Manuel Siegl, Dominik Geier, Björn Andreeßen, Sebastian Max, Esther Mose, Michael Zavrel, Thomas Becker
{"title":"数据同步技术及其对生物过程中自动重新校准软传感器预测性能的影响","authors":"Manuel Siegl, Dominik Geier, Björn Andreeßen, Sebastian Max, Esther Mose, Michael Zavrel, Thomas Becker","doi":"10.1007/s12257-024-00120-7","DOIUrl":null,"url":null,"abstract":"<p>Innovative soft sensor concepts can recalibrate automatically when the prediction performance decreases due to variations in raw materials, biological variability, and changes in process strategies. For automatic recalibration, data sets are selected from a data pool based on distance-based similarity criteria and then used for calibration. Nevertheless, the most appropriate data sets often are not reliably selected due to variances in the location of landmarks and process length of the bioprocesses. This can be overcome by synchronization methods that align the historical data sets with the current process and increase the accuracy of automatic selection and recalibration. This study investigated two different synchronization methods (dynamic time warping and curve registration) as preprocessing for the automatic selection of data sets using a distance-based similarity criterion for soft sensor recalibration. The prediction performance of the two soft sensors without synchronization was compared to the variants with synchronization and evaluated by comparing the normalized root mean squared errors. Curve registration improved the prediction performance on average by 24% (<i>Pichia pastoris</i>) and 9% (<i>Bacillus subtilis</i>). Using dynamic time warping, no substantial improvement in prediction performance could be achieved. A major factor behind this was the loss of information due to singularities caused by the changing process characteristics. The evaluation was performed on two target variables of real bioprocesses: biomass concentration prediction in <i>P. pastoris</i> and product concentration prediction in <i>B. subtilis</i>.</p>","PeriodicalId":8936,"journal":{"name":"Biotechnology and Bioprocess Engineering","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Data synchronization techniques and their impact on the prediction performance of automated recalibrated soft sensors in bioprocesses\",\"authors\":\"Manuel Siegl, Dominik Geier, Björn Andreeßen, Sebastian Max, Esther Mose, Michael Zavrel, Thomas Becker\",\"doi\":\"10.1007/s12257-024-00120-7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Innovative soft sensor concepts can recalibrate automatically when the prediction performance decreases due to variations in raw materials, biological variability, and changes in process strategies. For automatic recalibration, data sets are selected from a data pool based on distance-based similarity criteria and then used for calibration. Nevertheless, the most appropriate data sets often are not reliably selected due to variances in the location of landmarks and process length of the bioprocesses. This can be overcome by synchronization methods that align the historical data sets with the current process and increase the accuracy of automatic selection and recalibration. This study investigated two different synchronization methods (dynamic time warping and curve registration) as preprocessing for the automatic selection of data sets using a distance-based similarity criterion for soft sensor recalibration. The prediction performance of the two soft sensors without synchronization was compared to the variants with synchronization and evaluated by comparing the normalized root mean squared errors. Curve registration improved the prediction performance on average by 24% (<i>Pichia pastoris</i>) and 9% (<i>Bacillus subtilis</i>). Using dynamic time warping, no substantial improvement in prediction performance could be achieved. A major factor behind this was the loss of information due to singularities caused by the changing process characteristics. The evaluation was performed on two target variables of real bioprocesses: biomass concentration prediction in <i>P. pastoris</i> and product concentration prediction in <i>B. subtilis</i>.</p>\",\"PeriodicalId\":8936,\"journal\":{\"name\":\"Biotechnology and Bioprocess Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-06-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biotechnology and Bioprocess Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s12257-024-00120-7\",\"RegionNum\":4,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biotechnology and Bioprocess Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s12257-024-00120-7","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
创新的软传感器概念可在预测性能因原材料变化、生物变异和工艺策略变化而下降时自动重新校准。为实现自动重新校准,可根据基于距离的相似性标准从数据池中选择数据集,然后用于校准。然而,由于地标位置和生物过程的过程长度存在差异,通常无法可靠地选择最合适的数据集。同步方法可以克服这一问题,使历史数据集与当前流程保持一致,提高自动选择和重新校准的准确性。本研究调查了两种不同的同步方法(动态时间扭曲和曲线配准),作为使用基于距离的相似性标准自动选择数据集进行软传感器重新校准的预处理。通过比较归一化均方根误差,比较了两种无同步软传感器和有同步变体的预测性能。曲线注册使预测性能平均提高了 24%(Pichia pastoris)和 9%(枯草芽孢杆菌)。使用动态时间扭曲法,预测性能没有得到实质性提高。这背后的一个主要因素是由于过程特性变化造成的奇异性导致的信息损失。评估是在实际生物过程的两个目标变量上进行的:P. pastoris 的生物量浓度预测和 B. subtilis 的产物浓度预测。
Data synchronization techniques and their impact on the prediction performance of automated recalibrated soft sensors in bioprocesses
Innovative soft sensor concepts can recalibrate automatically when the prediction performance decreases due to variations in raw materials, biological variability, and changes in process strategies. For automatic recalibration, data sets are selected from a data pool based on distance-based similarity criteria and then used for calibration. Nevertheless, the most appropriate data sets often are not reliably selected due to variances in the location of landmarks and process length of the bioprocesses. This can be overcome by synchronization methods that align the historical data sets with the current process and increase the accuracy of automatic selection and recalibration. This study investigated two different synchronization methods (dynamic time warping and curve registration) as preprocessing for the automatic selection of data sets using a distance-based similarity criterion for soft sensor recalibration. The prediction performance of the two soft sensors without synchronization was compared to the variants with synchronization and evaluated by comparing the normalized root mean squared errors. Curve registration improved the prediction performance on average by 24% (Pichia pastoris) and 9% (Bacillus subtilis). Using dynamic time warping, no substantial improvement in prediction performance could be achieved. A major factor behind this was the loss of information due to singularities caused by the changing process characteristics. The evaluation was performed on two target variables of real bioprocesses: biomass concentration prediction in P. pastoris and product concentration prediction in B. subtilis.
期刊介绍:
Biotechnology and Bioprocess Engineering is an international bimonthly journal published by the Korean Society for Biotechnology and Bioengineering. BBE is devoted to the advancement in science and technology in the wide area of biotechnology, bioengineering, and (bio)medical engineering. This includes but is not limited to applied molecular and cell biology, engineered biocatalysis and biotransformation, metabolic engineering and systems biology, bioseparation and bioprocess engineering, cell culture technology, environmental and food biotechnology, pharmaceutics and biopharmaceutics, biomaterials engineering, nanobiotechnology, and biosensor and bioelectronics.