Reinforcement Learning of Optimal Input Excitation for Parameter Estimation With Application to Li-Ion Battery

Huang, Rui; Fogelquist, Jackson; Lin, Xinfan

doi:10.1109/tii.2023.3244342

Cited by 6 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When starting with model-assisted process development for a new product, the underlying process model needs to be trained with initial data, sometimes referred to as excitation design (De Luca et al, 2023;Ferreira et al, 2014;Huang et al, 2023). Traditionally, this design is either determined by methods of DoE such as a full or fractional factorial design (Freier et al, 2016) or space-filling designs such as LHS (Bader et al, 2023), Doehlert Designs (Pinto et al, 2019) and Sobol sequences (Siedentop et al, 2023).…”

Section: Calibration Design For Parallel Experimentsmentioning

confidence: 99%

Calibration design for pharmaceutical bioprocesses: A novel approach for knowledge transfer in Design of Experiments

Helleckes,

Wirnsperger,

Polak

et al. 2024

Preprint

View full text Add to dashboard Cite

Modern machine learning methods, and their use alongside established paradigms such as Quality by Design, have the potential to fundamentally change the way bioprocesses are developed. In particular, horizontal knowledge transfer methods, which seek to exploit data from historical processes to facilitate process development for a new product, provide an opportunity to rethink process development workflows. In this work, we firstly assess the potential of two knowledge transfer approaches, meta learning and one-hot encoding, in combination with Gaussian process (GP) models. We compare their performance to GPs developed only on data of the new process. Using simulated mammalian cell cultivation data, we observe that both knowledge transfer approaches outperform the individual-product approach. In the second part, we address the question whether experiments for a new product could be designed more effectively by exploiting existing knowledge. In particular, we suggest to specifically design few runs for the novel product to calibrate knowledge transfer models, a task that we coin calibration design. We propose a novel, customised metric to identify a set of calibration design runs, which exploits differences in process evolutions of historical products. In two simulated case studies, we observed that training with calibration designs yields similar test set errors compared to common approaches of Design of Experiments. However, much fewer experiments are needed for the former, suggesting an interesting alternative for future bioprocess development. Overall, the results suggest that process development could be significantly streamlined when systematically carrying knowledge from one product to the next.

show abstract

Section: Calibration Design For Parallel Experimentsmentioning

confidence: 99%

Calibration design for pharmaceutical bioprocesses: A novel approach for knowledge transfer in Design of Experiments

Helleckes,

Wirnsperger,

Polak

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…For the development of these models, a series of process runs are executed, referred to as excitation design. [40,57,58] Traditionally, the excitation design is either determined by methods of DoE such as a full or fractional factorial designs, [34,59] or space-filling designs such as LHS, [60] Doehlert Designs, [36] or Sobol sequences. [61] Irrespective of the design, these activities typically require the execution of several tens of runs before moving to larger scales.…”

Section: How Could Calibration Designs Change Process Development Wor...mentioning

confidence: 99%

Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses

Helleckes,

Wirnsperger,

Polak

et al. 2024

Biotechnology Journal

View full text Add to dashboard Cite

Modern machine learning has the potential to fundamentally change the way bioprocesses are developed. In particular, horizontal knowledge transfer methods, which seek to exploit data from historical processes to facilitate process development for a new product, provide an opportunity to rethink current workflows. In this work, we first assess the potential of two knowledge transfer approaches, meta learning and one‐hot encoding, in combination with Gaussian process (GP) models. We compare their performance with GPs trained only on data of the new process, that is, local models. Using simulated mammalian cell culture data, we observe that both knowledge transfer approaches exhibit test set errors that are approximately halved compared to those of the local models when two, four, or eight experiments of the new product are used for training. Subsequently, we address the question whether experiments for a new product could be designed more effectively by exploiting existing knowledge. In particular, we suggest to specifically design a few runs for the novel product to calibrate knowledge transfer models, a task that we coin calibration design. We propose a customized objective function to identify a set of calibration design runs, which exploits differences in the process evolution of historical products. In two simulated case studies, we observed that training with calibration designs yields similar test set errors compared to common design of experiments approaches. However, the former requires approximately four times fewer experiments. Overall, the results suggest that process development could be significantly streamlined when systematically carrying knowledge from one product to the next.

show abstract

A Non-dimensional Input Excitation Optimization Approach for Battery Health Parameter Estimation

Huang,

Fogelquist,

Kuang

et al. 2023

IFAC-PapersOnLine

View full text Add to dashboard Cite

Reinforcement Learning of Optimal Input Excitation for Parameter Estimation With Application to Li-Ion Battery

Cited by 6 publications

References 30 publications

Calibration design for pharmaceutical bioprocesses: A novel approach for knowledge transfer in Design of Experiments

Calibration design for pharmaceutical bioprocesses: A novel approach for knowledge transfer in Design of Experiments

Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses

A Non-dimensional Input Excitation Optimization Approach for Battery Health Parameter Estimation

Contact Info

Product

Resources

About