Open AccessJournal Article
Online data preprocessing in the adaptive process model building based on plant data
TL;DR: The online data pre processing and online model parameter updating are discussed and presented on two examples and the influence of data preprocessing on adaptive process model quality is analyzed.
read more
Abstract: Process variables which are concerned with the quality of final product cannot often be measured by a sensor. The alternative procedure is the estimation of these difficult-to-measure process variables for which it is necessary to have an appropriate process model. Process model building, based on plant data taken from the process database, is usually the most cost-effective way to obtain a process model. Since the quality of the built model depends heavily on the modelling data informativity, preprocessing of the available measured data is an important step in such process modelling. Processes are usually time-varying and non-stationary, so that the precision of the estimation based on process model with constant parameters degrades over time. Because of that, model parameters have to be updated online. However, in order to successfully keep the precision of the estimation, it is important to use the samples which do not contain errors in the parameter updating procedure which requires a quality online data preprocessing. The online data preprocessing and online model parameter updating are discussed and presented on two examples and the influence of data preprocessing on adaptive process model quality is analyzed.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Data supplement for a soft sensor using a new generative model based on a variational autoencoder and Wasserstein GAN
Xiao Wang,Han Liu +1 more
TL;DR: The VA-WGAN combining VAE with Wasserstein generative adversarial networks (WGAN) as a generative model is established to produce new samples for soft sensors by using the decoder of VAE as the generator in WGAN.
87
Data Preprocessing for Soft Sensor Using Generative Adversarial Networks
Xiao Wang
- 01 Nov 2018
TL;DR: A generative model named DWGAN based on improved Wasserstein generative adversarial networks (WGAN) is proposed to generate new samples for soft sensors, and experimental results show that the samples yielded by the proposed method behave more similarly with the real samples compared to samples provided by other methods.
12
Modelling and control of tinning line entry section using neural networks
TL;DR: A mathematical model and the design of the control of the drives of a tinning line entry section, using artificial neural networks, are developed and supplemented by neural controllers to satisfy the requirements specified for the individual drives and determined by the sheet metal tinning technology.
•Dissertation
Automatic and adaptive preprocessing for the development of predictive models
Manuel Martin Salvador
- 29 Jun 2017
TL;DR: A novel hybrid strategy combining Bayesian optimisation and common adaptive techniques is proposed to automatically adapt Multi-Component Predictive System (MCPS) and the feasibility of applying such automatic techniques for building and maintaining predictive models for real chemical production processes is evaluated.
6
Adaptive Estimation of Difficult-to-Measure Process Variables
TL;DR: PLSR process model is chosen as the basis of the difficult-to-measure process variable estimator while its parameters are updated in several ways—by the moving window method, recursive NIPALS algorithm, recursive kernel algorithm and Just-in-Time learning algorithm.
References
A theory for multiresolution signal decomposition: the wavelet representation
TL;DR: In this paper, it is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2 /sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions.
De-noising by soft-thresholding
TL;DR: The authors prove two results about this type of estimator that are unprecedented in several ways: with high probability f/spl circ/*/sub n/ is at least as smooth as f, in any of a wide variety of smoothness measures.
10.2K
•Book
Robust Regression and Outlier Detection
Peter J. Rousseeuw,Annick M. Leroy +1 more
- 01 Jan 1987
TL;DR: This paper presents the results of a two-year study of the statistical treatment of outliers in the context of one-Dimensional Location and its applications to discrete-time reinforcement learning.
7K
Estimation of the Mean of a Multivariate Normal Distribution
TL;DR: In this article, an unbiased estimate of risk is obtained for an arbitrary estimate, and certain special classes of estimates are then discussed, such as smoothing by using moving averages and trimmed analogs of the James-Stein estimate.