Gradient-based Fault Isolation 
Residual-based Fault Detection Systems 
Francisco Serdio Fernández 
Department of Knowledge-Based Mathematical Systems 
Johannes Kepler University Linz, Austria 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
for 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 Why Fault Isolation (FI) ? 
 FD with Residual-based approaches 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more ? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
Why Fault Detection? 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Why Fault Detection? 
 Products with high quality demands 
 High quality is required also in the production chain 
 High quality is required also in the supply chain 
[1] D. Blanchard. Supply Chain Management Best Practices. John Wiley & Sons, 
Hoboken, NJ, USA, 2007. 
 Continuity in the production lines 
 Minimum down-time 
[2] R. Iserman. Fault-Diagnosis Applications. Model-Based Condition Monitoring: 
Actuators, Drives, Machinery, Plants, Sensors, and Fault-tolerant Systems. Springer, 
Berlin Heidelberg, Germany, 2011. 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 High quality processes imply 
http://www.flll.Francisco Serdio jku.at/staff/francisco
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
Why Fault Detection? 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Manual supervision is not affordable or in some 
cases simply impossible 
 The precision of manual supervision usually depends 
 on the experience of the operators 
 and even on their performance on a given day 
[3] E. Lughofer, J.E. Smith, P. Caleb-Solly, M. Tahir, C. Eitzinger, D. Sannen and M. 
Nuttin. (2009). Human-machine interaction issues in quality control based on on-line 
image classication. IEEE Transactions on Systems, Man and Cybernetics, part A: 
Systems and Humans, 39(5), 960-971. 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
Why Fault Detection? 
 Manual process supervision 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 Why Fault Isolation (FI) ? 
 FD with Residual-based approaches 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more ? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Fault Isolation 
Detection 
Needle 
Needle !! 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
Why Fault Isolation? 
Haystack 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Why Fault Isolation? 
 Multiple sensor networks turned out to emerge 
in industrial settings and factories 
 Huge amount of sensors and actuators to check 
 Manual supervision is not affordable or in some 
cases simply impossible 
 Any valuable information regarding where the fault 
is 
located could be a great aid for the operator 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
  Isolation ! 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 Why Fault Isolation (FI) ? 
 FD with Residual-based approaches 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more ? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
FD with Residual-based approaches 
 Algebraic relationships among different sensors 
 Difference relationships among different sensor 
outputs and actuator inputs 
 Inconsistencies, expressed as residuals, can be 
used for detection and isolation purposes 
[4] V. Venkatasubramanian, R. Rengaswamy, S. Kavuri and K. Yin. (2003). A review of 
process fault detection and diagnosis: Part iii: Process history based methods. 
Computers & Chemical Engineering, 27(3), 327-346. 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 Analytical Redundancy 
 Direct redundancy 
 Temporal redundancy 
http://www.flll.Francisco Serdio jku.at/staff/francisco
FD with Residual-based approaches 
Analytical Redundancy graphically 
Moving from the signal space to the residual space: illustrating an untypical signal pattern 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Tracking residuals within a dynamic tolerance band 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Recall FD with Residual-based 
approaches 
 More information regarding Fault Detection in 
[5] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger and H. Efendic, Data-Driven Residual-Based 
Fault Detection for Condition Monitoring in Rolling Mills. Proceedings of the IFAC Conference on 
Manufacturing Modeling, Management and Control, MIM '2013, St. Petersburg, Russia, 2013, pp. 
1546-1551. (Winner of MIM 2013 Best paper award) 
[6] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger, and H. Efendic, Residual-based Fault Detection 
using Soft Computing techniques for Condition Monitoring at Rolling Mills. Information Sciences, 
vol. 259, pp. 304–330, 2014. 
[7] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger, M. Pichler and H. Efendic, Multivariate Fault 
Detection using Vector Autoregressive Moving Average and Orthogonal Transformation in the 
residual Space. Annual Conference of the Prognostics and Health Management Society, PHM 2013, 
New Orleans, LA, USA, 2013, pp. 548-555. 
[8] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger, and H. Efendic, Fault Detection in Multisensor 
Networks based on Multivariate Time-series Models and Orthogonal Transformations. 
Information Fusion, vol. under revision (minor), 2014. 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 Recall FD with Residual-based approaches 
 Why Fault Isolation (FI) ? 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Motivation of the FI Gradient-based 
approaches 
 We are blind about faults 
 We do not know how a fault looks like 
 We do not have fault patterns (labeled data) 
 Process variable contribution plot 
 There is an extension to non-linear PCA 
 It reverts back to the original process variables 
[9] P. Miller, R. Swanson, and C. Heckler, Contribution plots: A missing link in multivariate quality 
control. Applied Mathematics and Computer Science, vol. 8, p. 775792, 1998. 
[10] F. Jia, E. Martin, and A. Morris, Nonlinear principal components analysis with application to 
process fault detection. International Journal of Systems Science, vol. 31, p. 14731487, 2001. 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 There is literature about PCA 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Motivation of the FI Gradient-based 
approaches 
 Partial derivatives ! 
 With respect to a specific dimension can indicate the 
relative importance of the corresponding variable 
(channel) on that function 
 Can be computed according to the model expression 
 Can be computed by means of numeric tricks 
 We can plug a FI system to any FD model ! 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Motivation of the FI Gradient-based 
approaches 
 How do we revert back to the original process 
variables? 
 We compute the gradients of the model variables 
 We aggregate the gradients 
 We get a candidate responsible variable 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 We take the warning models 
 Crisp decision 
 Fuzzy decision 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Aggregating gradients 
 Biggest gradient as faulty channel 
 A channel is either (properly) isolated or not 
 Several channels are proposed as faulty 
 There are normalized against the channel with the 
highest gradient aggregation 
 By definition, it will produce always better results than 
its crisp counterpart 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 Crisp decision 
 Winner takes all approach 
 Fuzzy decision 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 FD with Residual-based approaches 
 Why Fault Isolation (FI) ? 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more ? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Tools to depict Fault Isolation 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 FD with Residual-based approaches 
 Why Fault Isolation (FI) ? 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
Results 
http://www.flll.Francisco Serdio jku.at/staff/francisco
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
Results 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 FD with Residual-based approaches 
 Why Fault Isolation (FI) ? 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more ? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Can do we more ? 
 We must work in how to aggregate the 
gradients 
 Weight the gradients with other data 
 We are using violation degree of the threshold 
 We are using quality of the model 
 Goal: narrow the Fault Isolation Gap (FIG) 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 Time frames (sliding windows) 
http://www.flll.Francisco Serdio jku.at/staff/francisco
 Why Fault Detection (FD) ? 
 FD with Residual-based approaches 
 Why Fault Isolation (FI) ? 
 Motivation of the FI Gradient-based approaches 
 Tools to depict Fault Isolation 
 Results 
 Can do we more ? 
 Conclusions 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Conclusions 
 We can perform Fault Isolation (FI) without 
information about the faults 
 Only based on warning models and gradients 
 We have introduced new tools to depict FI 
 We must still strength the results 
WCCI 2014 / July 6-11 / Beijing, China 
francisco.serdio@jku.at 
 Graphically 
 Numerically 
http://www.flll.Francisco Serdio jku.at/staff/francisco
Thanks a lot for your attention! 
WCCI 2014 / July 6-11 / Beijing, China 
{francisco.serdio,edwin.lughofer}@jku.at 
http://www.flll.jku.at/staff/{Francisco Serdio, Dr. Edwin Lughofer francisco,lughofer}

IEEE WCCI 2014

  • 1.
    Gradient-based Fault Isolation Residual-based Fault Detection Systems Francisco Serdio Fernández Department of Knowledge-Based Mathematical Systems Johannes Kepler University Linz, Austria WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at for http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 2.
     Why FaultDetection (FD) ?  Why Fault Isolation (FI) ?  FD with Residual-based approaches  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more ?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 3.
    WCCI 2014 /July 6-11 / Beijing, China francisco.serdio@jku.at Why Fault Detection? http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 4.
    Why Fault Detection?  Products with high quality demands  High quality is required also in the production chain  High quality is required also in the supply chain [1] D. Blanchard. Supply Chain Management Best Practices. John Wiley & Sons, Hoboken, NJ, USA, 2007.  Continuity in the production lines  Minimum down-time [2] R. Iserman. Fault-Diagnosis Applications. Model-Based Condition Monitoring: Actuators, Drives, Machinery, Plants, Sensors, and Fault-tolerant Systems. Springer, Berlin Heidelberg, Germany, 2011. WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  High quality processes imply http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 5.
    WCCI 2014 /July 6-11 / Beijing, China francisco.serdio@jku.at Why Fault Detection? http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 6.
     Manual supervisionis not affordable or in some cases simply impossible  The precision of manual supervision usually depends  on the experience of the operators  and even on their performance on a given day [3] E. Lughofer, J.E. Smith, P. Caleb-Solly, M. Tahir, C. Eitzinger, D. Sannen and M. Nuttin. (2009). Human-machine interaction issues in quality control based on on-line image classication. IEEE Transactions on Systems, Man and Cybernetics, part A: Systems and Humans, 39(5), 960-971. WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at Why Fault Detection?  Manual process supervision http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 7.
     Why FaultDetection (FD) ?  Why Fault Isolation (FI) ?  FD with Residual-based approaches  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more ?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 8.
    Fault Isolation Detection Needle Needle !! WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at Why Fault Isolation? Haystack http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 9.
    Why Fault Isolation?  Multiple sensor networks turned out to emerge in industrial settings and factories  Huge amount of sensors and actuators to check  Manual supervision is not affordable or in some cases simply impossible  Any valuable information regarding where the fault is located could be a great aid for the operator WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at   Isolation ! http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 10.
     Why FaultDetection (FD) ?  Why Fault Isolation (FI) ?  FD with Residual-based approaches  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more ?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 11.
    FD with Residual-basedapproaches  Algebraic relationships among different sensors  Difference relationships among different sensor outputs and actuator inputs  Inconsistencies, expressed as residuals, can be used for detection and isolation purposes [4] V. Venkatasubramanian, R. Rengaswamy, S. Kavuri and K. Yin. (2003). A review of process fault detection and diagnosis: Part iii: Process history based methods. Computers & Chemical Engineering, 27(3), 327-346. WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  Analytical Redundancy  Direct redundancy  Temporal redundancy http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 12.
    FD with Residual-basedapproaches Analytical Redundancy graphically Moving from the signal space to the residual space: illustrating an untypical signal pattern WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 13.
    Tracking residuals withina dynamic tolerance band WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 14.
    Recall FD withResidual-based approaches  More information regarding Fault Detection in [5] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger and H. Efendic, Data-Driven Residual-Based Fault Detection for Condition Monitoring in Rolling Mills. Proceedings of the IFAC Conference on Manufacturing Modeling, Management and Control, MIM '2013, St. Petersburg, Russia, 2013, pp. 1546-1551. (Winner of MIM 2013 Best paper award) [6] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger, and H. Efendic, Residual-based Fault Detection using Soft Computing techniques for Condition Monitoring at Rolling Mills. Information Sciences, vol. 259, pp. 304–330, 2014. [7] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger, M. Pichler and H. Efendic, Multivariate Fault Detection using Vector Autoregressive Moving Average and Orthogonal Transformation in the residual Space. Annual Conference of the Prognostics and Health Management Society, PHM 2013, New Orleans, LA, USA, 2013, pp. 548-555. [8] F. Serdio, E. Lughofer, K. Pichler, T. Buchegger, and H. Efendic, Fault Detection in Multisensor Networks based on Multivariate Time-series Models and Orthogonal Transformations. Information Fusion, vol. under revision (minor), 2014. WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 15.
     Why FaultDetection (FD) ?  Recall FD with Residual-based approaches  Why Fault Isolation (FI) ?  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 16.
    Motivation of theFI Gradient-based approaches  We are blind about faults  We do not know how a fault looks like  We do not have fault patterns (labeled data)  Process variable contribution plot  There is an extension to non-linear PCA  It reverts back to the original process variables [9] P. Miller, R. Swanson, and C. Heckler, Contribution plots: A missing link in multivariate quality control. Applied Mathematics and Computer Science, vol. 8, p. 775792, 1998. [10] F. Jia, E. Martin, and A. Morris, Nonlinear principal components analysis with application to process fault detection. International Journal of Systems Science, vol. 31, p. 14731487, 2001. WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  There is literature about PCA http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 17.
    Motivation of theFI Gradient-based approaches  Partial derivatives !  With respect to a specific dimension can indicate the relative importance of the corresponding variable (channel) on that function  Can be computed according to the model expression  Can be computed by means of numeric tricks  We can plug a FI system to any FD model ! WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 18.
    Motivation of theFI Gradient-based approaches  How do we revert back to the original process variables?  We compute the gradients of the model variables  We aggregate the gradients  We get a candidate responsible variable WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  We take the warning models  Crisp decision  Fuzzy decision http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 19.
    Aggregating gradients Biggest gradient as faulty channel  A channel is either (properly) isolated or not  Several channels are proposed as faulty  There are normalized against the channel with the highest gradient aggregation  By definition, it will produce always better results than its crisp counterpart WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  Crisp decision  Winner takes all approach  Fuzzy decision http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 20.
     Why FaultDetection (FD) ?  FD with Residual-based approaches  Why Fault Isolation (FI) ?  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more ?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 21.
    Tools to depictFault Isolation WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 22.
     Why FaultDetection (FD) ?  FD with Residual-based approaches  Why Fault Isolation (FI) ?  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 23.
    WCCI 2014 /July 6-11 / Beijing, China francisco.serdio@jku.at Results http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 24.
    WCCI 2014 /July 6-11 / Beijing, China francisco.serdio@jku.at Results http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 25.
     Why FaultDetection (FD) ?  FD with Residual-based approaches  Why Fault Isolation (FI) ?  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more ?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 26.
    Can do wemore ?  We must work in how to aggregate the gradients  Weight the gradients with other data  We are using violation degree of the threshold  We are using quality of the model  Goal: narrow the Fault Isolation Gap (FIG) WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  Time frames (sliding windows) http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 27.
     Why FaultDetection (FD) ?  FD with Residual-based approaches  Why Fault Isolation (FI) ?  Motivation of the FI Gradient-based approaches  Tools to depict Fault Isolation  Results  Can do we more ?  Conclusions WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 28.
    Conclusions  Wecan perform Fault Isolation (FI) without information about the faults  Only based on warning models and gradients  We have introduced new tools to depict FI  We must still strength the results WCCI 2014 / July 6-11 / Beijing, China francisco.serdio@jku.at  Graphically  Numerically http://www.flll.Francisco Serdio jku.at/staff/francisco
  • 29.
    Thanks a lotfor your attention! WCCI 2014 / July 6-11 / Beijing, China {francisco.serdio,edwin.lughofer}@jku.at http://www.flll.jku.at/staff/{Francisco Serdio, Dr. Edwin Lughofer francisco,lughofer}