Douglas L. Van Bossuyt, Britta Hale, R. Arlitt, N. Papakonstantinou
In an age of worsening global threat landscape and accelerating uncertainty, the design and manufacture of systems must increase resilience and robustness across both the system itself and the entire systems design process. We generally trust our colleagues after initial clearance/background checks; and systems to function as intended and within operating parameters after safety engineering review, verification, validation, and/or system qualification testing. This approach has led to increased insider threat impacts; thus we suggest moving to the “trust, but verify” approach embodied by the Zero-Trust paradigm. Zero-Trust is increasingly adopted for network security but has not seen wide adoption in systems design and operation. Achieving the goal of Zero-Trust throughout the systems lifecycle will help to ensure that no single bad actor -- whether human or machine learning / artificial intelligence (ML/AI) -- can induce failure anywhere in a system's lifecycle. Additionally, while ML/AI and their associated risks are already entrenched within the operations phase of many systems' lifecycles, ML/AI is gaining traction during the design phase. For example, generative design algorithms are increasingly popular but there is less understanding of potential risks. Adopting the Zero-Trust philosophy helps ensure robust and resilient design, manufacture, operations, maintenance, upgrade, and disposal of systems. We outline the rewards and challenges of implementing Zero-Trust and propose the Framework for Zero-Trust for the System Design Lifecycle. The paper highlights several areas of ongoing research with focus on high priority areas where the community should focus efforts.
{"title":"Zero-Trust for the System Design Lifecycle","authors":"Douglas L. Van Bossuyt, Britta Hale, R. Arlitt, N. Papakonstantinou","doi":"10.1115/1.4062597","DOIUrl":"https://doi.org/10.1115/1.4062597","url":null,"abstract":"\u0000 In an age of worsening global threat landscape and accelerating uncertainty, the design and manufacture of systems must increase resilience and robustness across both the system itself and the entire systems design process. We generally trust our colleagues after initial clearance/background checks; and systems to function as intended and within operating parameters after safety engineering review, verification, validation, and/or system qualification testing. This approach has led to increased insider threat impacts; thus we suggest moving to the “trust, but verify” approach embodied by the Zero-Trust paradigm. Zero-Trust is increasingly adopted for network security but has not seen wide adoption in systems design and operation. Achieving the goal of Zero-Trust throughout the systems lifecycle will help to ensure that no single bad actor -- whether human or machine learning / artificial intelligence (ML/AI) -- can induce failure anywhere in a system's lifecycle. Additionally, while ML/AI and their associated risks are already entrenched within the operations phase of many systems' lifecycles, ML/AI is gaining traction during the design phase. For example, generative design algorithms are increasingly popular but there is less understanding of potential risks. Adopting the Zero-Trust philosophy helps ensure robust and resilient design, manufacture, operations, maintenance, upgrade, and disposal of systems. We outline the rewards and challenges of implementing Zero-Trust and propose the Framework for Zero-Trust for the System Design Lifecycle. The paper highlights several areas of ongoing research with focus on high priority areas where the community should focus efforts.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"63 9","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72485877","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}
The prediction of the remaining useful life (RUL) is of great significance to ensure the safe operation of industrial equipment and to reduce the cost of regular preventive maintenance. However, the complex operating conditions and various fault modes make it difficult to extract features containing more degradation information with existing prediction methods. We propose a self-supervised learning method based on variational automatic encoder (VAE) to extract features of data's operating conditions and fault modes. Then the clustering algorithm is applied to the extracted features to divide data from different failure modes into different categories and reduce the impact of complex working conditions on the estimation accuracy. In order to verify the effectiveness of the proposed method, we conduct experiments with different network structures on the C-MAPSS dataset, and the results verified that our method can effectively improve the feature extraction capability of the model. In addition, the experimental results further demonstrate the superiority and necessity of using hidden features for clustering rather than raw data.
{"title":"Feature Extraction Based on Self-Supervised Learning for Remaining Useful Life Prediction","authors":"Zhenjun Yu, Ningbo Lei, Yu Mo, Xin Xu, Xiu Li, Biqing Huang","doi":"10.1115/1.4062599","DOIUrl":"https://doi.org/10.1115/1.4062599","url":null,"abstract":"\u0000 The prediction of the remaining useful life (RUL) is of great significance to ensure the safe operation of industrial equipment and to reduce the cost of regular preventive maintenance. However, the complex operating conditions and various fault modes make it difficult to extract features containing more degradation information with existing prediction methods. We propose a self-supervised learning method based on variational automatic encoder (VAE) to extract features of data's operating conditions and fault modes. Then the clustering algorithm is applied to the extracted features to divide data from different failure modes into different categories and reduce the impact of complex working conditions on the estimation accuracy. In order to verify the effectiveness of the proposed method, we conduct experiments with different network structures on the C-MAPSS dataset, and the results verified that our method can effectively improve the feature extraction capability of the model. In addition, the experimental results further demonstrate the superiority and necessity of using hidden features for clustering rather than raw data.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"26 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79114346","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}
Customization is an increasing trend in fashion product industry to reflect individual lifestyles. Previous studies have examined the idea of virtual footwear try-on in augmented reality (AR) using a depth camera. However, the depth camera restricts the deployment of this technology in practice. This research proposes to estimate the 6-DoF pose of a human foot from a color image using deep learning models to solve the problem. We construct a training dataset consisting of synthetic and real foot images that are automatically annotated. Three convolutional neural network models (DOPE, DOPE2, and YOLO6d) are trained with the dataset to predict the foot pose in real-time. The model performances are evaluated using metrics for accuracy, computational efficiency, and training time. A prototyping system implementing the best model demonstrates the feasibility of virtual footwear try-on using a RGB camera. Test results also indicate the necessity of real training data to bridge the reality gap in estimating the human foot pose.
{"title":"Virtual Footwear Try-on in Augmented Reality using Deep Learning Models","authors":"Chih-Hsing Chu, Ting-Yang Chou, S. Liu","doi":"10.1115/1.4062596","DOIUrl":"https://doi.org/10.1115/1.4062596","url":null,"abstract":"\u0000 Customization is an increasing trend in fashion product industry to reflect individual lifestyles. Previous studies have examined the idea of virtual footwear try-on in augmented reality (AR) using a depth camera. However, the depth camera restricts the deployment of this technology in practice. This research proposes to estimate the 6-DoF pose of a human foot from a color image using deep learning models to solve the problem. We construct a training dataset consisting of synthetic and real foot images that are automatically annotated. Three convolutional neural network models (DOPE, DOPE2, and YOLO6d) are trained with the dataset to predict the foot pose in real-time. The model performances are evaluated using metrics for accuracy, computational efficiency, and training time. A prototyping system implementing the best model demonstrates the feasibility of virtual footwear try-on using a RGB camera. Test results also indicate the necessity of real training data to bridge the reality gap in estimating the human foot pose.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48862810","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}
Cyber-physical-human systems (CPHS) are smart products and systems that offer services to their customers, supported by back-end systems (e.g., information, finance) and other infrastructure. In this paper, initial concepts and research issues are presented regarding the computational design of CPHS, CPHS families, and generations of these families. Significant research gaps are identified that should drive future research directions. The approach proposed here is a novel combination of generative and configuration design methods with product family design methodology and an explicit consideration of usability across all human stakeholders. With this approach, a wide variety of CPHS, including customized CPHS, can be developed quickly by sharing technologies and modules across CPHS family members, while ensuring user acceptance. The domain of assistive technology is used in this paper to provide an example field of practice that could benefit from a systematic design methodology and opportunities to leverage technology solutions.
{"title":"Research Issues in the Generative Design of Cyber-Physical-Human Systems","authors":"D. Rosen, C. Choi","doi":"10.1115/1.4062598","DOIUrl":"https://doi.org/10.1115/1.4062598","url":null,"abstract":"\u0000 Cyber-physical-human systems (CPHS) are smart products and systems that offer services to their customers, supported by back-end systems (e.g., information, finance) and other infrastructure. In this paper, initial concepts and research issues are presented regarding the computational design of CPHS, CPHS families, and generations of these families. Significant research gaps are identified that should drive future research directions. The approach proposed here is a novel combination of generative and configuration design methods with product family design methodology and an explicit consideration of usability across all human stakeholders. With this approach, a wide variety of CPHS, including customized CPHS, can be developed quickly by sharing technologies and modules across CPHS family members, while ensuring user acceptance. The domain of assistive technology is used in this paper to provide an example field of practice that could benefit from a systematic design methodology and opportunities to leverage technology solutions.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"25 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78249118","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}
In this paper we discuss the convergence of recent advances in deep neural networks (DNNs) with design of robotic mechanisms, which entails the conceptualization of the design problem as a learning problem from the space of design specifications to a parameterization of the space of mechanisms. We identify three key inter-related problems that are at the forefront of using the versatility of DNNs in solving mechanism design problems. The first problem is that of representation of mechanisms and their design specifications, where the representation challenges arise primarily from the non-Euclidean nature of the data. The second problem is that of developing the mapping from the space of design specifications to the mechanisms where, ideally, we would like to synthesize both type and dimensions of the mechanism for a wide variety of design specifications including path synthesis, motion synthesis, constraints on pivot locations, etc. The third problem is that of designing the neural network architecture for end-to-end training and generation of multiple candidate mechanisms for a given design specification. We also present a brief overview of the state-of-the-art on each of these problems and identify questions of potential interest to the research community.
{"title":"Deep Learning-Driven Design of Robot Mechanisms","authors":"A. Purwar, N. Chakraborty","doi":"10.1115/1.4062542","DOIUrl":"https://doi.org/10.1115/1.4062542","url":null,"abstract":"\u0000 In this paper we discuss the convergence of recent advances in deep neural networks (DNNs) with design of robotic mechanisms, which entails the conceptualization of the design problem as a learning problem from the space of design specifications to a parameterization of the space of mechanisms. We identify three key inter-related problems that are at the forefront of using the versatility of DNNs in solving mechanism design problems. The first problem is that of representation of mechanisms and their design specifications, where the representation challenges arise primarily from the non-Euclidean nature of the data. The second problem is that of developing the mapping from the space of design specifications to the mechanisms where, ideally, we would like to synthesize both type and dimensions of the mechanism for a wide variety of design specifications including path synthesis, motion synthesis, constraints on pivot locations, etc. The third problem is that of designing the neural network architecture for end-to-end training and generation of multiple candidate mechanisms for a given design specification. We also present a brief overview of the state-of-the-art on each of these problems and identify questions of potential interest to the research community.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"32 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80491098","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}
In recent years, Augmented Reality (AR) has been successfully applied in various fields to assist in the execution of manual tasks. However, there is still a lack of complete set of criteria for interface design for generating real-time interactive functions and effectively improving the task efficiency through AR. In this study, subjects performed two kinds of trajectory tracking tasks in AR, the simple trajectory and complex trajectory. Their task performance under five different sensory feedbacks, namely, central vision, peripheral vision, auditory sensation, tactile sensation and no feedback, were compared. The results show that in the trajectory tracking task in complex trajectories, the feedback information should not only provide prompts of error states, but also provide suggestions for correcting the actions to the subjects. In addition, compared with visual sensation and auditory sensation, the feedback information of tactile sensation has better adaptation. Furthermore, the subjects tend to rely on the real-time feedback of tactile sensation to complete difficult tasks. It was found that in the manual trajectory tracking task, determining whether the trajectory tracking task is within the acceptable trajectory range will be affected by the postures subjects use for the tasks, and will change the task performance. Therefore, it is suggested that when designing auxiliary functions, the limitations of the postures of the task should be considered. The experimental results and findings obtained in this study can provide a reference for the auxiliary interface design of manual tasks in AR.
{"title":"Assistive Sensory Feedback for Trajectory Tracking in Augmented Reality","authors":"I-Jan Wang, Lifen Yeh, Chih-Hsing Chu, Yan-Ting Huang","doi":"10.1115/1.4062543","DOIUrl":"https://doi.org/10.1115/1.4062543","url":null,"abstract":"\u0000 In recent years, Augmented Reality (AR) has been successfully applied in various fields to assist in the execution of manual tasks. However, there is still a lack of complete set of criteria for interface design for generating real-time interactive functions and effectively improving the task efficiency through AR. In this study, subjects performed two kinds of trajectory tracking tasks in AR, the simple trajectory and complex trajectory. Their task performance under five different sensory feedbacks, namely, central vision, peripheral vision, auditory sensation, tactile sensation and no feedback, were compared. The results show that in the trajectory tracking task in complex trajectories, the feedback information should not only provide prompts of error states, but also provide suggestions for correcting the actions to the subjects. In addition, compared with visual sensation and auditory sensation, the feedback information of tactile sensation has better adaptation. Furthermore, the subjects tend to rely on the real-time feedback of tactile sensation to complete difficult tasks. It was found that in the manual trajectory tracking task, determining whether the trajectory tracking task is within the acceptable trajectory range will be affected by the postures subjects use for the tasks, and will change the task performance. Therefore, it is suggested that when designing auxiliary functions, the limitations of the postures of the task should be considered. The experimental results and findings obtained in this study can provide a reference for the auxiliary interface design of manual tasks in AR.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47766946","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}
The introduction of the idea of “carbon neutrality” gives the development of low carbon and decarbonization a defined path. Climate change is a significant worldwide concern. To offer a theoretical foundation for the implementation of carbon reduction, this research first analyzes the idea of carbon footprinting, accounting techniques, and supporting technologies. The next section examines carbon emission reduction technologies in terms of lowering emissions and raising carbon sequestration. Digital intelligence technologies like the Internet of Things, big data, and artificial intelligence will be crucial throughout the process of reducing carbon emissions. The implementation pathways for increasing carbon sequestration primarily include ecological and technological carbon sequestration. Nevertheless, proving carbon neutrality requires measuring and monitoring greenhouse gas emissions from several industries, which makes it a challenging undertaking. Intending to increase the effectiveness of carbon footprint measurement, this study created a web-based program for computing and analyzing the whole life-cycle carbon footprint of items. The practical applications and difficulties of digital technologies, such as blockchain, the Internet of Things, and artificial intelligence in achieving a transition to carbon neutrality are also reviewed, and additional encouraging research ideas and recommendations are made to support the development of carbon neutrality.
{"title":"Carbon Neutrality: A Review","authors":"Bin He, Xin Yuan, Shusheng Qian, Bi Li","doi":"10.1115/1.4062545","DOIUrl":"https://doi.org/10.1115/1.4062545","url":null,"abstract":"\u0000 The introduction of the idea of “carbon neutrality” gives the development of low carbon and decarbonization a defined path. Climate change is a significant worldwide concern. To offer a theoretical foundation for the implementation of carbon reduction, this research first analyzes the idea of carbon footprinting, accounting techniques, and supporting technologies. The next section examines carbon emission reduction technologies in terms of lowering emissions and raising carbon sequestration. Digital intelligence technologies like the Internet of Things, big data, and artificial intelligence will be crucial throughout the process of reducing carbon emissions. The implementation pathways for increasing carbon sequestration primarily include ecological and technological carbon sequestration. Nevertheless, proving carbon neutrality requires measuring and monitoring greenhouse gas emissions from several industries, which makes it a challenging undertaking. Intending to increase the effectiveness of carbon footprint measurement, this study created a web-based program for computing and analyzing the whole life-cycle carbon footprint of items. The practical applications and difficulties of digital technologies, such as blockchain, the Internet of Things, and artificial intelligence in achieving a transition to carbon neutrality are also reviewed, and additional encouraging research ideas and recommendations are made to support the development of carbon neutrality.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"74 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78989807","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}
Yi Sun, Liping Xie, Chihua Lu, Zhien Liu, Wan Chen, Xiaolong Li
Acoustic sensitivity analysis is an essential technique to determine the direction of structural-acoustic optimization by evaluating the gradient of the objective functions with respect to the design variables. However, acoustic sensitivity analysis with respect to acoustic impedance, which is an important parameter representing the interior absorbent material in automotive acoustics, is lacking in the study. Moreover, acoustic sensitivity analysis implemented with conventional numerical methods is time and effort-consuming in automotive acoustics, due to the large-scale mesh generation. In this work, the impedance sensitivity analysis for automotive acoustics based on the discontinuous isogeometric boundary element method is presented. The regularized boundary integral equation with impedance boundary conditions is established, then the sensitivity is derived by differentiating the boundary integral equation. The efficiency of the proposed method is improved by employing the parallel technique and generalized minimal residual solver. A long duct example with an analytical solution validates the accuracy of the proposed method, and an automotive passenger compartment subjecting to impedance boundary conditions illustrates that the computing time of the proposed method is one order of magnitude less than the conventional method. This work presents an easily implementable and efficient tool to investigate acoustic sensitivity with respect to impedance, showing great potential in the application of automotive acoustics.
{"title":"Impedance Sensitivity Analysis Based on Discontinuous Isogeometric Boundary Element Method in Automotive Acoustics","authors":"Yi Sun, Liping Xie, Chihua Lu, Zhien Liu, Wan Chen, Xiaolong Li","doi":"10.1115/1.4062544","DOIUrl":"https://doi.org/10.1115/1.4062544","url":null,"abstract":"\u0000 Acoustic sensitivity analysis is an essential technique to determine the direction of structural-acoustic optimization by evaluating the gradient of the objective functions with respect to the design variables. However, acoustic sensitivity analysis with respect to acoustic impedance, which is an important parameter representing the interior absorbent material in automotive acoustics, is lacking in the study. Moreover, acoustic sensitivity analysis implemented with conventional numerical methods is time and effort-consuming in automotive acoustics, due to the large-scale mesh generation. In this work, the impedance sensitivity analysis for automotive acoustics based on the discontinuous isogeometric boundary element method is presented. The regularized boundary integral equation with impedance boundary conditions is established, then the sensitivity is derived by differentiating the boundary integral equation. The efficiency of the proposed method is improved by employing the parallel technique and generalized minimal residual solver. A long duct example with an analytical solution validates the accuracy of the proposed method, and an automotive passenger compartment subjecting to impedance boundary conditions illustrates that the computing time of the proposed method is one order of magnitude less than the conventional method. This work presents an easily implementable and efficient tool to investigate acoustic sensitivity with respect to impedance, showing great potential in the application of automotive acoustics.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"47 4 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89086508","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}
Conceptual design is the design phase that deploys product functions and structures based on user requirements and ultimately generates conceptual design solutions. The increasing diversification of products has led to the promotion of customized design that involves deep user participation. As a result, there has been a growing focus on user-centric conceptual design. In this regard, the relationship among users, designers, and design solutions has been subtly changed, which has brought challenges to the traditional designer-oriented design model. To address the complex understanding and decision-making problem caused by deeper user participation, emerging new user-centric product conceptual design models need to be discussed. In the new design model, addressing the changing or growing requirements of users through the design of solutions and leveraging multidisciplinary knowledge to guide the conceptual design process are the critical areas of focus. To further describe this design model, this paper examines the user-centric interconnection among users, designers, design solutions, and multi-domain knowledge. In order to optimize design solutions, the solution resolution process and knowledge mapping based on design deviations are considered effective approaches. In addition, the paper also presents the types of design deviations and the multi-domain knowledge support techniques.
{"title":"Harnessing Multi-Domain Knowledge for User-Centric Product Conceptual Design","authors":"Xin-biao Guo, Zechuan Huang, Ying Liu, Wu Zhao, Zeyuan Yu","doi":"10.1115/1.4062456","DOIUrl":"https://doi.org/10.1115/1.4062456","url":null,"abstract":"\u0000 Conceptual design is the design phase that deploys product functions and structures based on user requirements and ultimately generates conceptual design solutions. The increasing diversification of products has led to the promotion of customized design that involves deep user participation. As a result, there has been a growing focus on user-centric conceptual design. In this regard, the relationship among users, designers, and design solutions has been subtly changed, which has brought challenges to the traditional designer-oriented design model. To address the complex understanding and decision-making problem caused by deeper user participation, emerging new user-centric product conceptual design models need to be discussed. In the new design model, addressing the changing or growing requirements of users through the design of solutions and leveraging multidisciplinary knowledge to guide the conceptual design process are the critical areas of focus. To further describe this design model, this paper examines the user-centric interconnection among users, designers, design solutions, and multi-domain knowledge. In order to optimize design solutions, the solution resolution process and knowledge mapping based on design deviations are considered effective approaches. In addition, the paper also presents the types of design deviations and the multi-domain knowledge support techniques.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"44 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72786581","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}
In rotating machines, roller bearings are important and prone to frequent faults. Hence, accurate classification of bearing faults is significant in maintenance of machines. Towards this, a framework using the combination of signal processing, machine learning and deep learning algorithms has been proposed in contrast to traditional approaches. The benefits of each algorithm have been reaped in the proposed framework to overcome challenges met in fault identification. In this, Ensemble Empirical Mode Decomposition is applied on bearing vibration signals to reduce non-stationarity and noise. The 12 Intrinsic Mode Function (IMF) signals of 24k length obtained for 3 bearing conditions at 4 speeds constituted feature space of dimension [36*8*24000]. IMFs that have highest correlation coefficient with raw vibration signals are selected as features [3*8*24000] and intelligent algorithms are applied. Application of Principal Component Analysis on selected IMF feature space resulted in extraction of significant features retaining temporal characteristics along 2 major components [3*2*24000]. Considering the temporal dependence of faults in signals, a Stacked Long Short Term Memory (LSTM) deep network is chosen and trained with extracted features to improve fault classification. The performance of this developed framework has been evaluated for different metrics of stacked LSTM model. The proposed framework also satisfactorily surpassed the performance of stacked LSTM model trained with raw data, capable of auto-feature learning. The comparative results inclusive of models in relevant literature illustrate efficacy of developed combinational framework in handling dynamic vibration data for precise classification of bearing faults.
{"title":"Combinational Framework for Classification of Bearing Faults in Rotating Machines","authors":"Sujit Kumar, D. Ganga","doi":"10.1115/1.4062453","DOIUrl":"https://doi.org/10.1115/1.4062453","url":null,"abstract":"\u0000 In rotating machines, roller bearings are important and prone to frequent faults. Hence, accurate classification of bearing faults is significant in maintenance of machines. Towards this, a framework using the combination of signal processing, machine learning and deep learning algorithms has been proposed in contrast to traditional approaches. The benefits of each algorithm have been reaped in the proposed framework to overcome challenges met in fault identification. In this, Ensemble Empirical Mode Decomposition is applied on bearing vibration signals to reduce non-stationarity and noise. The 12 Intrinsic Mode Function (IMF) signals of 24k length obtained for 3 bearing conditions at 4 speeds constituted feature space of dimension [36*8*24000]. IMFs that have highest correlation coefficient with raw vibration signals are selected as features [3*8*24000] and intelligent algorithms are applied. Application of Principal Component Analysis on selected IMF feature space resulted in extraction of significant features retaining temporal characteristics along 2 major components [3*2*24000]. Considering the temporal dependence of faults in signals, a Stacked Long Short Term Memory (LSTM) deep network is chosen and trained with extracted features to improve fault classification. The performance of this developed framework has been evaluated for different metrics of stacked LSTM model. The proposed framework also satisfactorily surpassed the performance of stacked LSTM model trained with raw data, capable of auto-feature learning. The comparative results inclusive of models in relevant literature illustrate efficacy of developed combinational framework in handling dynamic vibration data for precise classification of bearing faults.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"25 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81018729","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：