Group-sparsity-enforcing fault discrimination and estimation with dynamic process data

2021 ◽  
Vol 105 ◽  
pp. 236-249
Author(s):  
Chao Shang ◽  
Liang Zhao ◽  
Xiaolin Huang ◽  
Hao Ye ◽  
Dexian Huang
Keyword(s):  
Dynamic Process ◽  
Group Sparsity ◽  
Process Data

scholarly journals Temporal-Spatial Neighborhood Enhanced Sparse Autoencoder for Nonlinear Dynamic Process Monitoring

Processes ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1079
Author(s):  
Nanxi Li ◽  
Hongbo Shi ◽  
Bing Song ◽  
Yang Tao
Keyword(s):  
Feature Extraction ◽  
Fault Detection ◽  
Process Monitoring ◽  
Dynamic Process ◽  
Process Data ◽  
Detection Scheme ◽  
Current Time ◽  
Neighborhood Information ◽  
Sparse Autoencoder ◽  
Current Sample

Data-based process monitoring methods have received tremendous attention in recent years, and modern industrial process data often exhibit dynamic and nonlinear characteristics. Traditional autoencoders, such as stacked denoising autoencoders (SDAEs), have excellent nonlinear feature extraction capabilities, but they ignore the dynamic correlation between sample data. Feature extraction based on manifold learning using spatial or temporal neighbors has been widely used in dynamic process monitoring in recent years, but most of them use linear features and do not take into account the complex nonlinearities of industrial processes. Therefore, a fault detection scheme based on temporal-spatial neighborhood enhanced sparse autoencoder is proposed in this paper. Firstly, it selects the temporal neighborhood and spatial neighborhood of the sample at the current time within the time window with a certain length, the spatial similarity and time serial correlation are used for weighted reconstruction, and the reconstruction combines the current sample as the input of the sparse stack autoencoder (SSAE) to extract the correlation features between the current sample and the neighborhood information. Two statistics are constructed for fault detection. Considering that both types of neighborhood information contain spatial-temporal structural features, Bayesian fusion strategy is used to integrate the two parts of the detection results. Finally, the superiority of the method in this paper is illustrated by a numerical example and the Tennessee Eastman process.

scholarly journals Spectral principal component analysis of dynamic process data

2002 ◽  
Vol 10 (8) ◽  
pp. 833-846 ◽  
Author(s):  
N.F. Thornhill ◽  
S.L. Shah ◽  
B. Huang ◽  
A. Vishnubhotla
Keyword(s):  
Principal Component Analysis ◽  
Dynamic Process ◽  
Principal Component ◽  
Component Analysis ◽  
Process Data ◽  
Spectral Principal Component Analysis

scholarly journals Learning Manifolds from Dynamic Process Data

Algorithms ◽  
2020 ◽  
Vol 13 (2) ◽  
pp. 30
Author(s):  
Frank Schoeneman ◽  
Varun Chandola ◽  
Nils Napp ◽  
Olga Wodo ◽  
Jaroslaw Zola
Keyword(s):  
Dynamic Process ◽  
Computational Models ◽  
Temporal Correlation ◽  
Scientific Data ◽  
Dimensional Manifold ◽  
Process Data ◽  
Temporal Correlations ◽  
Reduction Methods ◽  
Spectral Dimensionality ◽  
Low Dimensional

Scientific data, generated by computational models or from experiments, are typically results of nonlinear interactions among several latent processes. Such datasets are typically high-dimensional and exhibit strong temporal correlations. Better understanding of the underlying processes requires mapping such data to a low-dimensional manifold where the dynamics of the latent processes are evident. While nonlinear spectral dimensionality reduction methods, e.g., Isomap, and their scalable variants, are conceptually fit candidates for obtaining such a mapping, the presence of the strong temporal correlation in the data can significantly impact these methods. In this paper, we first show why such methods fail when dealing with dynamic process data. A novel method, Entropy-Isomap, is proposed to handle this shortcoming. We demonstrate the effectiveness of the proposed method in the context of understanding the fabrication process of organic materials. The resulting low-dimensional representation correctly characterizes the process control variables and allows for informative visualization of the material morphology evolution.

Representing and diagnosing dynamic process data using neural networks

1992 ◽  
Vol 5 (1) ◽  
pp. 11-21 ◽  
Author(s):  
R. Vaidyanathan ◽  
V. Venkatasubramanian
Keyword(s):  
Neural Networks ◽  
Dynamic Process ◽  
Process Data

Engaging Undergraduate Students in Child Language Research

2014 ◽  
Vol 17 (1) ◽  
pp. 4-16
Author(s):  
Jade H. Coston ◽  
Corine Myers-Jennings
Keyword(s):  
Undergraduate Students ◽  
Student Growth ◽  
Process Data ◽  
Research Knowledge ◽  
Research Dissemination ◽  
Language Sampling ◽  
Language Research ◽  
Language Sample Analysis ◽  
Turn Taking ◽  
Assessment Techniques

To better prepare the professionals and scholars of tomorrow in the field of communication sciences and disorders (CSD), a research project in which undergraduate students collected and analyzed language samples of child-parent dyads is presented. Student researchers gained broad and discipline-specific inquiry skills related to the ethical conduct of research, the literature review process, data collection using language assessment techniques, language sample analysis, and research dissemination. Undergraduate students majoring in CSD developed clinical research knowledge, skills, and dispositions necessary for future graduate level study and professional employment. In addition to the benefits of student growth and development, language samples collected through this project are helping to answer research questions regarding communicative turn-taking opportunities within the everyday routines of young children, the effects of turn-taking interactions on language development, and the construct validity of language sampling analysis techniques.

Red Flags: Barriers to Listening and Spoken Language in Children with Hearing Loss

2014 ◽  
Vol 24 (1) ◽  
pp. 11-18
Author(s):  
Andrea Bell ◽  
K. Todd Houston
Keyword(s):  
Hearing Loss ◽  
Early Diagnosis ◽  
Skill Acquisition ◽  
Dynamic Process ◽  
Spoken Language ◽  
Red Flags ◽  
Careful Monitoring ◽  
Auditory Development ◽  
Children With Hearing Loss ◽  
Family Centered

To ensure optimal auditory development for the acquisition of spoken language, children with hearing loss require early diagnosis, effective ongoing audiological management, well fit and maintained hearing technology, and appropriate family-centered early intervention. When these elements are in place, children with hearing loss can achieve developmental and communicative outcomes that are comparable to their hearing peers. However, for these outcomes to occur, clinicians—early interventionists, speech-language pathologists, and pediatric audiologists—must participate in a dynamic process that requires careful monitoring of countless variables that could impact the child's skill acquisition. This paper addresses some of these variables or “red flags,” which often are indicators of both minor and major issues that clinicians may encounter when delivering services to young children with hearing loss and their families.

COVID-19 complicated by pulmonary embolism treated with catheter directed thrombectomy

VASA ◽  
2020 ◽  
Vol 49 (4) ◽  
pp. 333-337 ◽  
Author(s):  
Francisco Leonardo Galastri ◽  
Leonardo Guedes Moreira Valle ◽  
Breno Boueri Affonso ◽  
Marcela Juliano Silva ◽  
Rodrigo Gobbo Garcia ◽  
...  
Keyword(s):  
Pulmonary Embolism ◽  
High Risk ◽  
Dynamic Process ◽  
Therapeutic Option ◽  
Massive Pulmonary Embolism ◽  
Percutaneous Intervention ◽  
Thromboembolic Events ◽  
Emergency Center ◽  
Catheter Directed Thrombolysis

Summary: COVID-19 is a recently identified illness that is associated with thromboembolic events. We report a case of pulmonary embolism in a patient with COVID-19, treated by catheter directed thrombectomy. A 57 year old patient presented to the emergency center with severe COVID-19 symptoms and developed massive pulmonary embolism. The patient was treated with catheter directed thrombolysis (CDT) and recovered completely. Coagulopathy associated with COVID-19 is present in all severe cases and is a dynamic process. We describe a case of massive/high risk pulmonary embolism, in a patient with COVID-19 receiving full anticoagulation, who was treated by percutaneous intervention. CDT can be an additional therapeutic option in patients with COVID-19 and pulmonary embolism that present with rapid clinical collapse.

Scientific Problem Solving in a Virtual Laboratory: A Comparison Between Individuals and Pairs

2008 ◽  
Vol 67 (2) ◽  
pp. 71-83 ◽  
Author(s):  
Yolanda A. Métrailler ◽  
Ester Reijnen ◽  
Cornelia Kneser ◽  
Klaus Opwis
Keyword(s):  
Visual Search ◽  
Problem Solving ◽  
Process Data ◽  
Scientific Problem ◽  
Domain Specific ◽  
Scientific Problem Solving ◽  
Before And After ◽  
Verbal Data ◽  
Psychological Knowledge ◽  
Problem Solving Task

This study compared individuals with pairs in a scientific problem-solving task. Participants interacted with a virtual psychological laboratory called Virtue to reason about a visual search theory. To this end, they created hypotheses, designed experiments, and analyzed and interpreted the results of their experiments in order to discover which of five possible factors affected the visual search process. Before and after their interaction with Virtue, participants took a test measuring theoretical and methodological knowledge. In addition, process data reflecting participants’ experimental activities and verbal data were collected. The results showed a significant but equal increase in knowledge for both groups. We found differences between individuals and pairs in the evaluation of hypotheses in the process data, and in descriptive and explanatory statements in the verbal data. Interacting with Virtue helped all students improve their domain-specific and domain-general psychological knowledge.

Sign in / Sign up

Export Citation Format

Share Document