Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network

In this paper, an integrated data validation/reconstruction and fault diagnosis approach is proposed for critical infrastructure systems. The proposed methodology is implemented in a two-stage approach. In the first stage, sensor communication faults are detected and corrected, in order to facilitate a reliable dataset to perform system fault diagnosis in the second stage. On the one hand, sensor validation and reconstruction are based on the combined use of spatial and time series models. Spatial models take advantage of the (mass-balance) relation between different variables in the system, whilst time series models take advantage of the temporal redundancy of the measured variables by means of Holt-Winters time series models. On the other hand, fault diagnosis is based on the learning-in-model-space approach that is implemented by fitting a series of models using a series of signal segments selected with a sliding window. In this way, each signal segment can be represented by one model. To rigorously measure the 'distance' between models, the distance in the model space is defined. The deterministic reservoir computing approach is used to approximate a model with the input-output dynamics that exploits spatial-temporal correlations existing in the original data. Finally, the proposed approach is successfully applied to the Barcelona water network.

[1]  Peter Tiño,et al.  Minimum Complexity Echo State Network , 2011, IEEE Transactions on Neural Networks.

[2]  V. K. Kanakoudis,et al.  The role of leaks and breaks in water networks: technical and economical solutions , 2001 .

[3]  José Carlos Príncipe,et al.  Analysis and Design of Echo State Networks , 2007, Neural Computation.

[4]  Garrison W. Cottrell,et al.  2007 Special Issue: Learning grammatical structure with Echo State Networks , 2007 .

[5]  Santiago Espin,et al.  Methodology of a data validation and reconstructions tool to improve the realiability of the water network supervision , 2010 .

[6]  Domenico Cotroneo,et al.  Software Faults Diagnosis in Complex OTS Based Safety Critical Systems , 2008, 2008 Seventh European Dependable Computing Conference.

[7]  D Burnell.  Auto-validation of district meter data , 2003 .

[8]  Peter Tiño,et al.  Simple Deterministically Constructed Cycle Reservoirs with Regular Jumps , 2012, Neural Computation.

[9]  Vicenç Puig,et al.  Operational Predictive Optimal Control of Barcelona Water Transport Network , 2011 .

[10]  VerstraetenD.,et al.  2007 Special Issue , 2007 .

[11]  Paul G. Plöger,et al.  Model-Based Fault Diagnosis Techniques for Mobile Robots , 2016 .

[12]  P. Vanrolleghem,et al.  Real time control of urban wastewater systems: where do we stand today? , 2004 .

[13]  Peter R. Winters,et al.  Forecasting Sales by Exponentially Weighted Moving Averages , 1960 .

[14]  Magdalene Marinaki,et al.  Optimal Real-time Control of Sewer Networks , 2005 .

[15]  John G. Harris,et al.  Automatic speech recognition using a predictive echo state network classifier , 2007, Neural Networks.

[16]  Vasilis Kanakoudis,et al.  Pipe Networks Risk Assessment Based on Survival Analysis , 2011 .

[17]  Vicenç Puig,et al.  Validation and reconstruction of flow meter data in the Barcelona water distribution network , 2010 .

[18]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[19]  J.J. Steil,et al.  Backpropagation-decorrelation: online recurrent learning with O(N) complexity , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[20]  Vasilis Kanakoudis,et al.  Water pipe network reliability assessment using the DAC method , 2011 .

[21]  K M Tsang.  Sensor data validation using gray models. , 2003, ISA transactions.

[22]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[23]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[24]  Zehong Yang,et al.  Short-term stock price prediction based on echo state networks , 2009, Expert Syst. Appl..

[25]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[26]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[27]  Huanhuan Chen,et al.  Learning in the Model Space for Cognitive Fault Diagnosis , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies , 2003, Comput. Chem. Eng..

[29]  Peter Steen Mikkelsen,et al.  Quality control of rain data used for urban runoff systems , 1997 .

[30]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[31]  Danilo P. Mandic,et al.  An Augmented Echo State Network for Nonlinear Adaptive Filtering of Complex Noncircular Signals , 2011, IEEE Transactions on Neural Networks.

[32]  Simon Haykin,et al.  Decoupled echo state networks with lateral inhibition , 2007, Neural Networks.

[33]  Steven X. Ding,et al.  Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools , 2008 .

[34]  Peter Tiño,et al.  Predictive Modeling with Echo State Networks , 2008, ICANN.

[35]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.