[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120074-en":3,"doc-seo-120074-105":30,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120074,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Machine Learning-Based Prediction of Optimal Switch Configurations for Boost Converters by PowerSynth - Poster Summary","Machine learning is used to predict optimal switch configurations for boost converters by leveraging numerical data generated from PowerSynth-based layout and performance optimization. The work scales and standardizes input features, splits data into training, validation, and test sets, and trains multiple regression models. Performance is evaluated with metrics such as mean squared error and R², then the best model predicts power density while accounting for switch losses and volume. High-accuracy training enables direct user-facing power-density comparisons, reducing manual design effort and improving design automation for power electronics.","University of Arkansas, Fayetteville  \nScholarWorks@UARK  \n\n| Electrical Engineering Research Experience for Undergraduates | Electrical Engineering |\n| --- | --- |\n| 2024\u003Cbr>Machine Learning-Based Prediction of Optimal Switch Configurations for Boost Converters by PowerSynth\u003Cbr>Mobolaji Ogunbiyi\u003Cbr>University of Arkansas, Fayetteville\u003Cbr>Follow this and additional works at: [https://scholarworks.uark.edu/elegreu](https://scholarworks.uark.edu/elegreu)\u003Cbr> Part of the Electrical and Computer Engineering Commons |  |\n\nCitation  \nOgunbiyi, M. (2024) . Machine Learning-Based Prediction of Optimal Switch Configurations for Boost Converters by PowerSynth. Electrical Engineering Research Experience for Undergraduates. Retrieved from [https://scholarworks.uark.edu/elegreu/16](https://scholarworks.uark.edu/elegreu/16)  \nThis Poster is brought to you for free and open access by the Electrical Engineering at ScholarWorks@UARK. It has been accepted for inclusion in Electrical Engineering Research Experience for Undergraduates by an authorized administrator of ScholarWorks@UARK. For more information, please contact [scholar@uark.edu](scholar@uark.edu),  \n[uarepos@uark.edu](uarepos@uark.edu).  \nInput  \nMachine Learning-Based Prediction of Optimal Switch AN NSF SPONSORED CENTER Configurations for Boost Converters by PowerSynth  \nREU student: Mobolaji Ogunbiyi, University of Maryland Baltimore County; Faculty: Dr. Alan Mantooth; Dr. Peng;  \nMentor: David Setor Agogo Mawuli, Zahra Saadatizadeh  \nBackground  \n● This project builds on the research presented in the paper titled \"Automated Layout Optimization Methods of a Bidirectional DC-DC ZVS Converter Using PowerSynth. \"  \n● The original study focuses on optimizing the design and automation of bidirectional DC-DC converters with zero-voltage switching (ZVS), emphasizing layout optimization using the PowerSynth tool.  \n● Key components such as switches and inductors are selected based on their performance in terms of power density and thermal analysis.  \n● The research integrates Monte Carlo optimization and PowerSynth for effective component layout and performance tradeoff analysis, aiming to achieve high power density and efficiency.  \nFig 1. Bidirectional ZVS dc-dc Converter  \n● This project extends the methodology of this study by creating a machine learning model to predict power density based on input parameters.  \n● Utilizing the numerical data generated from the optimization process, this project aims to automate the prediction of the most efficient switch configuration for a boost converter, thereby enhancing design automation practices.  \nMethodology  \n● Scaling: Standardized data using StandardScaler to ensure uniform contribution of all features.  \n● Split Data: Divided data into training (60%), validation (20%), and test (20%) sets.  \n● Model Selection: Trained 7 different types of regression utilizing the collected data  \n● Validation: Evaluated models on validation set using metrics like Mean Squared Error (MSE) and R ² Score.  \n● Model Testing: Assessed the best model's performance on the test set for accuracy and robustness.  \n● Density Calculation: Predicted power density using the model, considering the loss and volume of switches.  \nFig 5. Methodology Flow Chart  \nResults  \nModel Performances  \nModel  \nElastic Net  \nSGD Regressor Bayesian Ridge Linear Regression Random Forest Regressor Gradient Boosting Regressor  \nR2 Value  \n0.885  \n0.999 1.0 1.0  \n0.999  \n0.99  \nMean Squared  \nError 11676.903 0.178 1.36e-24 2.896e-26  \n10.985  \n14.772  \nFig 3. Model Evaluations  \nFig 2. Elastic Net Accuracy Model  \nCLI User  \nFig 4. As the model is trained with high accuracy, it allows for user to directly see all of the switches power density for user chosen  \nConclusion inputs  \nThis project successfully developed a machine learning model to predict the optimal switch for a boost converter, offering significant advancements over traditional optimization methods. The model automates the prediction ","cbCairbHR71E7CH0","https://ap.wps.com/l/cbCairbHR71E7CH0","pdf",472147,1,2,"English","en",105,"# Background\n# Methodology\n## Data preprocessing and splitting\n## Model selection and evaluation\n# Results\n## Model performance metrics\n# Conclusion","[{\"question\":\"What problem does the project solve?\",\"answer\":\"The project predicts the most efficient switch configuration for a boost converter by estimating power density from input parameters generated through PowerSynth optimization.\"},{\"question\":\"How is the machine learning model trained and evaluated?\",\"answer\":\"Data are standardized, split into training (60%), validation (20%), and test (20%), and seven regression models are trained and validated using mean squared error and R², then tested for robustness.\"},{\"question\":\"What benefits does the approach provide compared with manual optimization?\",\"answer\":\"The model automates prediction of optimal switch configurations, improves accuracy, provides data-driven insights, and reduces time and effort for manual layout and component trade-off analysis.\"}]","Machine Learning-Based Prediction of Optimal Switch Configurations for Boost Converters by PowerSynth - Poster Summary | PDF",1785728012,5,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"machine-learning-based-prediction-of-optimal-switch-configurations-for-boost-converters-by-powersynth-poster-summary","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/machine-learning-based-prediction-of-optimal-switch-configurations-for-boost-converters-by-powersynth-poster-summary/120074/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the project solve?","Question",{"text":74,"@type":75},"The project predicts the most efficient switch configuration for a boost converter by estimating power density from input parameters generated through PowerSynth optimization.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How is the machine learning model trained and evaluated?",{"text":79,"@type":75},"Data are standardized, split into training (60%), validation (20%), and test (20%), and seven regression models are trained and validated using mean squared error and R², then tested for robustness.",{"name":81,"@type":72,"acceptedAnswer":82},"What benefits does the approach provide compared with manual optimization?",{"text":83,"@type":75},"The model automates prediction of optimal switch configurations, improves accuracy, provides data-driven insights, and reduces time and effort for manual layout and component trade-off analysis.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":29,"slug":136},19,"General","general"]