The manufacturing systems of the future will be even more dependent on data than they are today. More and more data and information are being collected and communicated throughout product development lifecycles and across manufacturing value chains. To enable smarter manufacturing operations, new equipment often includes built-in data collection capabilities. Older equipment can be retrofitted inexpensively with sensors to collect a wide variety of data. Many manufacturers are in a quandary as to what to do with increasing quantities of data. Much hype currently surrounds the use of AI to process large data sets, but manufacturers struggle to understand how AI can be applied to improve manufacturing system performance. The gap lies in the lack of good information governance practices for manufacturing. This paper defines information governance in the manufacturing context as the set of principles that allow for consistent, repeatable, and trustworthy processing and use of data. The paper identifies three foundations for good information governance that are needed in the manufacturing environment-data quality, semantic context, and system context-and reviews the surrounding and evolving body of work. The work includes a broad base of standard methods that combines to create reusable information from raw data formats. An example from an additive manufacturing case study is used to show how those detailed specifications create the governance needed to build trust in the systems.
{"title":"Foundations of information governance for smart manufacturing.","authors":"K C Morris, Yan Lu, Simon Frechette","doi":"10.1520/ssms20190041","DOIUrl":"10.1520/ssms20190041","url":null,"abstract":"<p><p>The manufacturing systems of the future will be even more dependent on data than they are today. More and more data and information are being collected and communicated throughout product development lifecycles and across manufacturing value chains. To enable smarter manufacturing operations, new equipment often includes built-in data collection capabilities. Older equipment can be retrofitted inexpensively with sensors to collect a wide variety of data. Many manufacturers are in a quandary as to what to do with increasing quantities of data. Much hype currently surrounds the use of AI to process large data sets, but manufacturers struggle to understand how AI can be applied to improve manufacturing system performance. The gap lies in the lack of good information governance practices for manufacturing. This paper defines information governance in the manufacturing context as the set of principles that allow for consistent, repeatable, and trustworthy processing and use of data. The paper identifies three foundations for good information governance that are needed in the manufacturing environment-data quality, semantic context, and system context-and reviews the surrounding and evolving body of work. The work includes a broad base of standard methods that combines to create reusable information from raw data formats. An example from an additive manufacturing case study is used to show how those detailed specifications create the governance needed to build trust in the systems.</p>","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"134 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9074743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75078010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-01DOI: 10.1016/b978-0-12-820027-8.00004-6
James F. Davis, H. Malkani, J. Dyck, P. Korambath, J. Wise
{"title":"Cyberinfrastructure for the democratization of smart manufacturing","authors":"James F. Davis, H. Malkani, J. Dyck, P. Korambath, J. Wise","doi":"10.1016/b978-0-12-820027-8.00004-6","DOIUrl":"https://doi.org/10.1016/b978-0-12-820027-8.00004-6","url":null,"abstract":"","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"100 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80591218","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}
Economic value added is a primary metric for measuring manufacturing activity; however, this metric and others exclude approximately half of the economic activity necessary for producing manufactured goods. With the recent disruption in the supply of goods and services by the COVID-19 pandemic, the criticality of these supply chains to production has become more apparent. Measuring and understanding these additional activities is foundational to reducing the effect of supply chain disruption. Additionally, manufacturing supply chains are fundamental to any response to the virus, including the production of masks, tests, and eventually a vaccine. When looked at closely, manufacturing stands out as a key driver of our economy. New manufacturing technologies can be leveraged to differentiate products in multiple ways resulting in a greater variety of products made more efficiently, with less environmental impacts, and higher quality. In addition, the digitization of manufacturing supports supply chains that are more connected, anticipatory, and agile. Metrics are needed that better reflect the role manufacturing plays in society, that better identify the social gains manufacturing produces, and that better establish the total economic activity that drives production. In this paper we propose a macro-economic metric to better measure the influence of manufacturing on our economy as an example of one such measure. We argue a need for solidifying similar radical changes to our current ways of measuring manufacturing's relevance and emphasizing the impact of new technologies that support the manufacturing economic sector.
{"title":"Measuring Manufacturing's Significance in the USA.","authors":"K C Morris, Douglas S Thomas","doi":"10.1520/SSMS20200054","DOIUrl":"10.1520/SSMS20200054","url":null,"abstract":"<p><p>Economic value added is a primary metric for measuring manufacturing activity; however, this metric and others exclude approximately half of the economic activity necessary for producing manufactured goods. With the recent disruption in the supply of goods and services by the COVID-19 pandemic, the criticality of these supply chains to production has become more apparent. Measuring and understanding these additional activities is foundational to reducing the effect of supply chain disruption. Additionally, manufacturing supply chains are fundamental to any response to the virus, including the production of masks, tests, and eventually a vaccine. When looked at closely, manufacturing stands out as a key driver of our economy. New manufacturing technologies can be leveraged to differentiate products in multiple ways resulting in a greater variety of products made more efficiently, with less environmental impacts, and higher quality. In addition, the digitization of manufacturing supports supply chains that are more connected, anticipatory, and agile. Metrics are needed that better reflect the role manufacturing plays in society, that better identify the social gains manufacturing produces, and that better establish the total economic activity that drives production. In this paper we propose a macro-economic metric to better measure the influence of manufacturing on our economy as an example of one such measure. We argue a need for solidifying similar radical changes to our current ways of measuring manufacturing's relevance and emphasizing the impact of new technologies that support the manufacturing economic sector.</p>","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"4 no3 2020","pages":""},"PeriodicalIF":0.8,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8751656/pdf/nihms-1701362.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39817006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Gaikwad, Farhad Imani, Hui Yang, E. Reutzel, Prahalada K. Rao
{"title":"In Situ Monitoring of Thin-Wall Build Quality in Laser Powder Bed Fusion Using Deep Learning","authors":"A. Gaikwad, Farhad Imani, Hui Yang, E. Reutzel, Prahalada K. Rao","doi":"10.1520/ssms20190027","DOIUrl":"https://doi.org/10.1520/ssms20190027","url":null,"abstract":"","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"71 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2019-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90362740","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}
Convolutional neural networks are becoming a popular tool for image processing in the engineering and manufacturing sectors. However, managing the storage and distribution of trained models is still a difficult task, partially due to the lack of standardized methods for deep neural network representation. Additionally, the interoperability between different machine learning frameworks remains poor. This paper seeks to address this issue by proposing a standardized format for convolutional neural networks, based on the Predictive Model Markup Language (PMML). A new standardized schema is proposed to represent a range of convolutional neural networks, including classification, regression and semantic segmentation systems. To demonstrate the practical application of this standard, a semantic segmentation model, which is trained to detect casting defects in Xray images, is represented in the proposed PMML format. A high-performance scoring engine is developed to evaluate images and videos against the PMML model. The utility of the proposed format and the scoring engine is evaluated by benchmarking the performance of the defect detection models on a range of different computational platforms.
{"title":"A Standardized PMML Format for Representing Convolutional Neural Networks with Application to Defect Detection.","authors":"M. Ferguson, Y. T. Lee, A. Narayanan, K. Law","doi":"10.1520/ssms20190032","DOIUrl":"https://doi.org/10.1520/ssms20190032","url":null,"abstract":"Convolutional neural networks are becoming a popular tool for image processing in the engineering and manufacturing sectors. However, managing the storage and distribution of trained models is still a difficult task, partially due to the lack of standardized methods for deep neural network representation. Additionally, the interoperability between different machine learning frameworks remains poor. This paper seeks to address this issue by proposing a standardized format for convolutional neural networks, based on the Predictive Model Markup Language (PMML). A new standardized schema is proposed to represent a range of convolutional neural networks, including classification, regression and semantic segmentation systems. To demonstrate the practical application of this standard, a semantic segmentation model, which is trained to detect casting defects in Xray images, is represented in the proposed PMML format. A high-performance scoring engine is developed to evaluate images and videos against the PMML model. The utility of the proposed format and the scoring engine is evaluated by benchmarking the performance of the defect detection models on a range of different computational platforms.","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"72 1","pages":"79-97"},"PeriodicalIF":1.0,"publicationDate":"2019-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76665459","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}
Vincenzo Ferrero, A. Raman, Karl R. Haapala, Bryony DuPont
Sustainability considerations are becoming an intrinsic part of product design and manufacturing. Today’s consumers rely on package labeling to relay useful information about the environmental, social, and economic impacts of a given product. As such, eco-labeling has become an important influence on how consumers interpret the sustainability of products. Three categories of eco-labels are theorized: Type I labels are certified by a reputable third party; Type II are eco-labels that are self-declared, potentially lacking scientific merit; and Type III eco-labels indicate the public availability of product Life Cycle Assessment (LCA) data. Regardless of the type of eco-label used, it is uncertain if eco-labeling directly reflects improved product sustainability. This research focuses on exploring if eco-labeled products are veritably more sustainable. To do this, we perform a comparative study of eco-labeled and comparable conventional products using a triple-bottom-line sustainability assessment, including environmental, economic, and social impacts. Here we show that for a selected set of products, eco-labeling does, in fact, have a positive correlation with improved sustainability. On average, eco-labeled products have a 47.7 % reduced environmental impact, reduce product lifespan costs by 48.4 %, and are subject to positive social perception. However, Type II eco-labeling shows a slight negative correlation with product sustainability and economic cost. We found only one eco-labeled product (with Type II labeling) that had an increased environmental impact over the conventional alternative. In general, the results confirm that most eco-labels are indicative of improved product sustainability. However, there is evidence that suggests that eco-labeling, though accurate, can omit truths with intention to improve marketability.
{"title":"Validating the Sustainability of Eco-Labeled Products Using a Triple-Bottom-Line Analysis","authors":"Vincenzo Ferrero, A. Raman, Karl R. Haapala, Bryony DuPont","doi":"10.1520/ssms20190022","DOIUrl":"https://doi.org/10.1520/ssms20190022","url":null,"abstract":"Sustainability considerations are becoming an intrinsic part of product design and manufacturing. Today’s consumers rely on package labeling to relay useful information about the environmental, social, and economic impacts of a given product. As such, eco-labeling has become an important influence on how consumers interpret the sustainability of products. Three categories of eco-labels are theorized: Type I labels are certified by a reputable third party; Type II are eco-labels that are self-declared, potentially lacking scientific merit; and Type III eco-labels indicate the public availability of product Life Cycle Assessment (LCA) data. Regardless of the type of eco-label used, it is uncertain if eco-labeling directly reflects improved product sustainability. This research focuses on exploring if eco-labeled products are veritably more sustainable. To do this, we perform a comparative study of eco-labeled and comparable conventional products using a triple-bottom-line sustainability assessment, including environmental, economic, and social impacts. Here we show that for a selected set of products, eco-labeling does, in fact, have a positive correlation with improved sustainability. On average, eco-labeled products have a 47.7 % reduced environmental impact, reduce product lifespan costs by 48.4 %, and are subject to positive social perception. However, Type II eco-labeling shows a slight negative correlation with product sustainability and economic cost. We found only one eco-labeled product (with Type II labeling) that had an increased environmental impact over the conventional alternative. In general, the results confirm that most eco-labels are indicative of improved product sustainability. However, there is evidence that suggests that eco-labeling, though accurate, can omit truths with intention to improve marketability.","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"60 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2019-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84602815","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}
Vendy Eko Prasetyo, B. Belleville, B. Ozarska, J. Mo
Enhanced wood recovery mirrors a successful wood manufacturing operation. Studies of wood recovery in secondary wood processing, however, are scarce, particularly in furniture manu-facturing. Although recovery rates are under the continuous surveillance of sophisticated tech-nology, this attempt to monitor wood recovery would be especially challenging for small- to medium-sized furniture enterprises, as the capital investment in such technology would be substantial. This would hinder the possibility for improvements in production efficiency of the furniture industry. A methodology of wood recovery assessment in the furniture industry has been developed and proposed but has not been validated with a cellular production sys-tem, a different layout process and distinctive machinery, species, and other customer require-ments. The objective of this study is to assess the wood recovery protocol individually used in batch and cellular production systems, followed by examining the wood recovery of furniture manufacturing in these distinct production systems. Two Indonesian medium-sized furniture companies that individually operate batch and cellular production systems were employed, and two methods, mass and volume, were used to assess wood recovery at each furni-ture-making station. There was a significant difference in cumulative wood recovery rates be-tween batch and cellular production systems. Based on species and product dimensions, the average individual and cumulative wood recovery rates of furniture manufacturing resulted in a significant difference at the resawing and edging station. Large-dimension product recorded higher wood recovery level than small-dimension product. The wood recovery rates at the resawing and edging, surface planing, thickness planing, and trimming stations were mostly influenced by species, the quality of sawn timber, and cutting bills. Meanwhile, wood recovery at other stations was affected by product dimension and design. The mass method was the most acceptable method according to the measurement systems analysis.
{"title":"A Wood Recovery Assessment Method Comparison between Batch and Cellular Production Systems in the Furniture Industry","authors":"Vendy Eko Prasetyo, B. Belleville, B. Ozarska, J. Mo","doi":"10.1520/SSMS20190001","DOIUrl":"https://doi.org/10.1520/SSMS20190001","url":null,"abstract":"Enhanced wood recovery mirrors a successful wood manufacturing operation. Studies of wood recovery in secondary wood processing, however, are scarce, particularly in furniture manu-facturing. Although recovery rates are under the continuous surveillance of sophisticated tech-nology, this attempt to monitor wood recovery would be especially challenging for small- to medium-sized furniture enterprises, as the capital investment in such technology would be substantial. This would hinder the possibility for improvements in production efficiency of the furniture industry. A methodology of wood recovery assessment in the furniture industry has been developed and proposed but has not been validated with a cellular production sys-tem, a different layout process and distinctive machinery, species, and other customer require-ments. The objective of this study is to assess the wood recovery protocol individually used in batch and cellular production systems, followed by examining the wood recovery of furniture manufacturing in these distinct production systems. Two Indonesian medium-sized furniture companies that individually operate batch and cellular production systems were employed, and two methods, mass and volume, were used to assess wood recovery at each furni-ture-making station. There was a significant difference in cumulative wood recovery rates be-tween batch and cellular production systems. Based on species and product dimensions, the average individual and cumulative wood recovery rates of furniture manufacturing resulted in a significant difference at the resawing and edging station. Large-dimension product recorded higher wood recovery level than small-dimension product. The wood recovery rates at the resawing and edging, surface planing, thickness planing, and trimming stations were mostly influenced by species, the quality of sawn timber, and cutting bills. Meanwhile, wood recovery at other stations was affected by product dimension and design. The mass method was the most acceptable method according to the measurement systems analysis.","PeriodicalId":51957,"journal":{"name":"Smart and Sustainable Manufacturing Systems","volume":"42 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2019-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79926037","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号