unibuc-cs/FactorGraphLeakLocalization

该数据集包含了使用因子图优化技术进行水分配网络中漏水定位的实现和实验数据。该技术能够融合压力和需求传感器的读数，并估计网络中所有节点的时态和结构状态变化。研究方法引入了特定的水网络因子，并提出了由两个因子图组成的新架构：无泄漏状态估计因子图和泄漏定位因子图。当接收到新的传感器读数时，因子图更新当前和过去的状态，而不同于卡尔曼滤波和其他插值方法只估计当前网络状态。实验结果显示，因子图比非线性卡尔曼滤波方法如UKF更快，同时在定位方面也比最新的估计-定位方法有所改进。

This dataset contains the implementation and experimental data for leak localization in water distribution networks using factor graph optimization. The technique enables the fusion of pressure and demand sensor readings and estimates the temporal and structural state evolution across all network nodes. The methodology introduces specific water network factors and proposes a new architecture composed of two factor graphs: a leak-free state estimation factor graph and a leak localization factor graph. When a new sensor reading is obtained, factor graphs update both current and past states, unlike Kalman and other interpolation-based methods, which estimate only the current network state. Results show that factor graphs are much faster than nonlinear Kalman-based alternatives such as the UKF, while also providing improvements in localization compared to state-of-the-art estimation-localization approaches.