1
|
Siegl M, Kämpf M, Geier D, Andreeßen B, Max S, Zavrel M, Becker T. Generalizability of Soft Sensors for Bioprocesses through Similarity Analysis and Phase-Dependent Recalibration. SENSORS (BASEL, SWITZERLAND) 2023; 23:2178. [PMID: 36850777 PMCID: PMC9959347 DOI: 10.3390/s23042178] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/09/2023] [Revised: 02/08/2023] [Accepted: 02/13/2023] [Indexed: 06/18/2023]
Abstract
A soft sensor concept is typically developed and calibrated for individual bioprocesses in a time-consuming manual procedure. Following that, the prediction performance of these soft sensors degrades over time, due to changes in raw materials, biological variability, and modified process strategies. Through automatic adaptation and recalibration, adaptive soft sensor concepts have the potential to generalize soft sensor principles and make them applicable across bioprocesses. In this study, a new generalized adaptation algorithm for soft sensors is developed to provide phase-dependent recalibration of soft sensors based on multiway principal component analysis, a similarity analysis, and robust, generalist phase detection in multiphase bioprocesses. This generalist soft sensor concept was evaluated in two multiphase bioprocesses with various target values, media, and microorganisms. Consequently, the soft sensor concept was tested for biomass prediction in a Pichia pastoris process, and biomass and protein prediction in a Bacillus subtilis process, where the process characteristics (cultivation media and cultivation strategy) were varied. High prediction performance was demonstrated for P. pastoris processes (relative error = 6.9%) as well as B. subtilis processes in two different media during batch and fed-batch phases (relative errors in optimized high-performance medium: biomass prediction = 12.2%, protein prediction = 7.2%; relative errors in standard medium: biomass prediction = 12.8%, protein prediction = 8.8%).
Collapse
Affiliation(s)
- Manuel Siegl
- Chair of Brewing and Beverage Technology, School of Life Sciences, Technical University of Munich, 85354 Freising, Germany
| | - Manuel Kämpf
- Chair of Brewing and Beverage Technology, School of Life Sciences, Technical University of Munich, 85354 Freising, Germany
| | - Dominik Geier
- Chair of Brewing and Beverage Technology, School of Life Sciences, Technical University of Munich, 85354 Freising, Germany
| | - Björn Andreeßen
- Clariant Produkte (Deutschland) GmbH, 82152 Planegg, Germany
| | - Sebastian Max
- Clariant Produkte (Deutschland) GmbH, 82152 Planegg, Germany
| | - Michael Zavrel
- Clariant Produkte (Deutschland) GmbH, 82152 Planegg, Germany
- Professorship for Bioprocess Engineering, Technical University of Munich, Campus Straubing, 94315 Straubing, Germany
| | - Thomas Becker
- Chair of Brewing and Beverage Technology, School of Life Sciences, Technical University of Munich, 85354 Freising, Germany
| |
Collapse
|
2
|
Shohan S, Zeng Y, Chen X, Jin R, Shirwaiker R. Investigating dielectric spectroscopy and soft sensing for nondestructive quality assessment of engineered tissues. Biosens Bioelectron 2022; 216:114286. [DOI: 10.1016/j.bios.2022.114286] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Revised: 03/29/2022] [Accepted: 04/11/2022] [Indexed: 11/02/2022]
|
3
|
Siegl M, Brunner V, Geier D, Becker T. Ensemble-based adaptive soft sensor for fault-tolerant biomass monitoring. Eng Life Sci 2022; 22:229-241. [PMID: 35382536 PMCID: PMC8961066 DOI: 10.1002/elsc.202100091] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2021] [Revised: 10/26/2021] [Accepted: 11/29/2021] [Indexed: 11/08/2022] Open
Abstract
The accuracy and precision of soft sensors depend strongly on the reliability of underlying model inputs. These inputs (particularly readings of hardware sensors) are frequently subject to faults. This study aims to develop an adaptive soft sensor capable of reliable and robust biomass concentration predictions in the presence of faulty model inputs for a Pichia pastoris bioprocess. Hence, three soft sensor submodels were developed based on three independent model inputs (base addition, CO2 production, and mid-infrared spectrum). An ensemble-based algorithm combined the submodels to form an ensemble model, that is, an adaptive soft sensor, to achieve fault-tolerant prediction. The algorithm's basic steps are as follows: the initial determination of submodel reliability is followed by selecting appropriate submodels to generate a reliable prediction via variance-based weighting of the submodels. The adaptive soft sensor demonstrated high robustness and accuracy in biomass prediction in the presence of multiple simulated sensor faults (RMSE = 0.43 g L-1) and multiple real sensor faults (RMSE = 0.70 g L-1).
Collapse
Affiliation(s)
- Manuel Siegl
- Chair of Brewing and Beverage TechnologyTechnical University of MunichFreisingGermany
| | - Vincent Brunner
- Chair of Brewing and Beverage TechnologyTechnical University of MunichFreisingGermany
| | - Dominik Geier
- Chair of Brewing and Beverage TechnologyTechnical University of MunichFreisingGermany
| | - Thomas Becker
- Chair of Brewing and Beverage TechnologyTechnical University of MunichFreisingGermany
| |
Collapse
|
4
|
Taqvi SAA, Zabiri H, Tufa LD, Uddin F, Fatima SA, Maulud AS. A Review on Data‐Driven Learning Approaches for Fault Detection and Diagnosis in Chemical Processes. CHEMBIOENG REVIEWS 2021. [DOI: 10.1002/cben.202000027] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Affiliation(s)
- Syed Ali Ammar Taqvi
- NED University of Engineering & Technology Department of Chemical Engineering 75270 Karachi Pakistan
- NED University of Engineering and Technology Neurocomputation Lab, National Centre of Artificial Intelligence 75270 Karachi Pakistan
| | - Haslinda Zabiri
- Universiti Teknologi PETRONAS Chemical Engineering Department 32610 Seri Iskandar, Perak Darul Ridzuan Malaysia
| | - Lemma Dendena Tufa
- Addis Ababa Institute of Technology School of Chemical and Bioengineering King George VI St 1000 Addis Ababa Ethiopia
| | - Fahim Uddin
- NED University of Engineering & Technology Department of Chemical Engineering 75270 Karachi Pakistan
| | - Syeda Anmol Fatima
- Universiti Teknologi PETRONAS Chemical Engineering Department 32610 Seri Iskandar, Perak Darul Ridzuan Malaysia
| | - Abdulhalim Shah Maulud
- Universiti Teknologi PETRONAS Chemical Engineering Department 32610 Seri Iskandar, Perak Darul Ridzuan Malaysia
| |
Collapse
|
5
|
Frauendorfer E, Hergeth WD. Soft Sensor Applications in Industrial Vinylacetate-ethylene (VAE) Polymerization Processes. MACROMOL REACT ENG 2017. [DOI: 10.1002/mren.201700008] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Affiliation(s)
- Eric Frauendorfer
- Wacker Chemie AG; Johannes-Hess-Str. 24 84489 Burghausen Deutschland Germany
| | - Wolf-Dieter Hergeth
- Wacker Chemie AG; Johannes-Hess-Str. 24 84489 Burghausen Deutschland Germany
| |
Collapse
|
6
|
Wang H, Ni C, Yan X. Optimizing the echo state network based on mutual information for modeling fed-batch bioprocesses. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2016.11.007] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
7
|
Ni C, Yan X. Elman Neural Networks with Sensitivity Pruning for Modeling Fed-Batch Fermentation Processes. JOURNAL OF CHEMICAL ENGINEERING OF JAPAN 2015. [DOI: 10.1252/jcej.14we238] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Affiliation(s)
- Chunjuan Ni
- Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology
| | - Xuefeng Yan
- Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology
| |
Collapse
|
8
|
Yuan X, Ge Z, Song Z. Locally Weighted Kernel Principal Component Regression Model for Soft Sensing of Nonlinear Time-Variant Processes. Ind Eng Chem Res 2014. [DOI: 10.1021/ie4041252] [Citation(s) in RCA: 114] [Impact Index Per Article: 11.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Xiaofeng Yuan
- State Key
Laboratory of Industrial Control Technology, Institute of Industrial
Process Control, Department of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, Zhejiang, P. R. China
| | - Zhiqiang Ge
- State Key
Laboratory of Industrial Control Technology, Institute of Industrial
Process Control, Department of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, Zhejiang, P. R. China
| | - Zhihuan Song
- State Key
Laboratory of Industrial Control Technology, Institute of Industrial
Process Control, Department of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, Zhejiang, P. R. China
| |
Collapse
|
9
|
Wang H, Yan X. Reservoir Computing with Sensitivity Analysis Input Scaling Regulation and Redundant Unit Pruning for Modeling Fed-Batch Bioprocesses. Ind Eng Chem Res 2014. [DOI: 10.1021/ie500296f] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Heshan Wang
- Key Laboratory
of Advanced
Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, People’s Republic of China
| | - Xuefeng Yan
- Key Laboratory
of Advanced
Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, People’s Republic of China
| |
Collapse
|
10
|
Ge Z, Song Z. Online Monitoring and Quality Prediction of Multiphase Batch Processes with Uneven Length Problem. Ind Eng Chem Res 2014. [DOI: 10.1021/ie403210t] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Zhiqiang Ge
- State Key
Laboratory of Industrial
Control Technology, Institute of Industrial Process Control, Department
of Control Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China
| | - Zhihuan Song
- State Key
Laboratory of Industrial
Control Technology, Institute of Industrial Process Control, Department
of Control Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China
| |
Collapse
|
11
|
Facco P, Tomba E, Bezzo F, García-Muñoz S, Barolo M. Transfer of Process Monitoring Models between Different Plants Using Latent Variable Techniques. Ind Eng Chem Res 2012. [DOI: 10.1021/ie202974u] [Citation(s) in RCA: 20] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Pierantonio Facco
- CAPE-Lab,
Computer-Aided Process
Engineering Laboratory, Dipartimento di Ingegneria Industriale, Università di Padova, via Marzolo 9 − 35131 Padova PD, Italy
| | - Emanuele Tomba
- CAPE-Lab,
Computer-Aided Process
Engineering Laboratory, Dipartimento di Ingegneria Industriale, Università di Padova, via Marzolo 9 − 35131 Padova PD, Italy
| | - Fabrizio Bezzo
- CAPE-Lab,
Computer-Aided Process
Engineering Laboratory, Dipartimento di Ingegneria Industriale, Università di Padova, via Marzolo 9 − 35131 Padova PD, Italy
| | - Salvador García-Muñoz
- Pfizer Worldwide R&D, 445 Eastern Point Road, Groton, Connecticut 06340, United States
| | - Massimiliano Barolo
- CAPE-Lab,
Computer-Aided Process
Engineering Laboratory, Dipartimento di Ingegneria Industriale, Università di Padova, via Marzolo 9 − 35131 Padova PD, Italy
| |
Collapse
|
12
|
Liu Y, Gao Z, Li P, Wang H. Just-in-Time Kernel Learning with Adaptive Parameter Selection for Soft Sensor Modeling of Batch Processes. Ind Eng Chem Res 2012. [DOI: 10.1021/ie201650u] [Citation(s) in RCA: 84] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Yi Liu
- Key Laboratory of Pharmaceutical
Engineering of Ministry of Education, Institute of Process Equipment
and Control Engineering, Zhejiang University of Technology, Hangzhou, 310032, People's Republic of China
| | - Zengliang Gao
- Key Laboratory of Pharmaceutical
Engineering of Ministry of Education, Institute of Process Equipment
and Control Engineering, Zhejiang University of Technology, Hangzhou, 310032, People's Republic of China
| | - Ping Li
- State Key Laboratory of Industrial
Control Technology, Institute of Industrial Process Control, Zhejiang University, Hangzhou, 310027, People's Republic
of China
| | - Haiqing Wang
- College of Mechanical
and Electronic
Engineering, University of Petroleum (East China), West Changjiang Road, No. 66, Qingdao, 266555, People's Republic
of China
| |
Collapse
|
13
|
|
14
|
|