[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119782-en":3,"doc-seo-119782-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},119782,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Prediction of Blast Loads Using Machine Learning Approaches - DeNN vs ANN","Assessment of human injuries and structural damage from high-explosive detonations depends on understanding blast load parameters. Physical experiments and physics-based numerical tools demand extensive time and expertise, limiting their use for deterministic studies, while explosive scenarios remain inherently uncertain in charge size, mass, composition, and location. Machine learning enables rapid probabilistic analysis, but feature selection can cause domain-specific behavior. This paper presents a Direction-encoded Neural Network (DeNN) that expands prediction capability across variable domain sizes and movable obstacles, validated against a traditional ANN with global inputs.","PREDICTION OF BLAST LOADS USING MACHINE LEARNING  \nAPPROACHES  \nAdam DENNIS 1 , Samuel RIGBY2  \nAbstract: The assessment of human injuries and structural damage following the detonation of a high explosive requires an understanding of blast load parameters. Use of physical experiments or physics-based numerical tools require large amounts of time and expertise, often restricting their use to deterministic analyses. Since explosive events are inherently unpredictable and key variables (e.g. charge size, mass, composition, location) may not be known a priori, there is a clear need for rapid analysis tools that can embrace this uncertainty in a probabilistic framework. Machine learning tools have been developed for this purpose, however, the features of the problem that are selected as model inputs can result in predictions being fixed to a single domain, thus requiring the tool to be re-trained for every new scenario. This paper details how the Direction-encoded Neural Network (DeNN), a novel Machine Learning method, takes inspiration from the operation of robot vacuum cleaners to prevent this issue by considering the surroundings of each prediction point. Through comparisons to a traditional Artificial Neural Network (ANN), provided with global domain inputs, it is shown that the DeNN’s unique feature selection process allows for predictions in domains of variable sizes with movable obstacles, ultimately producing a tool that can be used in a range of studies without requiring additional task-specific training.  \nIntroduction  \nWith the continual presence of terrorist attacks, conflict and industrial accidents occurring all over the world, understanding the risk associated to the detonation of explosive materials is vital for designing and developing protective structures and procedures that can reduce any detrimental impact on human life. A key component of this involves developing an understanding of how the blast wave that emanates from an explosive compound propagates and interacts with its surroundings.  \nHistorically this was achieved using physical experiments in controlled test environments where the number of trials, extractable data points and variety of test scenarios is limited by cost, safety and expertise. However, the evolution of widely available computing power has meant that this approach is often replaced by validated numerical methods that can be evaluated without data limitations or health and safety risks.  \nSemi-empirical tools, such as the Kingery and Bulmash method (Kingery and Bulmash, 1984) , have been derived from experimental trials that enable the relationships between variables to be defined by simplified equations and charts. The can therefore be implemented rapidly with a reduced number of inputs, yet, this also restricts their use to a limited range of modelling scenarios. Conversely, validated Computational Fluid Dynamics (CFD) or Finite Element (FE) numerical models , such as Viper::Blast (Stirling, 2023) , and LS-DYNA (Livermore Software Technology Company, 2015) , obey conservation laws in a discretisation of space and time using estimated material properties in an attempt to accurately model the physics of the detonation and the subsequent wave interaction effects. They are therefore well suited to evaluating diverse problems, however, computation times can last many hours or days depending on the complexity of the problem and the desired level of predictive accuracy.  \nAt present, this computational analysis of explosive events is commonly performed using deterministic approaches , providing a single output to a well-defined problem. However, many researchers note that this ignores the variability of the explosion itself and the inherent uncertainty associated to the charge size, shape, location and material that is characteristic of the situations where explosions occur. Probabilistic approaches, such as the one shown in Figure 1, are therefore becoming more common so that the risk assoc","cbCaivltXUelzCp5","https://ap.wps.com/l/cbCaivltXUelzCp5","pdf",971441,1,10,"English","en",105,"# Introduction\n## Blast engineering background and motivation\n## Deterministic vs probabilistic analysis\n## Computational and semi-empirical modeling approaches\n# Machine Learning in Blast Engineering\n## Background and example applications","[{\"question\":\"Why are rapid analysis tools needed for blast load assessment?\",\"answer\":\"Detonation scenarios are uncertain and traditional experiments or physics-based models require significant time and expertise. Rapid tools support probabilistic evaluation rather than single deterministic outputs.\"},{\"question\":\"What problem can occur with machine learning features in blast prediction?\",\"answer\":\"Selected input features may cause predictions to become fixed to one domain, requiring retraining for new scenarios.\"},{\"question\":\"How does DeNN address domain dependence compared with a traditional ANN?\",\"answer\":\"DeNN uses a direction-encoded feature selection process inspired by robot vacuum coverage, considering the surroundings around each prediction point. Comparisons with an ANN using global inputs show DeNN supports variable-sized domains with movable obstacles without task-specific retraining.\"}]","Prediction of Blast Loads Using Machine Learning Approaches - DeNN vs ANN | PDF",1785726285,25,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"prediction-of-blast-loads-using-machine-learning-approaches-denn-vs-ann","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/prediction-of-blast-loads-using-machine-learning-approaches-denn-vs-ann/119782/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are rapid analysis tools needed for blast load assessment?","Question",{"text":75,"@type":76},"Detonation scenarios are uncertain and traditional experiments or physics-based models require significant time and expertise. Rapid tools support probabilistic evaluation rather than single deterministic outputs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem can occur with machine learning features in blast prediction?",{"text":80,"@type":76},"Selected input features may cause predictions to become fixed to one domain, requiring retraining for new scenarios.",{"name":82,"@type":73,"acceptedAnswer":83},"How does DeNN address domain dependence compared with a traditional ANN?",{"text":84,"@type":76},"DeNN uses a direction-encoded feature selection process inspired by robot vacuum coverage, considering the surroundings around each prediction point. Comparisons with an ANN using global inputs show DeNN supports variable-sized domains with movable obstacles without task-specific retraining.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]