检索结果-内蒙古大学图书馆

Diagnosis of incipient fault conditions in batch processes using estimated data covariance structures

IFAC-PapersOnLine 2017年第1期50卷 12779-12784页

作者： Qin, Yan Zhao, Chunhui Kruger, Uwe Zhang, Shumei State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Department of Biomedical Engineering Jonsson Engineering Center Rensselaer Polytechnic Institute TroyNY12019-3590 United States

This paper revisits the monitoring of traditional batch processes and introduces a different concept to diagnose incipient fault conditions. Traditional data-driven methods utilize a 3D arrangement of recorded data from a number of reference batches and unfold this arrangement to construct conventional non-negative squared monitoring statistics. To address the presence of non-stationary and non-Gaussian distributed process variables, the proposed concept relies on the statistical local approach. Following from the central limit theorem, the statistics derived from the statistical local approach have an asymptotic multivariate normal distribution. Moreover, the moving window approach that underlies the statistical local approach is applied over the entire batch cycle. This, in turn, allows describing the typically nonstationary trends in temperature and pressure variables as well as concentrations within a batch cycle. Through an application to a simulated penicillin fermentation process, the paper shows that monitoring statistics derived from the statistical local approach are more sensitive than traditional multivariate statistical methods. © 2017

关键词： Multivariant analysis batch data processing Normal distribution Process control Process monitoring Statistics batch process Central Limit Theorem Covariance structures Local approaches Multi variate normal distributions Multivariate statistical method Penicillin fermentation process Temperature and pressures

来源：评论

学校读者我要写书评

暂无评论

Machine-learning for biopharmaceutical batch process monitoring with limited data

引用

IFAC-PapersOnLine 2018年第18期51卷 126-131页

作者： Tulsyan, Aditya Garvin, Christopher Undey, Cenk Digital Integration & Predictive Technologies Amgen Inc. 360 Binney Street CambridgeMA02141 United States Digital Integration & Predictive Technologies Amgen Inc. 40 Technology Way West GreenwichRI02817 United States Digital Integration & Predictive Technologies Amgen Inc. One Amgen Center Drive Thousand OaksCA91320 United States

Commercial biopharmaceutical manufacturing comprises of multiple distinct processing steps that require effective and efficient monitoring of many variables simultaneously in real-time. This article addresses the problem of real-time statistical batch process monitoring (BPM) for biopharmaceutical processes with limited production history; herein, referred to as the ‘Low-N’ problem. In this article, we propose an approach to transition from a Low-N scenario to a Large-N scenario by generating an arbitrarily large number of in silico batch data sets. The proposed method is a combination of hardware exploitation and algorithm development. To this effect, we propose a Bayesian non-parametric approach to model a batch process, and then use probabilistic programming to generate an arbitrarily large number of dynamic in silico campaign data sets. The efficacy of the proposed solution is elucidated on an industrial process. © 2018

关键词： batch data processing Learning systems Process control Process monitoring Algorithm development batch process monitoring Efficient monitoring Industrial processs Low N problem Nonparametric approaches Probabilistic programming Statistical batch process monitoring

来源：评论

学校读者我要写书评

暂无评论

batch to Real-Time: Incremental data Collection & Analytics Platform 50

Batch to Real-Time: Incremental Data Collection & Analytics ...

引用

50th Annual Hawaii International Conference on System Sciences(HICSS)

作者： Aydin, Ahmet Arif Anderson, Kenneth M. Univ Colorado Boulder CO 80309 USA

ISBN: (纸本)9780998133102

Real-time data collection and analytics is a desirable but challenging feature to provide in data-intensive software systems. To provide highly concurrent and efficient real-time analytics on streaming data at interactive speeds requires a well-designed software architecture that makes use of a carefully selected set of software frameworks. In this paper, we report on the design and implementation of the Incremental data Collection & Analytics Platform (IDCAP). The IDCAP provides incremental data collection and indexing in real-time of social media data;support for real-time analytics at interactive speeds;highly concurrent batch data processing supported by a novel data model;and a front-end web client that allows an analyst to manage IDCAP resources, to monitor incoming data in real-time, and to provide an interface that allows incremental queries to be performed on top of large Twitter datasets.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Logging and manipulating batch process data

Logging and manipulating batch process data

引用

Proceeding of the 1995 Industrial Computing Technical conference ICA/95

作者： Sakmar, Michael W. Jameson, Dana R. Weeks, Kedrick B. Instrument Control Service Pensacola United States

Although continuous data collection is effective for continuous processes, batch processes are event driven and require data collection at precise times during execution. This paper addresses a unique approach to batch process data collection aimed at improving product quality by allowing the distributed control system to determine when to store process data based on real time process events. batch process data logging, data manipulation techniques, and the benefits of this approach are discussed.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

data unfolding PCA modelling and monitoring of multiphase batch processes

Data unfolding PCA modelling and monitoring of multiphase ba...

引用

13th IFAC Symposium on Large Scale Complex Systems: Theory and Applications, LSS 2013

作者： Chai, Yan Yang, Hua Zhao, Lifeng College of Information Science and Engineering Ocean University of China Qingdao China

Multiple phases are inherently characteristics of most batch processes in industrial manufacturing. In order to monitor this kind of batch process more accurately and efficiently, different multivariate statistical methods have been proposed recently. In this work, a new online monitoring approach is proposed with an efficient regularized batch-wise unfolding modeling approach. The approach computes the average correlation structure of the L-length moving window, while capturing the time varying characteristics of the batch process. Based on principal component analysis modeling, the control limits of SPE and 2 T statistics are then calculated for each phase PCA model for online monitoring. The approach needs fewer observations in the construction of batch data than traditional batch-wise unfolding monitoring methods. The L consecutive time periods are effectively averaged over a window, which results in a smoother PCA model especially for the transition period between phases. It makes the approach more applicable to online monitoring of the multiphase batch processes. Application examples show the advantages of the proposed method on online monitoring of multiphase batch processes. © IFAC.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Opportunities for improved batch data recording

Opportunities for improved batch data recording

引用

Proceedings of the 3rd Annual Conference of the Industrial Computing Society

作者： Benner, Stephen J. Consilium Inc Mountain View United States

Although batch record keeping is important, compliance to FDA regulations takes much more than addressing just the batch record. In this presentation, we will present how systems are being implemented to address the i... 详细信息

ISBN: (纸本)1556174640

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Diffusion Meets Few-shot Class Incremental Learning

arXiv

引用

arXiv 2025年

作者： Kim, Junsu Ku, Yunhoe Han, Dongyoon Baek, Seungryul UNIST Korea Republic of NAVER AI Lab Korea Republic of DeepBrain AI United States

Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data;while aiming to reduce catastrophic forgetting and learn new information. We propose Diffusion-FSCIL, a novel approach that employs a text-to-image diffusion model as a frozen backbone. Our conjecture is that FSCIL can be tackled using a large generative model’s capabilities benefiting from 1) generation ability via large-scale pre-training;2) multi-scale representation;3) representational flexibility through the text encoder. To maximize the representation capability, we propose to extract multiple complementary diffusion features to play roles as latent replay with slight support from feature distillation for preventing generative biases. Our framework realizes efficiency through 1) using a frozen backbone;2) minimal trainable components;3) batch processing of multiple feature extractions. Extensive experiments on CUB-200, miniImageNet, and CIFAR-100 show that Diffusion-FSCIL surpasses state-of-the-art methods, preserving performance on previously learned classes and adapting effectively to new ones. Our code is available at here. Copyright © 2025, The Authors. All rights reserved.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Robust predictive tracking fault-tolerant control for multiphase switched systems with asynchronous switching: A Lyapunov–Razumikhin method

引用

Journal of Process Control 2025年 151卷

作者： Shi, Huiyuan Jiang, Pu Li, Hui Su, Chengli Li, Ping School of Information and Control Engineering Liaoning Petrochemical University Fushun113001 China School of Information Engineering Liaodong University Dandong118001 China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China State Key Laboratory of Synthetical Automation for Process Industries College of Information Science and Engineering Northeastern University Shenyang110819 China

This paper develops a robust predictive tracking fault-tolerant control approach for a class typical of multiphase switched systems, i.e., multiphase batch processes, accompanied by asynchronous switching, small time delays, partial actuator faults and disturbances. First, an equivalent extended asynchronous switching model, including a match sub-model and a mismatch sub-model, is built. In this model, the Lyapunov–Razumikhin function method is chosen to handle time delays due to its ability to make the original states of the systems remain invariant set characteristics. Meanwhile, this method has the characteristics of small computation and low conservativeness in solving the linear matrix inequalities, which is appropriate for systems with small delays. Next, according to the stable sufficient conditions based on robust positively invariant sets and terminal constraint sets, the controller gains, the minimum and maximum dwell time are solved online to eliminate the asynchronous switching situation. Moreover, unlike the iterative learning method with globally constant controller gain, its system state cannot change in real time with the action of the desired controller gain, making state deviations occur over time. In contrast, the controller gain in this method can be corrected and updated to avoid state deviation issue in real time. Finally, a simulation case of injection molding process is used to demonstrate the feasibility of the proposed approach. © 2025 Elsevier Ltd

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

A micro vertically-allocated SU-8 check valve and its characteristics

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND processing SYSTEMS 2019年第1期25卷 245-255页

作者： Mao, Zebing Yoshida, Kazuhiro Kim, Joon-wan Tokyo Inst Technol Dept Mech Engn Sch Engn Midori Ku J3-124259 Nagatsuta Cho Yokohama Kanagawa 2258503 Japan Tokyo Inst Technol Lab Future Interdisciplinary Res Sci & Technol FI Midori Ku J3-124259 Nagatsuta Cho Yokohama Kanagawa 2258503 Japan

This paper proposes and develops a novel fabrication method to realize a micro vertically-allocated SU-8 check valve. The ordinary vertically-allocated SU-8 check valve formed by the photolithography has a limited overlap between an SU-8 cantilever and its valve seat, resulting in the low diodicity (i.e. the ratio of the forward flow to reverse flow rates). This overlap prevents the leakage through a bottom gap (a gap between a substrate and the SU-8 cantilever) and a top gap (a gap between a cover plate and the SU-8 cantilever) in the backward flow. These gaps, which are necessary for the movement of the SU-8 cantilever in the forward flow, must cause the leakage of check valves in the backward flow. To reduce the leakage and improve the diodicity, we propose to fabricate a novel fully-overlapped valve seat composed of channel walls, a bottom block, and a top block. To keep the advantages on the batch process of vertically-allocated SU-8 check valves, these blocks are desirable to be fabricated by the multi-layer process. We propose a multi-layer process for the bottom block and a novel beam forming process (a dose-controlled UV exposure) for the top block. In this paper, we design two types of check valves: (a) the ordinary partially-overlapped check valve;and (b) the proposed fully-overlapped check valve, to compare their diodicity. By investigating their flow rate characteristics experimentally, we conclude that the fully-overlapped check valve can reduce the leakage of 53.6% compared with the partially-overlapped check valve and increase the diodicity from 1.7 to 3.5 (about 2 times) at the supplied pressure of 18kPa. We also demonstrate that the novel check valve exhibits higher performance and also show that our fully-overlapped check valve can be potentially applied to various microfluidics.

关键词： batch data processing

来源：评论

学校读者我要写书评

暂无评论

Micro-total process system machine (μ-TPSM) for rapid synthesis of antiretroviral darunavir

引用

REACTION CHEMISTRY & ENGINEERING 2023年第4期8卷 908-916页

作者： Chauhan, Ruchi Rana, Abhilash Ghosh, Subhash Srihari, P. Singh, Ajay K. Indian Inst Chem Technol Dept Organ Synth & Proc Chem CSIR Hyderabad 500007 India Acad Sci & Innovat Res AcSIR Ghaziabad 201002 India

batch processes show great potential in antiretroviral darunavir (DRV) synthesis, but the longer process time, expensive catalyst, shortage of skilled manpower, laborious post-synthetic work-up, transport of one intermediate from one place to another, and need for maintaining expensive storage inventory are some major limitations. Herein, we report the first-ever individual continuous flow sequence involving 7 steps and an integrated micro-total process system machine (mu-TPSM) for the last 4 steps of API DRV synthesis. Employing this mu-TPSM, DRV could be synthesized within 41 min of total residence time with a 71% isolated yield, and an output of 0.8 g h(-1). The use of RANEY (R)-Ni instead of palladium on carbon renders the process more affordable.

关键词： batch data processing

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：