization and modeling of Acer truncatum seed oil deacidification by molecular distillation

Acer truncatum seed oil (ATO) is a unique woody oil resource, but its high acid value resulting from traditional pressing methods falls short of meeting the necessary food standards. In this research, molecular distillation (MD) was employed for the deacidification of ATO and compared with conventional techniques such as alkali refining and solvent extraction. Predictive models for MD deacidification were established through single-factor experiments, orthogonal experimental design (OED), response surface methodology (RSM), and genetic algorithm - back propagation artificial neural network (GA-BP-ANN). Using RSM, a fitting model was obtained with R = 0.999 and Rpre = 0.990 through multiple linear regression. The constructed BP-ANN model (3-9-1) exhibited R = 0.998 and Rpre = 0.998, indicating slightly higher prediction accuracy. With GA-BP-ANN, the optimal process conditions are an evaporator temperature of 190 °C, condensation temperature of 40 °C, scraper speed of 324 rpm, yielding an acid value of refined ATO at 0.240 ± 0.001 mg g−1. Therefore, under appropriate conditions, the MD deacidification method can produce high-quality refined ATO. The developed orthogonal, RSM, and GA-BP-ANN models demonstrated excellent capabilities in optimizing and predicting the MD deacidification process, meeting even the strictest food regulations.