View in EDS

Soft-sensing for compressor test time reduction with time-delay neural networks.

Saved in:
Bibliographic Details
Title: Soft-sensing for compressor test time reduction with time-delay neural networks.
Authors: Schwedersky, Bernardo B.1 (AUTHOR) bernardo@inf.ufpel.edu.br, Flesch, Rodolfo C.C.1,2 (AUTHOR) rodolfo.flesch@ufsc.br, Machado, João P.Z.2 (AUTHOR) joao.zomer.m@posgrad.ufsc.br, Nascimento, Ahryman S.B.2 (AUTHOR) a.nascimento@labmetro.ufsc.br, Schaefer, Maurício M.3 (AUTHOR) mauricio.m.schaefer@nidec-ga.com, Moser, Diogo R.3 (AUTHOR) diogo.r.moser@nidec-ga.com
Source: ISA Transactions. Jul2026, Vol. 174, p287-297. 11p.
Subjects: Artificial neural networks, Compressor performance, Machine learning, Prediction models, Industrial applications
Abstract: This study proposes a soft-sensor-based method to significantly shorten compressor performance evaluation tests and presents the results of its industrial application over five years by a compressor manufacturer. Traditional approaches demand long testing times to reach steady-state conditions, with overall test durations frequently surpassing two hours. In this work, a soft sensor based on a time-delay neural network (TDNN) was developed to monitor steady-state conditions of key performance parameters – cooling capacity, power consumption, and coefficient of performance – and to predict their final values. A dataset of 392 compressor evaluations was used for model development, and the proposed method achieved an overall reduction in test duration of close to 50%. This is accomplished because the proposed method incorporates a soft-sensing approach, trained on historical data, facilitating early detection of steady-state conditions and accelerating testing procedures. During five years of real industrial application, with the proposed approach tested in 9184 performance evaluations, this method demonstrated a 55% improvement in total test time, with more than 95% of the tests showing prediction errors below 2%. Therefore, the proposed tools resulted in consistent time savings and increased operational efficiency during their industrial evaluation. • A soft-sensing framework using time-delay neural networks is proposed. • It monitors steady-state conditions and predicts performance variables of compressors. • A 55% reduction in compressor testing time was achieved in industrial applications. • Prediction errors below 2% were observed in 95% of the tests. • Validated over five years on 9184 real-world compressor evaluations. [ABSTRACT FROM AUTHOR]
Copyright of ISA Transactions is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 194396210
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Soft-sensing for compressor test time reduction with time-delay neural networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Schwedersky%2C+Bernardo+B%2E%22">Schwedersky, Bernardo B.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> bernardo@inf.ufpel.edu.br</i><br /><searchLink fieldCode="AR" term="%22Flesch%2C+Rodolfo+C%2EC%2E%22">Flesch, Rodolfo C.C.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> rodolfo.flesch@ufsc.br</i><br /><searchLink fieldCode="AR" term="%22Machado%2C+João+P%2EZ%2E%22">Machado, João P.Z.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> joao.zomer.m@posgrad.ufsc.br</i><br /><searchLink fieldCode="AR" term="%22Nascimento%2C+Ahryman+S%2EB%2E%22">Nascimento, Ahryman S.B.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> a.nascimento@labmetro.ufsc.br</i><br /><searchLink fieldCode="AR" term="%22Schaefer%2C+Maurício+M%2E%22">Schaefer, Maurício M.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> mauricio.m.schaefer@nidec-ga.com</i><br /><searchLink fieldCode="AR" term="%22Moser%2C+Diogo+R%2E%22">Moser, Diogo R.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> diogo.r.moser@nidec-ga.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22ISA+Transactions%22">ISA Transactions</searchLink>. Jul2026, Vol. 174, p287-297. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Compressor+performance%22">Compressor performance</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Industrial+applications%22">Industrial applications</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study proposes a soft-sensor-based method to significantly shorten compressor performance evaluation tests and presents the results of its industrial application over five years by a compressor manufacturer. Traditional approaches demand long testing times to reach steady-state conditions, with overall test durations frequently surpassing two hours. In this work, a soft sensor based on a time-delay neural network (TDNN) was developed to monitor steady-state conditions of key performance parameters – cooling capacity, power consumption, and coefficient of performance – and to predict their final values. A dataset of 392 compressor evaluations was used for model development, and the proposed method achieved an overall reduction in test duration of close to 50%. This is accomplished because the proposed method incorporates a soft-sensing approach, trained on historical data, facilitating early detection of steady-state conditions and accelerating testing procedures. During five years of real industrial application, with the proposed approach tested in 9184 performance evaluations, this method demonstrated a 55% improvement in total test time, with more than 95% of the tests showing prediction errors below 2%. Therefore, the proposed tools resulted in consistent time savings and increased operational efficiency during their industrial evaluation. • A soft-sensing framework using time-delay neural networks is proposed. • It monitors steady-state conditions and predicts performance variables of compressors. • A 55% reduction in compressor testing time was achieved in industrial applications. • Prediction errors below 2% were observed in 95% of the tests. • Validated over five years on 9184 real-world compressor evaluations. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of ISA Transactions is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194396210
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.isatra.2026.02.004
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 287
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Compressor performance
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Industrial applications
        Type: general
    Titles:
      – TitleFull: Soft-sensing for compressor test time reduction with time-delay neural networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Schwedersky, Bernardo B.
      – PersonEntity:
          Name:
            NameFull: Flesch, Rodolfo C.C.
      – PersonEntity:
          Name:
            NameFull: Machado, João P.Z.
      – PersonEntity:
          Name:
            NameFull: Nascimento, Ahryman S.B.
      – PersonEntity:
          Name:
            NameFull: Schaefer, Maurício M.
      – PersonEntity:
          Name:
            NameFull: Moser, Diogo R.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 00190578
          Numbering:
            – Type: volume
              Value: 174
          Titles:
            – TitleFull: ISA Transactions
              Type: main
ResultId 1