Abstract:Seepage behavior assessment is an important part of the safety operation assessment of earth-rock dams, because of insufficient intelligent analysis of monitoring information, abnormal phenomena or measured values are often ignored or improperly processed. To improve the intelligent performance of the monitoring system, this article has established an assessment framework covering project quality, maintenance status, monitoring data analysis, and on-site inspection based on the relevant norms of seepage safety… Show more
“…At present, the measurement methods of diagnosis indexes are mainly divided into three categories: (1) subjective methods based on expert knowledge or engineering experience; the most commonly used is experts grading method [6], [7], [8]. This method show strong subjective randomness and may lead to uncoordinated or inconsistent grades with limitation of expert knowledge.…”
With multi-layers and multi-indexes, dam health diagnosis is an important way to diagnose the structural safety and health operation of dams. This study focuses on the measurement of diagnosis indexes in dam health diagnosis. The existing methods of constructing diagnosis indexes are mainly based on the subjective judgment of expert knowledge, and lack of consideration of the internal mapping relationship between diagnosis indexes and dam health levels. Therefore, it is necessary to introduce new theories and new methods to study the objective measurement of diagnostic indexes in combination with the characteristics of dam health diagnosis. Based on the Dempster-Shafer (D-S) evidence theory, a new concept lattices-based model for building basic probability assignments (BPAs) is proposed in this study. First, concept lattices under hesitant fuzzy linguistic term sets (HFLTSs) were established to formalize the qualitative and quantitative expression of expert knowledge. Then we defined a new distance of HFLTSs, named NWD. NWD is strict in mathematical definition and considers the non-overlapping HFLTSs. Based on NWD, the weight of the monitoring point for each health level was obtained through similarity analysis and finally transformed into the corresponding BPA. An engineering project demonstrated that the BPAs developed in this study could adequately describe the attributes of diagnosis indexes, forming reliable bases for the comprehensive diagnosis fusion. Simultaneously, the proposed method of building the BPA can significantly improve assignment efficiency, which can shed light on the development of dam operation behavior modelling.INDEX TERMS Basic probability assignment, concept lattice, dam health diagnosis, diagnosis index, D-S evidence theory.
“…At present, the measurement methods of diagnosis indexes are mainly divided into three categories: (1) subjective methods based on expert knowledge or engineering experience; the most commonly used is experts grading method [6], [7], [8]. This method show strong subjective randomness and may lead to uncoordinated or inconsistent grades with limitation of expert knowledge.…”
With multi-layers and multi-indexes, dam health diagnosis is an important way to diagnose the structural safety and health operation of dams. This study focuses on the measurement of diagnosis indexes in dam health diagnosis. The existing methods of constructing diagnosis indexes are mainly based on the subjective judgment of expert knowledge, and lack of consideration of the internal mapping relationship between diagnosis indexes and dam health levels. Therefore, it is necessary to introduce new theories and new methods to study the objective measurement of diagnostic indexes in combination with the characteristics of dam health diagnosis. Based on the Dempster-Shafer (D-S) evidence theory, a new concept lattices-based model for building basic probability assignments (BPAs) is proposed in this study. First, concept lattices under hesitant fuzzy linguistic term sets (HFLTSs) were established to formalize the qualitative and quantitative expression of expert knowledge. Then we defined a new distance of HFLTSs, named NWD. NWD is strict in mathematical definition and considers the non-overlapping HFLTSs. Based on NWD, the weight of the monitoring point for each health level was obtained through similarity analysis and finally transformed into the corresponding BPA. An engineering project demonstrated that the BPAs developed in this study could adequately describe the attributes of diagnosis indexes, forming reliable bases for the comprehensive diagnosis fusion. Simultaneously, the proposed method of building the BPA can significantly improve assignment efficiency, which can shed light on the development of dam operation behavior modelling.INDEX TERMS Basic probability assignment, concept lattice, dam health diagnosis, diagnosis index, D-S evidence theory.
“…Developing the lag function and enhancing the predictive accuracy of security monitoring models has emerged as a challenging area of research. He et al (2021) employed both static and dynamic Bayesian networks for the analysis of seepage anomalies in earth and rockfill dams, addressing shortcomings in existing monitoring models. Shi et al (2020)developed a seepage safety monitoring, incorporating the lag effect through the use of a radial basis function neural network.…”
Seepage significantly impacts the stability of earth and rockfill dams, making effective monitoring essential. Traditional Partial Least Squares (PLS) methods handle multicollinearity well but often lack predictive accuracy. Integrating neural networks, particularly Bidirectional Long Short-Term Memory (BiLSTM) networks, enhances accuracy by improving nonlinear data processing and memory of long-term dependencies. This research presents a novel PLS-BO-BiLSTM seepage model for rockfill dams, combining PLS with BiLSTM and Bayesian Optimization (BO). The model employs normal and Rayleigh distribution functions to account for lags in water depth and precipitation, optimized using the Grey Wolf Optimization (GWO) algorithm. Engineering case studies demonstrate the model's high predictive accuracy and generalizability, especially during sudden seepage increases caused by heavy rainfall.
“…The information is considered to have been adopted if the proportion of neighbors who have adopted it meets or surpasses the adoption threshold [10,11]. When the initial seed size is very tiny, the percolation theory can be used to estimate the proportion [12,13]. When the adoption threshold is fixed, the average degree scale change results in saddle point bifurcation, and with the increasing of network average degree, the final adoption scope increases continuously at first and then decreases discontinuously [14,15].…”
The local trend imitation(LTI) feature behavior has been deeply studied on specific complex networks, but still needs to be explored in more scenarios. In fact, the multiple networks with individual limited contact feature is more in line with the real scenario On the multiple limited networks,a novel model is proposed to investigate the effects of individual contact capacity heterogeneity. Then,information propagation mechanism is then measured and examined using a developed partition theory. The experimental results show crossover occurrences of phase transition. In the new network model, the final spreading scope exhibits a second-order continuous growth when individuals display a positive LTI behavior. Individuals have a passive LTI behavior, however, the final spreading scope exhibits a first-order discontinuous growth. Besides, a greatest ultimate spreading size appears at an ideal LTI parameter with the unit spreading probability changing. Additionally, individual contact capacity heterogeneity changes the rate of information spreading and the global adoption pattern. Eventually the outcomes of the theoretic analysis match those of the simulations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.