This paper highlights the use of aluminum oxide nanoparticles as an additive in diesel-butanol blends to show its effect on fuel consumption, emissions and performance. In the present experiment, different concentrations of aluminium oxide nanoadditives (30, 50, and 70 ppm) are used in alcohol-based biodiesel. Butanol has been used in concentrations of 5 and 10 % in diesel and therefore all blends are termed as B5 and B10 in addition to nanoparticle concentration to avoid complexity. These different blends (B5+30, B5+50, B5+70, B10+30, B10+50, B10+70) are tested for various engine loads at a constant speed of 1500 rpm. The experiment was performed on a Variable compression ratio (VCR) engine at varying compression ratios of 16, 17, and 18. Engine characteristics at different compositions of the blend at different compression ratios were provided by the interfaced computer through the software. The enhanced performance effects can be easily seen from the outcomes in the increment in brake thermal efficiency of the blends as compared to neat diesel. Considerable decrement can be observed in carbon monoxide (CO) and unburnt hydrocarbon (HC) values with an increase in compression ratio. Moderate reduction can be observed in NOx at higher loads in contrast to neat diesel.
{"title":"Evaluation of Aluminum Oxide Nanoparticle Blended with Alcohol Based Biodiesel at Variable Compression Ratios","authors":"Payal Sharma, Nathi Ram Chauhan, Manish Saraswat","doi":"10.5750/ijme.v1i1.1339","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1339","url":null,"abstract":"This paper highlights the use of aluminum oxide nanoparticles as an additive in diesel-butanol blends to show its effect on fuel consumption, emissions and performance. In the present experiment, different concentrations of aluminium oxide nanoadditives (30, 50, and 70 ppm) are used in alcohol-based biodiesel. Butanol has been used in concentrations of 5 and 10 % in diesel and therefore all blends are termed as B5 and B10 in addition to nanoparticle concentration to avoid complexity. These different blends (B5+30, B5+50, B5+70, B10+30, B10+50, B10+70) are tested for various engine loads at a constant speed of 1500 rpm. The experiment was performed on a Variable compression ratio (VCR) engine at varying compression ratios of 16, 17, and 18. Engine characteristics at different compositions of the blend at different compression ratios were provided by the interfaced computer through the software. The enhanced performance effects can be easily seen from the outcomes in the increment in brake thermal efficiency of the blends as compared to neat diesel. Considerable decrement can be observed in carbon monoxide (CO) and unburnt hydrocarbon (HC) values with an increase in compression ratio. Moderate reduction can be observed in NOx at higher loads in contrast to neat diesel.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this work, we used the cold spray process to coat a surface and investigated to understand the influence of various process parameters on the substrate surface temperature. The parameters we varied included the pressure, temperature, particle size, and particle speed of the titanium powder that we used in the cold spray coating process. It is a unique finding in the field of cold spray coating. For the substrate material, we chose steel and simulated the spray geometry using a two-dimensional axisymmetric model. This model employed a k-ɛ turbulence model with an implicit pressure-based solver of second-order precision. Our observations revealed that the surface temperature of the substrate reached its maximum value when the length of the injector was 15 mm. We also found that the most compatible length for the nozzle barrel was equal to the length of the particle injector.
{"title":"Effect of Process Parameters on the Substrate Surface in Cold Spray Coating","authors":"M. K. Press, M. Zunaid, Qasim Murtaza","doi":"10.5750/ijme.v1i1.1330","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1330","url":null,"abstract":"In this work, we used the cold spray process to coat a surface and investigated to understand the influence of various process parameters on the substrate surface temperature. The parameters we varied included the pressure, temperature, particle size, and particle speed of the titanium powder that we used in the cold spray coating process. It is a unique finding in the field of cold spray coating. For the substrate material, we chose steel and simulated the spray geometry using a two-dimensional axisymmetric model. This model employed a k-ɛ turbulence model with an implicit pressure-based solver of second-order precision. Our observations revealed that the surface temperature of the substrate reached its maximum value when the length of the injector was 15 mm. We also found that the most compatible length for the nozzle barrel was equal to the length of the particle injector.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mental health issues among college students are a growing concern, necessitating effective assessment methods to identify individuals at risk and provide timely interventions. In this paper, we propose and evaluate several computational models for mental health assessment based on demographic, academic, and psychological factors. Hence, this paper implemented the Probabilistic Deep Belief Bayesian Network (PDBBN) to classify students' mental health attributes. The proposed PDBBN network computes the probabilistic value of the mental health assessment of the students. With the estimation of the probabilistic model, the extracted features are applied in the Deep Belief Bayesian Network for the classification of student mental health with the Macromedia analysis in college students. The classification is performed with the consideration of information on gender, age, academic performance, social support scores, and self-reported levels of stress, anxiety, and depression, and each model across multiple epochs. Simulation is conducted in comparison with the proposed PDBBN model with the Convolutional Neural Network (CNN), and Deep Neural Network (DNN) models. The results indicate that PDBBN consistently outperforms CNN and DNN in terms of classification accuracy, precision, recall, and F1 score. The simulation analysis of results stated that the proposed PDBBN model achieves a higher classification accuracy of 0.98 which is significantly higher than the CNN and DNN models. Additionally, the proposed PDBBN model expressed that mental health of the students significantly impacts in the academic performance of the students.
{"title":"Online Assessment of Mental Health Micromedia for College Students Incorporating Bayesian Network Algorithm","authors":"YM He","doi":"10.5750/ijme.v1i1.1340","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1340","url":null,"abstract":"Mental health issues among college students are a growing concern, necessitating effective assessment methods to identify individuals at risk and provide timely interventions. In this paper, we propose and evaluate several computational models for mental health assessment based on demographic, academic, and psychological factors. Hence, this paper implemented the Probabilistic Deep Belief Bayesian Network (PDBBN) to classify students' mental health attributes. The proposed PDBBN network computes the probabilistic value of the mental health assessment of the students. With the estimation of the probabilistic model, the extracted features are applied in the Deep Belief Bayesian Network for the classification of student mental health with the Macromedia analysis in college students. The classification is performed with the consideration of information on gender, age, academic performance, social support scores, and self-reported levels of stress, anxiety, and depression, and each model across multiple epochs. Simulation is conducted in comparison with the proposed PDBBN model with the Convolutional Neural Network (CNN), and Deep Neural Network (DNN) models. The results indicate that PDBBN consistently outperforms CNN and DNN in terms of classification accuracy, precision, recall, and F1 score. The simulation analysis of results stated that the proposed PDBBN model achieves a higher classification accuracy of 0.98 which is significantly higher than the CNN and DNN models. Additionally, the proposed PDBBN model expressed that mental health of the students significantly impacts in the academic performance of the students.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine learning translation is the automated process of translating text from one language to another using computational algorithms and statistical models. neural network-based approaches, particularly using models like sequence-to-sequence (Seq2Seq) with attention mechanisms, have shown remarkable performance improvements in translation quality. This paper proposes a Statistical Stochastic Gradient Machine Translation Decoding (SSGM-TD) algorithm for the English–Chinese translation for the quality assessment. The proposed SSGM-TD model uses statistical analysis for the estimation and evaluation of the features for the computation of variables. The proposed SSGM – TD model estimates the stochastic gradient with the regression analysis for the feature estimation. The developed SSGM-TD model is implemented with the machine learning model for the automated translation of the English–Chinese languages. The simulation analysis is performed for the evaluation of the quality assessment in the translation process. The detailed evaluation is conducted using various metrics, including BLEU and METEOR scores, offering quantitative insights into the algorithm's performance. The classification process of the SSGM-TD algorithm is examined, revealing its proficiency in correctly classifying positive and negative instances. Precision, recall, and F1 score metrics provide a significant evaluation of the algorithm's classification capabilities. The decoding results and quality assessments are presented with providing a comprehensive view of the algorithm's strengths and potential areas for improvement. The quality assessments incorporate both quantitative metrics and human evaluations, ensuring a holistic understanding of the algorithm's translation capabilities. The consistency between automated metrics and human assessments underscores the algorithm's commendable performance in maintaining semantic accuracy and linguistic coherence.
{"title":"English-Chinese Translation Quality Assessment Based on Phrase Statistical Machine Translation Decoding Algorithm","authors":"Jing Li","doi":"10.5750/ijme.v1i1.1395","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1395","url":null,"abstract":"Machine learning translation is the automated process of translating text from one language to another using computational algorithms and statistical models. neural network-based approaches, particularly using models like sequence-to-sequence (Seq2Seq) with attention mechanisms, have shown remarkable performance improvements in translation quality. This paper proposes a Statistical Stochastic Gradient Machine Translation Decoding (SSGM-TD) algorithm for the English–Chinese translation for the quality assessment. The proposed SSGM-TD model uses statistical analysis for the estimation and evaluation of the features for the computation of variables. The proposed SSGM – TD model estimates the stochastic gradient with the regression analysis for the feature estimation. The developed SSGM-TD model is implemented with the machine learning model for the automated translation of the English–Chinese languages. The simulation analysis is performed for the evaluation of the quality assessment in the translation process. The detailed evaluation is conducted using various metrics, including BLEU and METEOR scores, offering quantitative insights into the algorithm's performance. The classification process of the SSGM-TD algorithm is examined, revealing its proficiency in correctly classifying positive and negative instances. Precision, recall, and F1 score metrics provide a significant evaluation of the algorithm's classification capabilities. The decoding results and quality assessments are presented with providing a comprehensive view of the algorithm's strengths and potential areas for improvement. The quality assessments incorporate both quantitative metrics and human evaluations, ensuring a holistic understanding of the algorithm's translation capabilities. The consistency between automated metrics and human assessments underscores the algorithm's commendable performance in maintaining semantic accuracy and linguistic coherence.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Glassy systems with the chemical composition xTiO2-(0.30-x)Bi2O3-0.10ZnO-0.60TeO2 (x = 0.05,0.10,0.15,0.20) have been synthesized using the melt quench approach. Numerous physical, electrical, optical, and other features of elastic moduli have been evaluated as titanium oxide concentration rises. The amorphous properties of the materials under inspection are displayed in the XRD pattern. As the concentration of arsenic rises, the glasses' density falls from 4.18 to 3.96 g/cm3, while their molar volume rises from 48.21 to 53.06 cm3mol-1. The elastic properties of the synthesized glasses, such as the shear (S) and longitudinal (L) stresses, bulk modulus (K), Young's modulus (Y), and Poisson's ratio (Pr), have all been measured using the measured values of the ultrasonic velocities. The increase in elastic moduli values showed that the materials' elastic qualities have been improved. The results are explained in terms of a significant structural alteration caused by molecular rearrangement, which controls the physical properties of the glass. The addition of titanium oxide is shown to cause a decrease in Urbach energies from 0.96 to 0.67 eV, which results in an increase in the optical band gap energies from 2.96 to 3.33 eV. DSC thermogram measurements reveal mechanically enhanced and thermally stable materials with potential for use in semiconducting devices.
{"title":"Effect of TiO₂ Addition on Elastic Moduli, Optical Bandgap, and Electrical Conductivity of xTiO₂-(0.30-x)Bi₂O₃-0.10ZnO-0.60TeO₂ Glassy Systems with Improved Thermal Stability","authors":"Dipankar Biswas, Arpan Mandal, Souvik Brahma Hota, Ashok Kumar, Gopal Krishan Gard, Rittwick Mondal, Nipu Modak","doi":"10.5750/ijme.v1i1.1375","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1375","url":null,"abstract":"Glassy systems with the chemical composition xTiO2-(0.30-x)Bi2O3-0.10ZnO-0.60TeO2 (x = 0.05,0.10,0.15,0.20) have been synthesized using the melt quench approach. Numerous physical, electrical, optical, and other features of elastic moduli have been evaluated as titanium oxide concentration rises. The amorphous properties of the materials under inspection are displayed in the XRD pattern. As the concentration of arsenic rises, the glasses' density falls from 4.18 to 3.96 g/cm3, while their molar volume rises from 48.21 to 53.06 cm3mol-1. The elastic properties of the synthesized glasses, such as the shear (S) and longitudinal (L) stresses, bulk modulus (K), Young's modulus (Y), and Poisson's ratio (Pr), have all been measured using the measured values of the ultrasonic velocities. The increase in elastic moduli values showed that the materials' elastic qualities have been improved. The results are explained in terms of a significant structural alteration caused by molecular rearrangement, which controls the physical properties of the glass. The addition of titanium oxide is shown to cause a decrease in Urbach energies from 0.96 to 0.67 eV, which results in an increase in the optical band gap energies from 2.96 to 3.33 eV. DSC thermogram measurements reveal mechanically enhanced and thermally stable materials with potential for use in semiconducting devices.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bend Erosion problems were found mostly common in pneumatic conveying plants. Swirling of particles before striking the bend has been noted as the best solution to minimize bend erosion rate. CFD k-w model in Ansys was applied to analyze mild steel bend erosion in the pipeline by pneumatically conveyed particles with a motor-operated swirling device. A part of the pipe before the bend is rotated at different velocities in different elbow geometries from 15° to 90° elbows. A combination of Eulerian and Lagrangian methods were utilized to track particles. Mathematical modelling of the swirling of particles on bent surfaces is taken into consideration with different elbow angle. The bend erosion rate was mitigated due to the swirling of particles. Different velocities and parameters are taken to evaluate the results. At different bend angles erosion rate is different and the swirling device minimizes the bend erosion rate.
{"title":"CFD Modelling of Swirling Device to Study Bend Erosion Rate at Different Bend Angles in Pneumatic Conveying System","authors":"Bharat Singh Yadav, Rajiv Chaudhary, R.C. Singh","doi":"10.5750/ijme.v1i1.1342","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1342","url":null,"abstract":"Bend Erosion problems were found mostly common in pneumatic conveying plants. Swirling of particles before striking the bend has been noted as the best solution to minimize bend erosion rate. CFD k-w model in Ansys was applied to analyze mild steel bend erosion in the pipeline by pneumatically conveyed particles with a motor-operated swirling device. A part of the pipe before the bend is rotated at different velocities in different elbow geometries from 15° to 90° elbows. A combination of Eulerian and Lagrangian methods were utilized to track particles. Mathematical modelling of the swirling of particles on bent surfaces is taken into consideration with different elbow angle. The bend erosion rate was mitigated due to the swirling of particles. Different velocities and parameters are taken to evaluate the results. At different bend angles erosion rate is different and the swirling device minimizes the bend erosion rate.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Predicting stock trends is a complex task influenced by various factors such as market sentiment, economic indicators, and company performance. Analysts often employ technical analysis, studying historical price patterns and trading volumes, as well as fundamental analysis, assessing financial statements and industry trends. Deep Learning models have also gained popularity for predicting stock trends, using algorithms to identify patterns and relationships in large datasets. Deep learning algorithms, particularly neural networks, excel at recognizing intricate patterns and relationships within complex datasets, making them well-suited for predicting stock prices, identifying trends, and managing risk. Hence, this paper proposed a Bird Swarm Optimization ARIMA LSTM (BSO-ARIMA-DL) model for stock trend prediction. The proposed BSO-ARIMA-DL model performance is applied in the company datasets Apple, Amazon, and Infosys for stock trend prediction. With the proposed BSO-ARIMA-DL model features are optimized for the identification of features in the dataset for the evaluation of optimal features. Upon the estimation of features, the ARIMA model with the LSTM architecture is implemented for the stock trend analysis. The proposed BSO-ARIMA-DL model deep learning model is implemented for the stock trend prediction in the companies. The results demonstrated that the proposed BSO-ARIMA-DL model exhibits a minimal error of ~10% minimal to the conventional ARIMA model.
{"title":"Optimized Deep Learning Model Architecture for the Feature Extraction to Predict Trend in Stock Market","authors":"N. Deepika, M. NirupamaBhat","doi":"10.5750/ijme.v1i1.1338","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1338","url":null,"abstract":"Predicting stock trends is a complex task influenced by various factors such as market sentiment, economic indicators, and company performance. Analysts often employ technical analysis, studying historical price patterns and trading volumes, as well as fundamental analysis, assessing financial statements and industry trends. Deep Learning models have also gained popularity for predicting stock trends, using algorithms to identify patterns and relationships in large datasets. Deep learning algorithms, particularly neural networks, excel at recognizing intricate patterns and relationships within complex datasets, making them well-suited for predicting stock prices, identifying trends, and managing risk. Hence, this paper proposed a Bird Swarm Optimization ARIMA LSTM (BSO-ARIMA-DL) model for stock trend prediction. The proposed BSO-ARIMA-DL model performance is applied in the company datasets Apple, Amazon, and Infosys for stock trend prediction. With the proposed BSO-ARIMA-DL model features are optimized for the identification of features in the dataset for the evaluation of optimal features. Upon the estimation of features, the ARIMA model with the LSTM architecture is implemented for the stock trend analysis. The proposed BSO-ARIMA-DL model deep learning model is implemented for the stock trend prediction in the companies. The results demonstrated that the proposed BSO-ARIMA-DL model exhibits a minimal error of ~10% minimal to the conventional ARIMA model.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Syed Asghar Husain Rizvi, Rohit Sahu, Ravi Butola, Manish Saraswat, Ajay Sharma, Harpreet S. Bhatia
This investigation is conducted to estimate the extent of residual stress induced in the workpiece when machined on EDM. The Residual stresses induced post machining a product can led to lower life and inadequate failures during service. AISI 4340 finds its applicability in propulsion parts of marine engine and thus chosen as the material for study. Tungsten-Copper is selected as material for tool. Response Surface Methodology (RSM) with Central Composite Design (CCD) is utilized preparing the trails using current, on-time of pulse, voltage, and duty factor as machine variables. X-Ray Diffraction (XRD) was performed to estimate the d-space lattice of machined as well as un-machined specimens. Furthermore, Scanning Electron Microscopy (SEM) was executed to analyze effect of residual stress on surface post machining. The model suggested that voltage and on duration were crucial factors for residual stress while duty factor and current were less influential. Residual stress in the machined surface results from gradual heating and cooling during machining. The developed model was predicted to be accurate through the validation test. The micro-cracks resulted from the thermal stresses developed during machining of the workpiece.
这项调查旨在估算电火花加工时工件中产生的残余应力。产品加工后产生的残余应力可能会导致产品寿命降低和在使用过程中出现故障。AISI 4340 适用于船用发动机的推进部件，因此被选为研究材料。刀具材料选择钨铜。采用中央复合设计（CCD）的响应面方法论（RSM），以电流、脉冲导通时间、电压和占空比作为机器变量进行试验。通过 X 射线衍射 (XRD) 来估算已加工和未加工试样的 d 空间晶格。此外，还使用扫描电子显微镜（SEM）分析了加工后表面残余应力的影响。模型表明，电压和通电时间是影响残余应力的关键因素，而占空比和电流的影响较小。加工表面的残余应力产生于加工过程中的逐渐加热和冷却。通过验证测试，预测所开发的模型是准确的。微裂纹产生于工件加工过程中产生的热应力。
{"title":"Modeling of Residual Stress During EDM of AISI 4340 for Marine Propulsion Application","authors":"Syed Asghar Husain Rizvi, Rohit Sahu, Ravi Butola, Manish Saraswat, Ajay Sharma, Harpreet S. Bhatia","doi":"10.5750/ijme.v1i1.1363","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1363","url":null,"abstract":"This investigation is conducted to estimate the extent of residual stress induced in the workpiece when machined on EDM. The Residual stresses induced post machining a product can led to lower life and inadequate failures during service. AISI 4340 finds its applicability in propulsion parts of marine engine and thus chosen as the material for study. Tungsten-Copper is selected as material for tool. Response Surface Methodology (RSM) with Central Composite Design (CCD) is utilized preparing the trails using current, on-time of pulse, voltage, and duty factor as machine variables. X-Ray Diffraction (XRD) was performed to estimate the d-space lattice of machined as well as un-machined specimens. Furthermore, Scanning Electron Microscopy (SEM) was executed to analyze effect of residual stress on surface post machining. The model suggested that voltage and on duration were crucial factors for residual stress while duty factor and current were less influential. Residual stress in the machined surface results from gradual heating and cooling during machining. The developed model was predicted to be accurate through the validation test. The micro-cracks resulted from the thermal stresses developed during machining of the workpiece.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multimedia plays a crucial role in English teaching by enhancing engagement, providing diverse learning experiences, and catering to different learning styles. English teaching through multimedia, while beneficial, presents challenges. Unequal access to technology and the digital divide can hinder some students' participation. Ensuring digital literacy and quality content selection is crucial to effective use. This paper proposed the Hidden Markov Model for English Teaching (HMM-ET) to improve the performance of college and university students. The proposed HMM-ET model computes the Markov chain of English teaching through multimedia technology. With the implementation of multimedia technology, the HMM model estimates the performance of students in colleges and universities. Through the estimation of HMM-ET the classification of students' performance in English learning is computed with the machine learning model. The performance of the students is examined comparatively with the conventional Support Vector Machine (SVM) and Random Forest. Through analysis of a dataset comprising observation sequences reflecting English learning tasks, HMM-ET consistently outperforms SVM and Random Forest, achieving an average accuracy of 96%, while SVM and Random Forest attain accuracies of 90% and 88% respectively.
{"title":"Application of Multimedia Technology in Teaching English in Colleges and Universities","authors":"Yuxun Chen","doi":"10.5750/ijme.v1i1.1365","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1365","url":null,"abstract":"Multimedia plays a crucial role in English teaching by enhancing engagement, providing diverse learning experiences, and catering to different learning styles. English teaching through multimedia, while beneficial, presents challenges. Unequal access to technology and the digital divide can hinder some students' participation. Ensuring digital literacy and quality content selection is crucial to effective use. This paper proposed the Hidden Markov Model for English Teaching (HMM-ET) to improve the performance of college and university students. The proposed HMM-ET model computes the Markov chain of English teaching through multimedia technology. With the implementation of multimedia technology, the HMM model estimates the performance of students in colleges and universities. Through the estimation of HMM-ET the classification of students' performance in English learning is computed with the machine learning model. The performance of the students is examined comparatively with the conventional Support Vector Machine (SVM) and Random Forest. Through analysis of a dataset comprising observation sequences reflecting English learning tasks, HMM-ET consistently outperforms SVM and Random Forest, achieving an average accuracy of 96%, while SVM and Random Forest attain accuracies of 90% and 88% respectively.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the construction of a virtual simulation experiment platform for intelligent construction, cutting-edge technologies converge to revolutionize traditional project management methodologies. By harnessing the power of virtual reality, statistical modeling, and machine learning, this platform empowers stakeholders to predict, optimize, and simulate construction projects with unprecedented accuracy and efficiency. This paper introduces the Virtual Statistical Machine Learning (VS-ML) platform and demonstrates its application in intelligent construction processes. Through comprehensive experimentation and simulation, the VS-ML platform accurately estimates construction project parameters, optimizes resource utilization, schedules tasks efficiently, and classifies project outcomes with high accuracy. Numerical results from our study showcase the platform's effectiveness in various aspects of construction project management. For instance, in construction projects estimation, scenarios ranging from Scenario 1 to Scenario 10 exhibit project durations between 100 to 150 days, cost estimates ranging from $470,000 to $550,000, and safety ratings varying from "Good" to "Excellent". Furthermore, labor efficiency and material waste estimations across scenarios demonstrate percentages ranging from 85% to 93% and 3% to 7%, respectively, with corresponding safety ratings. Additionally, task computations elucidate the durations, start dates, end dates, and resource allocations for individual tasks within construction projects. Lastly, classification results exhibit the predicted probabilities and class labels for samples, showcasing the platform's ability to accurately predict project outcomes. Overall, the findings underscore the potential of VS-ML in revolutionizing traditional construction practices through data-driven approaches, leading to improved project management, cost savings, and enhanced safety standards in the construction industry.
{"title":"Construction of Virtual Simulation Experiment Platform for Intelligent Construction Based on Statistical Machine Learning System Modelling","authors":"Pu Zhang","doi":"10.5750/ijme.v1i1.1384","DOIUrl":"https://doi.org/10.5750/ijme.v1i1.1384","url":null,"abstract":"In the construction of a virtual simulation experiment platform for intelligent construction, cutting-edge technologies converge to revolutionize traditional project management methodologies. By harnessing the power of virtual reality, statistical modeling, and machine learning, this platform empowers stakeholders to predict, optimize, and simulate construction projects with unprecedented accuracy and efficiency. This paper introduces the Virtual Statistical Machine Learning (VS-ML) platform and demonstrates its application in intelligent construction processes. Through comprehensive experimentation and simulation, the VS-ML platform accurately estimates construction project parameters, optimizes resource utilization, schedules tasks efficiently, and classifies project outcomes with high accuracy. Numerical results from our study showcase the platform's effectiveness in various aspects of construction project management. For instance, in construction projects estimation, scenarios ranging from Scenario 1 to Scenario 10 exhibit project durations between 100 to 150 days, cost estimates ranging from $470,000 to $550,000, and safety ratings varying from \"Good\" to \"Excellent\". Furthermore, labor efficiency and material waste estimations across scenarios demonstrate percentages ranging from 85% to 93% and 3% to 7%, respectively, with corresponding safety ratings. Additionally, task computations elucidate the durations, start dates, end dates, and resource allocations for individual tasks within construction projects. Lastly, classification results exhibit the predicted probabilities and class labels for samples, showcasing the platform's ability to accurately predict project outcomes. Overall, the findings underscore the potential of VS-ML in revolutionizing traditional construction practices through data-driven approaches, leading to improved project management, cost savings, and enhanced safety standards in the construction industry.","PeriodicalId":50313,"journal":{"name":"International Journal of Maritime Engineering","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141797358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：