An efficient online wkNN diagnostic strategy for variable refrigerant flow system based on coupled feature selection method

Abstract The refrigerant leakage would occur in a multi-split variable refrigerant flow (VRF) system after years of operation, thus contributing to the inefficient operation and even increased energy consumption. Diagnosing the refrigerant charge amount (RCA) malfunction in time is of great necessity to ensure the normal operation of VRF system and avoid superfluous energy waste. This paper proposes an efficient online weighted k-Nearest-Neighbor model (wkNN) strategy to diagnose the RCA malfunction of the VRF system, which is based on the coupled feature selection method. The minimal-redundancy-maximal-relevance (mRMR) algorithm is first applied to derive the subset of features that have the maximum correlation with the target category and the minimum redundancy among each other. The ReliefF algorithm is utilized to rank variables in descending order. Final variables importance is ascertained on the basis of the average weighs of importance of variables and contributions of variables to the model's classification error rate. Correlation analysis (CA) is implemented to verify the rationality of the selected variables. Finally, a subset of six variables is served as the input variables to establish three kinds of models. Results indicate that the coupled feature selection method outperforms the single feature selection method, and the proposed wkNN model based on the coupled feature selection method is superior to the other two models and achieves desirable diagnostic performance on both experimental and practical data.

[1]  Marko Robnik-Sikonja,et al.  Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF , 2004, Applied Intelligence.

[2]  Jiong Li,et al.  Extending the virtual refrigerant charge sensor (VRC) for variable refrigerant flow (VRF) air conditioning system using data-based analysis methods , 2016 .

[3]  Nam-Ho Kyong,et al.  Subsystem level fault diagnosis of a building's air-handling unit using general regression neural networks , 2004 .

[4]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[5]  Dimitris Kanellopoulos,et al.  Data Preprocessing for Supervised Leaning , 2007 .

[6]  Jin Wen,et al.  A model-based fault detection and diagnostic methodology based on PCA method and wavelet transform , 2014 .

[7]  James A. Anderson,et al.  An Introduction To Neural Networks , 1998 .

[8]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[9]  Luis Pérez-Lombard,et al.  A review on buildings energy consumption information , 2008 .

[10]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  R. Samworth.  Optimal weighted nearest neighbour classifiers , 2011, 1101.5783.

[12]  Shengwei Wang,et al.  A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression , 2013 .

[13]  Jin Wen,et al.  Diagnostic Bayesian networks for diagnosing air handling units faults – part I: Faults in dampers, fans, filters and sensors , 2017 .

[14]  Tolga N. Aynur,et al.  Variable refrigerant flow systems: A review , 2010 .

[15]  Philippe Renevey,et al.  SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in Brain-Computer Interfaces , 2005, Signal Process..

[16]  Steven T. Bushby,et al.  A rule-based fault detection method for air handling units , 2006 .

[17]  Leslie K. Norford,et al.  Robust model-based fault diagnosis for air handling units , 2015 .

[18]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[19]  Wei Liu,et al.  A principle component analysis-based random forest with the potential nearest neighbor method for automobile insurance fraud identification , 2017, Appl. Soft Comput..

[20]  Zehong Yang,et al.  A novel hybrid feature selection algorithm: using ReliefF estimation for GA-Wrapper search , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[21]  Seo Young Kim,et al.  Indoor unit fault detector for a multi-split VRF system in heating mode , 2014 .

[22]  José Hernández-Orallo,et al.  Volume under the ROC Surface for Multi-class Problems , 2003, ECML.

[23]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[24]  James E. Braun,et al.  A Methodology for Diagnosing Multiple Simultaneous Faults in Vapor-Compression Air Conditioners , 2007 .

[25]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[26]  Larry A. Rendell,et al.  The Feature Selection Problem: Traditional Methods and a New Algorithm , 1992, AAAI.

[27]  Reinhard Radermacher,et al.  Simulation of a VAV air conditioning system in an existing building for the cooling mode , 2009 .

[28]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[29]  Michal Jakubczyk,et al.  A framework for sensitivity analysis of decision trees , 2017, Central European Journal of Operations Research.