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

{"title":"STEP-NC Compliant Data Representations for Powder Bed Fusion in Additive Manufacturing","authors":"F. Milaat, P. Witherell, M. Hardwick, H. Yeung, Vincenzo Ferrero, Laetitia V. Monnier, Matthew Brown","doi":"10.1115/detc2022-90673","DOIUrl":"https://doi.org/10.1115/detc2022-90673","url":null,"abstract":"\u0000 Powder bed fusion (PBF) is an additive manufacturing (AM) technology that uses powerful beams to fuse powder material into layers of scanned patterns, thus producing parts with great geometric complexity. For PBF, process parameters, environmental control, and machining functions play critical roles in maintaining fabrication consistency and reducing potential part defects such as pores and grain growth. However, a major contributor to such defects can be attributed to poor data representations in the form of tessellated geometry and incoherent process plans. To address this issue, the Standard for the Exchange of Product model data Numerical Control (STEP-NC) recently added standardized data elements, entities, and attributes specifically for AM applications. Yet, the current STEP-NC data representations for AM lack definitions of process parameters and scan strategies that are commonly used in PBF processes. Therefore, characterization of the relationship between joint features, especially for PBF in AM, is missing. To bridge this gap, in this paper, an amended STEP-NC compliant data representation for PBF in AM is proposed. Specifically, the characteristics of the interlayer relationships in PBF, along with beam technology and AM strategy controls, are defined. Simulation results demonstrate the feasibility of granular process planning control, and the potential for producing high-quality parts with exact geometry and tolerance.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"10 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":"133936436","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}

{"title":"Knowledge Extraction Method to Support Domain Integrated Design Methodology","authors":"Siyuan Sun, Pavan Tejaswi Velivela, Yong Zeng, Y. Zhao","doi":"10.1115/detc2022-90688","DOIUrl":"https://doi.org/10.1115/detc2022-90688","url":null,"abstract":"\u0000 Nowadays, bio-inspiration has enhanced the creation of sustainable and innovative solutions to modern engineering problems. Nature could inspire mechanical engineers to develop innovative ideas as a great source for multifunctional and optimized designs. However, it is very difficult to extract desired design knowledge from primarily text-based databases and mainly focus on describing the biological system. The main objective of this study is to build a multi-label classification system to classify bio-inspired designs to support the Domain Integrated Design methodology. The proposed system integrates NLP and text mining with several machine learning models to learn and predict the functionalities of bio-inspired design. Various design functionalities were summarized based on the available resources from the AskNature database, then the main information extracted from the database, and they were labelled with corresponding multi-functionalities. Due to the high complexity of the multi-label classification system, multi-label classifiers were built based on different combinations of baseline classifiers and trained to classify selected AskNature pages. One case study was conducted to verify the impact of the proposed system. The results showed that the proposed system is feasible and would be a solution for classifying the bio-inspired design and functional basis knowledge extraction method to support DID methodology.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"17 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":"131147774","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}

{"title":"Decision Fusion Method for the Failure Form of Retired Parts Based on Cloud Model Optimization D-S Evidence Theory","authors":"Lei Wang, Cheng-qian Xu, Zelin Zhang, Xuhui Xia","doi":"10.1115/detc2022-89657","DOIUrl":"https://doi.org/10.1115/detc2022-89657","url":null,"abstract":"\u0000 The decision-making fusion of multi-source failure information for retired parts is vital to classify the failure forms of retired parts. There are various failure information detection methods for retired parts, however the results obtained by different detection methods are biased, one-sided, and uncertain, resulting in difficulty in decision making. Aiming at improving the classification accuracy and reliability of the failure forms for retired parts, we propose a fusion method for retired parts failure form decision-making based on the cloud-model optimization D-S evidence theory (CM-D-S). The cloud model solves the problem of strong subjectivity in the traditional D-S evidence theory and overcomes the negative effects caused by random factors. Through image processing, magnetic memory, and ultrasonic testing, the multi-source failure information of retired parts can be obtained, and the failure forms of retired parts are divided into fracture, corrosion, wear and deformation. The cloud model parameters are used to characterize different failure feature quantities sequentially, obtain the basic probability assignment matrix in the D-S evidence theory, and substituted into the D-S evidence theory model to combine and optimize multi-source failure information, and output the result of decision fusion, which is the multi-source failure form of the retired parts. The case shows that the CM-D-S decision-making method has high accuracy for failure form recognition, which proves the applicability and feasibility of the method.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"27 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":"130486816","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}

{"title":"Toward Formal Qualitative Reasoning to Support Functional Decomposition","authors":"Xiaoyang Mao, Chiradeep Sen","doi":"10.1115/detc2022-89940","DOIUrl":"https://doi.org/10.1115/detc2022-89940","url":null,"abstract":"\u0000 Functional decomposition is an important task in early systems engineering and design, where the overall function of the system is resolved into the functions of its components or subassemblies. Conventionally, this task is performed manually, because of multiple possible solution paths and the need for understanding the physics phenomena that could realize the desired effects. This paper presents an approach of developing a formal method for functional decomposition using physics-based qualitative reasoning. The representation includes three parts: (1) a natural language reasoner that detects the changes of physical states of material and energy flows, (2) a set of causation tables that abstract the knowledge of qualitative physics by capturing the causal relations between the various quantities involved in a physical phenomenon or process, and (3) a process-to-subgraph mapping that translate the physical processes into function structure constructs. The algorithm uses the above three representations and some topological reasoning to assemble function models that represent the decomposition of a given black box model. The paper illustrates the potential of this method for functional decomposition using an example of an air-heating device. The paper also discusses the limitations and challenges in maturing this approach into an end-usable design tool.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"1 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":"116276564","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}

{"title":"Synthetic Image Assisted Deep Learning Framework for Detecting Defects During Composite Sheet Layup","authors":"O. Manyar, Junyan Cheng, Reuben Levine, Vihan Krishnan, J. Barbič, Satyandra K. Gupta","doi":"10.1115/detc2022-90084","DOIUrl":"https://doi.org/10.1115/detc2022-90084","url":null,"abstract":"\u0000 Automation of high-performance manufacturing processes such as prepreg composite layup has been gaining a lot of interest lately. Reliable and accurate defect detection methods play a crucial role in the automation of such processes to maintain the desired quality. The composite prepreg layup process involves manipulation of sheet-like material. Traditional machine vision-based defect detection techniques are inept in detecting defects for such complex processes due to the nature of the defects. Advanced defect detection techniques enabled by deep learning are the key for such applications. However, Deep learning usually requires an enormous amount of physical images of the process which is infeasible in high-mix manufacturing applications. In this paper, we resolve the data generation problem for deep learning by presenting an approach where with a combination of finite element-based simulation and advanced graphics techniques we generate a dataset of photorealistic images of the defects. Approximately, 10000 synthetic images are generated and combined with around 1000 images of real sheets to train a ResNeSt-based deep learning model. We have also devised an efficient 2-stage methodology for training the deep learning network to detect wrinkle-like defects. With the trained model and data augmentation techniques, our method can achieve a mean Average Precision (mAP) of 0.98 on actual production data for detecting defects. The code and the entire dataset are available at: https://github.com/RROS-Lab/DeepSynthDefectDetector.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"70 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":"116352076","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}

{"title":"Hybrid Predictive Model for Assessing Spinal Loads for 3d Asymmetric Lifting","authors":"Rahid Zaman, J. Quarnstrom, Y. Xiang, Ritwik Rakshit, Jie Yang","doi":"10.1115/detc2022-89127","DOIUrl":"https://doi.org/10.1115/detc2022-89127","url":null,"abstract":"\u0000 In this study, a hybrid predictive model is used to predict 3D asymmetric lifting motion and assess potential musculoskeletal lower back injuries for asymmetric lifting tasks. The hybrid model has two modules: a skeletal module and an OpenSim musculoskeletal module. The skeletal module consists of a dynamic joint strength based 40 degrees of freedom spatial skeletal model. The skeletal module can predict the lifting motion, ground reaction forces (GRFs), and center of pressure (COP) trajectory using an inverse dynamics based optimization method. The equations of motion are built by recursive Lagrangian dynamics. The musculoskeletal module consists of a 324-muscle-actuated full-body lumbar spine model. Based on the generated kinematics, GRFs and COP data from the skeletal module, the musculoskeletal module estimates muscle activations using static optimization and joint reaction forces through the joint reaction analysis tool. Muscle activation results between simulated and experimental EMG are compared to validate the model. Finally, potential lower back injuries are evaluated for a specific-weight asymmetric lifting task. The shear and compression spine loads are compared to NIOSH recommended limits. At the beginning of the dynamic lifting process, the simulated compressive spine load beyond the NIOSH action limit but less than the permissible limit. This is due to the fatigue factors considered in NIOSH lifting equation.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"465 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":"116386850","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}

{"title":"Information Fusion-Based Meta-Learning for Few-Shot Fault Diagnosis Under Different Working Conditions","authors":"Tingli Xie, Xufeng Huang, Seung-Kyum Choi","doi":"10.1115/detc2022-90934","DOIUrl":"https://doi.org/10.1115/detc2022-90934","url":null,"abstract":"\u0000 With the development of deep learning and information technologies, intelligent fault diagnosis has been further developed, which achieves satisfactory identification of mechanical faults. However, the lack of labeled samples and complex working conditions can hinder the improvement of diagnostics models. In this article, a novel method called Information Fusion-based Meta-Learning (IFML) is explored for fault diagnosis with few-shot problems under different working conditions. Firstly, an information fusion and embedding module is applied to perform both data- and feature-level fusion of multi-source. The embedding module only contains one input layer and multiple convolutions, residual and batch normalization (BN) layers, which has the advantage of low computational cost and high generalization. Then the prototypical module is proposed to reduce the influence of domain-shift caused by different working conditions using the fusion representation, which can improve the performance of fault diagnosis. The approach is verified on artificial and real faults under 4 different working conditions from the KAt-DataCenter at Paderborn University. For the 3-way 1-shot classification on Task T1, the average testing accuracy of the proposed method is 97.14%. For the K-shot classification on different tasks, the proposed method achieves the highest average testing accuracy of 94.21%. The results show the proposed method outperforms other typical meta-learning methods in terms of testing accuracy and generalization capability.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"42 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":"126965227","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}

{"title":"Developing Requirements for a Manufacturing Training Platform: A Three-Pronged Approach","authors":"R. S. Renu, James Righter, Jada Lytch","doi":"10.1115/detc2022-89556","DOIUrl":"https://doi.org/10.1115/detc2022-89556","url":null,"abstract":"\u0000 The study reported in this paper is focused on training needs for manufacturing assembly line workers. Specifically, the objective is to investigate desired worker characteristics, upskilling opportunities, and need for a training platform targeted at assembly line workers in South Carolina. The study is performed in three parts: 1) a survey of South Carolina manufacturing professionals, 2) an analysis of manufacturing job ads, and 3) an analysis of publicly available data from O*NET®.\u0000 The survey consisted of 27 questions and primarily focused on learning objectives within the cognitive and psychomotor domains of Bloom’s taxonomy. The survey tool was also designed to determine industry perceptions of virtual training for manual assembly operations and perceptions of its potential benefits and limitations. Specific survey questions address the desired complexity of training objectives within the cognitive and psychomotor domains. The results from this survey will later be used provide a framework for customized, targeted training modules for assembly workers.\u0000 Job postings for assembly line workers were analyzed using Natural Language Processing techniques. Specifically, postings were analyzed to relate action verbs to the distinct domains of Bloom’s taxonomy of learning objectives. In addition, a frequency analysis of the verbs provided insight into skills that are in demand.\u0000 Preliminary survey results were compared to results from the job ads analysis and trends from O*NET® for alignment or discrepancies between announced characteristics and desired skills. This comparison provides insights into training requirements and upskilling opportunities for the manufacturing workforce. Further possibilities include targeted semi-structured interviews to explore knowledge gaps, pursue insights, and refine results.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"54 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":"127484162","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}

{"title":"Elasto-Plasticity, Damage and Multiphysics Effects on the Behavior of Adhesive Step Lap Joints","authors":"J. Michopoulos, N. Apetre, A. Iliopoulos, J. Steuben","doi":"10.1115/detc2022-90996","DOIUrl":"https://doi.org/10.1115/detc2022-90996","url":null,"abstract":"\u0000 The presence of damage in the adhesive material as well as combined environmental excitation in multi-material adhesive step-lap joints (ASLJ) often encountered in aircraft industries are frequently neglected. Historically, their design is based only within the scope of elasto-plastic failure. The present work describes the implementation and application of a computational framework enabling the performance evaluation of such joints under quasi-static loading conditions under the simultaneous presence of plasticity, damage and environmental stimulus. In particular, a ASLJ involving Ti-6Al-4V alloy adherents with a FM-300K adhesive is modeled under the proposed framework for various material responses and mutliphysics excitations. It is shown that the assumption of assuming elasto-plastic failure as being the only behavior defining the failure of the adhesive, may not be an adequate assumption for designing and qualifying ASLJs. Specifically, considering presence of plasticity, damage and environmental effects indicates that there are reasons to re-examine the design practices of such joints.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"1 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":"125862274","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}

{"title":"A Synthetic Tradespace Model for Tradespace Analysis and Exploration","authors":"C. Turner, N. Masoudi, Hannah Stewart, Julia Daniels, D. Gorsich, Denise M. Rizzo, G. Hartman, R. Agusti, Annette Skowronska, M. Castanier, S. H. Rapp","doi":"10.1115/detc2022-91080","DOIUrl":"https://doi.org/10.1115/detc2022-91080","url":null,"abstract":"\u0000 Tradespace analysis and exploration is used to frame a design problem. By taking stock of available technologies, predictions of the performance of a system defined from a combinatorial combination of technologies (from say a morphological matrix) can be made. Based on these assessments, tradeoffs between functional performance objectives (often termed simply Functional Objectives or FOs) can be made. The result of these performance tradeoffs or Trades, can then be used to define a target design space for a problem. That design space can then be characterized with criteria to determine the viability of the tradespace and the design problem.\u0000 However, the cost to develop the morphological matrix for the tradespace can be prohibitive. The tradespace at the US Army DEVCOM Ground Vehicle Systems Center (GVSC) took more than 2 years of effort by multiple staff and technical experts to develop and allows for the consideration of more than 1021 vehicles. To develop enhanced approaches to tradespace analysis and exploration to enhance programmatic decision-making, a simulated tradespace based on “synthetic data” is necessary. For tradespace studies within the Clemson University Virtual Prototyping of Ground Systems (VIPR-GS) it was necessary to develop a synthetic tradespace model to serve as a basis for evaluating improved approaches to tradespace analysis, exploration and decision-making methods.\u0000 Within this work, we describe the state-of-the-art for developing models of the tradespace, formulations of functional objectives and defined models to represent different synthetic variable types to produce a synthetic tradespace with far less effort. Using this approach, we demonstrate the development of an example of a synthetic tradespace for small semi-autonomous ground vehicles developed within the VIPR Center that can be used to evaluate vehicle designs for the Clemson Deep Orange Project Vehicle and at GVSC. Finally, we will explore how this tradespace model can be used to facilitate decision-making surrounding the tradespace in the future.","PeriodicalId":382970,"journal":{"name":"Volume 2: 42nd Computers and Information in Engineering Conference (CIE)","volume":"18 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":"122327683","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}