检索结果-内蒙古大学图书馆

22nd World Congress of the International Federation of Automatic Control (IFAC)

作者： Shin, Seung-Jun Um, Jumyung Hanyang Univ Sch Interdisciplinary Ind Studies Seoul South Korea Kyung Hee Univ Dept Ind & Management Syst Engn Yongin South Korea

ISBN: (纸本)9781713872344

The article presents a systematic approach to integrate predictive model markup language (PMML) with Asset Administration Shell (AAS) for manufacturing interoperability. The present system aims to exchange and share PMML, i.e., data analytics models, across AASs, i.e., asset representations of heterogeneous manufacturing assets. Furthermore, the present system is designed to automatically generate data analytics models on production machines, convert models into the PMML format, create AAS instances for the machines, and embed the PMML models onto the AAS instances. The article includes the design architecture, including a concept model, system architecture, information structure. An AAS client-server prototype is implemented to demonstrate the feasibility of the present system. In the prototype, a server creates and transmits the AAS that corresponds to a production machine and contains submodels associated with PMML-based energy prediction models derived by regression analysis and artificial neural network. A client receives and parses the AAS and its PMML models to predict energy consumed in the machine. Copyright (c) 2023 The Authors.

关键词： Asset Administration Shell predictive model markup language Interoperability Smart Factory Manufacturing Intelligence Energy Prediction

来源：评论

学校读者我要写书评

暂无评论

Integrating predictive model markup language with Asset Administration Shell

引用

IFAC-PapersOnLine 2023年第2期56卷 9823-9830页

作者： Seung-Jun Shin Jumyung Um School of Interdisciplinary Industrial Studies Hanyang University Seoul Republic of Korea Department of Industrial & Management Systems Engineering Kyung Hee University Yongin Republic of Korea

关键词： Asset Administration Shell predictive model markup language Interoperability Smart Factory Manufacturing Intelligence Energy Prediction

来源：评论

学校读者我要写书评

暂无评论

Deploying data analytics models in asset administration shells: Energy prediction in manufacturing

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 138卷

作者： Shin, Seung-Jun Um, Jumyung Hanyang Univ Sch Interdisciplinary Ind Studies Seoul South Korea Kyung Hee Univ Dept Ind & Management Syst Engn Yongin South Korea

This article presents the development of a systematic method to generate and deploy data analytics models in an Asset Administration Shell (AAS). This method aims to exchange and share predictive model markup language (PMML) and Portable Format for Analytics (PFA), i.e., model representation languages in the machine learning domain, in heterogeneous manufacturing assets through integration with AASs, i.e., a standardized digital model of manufacturing assets, for interoperable manufacturing intelligence. This article includes design specifications to identify the system's concept, architecture, and information structure. The article also presents a prototype implementation to demonstrate the feasibility and usability of this system in a facility energy-prediction scenario. In the prototype, an AAS server generates energy prediction models for production machines using linear regression and artificial neural network and converts the models into the PMML and PFA formats. The server then automatically creates and transmits the AASs that contain the submodels corresponding to the PMML and PFA-formatted machine learning models. An AAS client receives and interprets the AASs to predict the energy values consumed in the machines, as the client can act as a factory energy management system.

关键词： Asset administration shell predictive model markup language Portable format for analytics Manufacturing intelligence Interoperability Energy-efficient manufacturing

来源：评论

学校读者我要写书评

暂无评论

A Standardized PMML Format for Representing Convolutional Neural Networks with Application to Defect Detection

引用

SMART AND SUSTAINABLE MANUFACTURING SYSTEMS 2019年第1期3卷 79-97页

作者： Ferguson, Max Lee, Yung-Tsun Tina Narayanan, Anantha Law, Kincho H. Stanford Univ Dept Civil & Environm Engn Y2E2 Bldg473 Via Ortega Stanford CA 94305 USA NIST Syst Integrat Div 100 Bur Dr Gaithersburg MD 20899 USA Univ Southern Calif Viterbi Sch Engn Los Angeles CA 90007 USA

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 that is partially due to the lack of standardized methods for deep neural network representation. Additionally, the interoperability between different machine learning frameworks remains poor. This article 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 X-ray 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.

关键词： smart manufacturing predictive model markup language machine learning models defect detection automated surface inspection convolutional neural networks standard image processing

来源：评论

学校读者我要写书评

暂无评论

A Data Processing Pipeline for Prediction of Milling Machine Tool Condition from Raw Sensor Data

SMART AND SUSTAINABLE MANUFACTURING SYSTEMS

引用

SMART AND SUSTAINABLE MANUFACTURING SYSTEMS 2018年第1期2卷 40-63页

作者： Ferguson, M. Bhinge, R. Park, J. Lee, Y. T. Law, K. H. Stanford Univ Civil & Environm Engn Y2E2 Bldg473 Via Ortega Stanford CA 94305 USA Infinite Uptime Inc 2150 Shattuck Ave Berkeley CA 94704 USA Korea Adv Inst Sci & Technol Ind & Syst Engn 291 Daehak Ro Daejeon 305701 South Korea NIST Syst Integrat Div 100 Bur Dr Gaithersburg MD USA Stanford Univ Civil & Environm Engn Y2E2 Bldg Stanford CA 94305 USA

With recent advances in sensor and computing technology, it is now possible to use real-time machine learning techniques to monitor the state of manufacturing machines. However, making accurate predictions from raw sensor data is still a difficult challenge. In this work, a data processing pipeline is developed to predict the condition of a milling machine tool using raw sensor data. Acceleration and audio time series sensor data are aggregated into blocks that correspond to the individual cutting operations of the Computer Numerical Control milling machine. Each block of data is preprocessed using well-known and computationally efficient signal processing techniques. A novel kernel function is proposed to approximate the covariance between preprocessed blocks of time series data. Several Gaussian process regression models are trained to predict tool condition, each with a different covariance kernel function. The model with the novel covariance function outperforms the models that use more common covariance functions. The trained models are expressed using the predictive model markup language where possible to demonstrate how the predictive model component of the pipeline can be represented in a standardized form. The tool condition model is shown to be accurate, especially when predicting the condition of lightly worn tools.

关键词： tool condition monitoring Gaussian process regression machine learning sustainable manufacturing predictive model markup language

来源：评论

学校读者我要写书评

暂无评论

Smart Mobile Application for the Prediction of the Loss of Signal in Telecommunication Networks Basing on Meteorological Variables 3rd

引用

3rd International Conference on Technology Trends (CITT)

作者： Guerrero Goyes, Kenya Anmarit Aguilar Zambrano, Angie Sthepanie Nunez Villalba, Gabriel Fernando Samaniego Mena, Eduardo Amable Univ Tecn Estatal Quevedo Quevedo Ecuador

ISBN: (纸本)9783319727271;9783319727264

The objective of the research project was developing a mobile app to allow the signal loss prediction. The prediction is based on meteorological characteristic, because it is looking to support the decision-making by the telecommunication specialists. A data Pre-processing realized by the outlier's deletion and variables correlations resulted in a new Dataset. Different data mining classification techniques were analyzed using an optimization approach. The result of this analysis allows to determinate that, the algorithm based on Artificial Neural Networks was the one who has the better accuracy index. It was almost the 100% of accuracy. The project Aim to take advantage of an obtained model, it was represented in the predictive model markup language (PMML) and processed with JAVA technologies in a mobile app development. The app name is SignalPred;this app predicts signal loss through the signal reading of meteorological variables.

关键词： Signal loss Datamining Artificial Neural Networks predictive model markup language Mobile application

来源：评论

学校读者我要写书评

暂无评论

Mobile application for predictive modelling in hurdles race 2

Mobile application for predictive modelling in hurdles race

引用

2ND INTERNATIONAL CONFERENCE ON TECHNOLOGY AND INNOVATION IN SPORTS, HEALTH AND WELLBEING

作者： Przednowek, Krzysztof Wiktorowicz, Krzysztof Krzeszowski, Tomasz Tumidajewicz, Mateusz Iskra, Janusz Univ Rzeszow Fac Phys Educ Towarnickiego 3 PL-35959 Rzeszow Poland Rzeszow Univ Technol Fac Elect & Comp Engn Wincentego Pola 2 PL-35959 Rzeszow Poland Opole Univ Technol Fac Phys Educ & Physiotherapy Proszkowska 76 PL-45758 Opole Poland

ISBN: (纸本)9781538684559

This paper presents a mobile expert system for Android platform, named R-tificial Trainer, to support the work of a hurdles coach in planning training programmes. The main feature of the developed application is the ability to generate training loads and predict results for an athlete. It includes a database of players and allows the user to generate training plan in PDF format. The application has been tested on a dataset of athletes practising hurdles on the 110 metres. The database contains 120 training programmes made by 18 athletes. The application uses the predictive model markup language standard. The predictive models include linear models in the form of ordinary least squares and LASSO regressions and nonlinear model in the form of a multilayer perceptron with exponential function. To choose the best method, the leave-one-out cross-validation is used. The lowest validation error was achieved by multilayer perceptron.

关键词： mobile application expert systems predictive model markup language hurdles race predictive models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a PMML-Based GPR Scoring Engine on a Cloud Platform and Microcomputer Board for Smart Manufacturing 4

Evaluation of a PMML-Based GPR Scoring Engine on a Cloud Pla...

引用

4th IEEE International Conference on Big Data (Big Data)

作者： Ferguson, Max Law, Kincho H. Bhinge, Raunak Dornfeld, David Park, Jinkyoo Lee, Yung-Tsun Tina Stanford Univ Civil & Environm Engn Stanford CA 94305 USA Univ Calif Berkeley Mech Engn Berkeley CA 94720 USA Korea Adv Inst Sci & Technol Ind & Syst Engn Daejeon South Korea NIST Syst Integrat Div Gaithersburg MD 20899 USA

ISBN: (纸本)9781467390057

The use of data-driven predictive models is becoming increasingly popular in engineering and manufacturing sectors. This paper discusses the deployment of Gaussian Process Regression (GPR) predictive models for smart manufacturing. A scoring engine is developed based on the predictive model markup language (PMML) standard to illustrate the portability of predictive models among different statistical tools and different platforms. Specifically, we evaluate the tradeoffs between embedding GPR-based predictive models on a physical device and executing the predictive models on a managed cloud platform like the Google Compute Engine. We compare the performance of the two deployment strategies with two predictive models, namely an energy consumption model and a milling tool condition model, that are built with data from a Mori Seiki CNC milling machine. We describe how the response time of the two deployment strategies is related to the network latency and computational speed of the scoring machine hardware. It is shown that the time required to calculate model predictions is a significant factor in the overall response time of the embedded scoring engine. We demonstrate that the scoring engine on the cloud platform can achieve a lower response time and higher prediction rate than the microcomputer, due to the superior computational performance of the cloud-based hardware.

关键词： scoring engine predictive model markup language energy prediction model milling machine

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：