Soner Camuz, Anders Liljerehn, Kristina Wärmefjord, R. Söderberg
Maintaining an even pressure distribution in an indexable cutting tool interface is crucial to the life expectancy of a carbide insert. Avoiding uneven pressure distribution is highly relevant for intermittent cutting operations because two load cases arise for full immersion, inside and outside the cutting zone, which can cause alternating contact positioning. Current positioning methodologies, such as 3-2-1 principles, do not consider external mechanical forces, which must be considered for insert-tool body positioning designs. Therefore, this paper proposes an algorithm to calculate a contact index to aid in the design of locating schemes for the early design phases of insert-tool body interface design. The results indicate that it is possible to visualize where a contact condition needs to exist to give support based on the mechanical loads acting on the insert.
{"title":"Algorithm for Detecting Load-Carrying Regions within the Tip Seat of an Indexable Cutting Tool","authors":"Soner Camuz, Anders Liljerehn, Kristina Wärmefjord, R. Söderberg","doi":"10.1115/1.4064255","DOIUrl":"https://doi.org/10.1115/1.4064255","url":null,"abstract":"\u0000 Maintaining an even pressure distribution in an indexable cutting tool interface is crucial to the life expectancy of a carbide insert. Avoiding uneven pressure distribution is highly relevant for intermittent cutting operations because two load cases arise for full immersion, inside and outside the cutting zone, which can cause alternating contact positioning. Current positioning methodologies, such as 3-2-1 principles, do not consider external mechanical forces, which must be considered for insert-tool body positioning designs. Therefore, this paper proposes an algorithm to calculate a contact index to aid in the design of locating schemes for the early design phases of insert-tool body interface design. The results indicate that it is possible to visualize where a contact condition needs to exist to give support based on the mechanical loads acting on the insert.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139007456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weiwei Liu, Jiahe Qiu, YuJiang Wang, Tao Li, Shujie Liu, Guangda Hu, Lin Xue
The detection of surface damage is an important part of the process before remanufacturing retired steel shaft (RSS). Traditional damage detection is mainly done manually, which is time-consuming and error-prone. In recent years, computer vision methods have been introduced into the community of surface damage detection. However, some advanced typical object detection methods perform poorly in the detection of surface damage on RSS due to the complex surface background and rich diversity of damage patterns and scales. To address these issues, we propose a Faster-RCNN-based surface damage detection method for RSS. To improve the adaptability of the network, we endow it with a feature pyramid network (FPN) as well as adaptable multi-scale information modifications to the region proposal network (RPN). In this paper, a detailed study of an FPN-based feature extraction network and the multi-scale object detection network is conducted. Experimental results show that our method improves the mAP score by 8.9% compared with the original Faster-RCNN for surface damage detection of RSS, and the average detection accuracy for small objects is improved by 18.2%. Compared with the current advanced object detection methods, our method is more advantageous for the detection of multi-scale objects.
{"title":"Multi-scale feature fusion convolutional neural network for surface damage detection in retired steel shafts","authors":"Weiwei Liu, Jiahe Qiu, YuJiang Wang, Tao Li, Shujie Liu, Guangda Hu, Lin Xue","doi":"10.1115/1.4064257","DOIUrl":"https://doi.org/10.1115/1.4064257","url":null,"abstract":"\u0000 The detection of surface damage is an important part of the process before remanufacturing retired steel shaft (RSS). Traditional damage detection is mainly done manually, which is time-consuming and error-prone. In recent years, computer vision methods have been introduced into the community of surface damage detection. However, some advanced typical object detection methods perform poorly in the detection of surface damage on RSS due to the complex surface background and rich diversity of damage patterns and scales. To address these issues, we propose a Faster-RCNN-based surface damage detection method for RSS. To improve the adaptability of the network, we endow it with a feature pyramid network (FPN) as well as adaptable multi-scale information modifications to the region proposal network (RPN). In this paper, a detailed study of an FPN-based feature extraction network and the multi-scale object detection network is conducted. Experimental results show that our method improves the mAP score by 8.9% compared with the original Faster-RCNN for surface damage detection of RSS, and the average detection accuracy for small objects is improved by 18.2%. Compared with the current advanced object detection methods, our method is more advantageous for the detection of multi-scale objects.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139010009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Singh, Rahul Rai, Raj Pradip Khawale, Darshil Patel, Dustin Bielecki, Ryan Nguyen, Jun Wang, Zhibo Zhang
A paradigm shift in the computational design synthesis domain is being witnessed by the onset of the innovative usage of machine learning techniques. The rapidly evolving paradigmatic shift calls for systematic and comprehensive assimilation of extant knowledge at the intersection of machine learning and computational design synthesis. Understanding nuances, identifying research gaps, and outlining the future direction for cutting-edge research is imperative. This paper outlines a hybrid literature review consisting of a thematic and framework synthesis survey to enable conceptual synthesis of information at the convergence of computational design, machine learning, and big-data models. The thematic literature survey aims at conducting an in-depth descriptive survey along the lines of a broader theme of machine learning in computational design. The framework synthesis-based survey tries to encapsulate the research findings in a conceptual framework to understand the domain better. The framework is based on the computational design synthesis (CDS) process, which consists of four sub-modules: representation, generation, evaluation, and guidance. Each sub-module has undergone an analysis to identify potential research gaps and formulate research questions. Additionally, we consider the limitations of our study and pinpoint the realms where the research can be extended in the future.
{"title":"Deep Learning in Computational Design Synthesis: A Comprehensive Review","authors":"S. Singh, Rahul Rai, Raj Pradip Khawale, Darshil Patel, Dustin Bielecki, Ryan Nguyen, Jun Wang, Zhibo Zhang","doi":"10.1115/1.4064215","DOIUrl":"https://doi.org/10.1115/1.4064215","url":null,"abstract":"\u0000 A paradigm shift in the computational design synthesis domain is being witnessed by the onset of the innovative usage of machine learning techniques. The rapidly evolving paradigmatic shift calls for systematic and comprehensive assimilation of extant knowledge at the intersection of machine learning and computational design synthesis. Understanding nuances, identifying research gaps, and outlining the future direction for cutting-edge research is imperative. This paper outlines a hybrid literature review consisting of a thematic and framework synthesis survey to enable conceptual synthesis of information at the convergence of computational design, machine learning, and big-data models. The thematic literature survey aims at conducting an in-depth descriptive survey along the lines of a broader theme of machine learning in computational design. The framework synthesis-based survey tries to encapsulate the research findings in a conceptual framework to understand the domain better. The framework is based on the computational design synthesis (CDS) process, which consists of four sub-modules: representation, generation, evaluation, and guidance. Each sub-module has undergone an analysis to identify potential research gaps and formulate research questions. Additionally, we consider the limitations of our study and pinpoint the realms where the research can be extended in the future.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138590218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The Journal of Computing and Information Science in Engineering (JCISE) publishes articles related to scientific computing methods (e.g., modeling, simulation, representation, algorithm) and computational tools (e.g., high-performance computing, virtual and augmented reality) that aim to improve engineering products and systems for their complete lifecycle (e.g., design, manufacturing, operation, maintenance, disposal, and recycling). The interest areas include computational geometry, computer-aided design and manufacturing, cyber-physical systems, human-machine interface, machine intelligence, machine learning, modeling and simulation, precision engineering, product lifecycle management, reverse engineering, and systems engineering.
{"title":"JCISE Editorial Board - Year 2023","authors":"Yan Wang","doi":"10.1115/1.4064046","DOIUrl":"https://doi.org/10.1115/1.4064046","url":null,"abstract":"Abstract The Journal of Computing and Information Science in Engineering (JCISE) publishes articles related to scientific computing methods (e.g., modeling, simulation, representation, algorithm) and computational tools (e.g., high-performance computing, virtual and augmented reality) that aim to improve engineering products and systems for their complete lifecycle (e.g., design, manufacturing, operation, maintenance, disposal, and recycling). The interest areas include computational geometry, computer-aided design and manufacturing, cyber-physical systems, human-machine interface, machine intelligence, machine learning, modeling and simulation, precision engineering, product lifecycle management, reverse engineering, and systems engineering.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135092539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Laetitia Monnier, William Bernstein, Vincenzo Ferrero, Sebti Foufou
Abstract Developing a more automated industrial digital thread is vital to realize the smart manufacturing and Industry 4.0 vision. The digital thread allows for efficient sharing across product lifecycle stages. Current techniques are not robust in relating downstream data, such as manufac- turing and inspection information, back to design for bet- ter decision making. In response, we previously presented a methodology that aligns numerical control (NC) code, a standard for representing machine tool instructions, to controller data represented in MTConnect, a standard that provides a vocabulary for generalizing execution logs from different machine tools and devices. This paper ex- tends our previous work by automating the tool identifi- cation using a k-means clustering algorithm to refine the alignment of the data. In doing so, we compare differ- ent distance techniques to analyze the spatial-temporal registration of the two datasets, i.e., the NC code and MTConnect data. Then, we assess the efficiency of our method through an error measurement technique that ex- presses the quality of the alignment. Finally, we apply our methodology to a case study that includes verified process plans and real execution data, derived from the Smart Manufacturing Systems Test Bed hosted at the National Institute of Standards and Technology. Our anal- ysis illustrates that dynamic time warping achieves the best point registration with the least errors compared with other alignment techniques.
{"title":"An automated approach for segmenting numerical control data with controller data for machine tools","authors":"Laetitia Monnier, William Bernstein, Vincenzo Ferrero, Sebti Foufou","doi":"10.1115/1.4064036","DOIUrl":"https://doi.org/10.1115/1.4064036","url":null,"abstract":"Abstract Developing a more automated industrial digital thread is vital to realize the smart manufacturing and Industry 4.0 vision. The digital thread allows for efficient sharing across product lifecycle stages. Current techniques are not robust in relating downstream data, such as manufac- turing and inspection information, back to design for bet- ter decision making. In response, we previously presented a methodology that aligns numerical control (NC) code, a standard for representing machine tool instructions, to controller data represented in MTConnect, a standard that provides a vocabulary for generalizing execution logs from different machine tools and devices. This paper ex- tends our previous work by automating the tool identifi- cation using a k-means clustering algorithm to refine the alignment of the data. In doing so, we compare differ- ent distance techniques to analyze the spatial-temporal registration of the two datasets, i.e., the NC code and MTConnect data. Then, we assess the efficiency of our method through an error measurement technique that ex- presses the quality of the alignment. Finally, we apply our methodology to a case study that includes verified process plans and real execution data, derived from the Smart Manufacturing Systems Test Bed hosted at the National Institute of Standards and Technology. Our anal- ysis illustrates that dynamic time warping achieves the best point registration with the least errors compared with other alignment techniques.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135391013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This paper presents an approach based on deep neural networks for interactive digital transformation and simulation of n-bar planar linkages composed of revolute and prismatic joints from hand-drawn sketches. Rather than relying solely on computer vision, our approach leverages the topological knowledge of linkage mechanisms in combination with the output of a convolutional deep neural network. This creates a framework for recognition of hand-drawn sketches. Our methodology involves first generating a dataset of synthetic images of linkage mechanism sketches that resemble hand-drawn sketches. We then fine-tune a state-of-the-art deep neural network capable of detecting discrete objects using a set of building blocks of linkage mechanisms, specifically joints and links in various positions, scales, and orientations. We perform a topological analysis on the set of detected objects to create a kinematic model of the sketched mechanisms. Results indicate that our algorithm performs well on hand-drawn sketches, and it can aid in the conversion of such sketches into their digital representations. This has implications for effective communication, analysis, cataloging, and classification of planar mechanisms. Furthermore, our approach could lay the groundwork for image-based synthesis of planar mechanisms, which would be insensitive to their complexity or properties, such as the algebraic degree of the coupler curves.
{"title":"Transforming Hand-drawn Sketches of Linkage Mechanisms into their Digital Representation","authors":"Anar Nurizada, Anurag Purwar","doi":"10.1115/1.4064037","DOIUrl":"https://doi.org/10.1115/1.4064037","url":null,"abstract":"Abstract This paper presents an approach based on deep neural networks for interactive digital transformation and simulation of n-bar planar linkages composed of revolute and prismatic joints from hand-drawn sketches. Rather than relying solely on computer vision, our approach leverages the topological knowledge of linkage mechanisms in combination with the output of a convolutional deep neural network. This creates a framework for recognition of hand-drawn sketches. Our methodology involves first generating a dataset of synthetic images of linkage mechanism sketches that resemble hand-drawn sketches. We then fine-tune a state-of-the-art deep neural network capable of detecting discrete objects using a set of building blocks of linkage mechanisms, specifically joints and links in various positions, scales, and orientations. We perform a topological analysis on the set of detected objects to create a kinematic model of the sketched mechanisms. Results indicate that our algorithm performs well on hand-drawn sketches, and it can aid in the conversion of such sketches into their digital representations. This has implications for effective communication, analysis, cataloging, and classification of planar mechanisms. Furthermore, our approach could lay the groundwork for image-based synthesis of planar mechanisms, which would be insensitive to their complexity or properties, such as the algebraic degree of the coupler curves.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135391009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Monitoring the health condition as well as predicting the performance of Lithium-ion batteries are crucial to the reliability and safety of electrical systems such as electric vehicles. However, estimating the discharge capacity and end-of-discharge (EOD) of a battery in real-time remains a challenge. Few works have been reported on the relationship between the capacity degradation of a battery and EOD. We introduce a new data-driven method that combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) models to predict the discharge capacity and the EOD using online condition monitoring data. The CNN model extracts long-term correlations among voltage, current, and temperature measurements and then estimates the discharge capacity. The BiLSTM model extracts short-term dependencies in condition monitoring data and predicts the EOD for each discharge cycle while utilizing the capacity predicted by CNN as an additional input. By considering the discharge capacity, the BiLSTM model is able to use the long-term health condition of a battery to improve the prediction accuracy of its short-term performance. We demonstrated that the proposed method can achieve online discharge capacity estimation and EOD prediction efficiently and accurately.
{"title":"Data-Driven Online Prediction of Discharge Capacity and End-of-Discharge of Lithium-ion Battery","authors":"Junchuan Shi, Yupeng Wei, Dazhong Wu","doi":"10.1115/1.4063985","DOIUrl":"https://doi.org/10.1115/1.4063985","url":null,"abstract":"Abstract Monitoring the health condition as well as predicting the performance of Lithium-ion batteries are crucial to the reliability and safety of electrical systems such as electric vehicles. However, estimating the discharge capacity and end-of-discharge (EOD) of a battery in real-time remains a challenge. Few works have been reported on the relationship between the capacity degradation of a battery and EOD. We introduce a new data-driven method that combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) models to predict the discharge capacity and the EOD using online condition monitoring data. The CNN model extracts long-term correlations among voltage, current, and temperature measurements and then estimates the discharge capacity. The BiLSTM model extracts short-term dependencies in condition monitoring data and predicts the EOD for each discharge cycle while utilizing the capacity predicted by CNN as an additional input. By considering the discharge capacity, the BiLSTM model is able to use the long-term health condition of a battery to improve the prediction accuracy of its short-term performance. We demonstrated that the proposed method can achieve online discharge capacity estimation and EOD prediction efficiently and accurately.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Noah Hill, Matthew Ebert, Mena Maurice, Vinayak Krishnamurthy
Abstract We present a novel methodology to generate mechanical structures based on fractal geometry by using the chaos game, which generates self-similar point sets within a polygon. Using the Voronoi decomposition of these points, we are able to generate groups of self-similar structures that can be related back to their chaos game parameters, namely the polygonal domain, fractional distance, and number of samples. Our approach explores the use of forward design of generative structures, which in some cases can be easier to use for designing than inverse generative design techniques. To this end, the central hypothesis of our work is that structures generated using the chaos game can generate families of self-similar structures that, while not identical, exhibit similar mechanical behavior in a statistical sense. We present a systematic study of these self-similar structures through modal analysis and tensile loading and demonstrate a preliminary confirmation of our hypothesis.
{"title":"Cellular Chaos: Statistically Self-Similar Structures based on Chaos Game","authors":"Noah Hill, Matthew Ebert, Mena Maurice, Vinayak Krishnamurthy","doi":"10.1115/1.4063987","DOIUrl":"https://doi.org/10.1115/1.4063987","url":null,"abstract":"Abstract We present a novel methodology to generate mechanical structures based on fractal geometry by using the chaos game, which generates self-similar point sets within a polygon. Using the Voronoi decomposition of these points, we are able to generate groups of self-similar structures that can be related back to their chaos game parameters, namely the polygonal domain, fractional distance, and number of samples. Our approach explores the use of forward design of generative structures, which in some cases can be easier to use for designing than inverse generative design techniques. To this end, the central hypothesis of our work is that structures generated using the chaos game can generate families of self-similar structures that, while not identical, exhibit similar mechanical behavior in a statistical sense. We present a systematic study of these self-similar structures through modal analysis and tensile loading and demonstrate a preliminary confirmation of our hypothesis.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mehdi Taghizadeh, Mohammad Amin Nabian, Negin Alemazkoor
Abstract We propose a novel method for solving partial differential equations using multi-fidelity physics-informed generative adversarial networks. Our approach incorporates physics-supervision into the adversarial optimization process to guide the learning of the generator and discriminator models. The generator has two components: one that approximates the low-fidelity response of the input and another that combines the input and low-fidelity response to generate an approximation of high-fidelity responses. The discriminator identifies whether the input-output pairs accord not only with the actual high-fidelity response distribution, but also with physics. The effectiveness of the proposed method is demonstrated through numerical examples and compared to existing methods.
{"title":"Multi-fidelity Physics-informed Generative Adversarial Network for Solving Partial Differential Equations","authors":"Mehdi Taghizadeh, Mohammad Amin Nabian, Negin Alemazkoor","doi":"10.1115/1.4063986","DOIUrl":"https://doi.org/10.1115/1.4063986","url":null,"abstract":"Abstract We propose a novel method for solving partial differential equations using multi-fidelity physics-informed generative adversarial networks. Our approach incorporates physics-supervision into the adversarial optimization process to guide the learning of the generator and discriminator models. The generator has two components: one that approximates the low-fidelity response of the input and another that combines the input and low-fidelity response to generate an approximation of high-fidelity responses. The discriminator identifies whether the input-output pairs accord not only with the actual high-fidelity response distribution, but also with physics. The effectiveness of the proposed method is demonstrated through numerical examples and compared to existing methods.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135634426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In the rapidly advancing field of multi-modal machine learning (MMML), the convergence of multiple data modalities has the potential to reshape various applications. This paper presents a comprehensive overview of the current state, advancements, and challenges of MMML within the sphere of engineering design. The review begins with a deep dive into five fundamental concepts of MMML:multi-modal information representation, fusion, alignment, translation, and co-learning. Following this, we explore the cutting-edge applications of MMML, placing a particular emphasis on tasks pertinent to engineering design, such as cross-modal synthesis, multi-modal prediction, and cross-modal information retrieval. Through this comprehensive overview, we highlight the inherent challenges in adopting MMML in engineering design, and proffer potential directions for future research. To spur on the continued evolution of MMML in engineering design, we advocate for concentrated efforts to construct extensive multi-modal design datasets, develop effective data-driven MMML techniques tailored to design applications, and enhance the scalability and interpretability of MMML models. MMML models, as the next generation of intelligent design tools, hold a promising future to impact how products are designed.
{"title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","authors":"Binyang Song, Rui Zhou, Faez Ahmed","doi":"10.1115/1.4063954","DOIUrl":"https://doi.org/10.1115/1.4063954","url":null,"abstract":"Abstract In the rapidly advancing field of multi-modal machine learning (MMML), the convergence of multiple data modalities has the potential to reshape various applications. This paper presents a comprehensive overview of the current state, advancements, and challenges of MMML within the sphere of engineering design. The review begins with a deep dive into five fundamental concepts of MMML:multi-modal information representation, fusion, alignment, translation, and co-learning. Following this, we explore the cutting-edge applications of MMML, placing a particular emphasis on tasks pertinent to engineering design, such as cross-modal synthesis, multi-modal prediction, and cross-modal information retrieval. Through this comprehensive overview, we highlight the inherent challenges in adopting MMML in engineering design, and proffer potential directions for future research. To spur on the continued evolution of MMML in engineering design, we advocate for concentrated efforts to construct extensive multi-modal design datasets, develop effective data-driven MMML techniques tailored to design applications, and enhance the scalability and interpretability of MMML models. MMML models, as the next generation of intelligent design tools, hold a promising future to impact how products are designed.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135320575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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：