Online sensor validation in sensor networks for bioprocess monitoring using swarm intelligence

• Published in: Analytical and bioanalytical chemistry Vol. 412; no. 9; pp. 2165 - 2175
• Main Authors: Brunner, Vincent, Klöckner, Lukas, Kerpes, Roland, Geier, Dominik Ulrich, Becker, Thomas
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2020; Springer; Springer Nature B.V
• Subjects: Advances in Process Analytics and Control Technology; Algorithms; Analysis; Analytical Chemistry; Artificial Intelligence; Batch Cell Culture Techniques - instrumentation; Batch processes; Batch processing; Biochemistry; bioprocessing; Bioreactors; Biosensing Techniques - instrumentation; Characterization and Evaluation of Materials; Chemistry; Chemistry and Materials Science; Control systems; Divergence; Equipment Design; Error detection; Fault detection; Food Science; Intelligence; Internet; Laboratory Medicine; Mathematical optimization; Models, Biological; Monitoring; Monitoring/Environmental Analysis; On-line systems; Particle swarm optimization; Pichia pastoris; prediction; Prediction models; Process control; Process controls; processing time; Quality management; Regularization; Research Paper; Saccharomycetales - cytology; Saccharomycetales - metabolism; Sensors; Swarm intelligence; swarms; Time dependence; Turbidity; Yeast; Germany; Sensor fault; Sensor network; Fault detection; Online validation; Particle swarm optimization
• ISSN: 1618-2642; 1618-2650; 1618-2650
• DOI: 10.1007/s00216-019-01927-7

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.