Novel soft sensor development using echo state network integrated with singular value decomposition: Application to complex chemical processes

He, Yan‐Lin; Tian, Ye; Xu, Yuan; Zhu, Qunxiong

doi:10.1016/j.chemolab.2020.103981

Cited by 56 publications

(20 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantages of DL over traditional methods are widely discussed in the paper. For instance, DL: Since 2014, several studies, particularly in industrial processes, have applied DL for predicting process variables that are hard-to-measure [133,[139][140][141][142][143][144][145]. A detailed discussion of the current state of the art of virtual sensors based on DL is given in [133].…”

Section: Recent Advances In Machine Learning Conceptsmentioning

confidence: 99%

“…A key issue for ESN is to determine W out utilizing the known samples [156]. The ESN's low computational complexity and its ability to capture the process data's dynamic relationships (due to the reservoir's self-and feedback connections and a sparse connection weight matrix) makes it ideal for real-time monitoring, fault detection (important for data quality assurance), and monitoring the reliability of the model predictions [139,141]. Monitoring the reliability is achieved by tracking the ESN reservoir's internal state values.…”

Section: Echo State Network (Esns)mentioning

confidence: 99%

See 1 more Smart Citation

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

Paepae

Bokoro

Kyamakya

2021

Sensors

View full text Add to dashboard Cite

Rapid urbanization, industrial development, and climate change have resulted in water pollution and in the quality deterioration of surface and groundwater at an alarming rate, deeming its quick, accurate, and inexpensive detection imperative. Despite the latest developments in sensor technologies, real-time determination of certain parameters is not easy or uneconomical. In such cases, the use of data-derived virtual sensors can be an effective alternative. In this paper, the feasibility of virtual sensing for water quality assessment is reviewed. The review focuses on the overview of key water quality parameters for a particular use case and the development of the corresponding cost estimates for their monitoring. The review further evaluates the current state-of-the-art in terms of the modeling approaches used, parameters studied, and whether the inputs were pre-processed by interrogating relevant literature published between 2001 and 2021. The review identified artificial neural networks, random forest, and multiple linear regression as dominant machine learning techniques used for developing inferential models. The survey also highlights the need for a comprehensive virtual sensing system in an internet of things environment. Thus, the review formulates the specification book for the advanced water quality assessment process (that involves a virtual sensing module) that can enable near real-time monitoring of water quality.

show abstract

Section: Recent Advances In Machine Learning Conceptsmentioning

confidence: 99%

Section: Echo State Network (Esns)mentioning

confidence: 99%

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

Paepae

Bokoro

Kyamakya

2021

Sensors

View full text Add to dashboard Cite

show abstract

“… 34 Lately, a novel soft sensor development using an echo state network (ESN) integrated with a singular value decomposition was proposed and applied to complex chemical processes. 35 In addition, a recurrent neural network (RNN) has also been introduced to construct nonlinear dynamic soft sensors for quality prediction. 36 Although RNN is a mainstream deep-learning model, it still suffers from the problem of gradient vanishing and exploding due to the “tanh” activation function.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Dynamic Soft Sensor Development with a Supervised Hybrid CNN-LSTM Network for Industrial Processes

Zheng

et al. 2022

ACS Omega

View full text Add to dashboard Cite

A soft sensor is a key component when a real-time measurement is unavailable for industrial processes. Recently, soft sensor models based on deep-learning techniques have been successfully applied to complex industrial processes with nonlinear and dynamic characteristics. However, the conventional deep-learning-based methods cannot guarantee that the quality-relevant features are included in the hidden states when the modeling samples are limited. To address this issue, a supervised hybrid network based on a dynamic convolutional neural network (CNN) and a long short-term memory (LSTM) network is designed by constructing multilayer dynamic CNN-LSTM with improved structures. In each time instant, data augmentation is implemented by dynamic expansion of the original samples. Moreover, multiple supervised hidden units are trained by adding quality variables as part of the layer input to acquire a better quality-related feature learning performance. The effectiveness of the proposed soft senor development is validated through two industrial applications, including a penicillin fermentation process and a debutanizer column.

show abstract

“…Singular value decomposition is a very important tool that is core to the development of new technologies, being used, for example, in soft sensors [8], as well as for the estimataion of 5G channel parameters [9]. In fact, SVD shows its value as a computationally efficient dimensionality reduction method when confronted with large amounts of data [10], which is often sharded, a situation which has prompted innovations such as privacy-preserving SVD [11].…”

Section: Introductionmentioning

confidence: 99%

Scalability of k-Tridiagonal Matrix Singular Value Decomposition

et al. 2021

View full text Add to dashboard Cite

Singular value decomposition has recently seen a great theoretical improvement for k-tridiagonal matrices, obtaining a considerable speed up over all previous implementations, but at the cost of not ordering the singular values. We provide here a refinement of this method, proving that reordering singular values does not affect performance. We complement our refinement with a scalability study on a real physical cluster setup, offering surprising results. Thus, this method provides a major step up over standard industry implementations.

show abstract

Novel soft sensor development using echo state network integrated with singular value decomposition: Application to complex chemical processes

Cited by 56 publications

References 33 publications

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

Nonlinear Dynamic Soft Sensor Development with a Supervised Hybrid CNN-LSTM Network for Industrial Processes

Scalability of k-Tridiagonal Matrix Singular Value Decomposition

Contact Info

Product

Resources

About