Fault detection of excavator’s hydraulic system based on dynamic principal component analysis

Abstract

In order to improve reliability of the excavator’s hydraulic system, a fault detection approach based on dynamic principal component analysis(PCA) was proposed. Dynamic PCA is an extension of PCA, which can effectively extract the dynamic relations among process variables. With this approach, normal samples were used as training data to develop a dynamic PCA model in the first step. Secondly, the dynamic PCA model decomposed the testing data into projections to the principal component subspace(PCS) and residual subspace(RS). Thirdly, T² statistic and Q statistic performed as indexes of fault detection in PCS and RS, respectively. Several simulated faults were introduced to validate the approach. The results show that the dynamic PCA model developed is able to detect overall faults by using T² statistic and Q statistic. By simulation analysis, the proposed approach achieves an accuracy of 95% for 20 test sample sets, which shows that the fault detection approach can be effectively applied to the excavator’s hydraulic system.

Keywords

hydraulic system / excavator / fault detection / principal component analysis / multivariate statistics

References

[1] HeQ.-h., ZhangD.-q., HaoP., ZhuJ.-xin.. Model and experimental research on control of hydraulic excavator’s manipulator [J]. Journal of Central South University: Science and Technology, 2006, 37(3): 542-546

[2] LattinJ. M., CarrollJ. D., GreeenP. E.Analyzing multivariate data [M], 2003, Beijing, China Machine Press

[3] WangH.-wen.Partial least squares regression approach and application [M], 1999, Beijing, National Defense Industry Press

[4] ChiangL. H., RussellE. L., BraatzR. D.Fault detection and diagnosis in industrial systems [M], 2001, London, Springer-Verlag London Limited

[5] ChenJ. H., LiuK. C.. On-line batch process monitoring using dynamic PCA and dynamic PLS models [J]. Chemical Engineering Science, 2002, 57(1): 63-75

[6] FallahatiD. M., BackonjaM., EghbalniaH., AssadiA.H.. Dynamic PCA for network feature extraction in multi-electrode recording of neurophysiological data in cortical substrate of pain [J]. Neurocomputingm, 2002, 44/46: 401-405

[7] PöllänenK., HäkkinenA., ReinikainenS. P., RantanenJ., MinkkinenP.. Dynamic PCA-based MSPC charts for nucleation prediction in batch cooling crystallization processes [J]. Chemometrics and Intelligent Laboratory Systems, 2006, 84(1/2): 126-133

[8] LinW.-l., QianY., LiX.-xi.. Nonlinear dynamic principal component analysis for on-line process monitoring and diagnosis [J]. Computers and Chemical Engineering, 2000, 24(2/7): 423-429

[9] IsermannR.Fault-diagnosis systems: An introduction from fault detection to fault tolerance [M], 2006, Berlin, Springer-Verlag

[10] ChiangL. H., RussellE. L., BraatzR. D.. Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis [J]. Chemometrics and Intelligent Laboratory Systems, 2000, 51(1): 81-93

[11] LeeC. K., ChoiS. W., LeeI. B.. Sensor fault identification based on time-lagged PCA in dynamic processes [J]. Chemometrics and Intelligent Laboratory Systems, 2004, 70(2): 165-178

[12] ZhouR.-s., JiaoZ.-x., WangS.-ping.. Current research and developing trend on fault diagnosis of hydraulic systems [J]. Chinese Journal of Mechanical Engineering, 2006, 42(9): 6-14

[13] HeQ.-h., ZhangD.-q., HaoP., ZhangX.-hai.. Study on motion simulation of hydraulic excavator’s manipulator [J]. Acta Simulata Systematica Sinica, 2006, 18(3): 735-738

[14] Marquis-FavreW., BideauxE., ScavardaS.. A planar mechanical library in the AMESim simulation software (Part I): Formulation of dynamics equations [J]. Simulation Modeling Practice and Theory, 2006, 14(1): 25-46

[15] Marquis-FavreW., BideauxE., ScavardaS.. A planar mechanical library in the AMESim simulation software (Part II): Library composition and illustrative example [J]. Simulation Modelling Practice and Theory, 2006, 14(2): 95-111

[16] PratapR.Getting started with MATLAB 7: A quick introduction for scientists and engineers [M], 2005, New York, Oxford University Press USA

[17] KayS.Intuitive probability and random processes using Matlab [M], 2006, New York, Springer