Abstract：[Objective] Evidence theory, an effective multisource information fusion method, has been widely applied in the field of dam safety monitoring and health diagnosis. However, two limitations must be addressed: the accuracy of evaluation results of existing conflicting evidence-processing methods is low, and the existing fusion weight calculation methods may result in unreasonable fusion weights when the differences in the contribution of each monitoring type to the dam safety evaluation results are ignored. In this paper, we propose a comprehensive evaluation method for dam safety considering fusion weight optimization and conflicting information sources. The negative impact of conflicting evidence on the accuracy of information fusion is significantly eliminated by means of both decreasing conflicting information generation sources and preprocessing evidence bodies. Furthermore, reasonable fusion weights for each monitoring type can be obtained through subjective assignment. [Methods] In the data preprocessing stage, we propose the STL (seasonal-trend decomposition procedure based on loess)-iForest (isolation forest algorithm) method for temporal outlier detection. First, the original dam safety monitoring sequence data are decomposed into trend, seasonal, and residual terms using the STL temporal decomposition method, which eliminates the influence of data trend and periodicity on the total error rejection accuracy. Then, the iForest algorithm is used to remove outliers from the data of the residual term. Finally, the data are reconstructed using the Hermite interpolation method. Using the above methods, we suppress the generation of conflicting evidence at the source as much as possible. In the multisource information fusion stage, we calculate the evidence fusion weight of low-level information using the χ2 divergence and Shannon entropy, which can overcome the shortcomings of traditional distance metrics, such as the Euclidean distance, which have poor reliability of fusion results. For high-level information, we use the scaling method to determine the corresponding fusion weight to ensure that the weight reflects the difference in the contribution of different monitoring types to the dam safety evaluation results. [Results] The results with data preprocessing show that the STL temporal decomposition method separates the trend term and seasonal term of the data well and keeps the outliers in the residual terms, providing a good basis for outlier detection. Then, the iForest algorithm can detect all obvious outliers in the data, which shows that the proposed outlier detection method can ensure the high reliability of the multisource monitoring data by eliminating conflicting evidence from the sources. In the multisource information fusion method proposed in this paper, the discrete degree and uncertainty of the evidence are fully considered to ensure the accuracy of the evaluation results, especially in the case of conflicting evidence, which is consistent with the actual situation. Compared with evidence theory based on the Euclidean distance and the case of unexcluded data coarseness, the proposed method improves the probability corresponding to the basic normal state to 0.842, indicating that the method has better reliability. [Conclusions] The proposed method shows high-accuracy fusion results and high-reliability qualitative evaluation results. In addition, it can accurately quantify the differences in the contributions of each monitoring type to the comprehensive dam safety evaluation results. The proposed method has considerable potential in the diagnosis of dam safety, given its high accuracy and good robustness.
王雷, 王晓玲, 张君, 余佳, 王佳俊. 考虑融合权重优化与冲突信息来源的大坝安全综合评价方法[J]. 清华大学学报（自然科学版）, 2023, 63(10): 1566-1575.
WANG Lei, WANG Xiaoling, ZHANG Jun, YU Jia, WANG Jiajun. Comprehensive evaluation method for dam safety considering fusion weight optimization and conflicting information sources. Journal of Tsinghua University(Science and Technology), 2023, 63(10): 1566-1575.
[1] 中华人民共和国水利部. 2020年全国水利发展统计公报[M].北京:中国水利水电出版社, 2021. Ministry of Water Resources, People's Republic of China. 2020 Statistic bulletin on China water activities[M]. Beijing:China Water&Power Press, 2021.(in Chinese) [2] 吴中如,徐波,顾冲时,等.大坝服役状态的综合评判方法[J].中国科学:技术科学, 2012, 42(11):1243-1254. WU Z R, XU B, GU C S, et al. Comprehensive evaluation methods for dam service status[J]. Science China:Technological Sciences, 2012, 42(11):1243-1254.(in Chinese) [3] 何金平.大坝健康状态综合诊断方法研究进展[J].水电与新能源, 2016(1):1-6, 11. HE J P. Advances in comprehensive diagnostic methods for dam health status[J]. Hydropower and New Energy, 2016(1):1-6, 11.(in Chinese) [4] 何金平,高全.一种适应大坝健康诊断的改进云合并算法[J].武汉大学学报(信息科学版), 2018, 43(7):1022-1029. HE J P, GAO Q. An improved algorithm of cloud fusion for dam health diagnosis[J]. Geomatics and Information Science of Wuhan University, 2018, 43(7):1022-1029.(in Chinese) [5] 李婷婷.混凝土坝健康诊断及其预警系统[D].南京:河海大学, 2006. LI T T. Health diagnosis and early-warning system for concrete dam[D]. Nanjing:Hohai University, 2006.(in Chinese) [6] 施玉群,何金平.基于信息熵的大坝多效应量聚类融合诊断模型[J].水力发电学报, 2013, 32(5):239-243. SHI Y Q, HE J P. Multiple effect quantity fusion diagnosis model of dam health based on information entropy and cluster analysis[J]. Journal of Hydroelectric Engineering, 2013, 32(5):239-243.(in Chinese) [7] 徐小蓉,何涛洪,雷峥琦,等.超长坝段堆石混凝土重力坝蓄水运行安全评价[J].清华大学学报(自然科学版), 2022, 62(9):1375-1387. XU X R, HE T H, LEI Z Q, et al. Safety evaluation of rock-filled concrete gravity dam with long section during the impoundment operation period[J]. Journal of Tsinghua University (Science and Technology), 2022, 62(9):1375-1387.(in Chinese) [8] ORMANN L, ZARDARI M A, MATTSSON H, et al. Numerical analysis of strengthening by rockfill embankments on an upstream tailings dam[J]. Canadian Geotechnical Journal, 2013, 50(4):391-399. [9] RIBAS J R, SEVERO J C R, FELIX L C G, et al. Prioritization of hydroelectric power plant earth dam safety procedures:A multi-criteria approach[J]. Environmental Earth Sciences, 2021, 80(24):815. [10] MASOUMI I, AHANGARI K, NOORZAD A. Integrated fuzzy decision approach for reliability improvement of dam instrumentation and monitoring[J]. Journal of Structural Integrity and Maintenance, 2018, 3(2):114-125. [11] YUCESAN M, KAHRAMAN G. Risk evaluation and prevention in hydropower plant operations:A model based on Pythagorean fuzzy AHP[J]. Energy Policy, 2019, 126:343-351. [12] 闫滨,高真伟,李东艳. RBF神经网络在大坝安全综合评价中的应用[J].岩石力学与工程学报, 2008, 27(S2):3991-3997. YAN B, GAO Z W, LI D Y. Application of radial basis function neural network to comprehensive evaluation of dam safety[J]. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(S2):3991-3997.(in Chinese) [13] SEVIERI G, DE FALCO A. Dynamic structural health monitoring for concrete gravity dams based on the Bayesian inference[J]. Journal of Civil Structural Health Monitoring, 2020, 10(2):235-250. [14] SU H Z, WEN Z P, SUN X R, et al. Multisource information fusion-based approach diagnosing structural behavior of dam engineering[J]. Structural Control and Health Monitoring, 2018, 25(2):e2073. [15] 何金平,马传彬,施玉群.高拱坝多效应量改进型D-S证据理论融合模型[J].武汉大学学报(信息科学版), 2012, 37(12):1397-1400. HE J P, MA C B, SHI Y Q. Multi-effect-quantity fusion model of high arch dam based on improved D-S evidence theory[J]. Geomatics and Information Science of Wuhan University, 2012, 37(12):1397-1400.(in Chinese) [16] WU X G, DUAN J C, ZHANG L M, et al. A hybrid information fusion approach to safety risk perception using sensor data under uncertainty[J]. Stochastic Environmental Research and Risk Assessment, 2018, 32(1):105-122. [17] 周心怡,胡蕾,张启灵.考虑谷幅收缩变形的高拱坝多源信息融合安全评判[J].长江科学院院报, 2023, 40(1):87-93. ZHOU X Y, HU L, ZHANG Q L. Safety evaluation of high arch dam based on multi-source information fusion in consideration of valley shrinkage deformation[J]. Journal of Yangtze River Scientific Research Institute, 2023, 40(1):87-93.(in Chinese) [18] 王燕,叶伟,马福恒.基于D-S证据理论融合采空区多源信息的大坝安全评价[J].水利水电技术, 2020, 51(4):175-183. WANG Y, YE W, MA F H. D-S evidence theory-based dam safety assessment fused with multi-source information of goaf area[J]. Water Resources and Hydropower Engineering, 2020, 51(4):175-183.(in Chinese) [19] 叶伟,马福恒,周海啸.加权优化的D-S证据理论在大坝安全评价中的应用[J].水电能源科学, 2016, 34(6):96-99. YE W, MA F H, ZHOU H X. Application of weight optimized D-S evidence theory in dam safety evaluation[J]. Water Resources and Power, 2016, 34(6):96-99.(in Chinese) [20] LI B, YANG J, HU D X. Dam monitoring data analysis methods:A literature review[J]. Structural Control and Health Monitoring, 2020, 27(3):e2501. [21] 肖白,周文凯,姜卓.基于孤立森林、模态分解和神经网络的空间负荷态势感知[J].电力系统自动化, 2022, 46(18):190-198. XIAO B, ZHOU W K, JIANG Z. Spatial load situation awareness based on isolation forest, mode decomposition and neural networks[J]. Automation of Electric Power Systems, 2022, 46(18):190-198.(in Chinese) [22] GAO X Y, XIAO F Y. A generalized χ2 divergence for multisource information fusion and its application in fault diagnosis[J]. International Journal of Intelligent Systems, 2022, 37(1):5-29. [23] 何金平.大坝安全监测理论与应用[M].北京:中国水利水电出版社, 2010. HE J P. Theory and application of dam safety monitoring[M]. Beijing:China Water&Power Press, 2010.(in Chinese) [24] 张力,王红瑞,郭琲楠,等.基于时序分解与机器学习的非平稳径流序列集成模型与应用[J].水科学进展, 2023, 34(1):42-52. ZHANG L, WANG H R, GUO B N, et al. Integrated model and application of non-stationary runoff based on time series decomposition and machine learning[J]. Advances in Water Science, 2023, 34(1):42-52.(in Chinese) [25] 康兵义,李娅,邓勇,等.基于区间数的基本概率指派生成方法及应用[J].电子学报, 2012, 40(6):1092-1096. KANG B Y, LI Y, DENG Y, et al. Determination of basic probability assignment based on interval numbers and its application[J]. Acta Electronica Sinica, 2012, 40(6):1092-1096.(in Chinese) [26] XIAO F Y. Multi-sensor data fusion based on the belief divergence measure of evidences and the belief entropy[J]. Information Fusion, 2019, 46:23-32.
2023, Vol. 63 
