STAMM: Soft sensor moniToring and mAintenance framework for Machine learning Models

Artificial intelligence (AI) and machine learning (ML) models as well as Digital shadows and Digital twins as well as Digital shadows and Digital twins have been, and are being, developed for a variety of applications, including industrial process supervision, bioprocess optimization, energy management, and environmental monitoring. In cases where models have the aim to classify, predict, or forecast a variable of interest then these models must become deployable in real-time so that their ...

Programme: Bioindustry 4.0

Public web page: https://stamm.inrae.fr

Soft sensor: Cubist Regresion

Model Identification

Cubist is a rule-based model that is an extension of Quinlan’s M5 model tree. A tree is grown where the terminal leaves contain linear regression models. These models are based on the predictors used in previous splits. This soft sensor ML (version V.1.0) has the ID 0003[R]penicillinCUBIST. Its authors are Acosta-Pavas, J. C., Robles-Rodriguez, C. E., Griol, D., Daboussi, F., Aceves-Lara, C. A., & Corrales, D. C., and it is associated with the publication available ...

Creator: David Camilo Corrales

Submitter: David Camilo Corrales

Towards a machine learning operations (MLOps) soft sensor for real-time predictions in industrial-scale fed-batch fermentation

Abstract (Expand)

Real-time predictions in fermentation processes are crucial because they enable continuous monitoring and control of bioprocessing. However, the availability of online measurements is limited by the … availability and feasibility of sensing technology. Soft sensors - or software sensors that convert available measurements into measurements of interest (product yield, quality, etc.) - have the potential to improve efficiency and product quality. Machine learning (ML) based soft sensors have gained increased popularity over the years since they can incorporate variables that are measured in real-time, and exploit the intricate patterns embedded in such voluminous datasets. However, ML-based soft sensor requires more than just a classical ML learner with an unseen test set to evaluate the quality prediction of the model. When a ML model is deployed in production, its performance can deteriorate rapidly leading to an unanticipated decline in the quality of the output and predictions. Here a proof concept of Machine Learning Operations (MLOps) to automate the end-to-end soft sensor lifecycle in industrial scale fed-batch fermentation, from development and deployment to maintenance and monitoring is proposed. Using the industrial-scale penicillin fermentation (IndPenSim) dataset that includes 100 fermentation batches, to build a soft sensor based on Long Short Term Memory (LSTM) for penicillin concentration prediction. The batches containing deviations in the processes (91–100) were used to assess concept drift of the LSTM soft sensor. The evaluation of concept drift is evidenced by the soft sensor performance falling below the set threshold based on the Population Stability Index (PSI), which automatically triggers an alert to run the retraining pipeline.

Authors: Brett Metcalfe, Juan Camilo Acosta-Pavas, Carlos Eduardo Robles-Rodriguez, George K. Georgakilas, Theodore Dalamagas, Cesar Arturo Aceves-Lara, Fayza Daboussi, Jasper J Koehorst, David Camilo Corrales

Date Published: 1st Mar 2025

Publication Type: Journal

Powered by
 (v.1.17.2)
About IBISBA | About IBISBA Knowledge Hub | Funding and Programmes | Credits | Terms & Conditions
Copyright © 2008 - 2025 The University of Manchester and HITS gGmbH
IBISBA is a pan-European research infrastructure currently funded through multiple EU projects: IBISBA 1.0 (H2020 grant agreement No. 730976), PREP-IBISBA (H2020 grant agreement No. 871118) and the follow-on project IBISBA-DIALS (grant agreement No. 101131085) and BIOINDUSTRY 4.0 (Grant agreement No. 101094287). Registering data or other knowledge assets on this platform is the sole responsibility of Users. IBISBA cannot be held responsible for misuse or misappropriation of data and assets belonging to a Third Party.