Volume 2: 42nd Computers and Information in Engineering Conference (CIE)最新文献_第3页

A Comparative Study of Surrogate Modeling of Nonlinear Dynamic Systems 非线性动态系统代理建模方法的比较研究

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-90027

Ying Zhao, Chen Jiang, M. A. Vega, Michael D. Todd, Zhen Hu

{"title":"A Comparative Study of Surrogate Modeling of Nonlinear Dynamic Systems","authors":"Ying Zhao, Chen Jiang, M. A. Vega, Michael D. Todd, Zhen Hu","doi":"10.1115/detc2022-90027","DOIUrl":"https://doi.org/10.1115/detc2022-90027","url":null,"abstract":"\u0000 Surrogate models play a vital role in overcoming the computational challenge in designing and analyzing nonlinear dynamic systems, especially in the presence of uncertainty. This paper presents a comparative study of different surrogate modeling techniques for nonlinear dynamic systems. Four surrogate modeling methods, namely Gaussian process (GP) regression, a long short-term memory (LSTM) network, a convolutional neural network (CNN) with LSTM (CNN-LSTM), and a CNN with bidirectional LSTM (CNN-BLSTM), are studied and compared. All these model types can predict future behavior of dynamic systems over long periods based on training data from relatively short periods. The multidimensional inputs of surrogate models are organized in a nonlinear autoregressive exogenous model (NARX) scheme to enable recursive prediction over long periods, where current predictions replace inputs from the previous time window. The Bouc-Wen nonlinear dynamic model, which can flexibly capture the behavior of many inelastic material models, is used to compare the performance of the four surrogate modeling techniques. The results show that the GP-NARX surrogate model tends to have more stable performance than the other three deep learning-based methods for this particular example. The tuning effort of GP-NARX is also much lower than its deep learning-based counterparts.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124669224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

ShapOrator: Enabling Design Iteration for Young Designers Through Shape Verbalization ShapOrator:通过形状语言化实现年轻设计师的设计迭代

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-90176

S. Vyas, Ting-Ju Chen

{"title":"ShapOrator: Enabling Design Iteration for Young Designers Through Shape Verbalization","authors":"S. Vyas, Ting-Ju Chen","doi":"10.1115/detc2022-90176","DOIUrl":"https://doi.org/10.1115/detc2022-90176","url":null,"abstract":"\u0000 We investigate speech-based input as a means to enable reflective thinking for younger individuals (middle- and high-school students) during design iterations. Verbalization offers a unique way to externalize ideas in early design and could therefore lead to new pathways for exploration and iteration, especially for K-12 students who possess the creative potential but are not technically trained in the design process. Interactive design systems, however, by-and-large utilize sketching, multi-touch, and gestural inputs. As a result, (1) there is little know-how regarding how to operationalize verbal inputs as a meaningful way to facilitate idea exploration and (2) there is little fundamental understanding of the underlying cognitive mechanisms for iteration through verbal communication. We take the initial steps towards these gaps by first designing and implementing the ShapOrator interface that takes verbal descriptions of geometric parameters (shape, size, instances) in a semi-natural language form and determines the appropriate transformations to a given design artifact modeled as a shape assembly. Using ShapOrator as our experimental setup we conducted an in-depth observational study on 10 middle- and high-school students tasked with designing spaceships. Our study revealed that participants were able to create a variety of designs while associating functional and topical contexts to their spaceships throughout the design iteration process.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129772643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Morphological Evaluation of Shoulder Parameters: A Medical Support Tool for the Diagnosis 肩部参数的形态学评价:诊断的医学支持工具

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-89974

Anna Ghidotti, Fabio Locatelli, Nicolò Belotti, D. Regazzoni, C. Rizzi

{"title":"A Morphological Evaluation of Shoulder Parameters: A Medical Support Tool for the Diagnosis","authors":"Anna Ghidotti, Fabio Locatelli, Nicolò Belotti, D. Regazzoni, C. Rizzi","doi":"10.1115/detc2022-89974","DOIUrl":"https://doi.org/10.1115/detc2022-89974","url":null,"abstract":"\u0000 Shoulder disorders are very common in the middle-aged population, due to several causes. The traditional diagnosis relies on the knowledge and the experience of the physician but a clinical misinterpretation in this early phase can have serious consequences for the patient’s health. The aim of this study is to investigate morphological shoulder parameters, as indicators of healthy or pathological conditions. In this way, it is possible to generate a quantitative report, based on measurements. It can be exploited as a medical support tool for physicians to either confirm the diagnosis, or to raise reasonable doubts, as far as the results differed. However, not all the shoulder disorders can be identified through this approach. Magnetic Resonance and Computed Tomography images of pathological shoulders have been employed for the study. The predefined morphological parameters have been measured on 2D medical images as well as from 3D reconstructed virtual model. Critical Shoulder Angle has been identified as the most significant parameter. It is well known that it is affected by Glenoid Inclination, Lateral Acromial Extension and Acromial Height. However, the contribution of each factor is not clear. Hence, a statistical analysis has been performed to understand how its sub-parameters influence it.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128641110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Review of Transfer Learning in Additive Manufacturing Modeling 增材制造建模中的迁移学习研究进展

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-89300

Yifan Tang, M. R. Dehaghani, G. Wang

{"title":"Review of Transfer Learning in Additive Manufacturing Modeling","authors":"Yifan Tang, M. R. Dehaghani, G. Wang","doi":"10.1115/detc2022-89300","DOIUrl":"https://doi.org/10.1115/detc2022-89300","url":null,"abstract":"\u0000 The process-structure-property modeling of additive manufacturing (AM) products plays an important role in process and quality control. In practice however, only limited data are available for each product due to its expensive material and time-consuming fabricating process, which becomes an obstacle to achieve high quality models. Transfer learning (TL) is a new and promising approach that the model of one product (source) may be reused for another product (target) with limited new data on the target. This paper focuses on reviewing applications of TL in AM modeling in order to help further research in this area. To clarify the specific topic, the problem definition is presented, as well as the differences between TL, multi-fidelity modeling, and multi-task learning. Then current applications of TL in AM modeling are summarized according to different TL approaches. To better understand the performances of different TL approaches, several representative TL-assisted AM modeling methods are reproduced and tested on an open-source dataset. Based on the test results, their effectiveness and limitations are discussed in detail. Finally, future research directions about TL in AM modeling are discussed in hope to explore more potential of TL in boosting the AM model performance.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130187753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using Coaxial Melt Pool Monitoring Images to Estimate Cooling Rate for Powder Bed Fusion Additive Manufacturing 利用同轴熔池监测图像估计粉末床熔融增材制造的冷却速率

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-89934

Zhuo Yang, B. Lane, Yan Lu, H. Yeung, Jaehyuk Kim, Yande Ndiaye, S. Krishnamurty

引用次数: 0

Normalization and Dimension Reduction for Machine Learning in Advanced Manufacturing 先进制造中机器学习的归一化与降维

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-89921

Jida Huang, Tsz-Ho Kwok

{"title":"Normalization and Dimension Reduction for Machine Learning in Advanced Manufacturing","authors":"Jida Huang, Tsz-Ho Kwok","doi":"10.1115/detc2022-89921","DOIUrl":"https://doi.org/10.1115/detc2022-89921","url":null,"abstract":"\u0000 With the advances in sensing and communication techniques, data collection has become much easier in manufacturing processes. Machine learning (ML) is a vital tool for manufacturing data analytics to leverage the underlying informatics carried by data. However, the varieties of data formats, dimensionality, and manufacturing types hugely hinder the learning efficiency of ML methods. Data preparation is critical for exploiting the potential of ML in manufacturing problems. This paper investigates how data preparation affects the ML efficacy in manufacturing data. Specifically, we study the influences of data normalization and dimension reduction on the ML performance for various types of manufacturing problems. We conduct comparison studies of data with/without pre-processing on different manufacturing processes, such as casting, milling, and additive manufacturing. Experimental results reveal that different pre-processing methods have a distinct effect on learning efficiency. Normalization is helpful for both numerical and image data, while dimension reduction — this paper uses principal component analysis (PCA) — is not useful for low-dimensional numerical manufacturing data. Combining both normalization and PCA can significantly enhance the learning efficiency of high-dimensional data. After that, we summarize several practical guidelines for manufacturing data preparation for ML, which provide a valuable basis for future manufacturing data analysis with ML approaches.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117033790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Resilience Modeling in Complex Engineered Systems With Human-Machine Interactions 具有人机交互的复杂工程系统的弹性建模

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-89531

Lukman Irshad, Daniel E. Hulse

{"title":"Resilience Modeling in Complex Engineered Systems With Human-Machine Interactions","authors":"Lukman Irshad, Daniel E. Hulse","doi":"10.1115/detc2022-89531","DOIUrl":"https://doi.org/10.1115/detc2022-89531","url":null,"abstract":"\u0000 In recent times, there has been a growing interest in resilience-based design. Resilience-based design operates on the concept that failures and unexpected events will happen, and when they occur, complex engineered systems should be able to operate within acceptable bounds and recover reasonably. Humans can contribute to the resilience of a system by quickly detecting unforeseen events and taking corrective measures. To this effect, researchers have proposed guidelines and design approaches that can help promote human-system resilience. However, there is no early design stage tool to validate if a system is indeed resilient after applying these guidelines and design methods. In this research, we integrate the Human Error and Functional Failure Reasoning (HEFFR) framework into the fmd-tools toolkit to enable designers to model the combined (machine, human, and joint) failures, including their propagation and dynamic effects, during early design stages. This integrated tool also allows designers to model the effects of performance shaping factors, team dynamics, and human-machine interactions in systems of systems. A demonstrative example of a remotely operated rover is explored to demonstrate how this approach can be applied to understand resilience in complex engineered systems with human interactions.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115344554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Multi-Fidelity Physics-Constrained Neural Networks With Minimax Architecture for Materials Modeling 多保真物理约束神经网络与极大极小结构的材料建模

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-91219

Dehao Liu, Pranav Pusarla, Yan Wang

{"title":"Multi-Fidelity Physics-Constrained Neural Networks With Minimax Architecture for Materials Modeling","authors":"Dehao Liu, Pranav Pusarla, Yan Wang","doi":"10.1115/detc2022-91219","DOIUrl":"https://doi.org/10.1115/detc2022-91219","url":null,"abstract":"\u0000 Data sparsity is still the main challenge to apply machine learning models to solve complex scientific and engineering problems. The root cause is the “curse of dimensionality” in training these models. Training algorithms need to explore and exploit in a very high dimensional parameter space to search the optimal parameters for complex models. In this work, a new scheme of multi-fidelity physics-constrained neural networks with minimax architecture is proposed to improve the data efficiency of training neural networks by incorporating physical knowledge as constraints and sampling data with various fidelities. In this new framework, fully-connected neural networks with two levels of fidelities are combined to improve the prediction accuracy. The low-fidelity neural network is used to approximate the low-fidelity data, whereas the high-fidelity neural network is adopted to approximate the correlation function between the low-fidelity and high-fidelity data. To systematically search the optimal weights of various losses for reducing the training time, the Dual-Dimer algorithm is adopted to search high-order saddle points of the minimax optimization problem. The proposed framework is demonstrated with two-dimensional heat transfer, phase transition, and dendritic growth problems, which are fundamental in materials modeling. With the same set of training data, the prediction error of the multi-fidelity physics-constrained neural network with minimax architecture can be two orders of magnitude lower than that of the multi-fidelity neural network with minimax architecture.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115288225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards a Porosity Aware Stochastic Framework for Computing Apparent Mechanical Properties of Additively Manufactured Parts 基于孔隙率感知的增材制造零件表观力学性能随机计算框架研究

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-90992

A. Iliopoulos, Colin A. Stewart, A. Birnbaum, J. Steuben, D. Rowenhorst, J. Michopoulos

{"title":"Towards a Porosity Aware Stochastic Framework for Computing Apparent Mechanical Properties of Additively Manufactured Parts","authors":"A. Iliopoulos, Colin A. Stewart, A. Birnbaum, J. Steuben, D. Rowenhorst, J. Michopoulos","doi":"10.1115/detc2022-90992","DOIUrl":"https://doi.org/10.1115/detc2022-90992","url":null,"abstract":"\u0000 The presence of pores in parts generated via metal Additive Manufacturing (AM) may substantially impact their mechanical performance. To understand the resulting performance, it is essential to identify the quantitative relationship between the size, shape, and location of the pores and the mechanical properties of the manufactured part. To obtain insight into this relationship, we have initiated the development of a stochastic framework that takes as input digital microscope images of AM part sections and provides as output the distribution of mechanical properties of interest such as the apparent (in the global sense) yield stress and the stress-strain response. The distribution of these pores has a semi-stochastic nature, which depends on the process type, process parameters, material type, and AM path. Firstly, we calculate various pore metrics using digital image processing techniques. The metrics are related to geometric characteristics, such as the distance of the pore from the specimen surface. Subsequently, we generate a two-dimensional distribution based on non-parametric principles. We use this distribution to sample exemplified geometries and develop multiple Finite Element Models (FEM). Then we perform virtual experiments to calculate the non-linear stress-strain response for each FEM. The results are then distributed to bins in order to generate distributions and histograms of mechanical properties of interest. We demonstrate the framework by applying it on an AM-produced conformal pressure vessel to show its capacity in computing the distribution of relevant quantities.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126856193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and Research of Intelligent QA System for Flight Crew Operating Manual 机组操作手册智能QA系统的设计与研究

Volume 2: 42nd Computers and Information in Engineering Conference (CIE) Pub Date : 2022-08-14 DOI: 10.1115/detc2022-90768

Xin Tan, Jingshu Zhong, Yu Jin, Yan Liang, Yu Zheng, Ying Liu

引用次数: 0