A self-matching model for online anomaly recognition of safety monitoring data in dams

Abstract

The online anomaly recognition of real-time dam safety monitoring data, such as deformation and seepage data from the automatic sensing instruments (e.g., the osmometer and the multi-point displacement meter), has the premise of ensuring data reliability, and it is also one of the core functional modules of online dam safety monitoring. To compensate for the limitation of a single method to identify outliers and further improve the reliability and the rapidity of the anomaly recognition of dam safety monitoring data, a self-matching model based on data-types for online anomaly recognition (SMM) was proposed in this paper. Based on a detailed classification of dam safety monitoring data sequences, this article describes a comparison and analysis of the applicability of a statistical regression model based on the least-squares regression (LSR) model and the online robust recognition and early warning (RREW) model for different datatype sequences. For the single-step-type sequences and normal-type sequences with low fitting accuracy, which could not be completely identified by the two models above, an improved cloud model recognition method based on the diurnal variation rate (ICM) was proposed to compensate for the limitations. Finally, the SMM was determined, that is, the LSR model was used for the multi-point-outlier-type and normal-type sequences with high fitting accuracy, the RREW model method was used for the double-step-type and oscillatory-type sequences, and the ICM method was used for the single-step-type sequences and normal-type sequences with low fitting accuracy. The engineering application of the Dadu River Basin showed that this method effectively solved the problems of low calculation efficiency and a 2% misjudgment rate when using the RREW model alone, and this method greatly improved the accuracy and timeliness of the anomaly recognition of dam safety monitoring data, so it had important theoretical significance and engineering application value.

Keywords

Data-type recognition method self-matching improved cloud model computational efficiency recognition accuracy

Get full access to this article

View all access options for this article.

References

Omar

Ngadi

Jebur

, et al. Machine learning techniques for anomaly detection: an overview. Int J Computer Appl 2013; 79(2): 33–41.

Cheng

Zheng

. Two online dam safety monitoring models based on the process of extracting environmental effect. Adv Eng Softw 2013; 57: 48–56.

Prakash

Sadhu

Narasimhan

, et al. Initial service life data towards structural health monitoring of a concrete arch dam. Struct Control Health Monit 2018; 25(1): 1–19.

Salazar

Toledo

MÁ

González

, et al. Early detection of anomalies in dam performance: a methodology based on boosted regression trees. Struct Control Health Monit 2017; 24(11): 1–16.

Salazar

González

Toledo

MÁ

, et al. A methodology for dam safety evaluation and anomaly detection based on boosted regression trees. In: European workshop on structural health monitoring, 2016, Bilbao, Spain, 21 December 2016, pp. 39–58.

Balsamo

Betti

. Data-based structural health monitoring using small training data sets. Struct Control Health Monit 2015; 22(10): 1240–1264.

Mukhopadhyay

Lus

Betti

. Structural identification with incomplete instrumentation and global identifiability requirements under base excitation. Struct Control Health Monit 2015; 22(7): 1024–1047.

Barthorpe

Manson

Worden

. On multi-site damage identification using single-site training data. J Sound Vibration 2017; 409: 43–64.

Salazar

Morán

Toledo

MÁ

, et al. Data-based models for the prediction of dam behaviour: A review and some methodological considerations. Arch Comput Methods Eng 2017; 24(1): 1–21.

10.

De Sortis

Paoliani

. Statistical analysis and structural identification in concrete dam monitoring. Eng Structures 2007; 29(1): 110–120.

11.

Kang

Liu

. Temperature effect modeling in structural health monitoring of concrete dams using kernel extreme learning machines. Struct Health Monit 2020; 19(4): 987–1002.

12.

Mata

. Interpretation of concrete dam behaviour with artificial neural network and multiple linear regression models. Eng Structures 2011; 33(3): 903–910.

13.

Yue

Deng

. Hybrid GA/SIMPLS as alternative regression model in dam deformation analysis. Eng Appl Artif Intelligence 2012; 25(3): 468–475.

14.

Roushangar

Garekhani

Alizadeh

. Forecasting daily seepage discharge of an earth dam using wavelet-mutual information-gaussian process regression approaches. Geotechnical Geol Eng 2016; 34(5): 1313–1326.

15.

Wen

. Structure analysis for concrete-faced rockfill dams based on information entropy theory and finite element method. Int J Numer Anal Methods Geomechan 2012; 36(8): 1041–1055.

16.

Huang

Hua

Song

. Unascertained filtering method for monitoring data of earth rock-fill dams. J Yangtze River Scientific Res Inst 2006; 23(03): 32–35, (in Chinese).

17.

Cui

Zhang

Wang

, et al. Exploration and practice of online monitoring and management platform for hydropower dam. Dam Saf 2018; 02: 31–36, (in Chinese).

18.

Zhang

, et al. Research and application of on-line safety monitoring system for Jinping arch dam. Dam Saf 2018; 02: 37–41, (in Chinese).

19.

Stojanovic

Milivojevic

Ivanovic

, et al. Adaptive system for dam behavior modeling based on linear regression and genetic algorithms. Adv Eng Softw 2013; 65: 182–190.

20.

Wen

Wang

. Outlier detection and correction during the process of groundwater lever monitoring base on Pauta criterion with self-learning and smooth processing. In: Theory, methodology, tools and applications for modeling and simulation of complex systems. Singapore: Springer, 2016, pp. 497–503.

21.

Wen

Yan

, et al. Early-warning model of deformation safety for roller compacted concrete arch dam considering time-varying characteristics. Compos Structures 2018; 203: 373–381.

22.

Chatterjee

Mächler

. Robust regression: a weighted least squares approach. Commun Stat - Theor Methods 1997; 26(6): 1381–1394.

23.

Nowel

. Robust m-estimation in analysis of control network deformations: classical and new method. J Surv Eng 2015; 141(4): 04015002.

24.

Habibi

. Kinetic study of an in situ inhibited polymerization using robust M-statistics. Chem Eng Res Des 2009; 87(1): 1–12.

25.

Maddala

Yin

. 10 Outliers, unit roots and robust estimation of nonstationary time series. Handbook Stat 1997; 15(97): 237–266.

26.

Touati

Idres

Kahlouche

. A robust method for relative gravity data estimation with high efficiency. Surv Geophys 2009; 31(1): 69–83.

27.

Erdoğan

. The effects of additive outliers on time series components and robust estimation: a case study on the oymapinar dam, turkey. Exp Tech 2012; 36(3): 39–52.

28.

Wang

, et al. Application of Kalman filtering algorithm based M-estimation in deformation monitoring of concrete gravity dam. Water Res Power 2015; 33(12): 89–92, (in Chinese).

29.

Touati

Benaraba

. Robust inversion method for jointly estimating parameters and variance components from heterogeneous monitoring data. Inverse Probl Sci Eng 2017; 26(4): 530–552.

30.

Xiong

Nie

, et al. Identification and processing of outliers in data based on improved quantile method. In: IEEE 2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China, 11–13 October 2019: 406–410.

31.

, et al. An online anomaly recognition and early warning model for dam safety monitoring data. Struct Health Monit 2020; 19(3): 796–809.

32.

Zhang

, et al. Cloud model and application overview. Computer Eng Des 2011; 32(12): 4198–4201, (in Chinese).

33.

Yang

. Principle and implement of power quality real-time status diagnosis based on cloud model. Adv Eng Sci 2015; 47(01): 167–172, (in Chinese).

34.

Torr

PHS

Murray

. Outlier detection and motion segmentation. Int Soc Opti Eng 1993; 2059: 432–443.

35.

Hodge

Austin

. A Survey of outlier detection methodologies. Artif Intelligence Rev 2004; 22(2): 85–126.

36.

Bukenya

Moyo

Beushausen

, et al. Health monitoring of concrete dams: a literature review. J Civil Struct Health Monit 2014; 4(4): 235–244.

37.

Demirkaya

Balcilar

. The contribution of soft computing techniques for the interpretation of dam deformation. In: Proceedings of the FIG Working Week 2012, Rome, Italy, 29 May 2012, pp. 12–14.

38.

Tukey

. Exploratory Data Analysis. Reading, MA: Addison-Wesley, 1977.

39.

Huber

. Robust estimation of a location parameter. Ann Math Stat 1964; 35(1): 73–101.

40.

Wei

Yuan

, et al. Combination forecast model for concrete dam displacement considering residual correction. Struct Health Monit 2019; 18(1): 232–244.

41.

Wen

Chen

, et al. Dam safety prediction model considering chaotic characteristics in prototype monitoring data series. Struct Health Monit 2016; 15(6): 639–649.

42.

Chen

Huang

, et al. A spatio-temporal clustering and diagnosis method for concrete arch dams using deformation monitoring data. Struct Health Monit 2019; 18(5–6): 1355–1371.

43.

Gao

Wang

, et al. Novel algorithm of backward cloud model without certainty. Appl Res Comput 2013; 30(08): 2262–2265, (in Chinese).

44.

Liu

, et al. Artificial intelligence with uncertainty. J Softw 2004; 15(11): 1583–1594, (in Chinese).

45.

Liu

. Statistics on atomized feature of normal cloud model. J Beijing Univ Aeronautics Astronautics 2010; 36(11): 1320–1324, (in Chinese).

46.

Liu

. Study on the universality of the normal cloud model. Eng Sci 2004; 6(8): 28–34, (in Chinese).

47.

Liu

, et al. Some statistical analysis of the normal cloud model. Inf Control 2005; 34(2): 236–239, (in Chinese).

48.

Zhao

Jin

, et al. Singular value diagnosis in dam safety monitoring effect values. Sci China Technol Sci 2011; 54(5): 1169–1176.

49.

Baştanlar

Ozuysal

. Introduction to machine learning. Met Mol Biol (Clifton, N.J.) 2014; 1107: 105–128.