Engineering reports : open access最新文献_第5页

Improving Manufacturing Efficiency in Developing Countries: A Value Stream Mapping Case Study of a Tanzanian Rice Mill 提高发展中国家的制造业效率：坦桑尼亚碾米厂价值流映射案例研究

IF 2

Engineering reports : open access Pub Date : 2025-09-22 DOI: 10.1002/eng2.70401

Juma Mohamed Matindana, Francis Daudi Sinkamba

{"title":"Improving Manufacturing Efficiency in Developing Countries: A Value Stream Mapping Case Study of a Tanzanian Rice Mill","authors":"Juma Mohamed Matindana, Francis Daudi Sinkamba","doi":"10.1002/eng2.70401","DOIUrl":"https://doi.org/10.1002/eng2.70401","url":null,"abstract":"As competition among industries increases in terms of quality, price, and flexibility, there is a need for industries to apply new advanced manufacturing philosophies, such as Lean Manufacturing (LM), for operational excellence in today's dynamic market. Manufacturing industries in Tanzania are now thinking of applying LM tools such as value stream mapping (VSM) to detect and eliminate waste in their production processes for improvements in their operations and the contribution of the manufacturing sector to the Gross Domestic Product (GDP) of the country, which stands at 8% as of date. This study applied VSM for one rice milling industry as a case study of food industries to identify nonvalue-added and value-added activities. The study comprised three phases, which were data collection from the industry, analysis of data, and mapping of actual and future state maps using the EdrawMax software version 10.5.0. Future state maps indicated that there would be significant improvements in the reduction of lead time by 44.3%, cycle time increase by 5%, increase in employee performance indicator from 88.3% to 91.7%, increase in quantitative production indicator from 82.8% to 90.5%, and increment of income generated after the elimination of identified activities which do not add value in their production operations. The study is beneficial for manufacturing owners and practitioners as it highlights how organizations can improve operational efficiency in terms of time reduction and an increase in income using VSM. The study recommends that the owners and practitioners of Tanzanian manufacturing industries and other developing countries should conduct VSM for each production process of their operations to improve the efficiency of their organizations and the contribution of the sector to the economy of the country.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70401","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Latent Feature-Based Type 2 Diabetes Prediction Using a Hybrid Stacked Sparse Autoencoder and Machine Learning Models 使用混合堆叠稀疏自编码器和机器学习模型的基于潜在特征的2型糖尿病预测

IF 2

Engineering reports : open access Pub Date : 2025-09-22 DOI: 10.1002/eng2.70358

Abdussamad, Hanita Daud, Rajalingam Sokkalingam, Muhammad Zubair, Iliyas Karim Khan, Zafar Mahmood

{"title":"Latent Feature-Based Type 2 Diabetes Prediction Using a Hybrid Stacked Sparse Autoencoder and Machine Learning Models","authors":"Abdussamad, Hanita Daud, Rajalingam Sokkalingam, Muhammad Zubair, Iliyas Karim Khan, Zafar Mahmood","doi":"10.1002/eng2.70358","DOIUrl":"https://doi.org/10.1002/eng2.70358","url":null,"abstract":"Early and precise prediction of Type 2 diabetes is vital for effective intervention. However, extracting meaningful insights from high-dimensional datasets with sparse values remains challenging. Sparsity and redundant features often hinder traditional machine learning algorithms' ability to identify informative patterns. While conventional Stacked Sparse Autoencoders (SSAE) can capture key features in dense data, they typically struggle with high-dimensional sparse data, reducing classification accuracy. To address this limitation, the study proposes a Hybrid Stacked Sparse Autoencoder (HSSAE) algorithm designed for robust feature extraction and classification in sparse data environments. The architecture incorporates L1 and L2 regularization within a binary cross-entropy loss and employs dropout and batch normalization to improve generalization and training stability. The HSSAE algorithm's performance was tested with a sigmoid classifier and various machine learning techniques. When combined with a sigmoid layer, the model achieved 89% accuracy and an F1 score of 0.89. It also outperformed baseline models when integrated with traditional classifiers; notably, the HSSAE + K-Nearest Neighbor (KNN) achieved an F1 score of 0.91, a recall of 0.98, 90% accuracy, and the lowest hamming loss of 0.10. Comparative evaluations included baseline classifiers like Logistic Regression (LR), KNNs, Naïve Bayes (NB), AdaBoost, and XGBoost, applied directly to the preprocessed dataset. An ablation study tested these classifiers on features extracted via the SSAE. In both cases, the HSSAE algorithm showed superior performance across all metrics. These findings demonstrate the HSSAE algorithm's effectiveness in extracting discriminative features from sparse, high-dimensional data, emphasizing its potential for clinical decision support systems requiring high accuracy and reliability.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70358","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrated Assessment of Mechanical and Electrochemical Properties of Additively Manufactured IN 718 Alloy Using Taguchi and Super Ranking Approaches 用田口法和超排序法综合评价增材制造IN 718合金的力学和电化学性能

IF 2

Engineering reports : open access Pub Date : 2025-09-22 DOI: 10.1002/eng2.70400

Pooja. G. Thorat, Avinash Lakshmikanthan, Mohan Nagaraj, Manjunath Patel Gowdru Chandrashekarappa, Oguzhan Der, Chithirai Pon Selvan, Raghupatruni Venkata Satya Prasad

{"title":"Integrated Assessment of Mechanical and Electrochemical Properties of Additively Manufactured IN 718 Alloy Using Taguchi and Super Ranking Approaches","authors":"Pooja. G. Thorat, Avinash Lakshmikanthan, Mohan Nagaraj, Manjunath Patel Gowdru Chandrashekarappa, Oguzhan Der, Chithirai Pon Selvan, Raghupatruni Venkata Satya Prasad","doi":"10.1002/eng2.70400","DOIUrl":"https://doi.org/10.1002/eng2.70400","url":null,"abstract":"The increased adoption of IN 718 alloy in marine and aerospace applications faces critical challenges due to aggressive chloride-induced degradation, making understanding its corrosion resistance imperative. Evaluating its mechanical performance (micro-hardness: MH and ultimate tensile strength: UTS) is equally essential and represents a critical area of study. The mechanical performance of IN 718 alloy is reliant on four influencing variables (laser power, scan speed, laser beam spot size, and layer thickness) of the selective laser melting (SLM) technique. The Taguchi L9 matrix is designed to study and analyze the parameters and optimize the responses. Laser power showed a dominant impact on the mechanical performance of printed parts. Taguchi determined that optimal conditions were found to be different for both UTS and MH. The super ranking method determined that optimized SLM conditions resulted in MH and UTS values of 344.8 HV and 1051.2 MPa, as experimentally determined. Microstructural characterization was performed on IN 718 alloy powder, and fracture morphology was conducted at different parametric conditions. The corrosion behavior of optimized SLM-processed IN 718 alloy was evaluated in 0.1 M H2SO4 with varying NaCl concentrations (0.1–0.7 M) using potentiodynamic polarization and electrochemical impedance at room temperature. The addition of 0.7 M NaCl to 0.1 M H2SO4 provided the highest inhibition activity for IN 718 alloy, indicating that printed optimized parts can enhance its corrosion resistance in acidic environments.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70400","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Monolithic Tandem Solar Cell With Co-Sensitized DSSC and Perovskite Sub-Cells Using Spectral Filtering for High-Efficiency Photon Management 利用光谱滤波实现高效光子管理的共敏DSSC和钙钛矿亚电池单片串联太阳能电池

IF 2

Engineering reports : open access Pub Date : 2025-09-22 DOI: 10.1002/eng2.70409

Diptanu Dey, Raj Chakraborty, Punam Das, Diptanu Das, Pronob K. Ghosh

{"title":"Monolithic Tandem Solar Cell With Co-Sensitized DSSC and Perovskite Sub-Cells Using Spectral Filtering for High-Efficiency Photon Management","authors":"Diptanu Dey, Raj Chakraborty, Punam Das, Diptanu Das, Pronob K. Ghosh","doi":"10.1002/eng2.70409","DOIUrl":"https://doi.org/10.1002/eng2.70409","url":null,"abstract":"Recent advances in dye-sensitized and perovskite solar technologies have enabled tandem architectures to surpass single-junction efficiency limits. This work reports a high-efficiency monolithic tandem solar cell combining a co-sensitized dye-sensitized solar cell (DSSC) top sub-cell with a triple-cation perovskite bottom sub-cell. The DSSC, based on a mesoporous TiO2 photoanode co-sensitized with SM315 and ZnTPP dyes, harvests light from 400 to 650 nm. The bottom cell, using a Cs/FA/MA mixed-halide perovskite, targets near-infrared photons (650–850 nm). A dielectric multilayer optical filter facilitates spectral splitting, while a thin indium tin oxide recombination layer ensures efficient series connection and current matching. Under calibrated dual-LED illumination (∼125 mW/cm2), the tandem achieved a lab-measured power conversion efficiency (PCE) of 33.7%, with a simulated maximum of ∼36.8% and an average reproducible PCE of 33.2% ± 0.4% (n = 3). When tested under a class AAA AM1.5G solar simulator (100 mW/cm2), the device produced a baseline PCE of 27.1% (short-circuit current density, JSC = 16.1 mA/cm2, open-circuit voltage, VOC = 1.95 V, fill factor, FF = 0.72). These values are in-house laboratory results, not certified records. UV–Vis, FTIR, external quantum efficiency, and EIS confirmed effective charge transport and spectral complementarity. Surface and interface morphology were characterized by AFM, SEM, and HRTEM. Stability testing showed > 96% retention after 500 h at 25°C and ∼86% at 60°C. Outdoor field testing under tropical weather confirmed functional robustness. This scalable, solution-processed tandem architecture shows promise for next-generation photovoltaics, including building-integrated and indoor energy applications.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70409","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Empirical Modeling and Osprey-Based Optimization of AlSi10Mg Tensile Strength in Selective Laser Melting 选择性激光熔化AlSi10Mg拉伸强度的经验建模及基于osprey的优化

IF 2

Engineering reports : open access Pub Date : 2025-09-20 DOI: 10.1002/eng2.70413

Nagareddy Gadlegaonkar, Premendra J. Bansod, Avinash Lakshmikanthan, Krishnakant Bhole, Manjunath Patel Gowdru Chandrashekarappa, Chithirai Pon Selvan

{"title":"Empirical Modeling and Osprey-Based Optimization of AlSi10Mg Tensile Strength in Selective Laser Melting","authors":"Nagareddy Gadlegaonkar, Premendra J. Bansod, Avinash Lakshmikanthan, Krishnakant Bhole, Manjunath Patel Gowdru Chandrashekarappa, Chithirai Pon Selvan","doi":"10.1002/eng2.70413","DOIUrl":"https://doi.org/10.1002/eng2.70413","url":null,"abstract":"AlSi10Mg alloy, known for its better strength-to-weight ratio, corrosion resistance, thermal stability, and castability, led to its use for widespread engineering applications. Optimizing tensile strength ensures better structural and functional integrity of parts subjected to loading applications. The mechanical strength of parts is sensitive to selective laser melting (SLM) parameters. Improper setting of SLM parameters (laser power, focal plane, and scan speed) led to the introduction of defects (unmelted powders, porosity, keyholes, and weak bonding layer) that reduce the mechanical performance. The morphology of AlSi10Mg powder confirms the particle size of 30 ± 5 μm with spherical and single dispersed characteristics. The EDAX analysis confirms the aluminium, silicon, and magnesium compositions with 87.49%, 10.08%, and 2.43%, respectively. The experimental plan, as per central composite design (CCD), allows the investigator to analyze the SLM parameters on the tensile strength performance of printed parts. The scan speed contribution to enhancing the tensile strength performance is significant. All interaction factors were significant despite negligible contributions observed for the individual effects of laser power and focal plane. The impact of SLM parameters exhibits nonlinear behavior with tensile strength. The derived empirical relationships predict 10 test cases with a percent deviation ranging between −3.74% and +3.24%, resulting in a mean absolute percent error equal to 2.7%. Osprey Optimization Algorithm (OOA) determined condition maximizes the tensile strength to 392.4 ± 2.5 MPa, displaying a ductile fracture with minor dimples, keyhole cavities, and stream flow patterns.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70413","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145102272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fins Arrangements and Al2O3 Nanoparticles Concentrations Effects on Melting Time of RT82 Paraffin PCM in Double-Pipe Heat Exchanger 翅片排列和Al2O3纳米颗粒浓度对RT82石蜡PCM在双管换热器中熔化时间的影响

IF 2

Engineering reports : open access Pub Date : 2025-09-20 DOI: 10.1002/eng2.70381

Jinan Saleem Abdul Kareem, M. Hatami, Ali Kianifar, Hameed K. Hamzah

{"title":"Fins Arrangements and Al2O3 Nanoparticles Concentrations Effects on Melting Time of RT82 Paraffin PCM in Double-Pipe Heat Exchanger","authors":"Jinan Saleem Abdul Kareem, M. Hatami, Ali Kianifar, Hameed K. Hamzah","doi":"10.1002/eng2.70381","DOIUrl":"https://doi.org/10.1002/eng2.70381","url":null,"abstract":"The current study includes the numerical modeling of a Double-Pipe Heat Exchanger containing a phase change material mixed with Al2O3 nanoparticles at different fins configurations. The objectives of this study are the determination of the effect of nanoparticles on the melting process of PCM and evaluating the melting time for different configurations of copper fins through the heat exchanger. The numerical study used COMSOL Multiphysics based on the enthalpy method. Paraffin RT82 was used as a phase change material with aluminum oxide nanoparticles (Al2O3). The results showed that the number of fins leads to a faster and more efficient melting process compared to a heat exchanger that does not contain fins. However, this reduces the amount of PCM present inside the annular domain, and thus the amount of heat stored decreases. The time of full melting of the PCM was equal to 193.96 min, while the time decreased to reach 187.5 and 181.46 min when the nano concentration was increased to 4% and 6%, respectively. The third case contributed to saving 31.89% of the melting time, followed by the seventh case by 27%, while the second and fifth cases were the least effective by 9.4% and 10.52%, respectively.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70381","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145102270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Explainable AI for Generalizable PCOS Diagnosis: A Geographically Validated Ensemble Learning Approach With Feature Selection 可解释的人工智能用于多囊卵巢综合征的诊断：一种具有特征选择的地理验证集成学习方法

IF 2

Engineering reports : open access Pub Date : 2025-09-20 DOI: 10.1002/eng2.70395

Sonia Akter, Saha Reno

{"title":"Explainable AI for Generalizable PCOS Diagnosis: A Geographically Validated Ensemble Learning Approach With Feature Selection","authors":"Sonia Akter, Saha Reno","doi":"10.1002/eng2.70395","DOIUrl":"https://doi.org/10.1002/eng2.70395","url":null,"abstract":"Diagnosing Polycystic Ovary Syndrome (PCOS) is challenging due to its varied symptoms and the absence of a single definitive test. This study develops a robust and interpretable machine learning framework to enhance PCOS diagnosis and its applicability across diverse patient populations. From an initial set of 45 clinical features, 23 were selected for their strong statistical and biological relevance to established PCOS diagnostic criteria. Our novel approach combines these features within a weighted ensemble of classifiers, which significantly outperformed individual models. The final model achieved a 94.34% accuracy and a strong AUC of 93.38%, surpassing previous benchmarks. Critically, the model demonstrated consistent and reliable performance across distinct geographic cohorts, validating its generalizability. Furthermore, the use of explainable AI techniques ensures the model's decisions are transparent and clinically interpretable for healthcare providers. These findings confirm that this ensemble-driven tool can serve as a reliable, scalable, and practical aid for the early and accurate detection of PCOS in clinical settings.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70395","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Medical Waste to Energy: Pyrolysis Oil of Saline Containers Waste Fuelled CI Engine Characteristics Evaluation With Hybrid Nano-Fuel 医疗废物转化为能源：盐容器废物热解油燃料CI发动机特性评价与混合纳米燃料

IF 2

Engineering reports : open access Pub Date : 2025-09-19 DOI: 10.1002/eng2.70389

T. Sathish, P. Suresh Kumar, R. Prasath, Rasan Sarbast Faisal, Tariq Alkhrissat, A. Johnson Santhosh, A. Anderson

{"title":"Medical Waste to Energy: Pyrolysis Oil of Saline Containers Waste Fuelled CI Engine Characteristics Evaluation With Hybrid Nano-Fuel","authors":"T. Sathish, P. Suresh Kumar, R. Prasath, Rasan Sarbast Faisal, Tariq Alkhrissat, A. Johnson Santhosh, A. Anderson","doi":"10.1002/eng2.70389","DOIUrl":"https://doi.org/10.1002/eng2.70389","url":null,"abstract":"The growing medical industry plays a crucial role in maintaining human health. However, it also generates a significant amount of medical waste, including plastic saline containers. Properly managing this waste is essential to minimize environmental pollution and reduce the burden on waste management systems. Converting saline container waste into fuel through the pyrolysis process presents a valuable solution for energy demand. Transforming this saline container waste into a useful resource addresses the issue of plastic waste pollution. This research aims to support the Sustainable Development Goals of 3, 7, 11, 12, and 13. The produced Pyrolysis oil of Saline container Wastes (POSCW) was used to prepare three different blends (25, 50, and 75 vol% concentration with diesel) of biodiesel, two different nano-fuels, and one hybrid nano-fuel. The POSCW100, POSCW75D25, POSCW50D50, POSCW25D75, POSCW25D75 + CONP, POSCW25D75 + MWCNT, and POSCW25D75 + CONP/MWCNT were prepared, characterized for fuel properties, and tested in a 5.2 kW CI engine test rig at constant speed and various load conditions along with standard fuel of Pure diesel (PD100). The results reveal that POSCW100 recorded near-diesel performances. Nano-fuels and hybrid nano-fuels recorded appreciable results, particularly the POSCW25D75 + CONP/MWCNT hybrid nano-fuel, which outperformed in terms of in-cylinder pressure, heat release rate, engine performance, and emission performance.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design of a High Return Loss 4 × 4 Butler Matrix Without Crossover for 5G Base Station 5G基站高回波损耗无交叉4 × 4管家矩阵设计

IF 2

Engineering reports : open access Pub Date : 2025-09-19 DOI: 10.1002/eng2.70408

Mohammad Bod, Fatemeh Geran

引用次数: 0

Development and Validation of ANN Models for Water Absorption in Sawdust and Kenaf Fiber-Reinforced Polystyrene Composites 木屑和红麻纤维增强聚苯乙烯复合材料吸水率的人工神经网络模型的建立与验证

IF 2

Engineering reports : open access Pub Date : 2025-09-19 DOI: 10.1002/eng2.70393

Jothi Arunachalam Solairaju, Saravanan Rathinasamy, Sathish Thanikodi, Bashar Tarawneh, Vinuja Gurumoorthy, Johnson Santhosh Antony, Anderson Arul Gnana Dhas

{"title":"Development and Validation of ANN Models for Water Absorption in Sawdust and Kenaf Fiber-Reinforced Polystyrene Composites","authors":"Jothi Arunachalam Solairaju, Saravanan Rathinasamy, Sathish Thanikodi, Bashar Tarawneh, Vinuja Gurumoorthy, Johnson Santhosh Antony, Anderson Arul Gnana Dhas","doi":"10.1002/eng2.70393","DOIUrl":"https://doi.org/10.1002/eng2.70393","url":null,"abstract":"This research paper involved modeling the water absorption behavior of polystyrene (PS) composites with sawdust and kenaf fiber (KF) reinforcement using the Artificial Neural Network (ANN) method. The composites were made by manual mixing combined with the hand lay-up process at room temperature (25°C ± 2°C) and cured in an open mold over 7 days at ambient temperature. The water absorption measurements were done according to the ASTM D1037-99. The findings were that the water uptake was enhanced by filler content as well as immersion duration in the sawdust composite and KF. The ANN model also had good accuracy; the coefficients of determination (R2) in all the ANN models were more than 0.98 in all the training, validating, and test sets of both types of materials. Also, values of root mean square error (RMSE) were low (less than 1 wt%), indicating that this model was very accurate in forecasting the behavior of water absorption. Parity plots indicated that there was a good balance of the performance of the predictions, which captured the low and high values of absorption. Moreover, the p value was lower than 0.05, which showed ANOVA results are statistically significant.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 9","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70393","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0