Novel common and special feature extraction method for modeling multi-grade processes

Jingxiang Liu; Tao Liu; Junghui Chen

首页> 外文期刊>IFAC PapersOnLine >Novel common and special feature extraction method for modeling multi-grade processes

【24h】

Novel common and special feature extraction method for modeling multi-grade processes

机译：用于建模多级过程的新颖的公共特征和特殊特征提取方法

获取原文

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

In the processing industries, operating conditions often change to meet the requirements of the market and customers. To cope with the difficulty of on-line quality prediction for such multi-grade processes widely operated in process industries, a novel common and special feature extraction method is proposed for modeling multi-grade processes. A common feature extraction algorithm is proposed to determine the common directions shared by different grades of these processes. After extracting the common features, a partial least-squares modelling algorithm is used to extract the special directions for each grade, respectively. Hence, product quality prediction can be simply conducted by integrating the common and special parts of each grade for model building. A numerical case and an industrial polyethylene process are used to demonstrate the effectiveness and advantage of the proposed method.

机译：在加工业中，操作条件经常发生变化，以满足市场和客户的需求。为了解决在过程工业中广泛使用的这种多级过程的在线质量预测的困难，提出了一种新颖的通用和特殊特征提取方法来建模多级过程。提出了一种共同特征提取算法，以确定这些过程的不同等级所共有的共同方向。在提取共同特征之后，使用偏最小二乘建模算法分别提取每个年级的特殊方向。因此，通过集成每个等级的通用和特殊部分以进行模型构建，可以简单地进行产品质量预测。数值案例和工业聚乙烯工艺被用来证明该方法的有效性和优势。

著录项

来源
《IFAC PapersOnLine》 |2018年第18期|共6页
作者
Jingxiang Liu; Tao Liu; Junghui Chen;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种
中图分类自动化技术、计算机技术;
关键词
multi-grade processcommon feature extractionsoft sensorlimited dataPLS;

机译：多级过程通用特征提取软传感器有限数据PLS;

相似文献

外文文献
中文文献
专利

1. Novel common and special features extraction for monitoring multi-grade processes [J] . Liu Jingxiang, Liu Tao, Chen Junghui, Journal of Process Control . 2018,第期

机译：用于监测多级流程的新型常见和特殊功能
2. Quality prediction for multi-grade processes by just-in-time latent variable modeling with integration of common and special features [J] . Jingxiang Liu, Tao Liu, Junghui Chen Chemical Engineering Science . 2018,第期

机译：通过集成共同和特殊功能的立交潜变量建模对多年级过程的质量预测
3. Special features of using methods of mathematical modelling for the determination of electron beam welding conditions [J] . A.V. Shcherbakov, A.L. Goncharov, A.P. Sliva Welding International . 2012,第8期

机译：使用数学建模方法确定电子束焊接条件的特点
4. Novel common and special feature extraction method for modeling multi-grade processes [C] . Jingxiang Liu, Tao Liu, Junghui Chen IFAC International Symposium on Advanced Control of Chemical Processes . 2018

机译：用于建模多等工艺的新型常见和特殊特征提取方法
5. Pattern recognition and feature extraction using lidar-derived elevation models in GIS: A comparison between visualization techniques and automated methods for identifying prehistoric ditch-fortified sites in North Dakota [D] . Radermacher, Matthew Jeffery. 2016

机译：使用GIS中基于激光雷达的高程模型进行模式识别和特征提取：可视化技术与识别北达科他州史前沟壑加固地点的自动化方法之间的比较
6. Statistical Methods for Proteomic Biomarker Discovery based on Feature Extraction or Functional Modeling Approaches [O] . Jeffrey S. Morris -1

机译：基于特征提取或功能建模方法对蛋白质组学生物标志物发现的统计方法
7. ABSTRACT Various body parts or organs can be analysed to identify the different diseases in the human body. Fingernail analysis is one of the ways to identify disease in the human body. Nails are the body part which are farthest from the heart and therefore receive oxygen at last. As a result the nails are the first who show the symptoms of a disease in the human body. Fingernails can be easily captured for diagnosis and there are no heavy equipment or no specific conditions required to use nail image for disease diagnosis, like in other tests and scanning processes. Human nails deliver beneficial information about complaints or any nutritive imbalances in the human body depending upon their shape, texture and colour. In human beings, numerous systemic and skin diseases can be easily analyzed through careful examination of nails of both the limbs. A lot of nail illnesses have been found to be primary signs of numerous underlying systemic illnesses. The colour, texture or shape changes in nails are signs of many diseases mainly affecting nails. Considering all these properties of nails a system is proposed that uses digital image processing (DIP) methods for identifying such changes in the human nail to get more precise results and predict numerous diseases effortlessly. With the emerging Internet of Things (IOT) concept the generated report is made available remotely, this will help users to reduce transportation efforts. As the system has to deal with large and private data, the security of data must be ensured. To keep the data confidential, the Blockchain concept which is one of the most emerging concepts in the field of data management is used. The paper contains the implementation of the digital image processing for feature extraction of nail images, usage of IOT (ThingSpeak cloud) for data storage and implementation of Blockchain to keep the system secured and theft free. KEY WORDS: Int ernet of thin gs (IOT), Image proc essin g, Thin gSpeak, RG B vavalues, Mean pi xel vavalues, Bloc kchain , Hash key. Disease Diagnostic System: Abnormalities in Human Nail [O] . Pranav S. Wazarkar 2020

机译：摘要的各个身体部位或器官可被分析以识别在人体内的不同的疾病。指甲分析来识别人体疾病的方法之一。指甲是身体一部分是离心脏最远，因此在最后接受氧气。作为结果，指甲是第一谁表现出人体疾病的症状。指甲可以容易地捕获用于诊断和没有重装或需要使用指甲图像用于疾病诊断，比如在其他测试和扫描过程没有特定的条件。人的指甲提供有关投诉或取决于它们的形状，纹理和色彩在人体内的任何营养失衡有益的信息。在人类中，许多全身性皮肤疾病是可以很容易地通过两个四肢指甲的仔细检查分析。很多指甲病已发现众多潜在系统性疾病的主要症状。在指甲的颜色，质地和形状的变化是许多疾病主要影响指甲的迹象。考虑到所有的指甲的这些性能的系统被提出，用于识别人指甲这样的变化以获得更精确的结果，并毫不费力预测许多疾病用途的数字图像处理（DIP）方法。随着物联网（IOT）的概念，新兴的互联网将生成的报告提供远程，这将帮助用户降低运输工作。由于系统必须处理大量的私人数据，数据的安全性必须得到保证。为了保持数据的机密性，使用Blockchain的概念，它是在数据管理领域的大多数新兴的概念之一。本文包含了数字图像处理的指甲图像，IOT（ThingSpeak云）的使用为数据存储和执行Blockchain的特征提取的执行，以保持固定的系统和盗窃免费。关键词：诠释薄GS（IOT），图像的ERNET PROC essin克，薄型gSpeak，RG乙vavalues，平均数PI XEL vavalues，阵营kchain，哈希密钥。疾病诊断系统：在人类指甲异常

Novel common and special feature extraction method for modeling multi-grade processes

摘要

著录项

相似文献

相关主题

期刊订阅