Abstract
Sensor faults can impede the functionality of monitoring and control systems for bioprocesses. Hence, suitable systems need to be developed to validate the sensor readings prior to their use in monitoring and control systems. This study presents a novel approach for online validation of sensor readings. The basic idea is to compare the original sensor reading with predictions for this sensor reading based on the remaining sensor network’s information. Deviations between original and predicted sensor readings are used to indicate sensor faults. Since especially batch processes show varying lengths and different phases (e.g., lag and exponential phase), prediction models that are dependent on process time are necessary. The binary particle swarm optimization algorithm is used to select the best prediction models for each time step. A regularization approach is utilized to avoid overfitting. Models with high complexity and prediction errors are penalized, resulting in optimal predictions for the sensor reading at each time step (5% mean relative prediction error). The sensor reliability is calculated by the Kullback–Leibler divergence between the distribution of model-based predictions and the distribution of a moving window of original sensor readings (moving window size = 10 readings). The developed system allows for the online detection of sensor faults. This is especially important when sensor data are used as input to soft sensors for critical quality attributes or the process control system. The proof-of-concept is exemplarily shown for a turbidity sensor that is used to monitor a Pichia pastoris-batch process.
Similar content being viewed by others
References
Nicoletti M, Jain L, Giordano R. Computational intelligence techniques as tools for bioprocess modelling, optimization, supervision and control. Computational intelligence techniques for bioprocess modelling, supervision and control. Berlin: Springer; 2009. p. 1–23.
Sharma AB, Golubchik L, Govindan R. Sensor faults: detection methods and prevalence in real-world datasets. ACM TOSN. 2010;6(3):23.
Balaban E, Saxena A, Bansal P, Goebel KF, Curran S. Modeling, detection, and disambiguation of sensor faults for aerospace applications. IEEE Sensors J. 2009;9(12):1907–17.
Mehranbod N, Soroush M, Piovoso M, Ogunnaike BA. Probabilistic model for sensor fault detection and identification. AIChE J. 2003;49(7):1787–802.
Cha Y-J, Agrawal AK. Robustness studies of sensor faults and noises for semi-active control strategies using large-scale magnetorheological dampers. J Vib Control. 2016;22(5):1228–43.
Zhang HQ, Yan Y. A wavelet-based approach to abrupt fault detection and diagnosis of sensors. IEEE Trans Instrum Meas. 2001;50(5):1389–96.
Feital T, Pinto JC. Use of variance spectra for in-line validation of process measurements in continuous processes. Can J Chem Eng. 2015;93(8):1426–37.
Becker T, Breithaupt D, Doelle HW, Fiechter A, Schlegel G, Shimizu S, et al. Biotechnology, 5. Monitoring and modeling of bioprocesses. Ullmann’s encyclopedia of industrial chemistry. 2009.
Das A, Maiti J, Banerjee R. Process monitoring and fault detection strategies: a review. Int J Qual Reliab Manag. 2012;29(7):720–52.
Isermann R. Fault-diagnosis systems: an introduction from fault detection to fault tolerance: Springer Science & Business Media; 2006.
Kourti T. Application of latent variable methods to process control and multivariate statistical process control in industry. Int J Adapt Control Signal Process. 2005;19(4):213–46.
Goulding PR, Lennox B, Sandoz DJ, Smith KJ, Marjanovic O. Fault detection in continuous processes using multivariate statistical methods. Int J Syst Sci. 2000;31(11):1459–71.
Krause D, Hussein M, Becker T. Online monitoring of bioprocesses via multivariate sensor prediction within swarm intelligence decision making. Chemom Intell Lab Syst. 2015;145:48–59.
Mehranbod N, Soroush M, Panjapornpon C. A method of sensor fault detection and identification. J Process Control. 2005;15(3):321–39.
Guo T-H, Nurre J, editors. Sensor failure detection and recovery by neural networks. Neural Networks, 1991., IJCNN-91-Seattle international joint conference on; 1991: IEEE.
Zarei J, Shokri E. Robust sensor fault detection based on nonlinear unknown input observer. Measurement. 2014;48:355–67.
Dunia R, Qin SJ, Edgar TF, McAvoy TJ. Identification of faulty sensors using principal component analysis. AIChE J. 1996;42(10):2797–812.
Alag S, Agogino AM, Morjaria M. A methodology for intelligent sensor measurement, validation, fusion, and fault detection for equipment monitoring and diagnostics. AI EDAM. 2001;15(4):307–20.
Ibargüengoytia PH, Vadera S, Sucar LE. A probabilistic model for information and sensor validation. Comput J. 2005;49(1):113–26.
Frank PM. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: a survey and some new results. Automatica. 1990;26(3):459–74.
Khanesar MA, Teshnehlab M, Shoorehdeli MA, editors. A novel binary particle swarm optimization. Control & Automation, 2007. MED’07. Mediterranean conference on; 2007: IEEE.
Harms J, Wang X, Kim T, Yang X, Rathore AS. Defining process design space for biotech products: case study of Pichia pastoris fermentation. Biotechnol Prog. 2008;24(3):655–62.
Stratton J, Chiruvolu V, Meagher M. High cell-density fermentation. Pichia protocols. Berlin: Springer; 1998. p. 107–20.
Ündey C, Williams BA, Cınar A. Monitoring of batch pharmaceutical fermentations: data synchronization, landmark alignment, and real-time monitoring. IFAC Proc Vol. 2002;35(1):271–6.
Chong I-G, Jun C-H. Performance of some variable selection methods when multicollinearity is present. Chemom Intell Lab Syst. 2005;78(1):103–12.
Wold S, Sjöström M, Eriksson L. PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst. 2001;58(2):109–30.
Kennedy J, Eberhart RC, editors. A discrete binary version of the particle swarm algorithm. Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE international conference on; 1997: IEEE.
Del Valle Y, Venayagamoorthy GK, Mohagheghi S, Hernandez J-C, Harley RG. Particle swarm optimization: basic concepts, variants and applications in power systems. IEEE Trans Evol Comput. 2008;12(2):171–95.
Shi Y, Eberhart RC, editors. Parameter selection in particle swarm optimization. International conference on evolutionary programming. Berlin: Springer; 1998.
Kullback S, Leibler RA. On information and sufficiency. Ann Math Stat. 1951;22(1):79–86.
Gregory M, Thornhill N. The effects of aeration and agitation on the measurement of yeast biomass using a laser turbidity probe. Bioprocess Eng. 1997;16(6):339–44.
Acknowledgments
This study was funded by the German Federal Ministry of Education and Research (grant number 031B0475E) and the German Research Foundation (grant number BE 2245/17-1).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Published in the topical collection Advances in Process Analytics and Control Technology with guest editor Christoph Herwig.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Brunner, V., Klöckner, L., Kerpes, R. et al. Online sensor validation in sensor networks for bioprocess monitoring using swarm intelligence. Anal Bioanal Chem 412, 2165–2175 (2020). https://doi.org/10.1007/s00216-019-01927-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00216-019-01927-7