A5044651257- Water Systems and Optimization
- Water Quality Monitoring Technologies
- Underwater Vehicles and Communication Systems
- Geophysical Methods and Applications
- Music and Audio Processing
- Underwater Acoustics Research
- Anomaly Detection Techniques and Applications
- Hydrological Forecasting Using AI
- Water Treatment and Disinfection
- Infrastructure Maintenance and Monitoring
- Geotechnical Engineering and Underground Structures
- Water resources management and optimization
- High voltage insulation and dielectric phenomena
- Time Series Analysis and Forecasting
- Urban Heat Island Mitigation
- Blind Source Separation Techniques
- Urban Green Space and Health
- Regional Economic and Spatial Analysis
- Advanced Algorithms and Applications
- Image and Signal Denoising Methods
- Machine Learning and ELM
- Evaluation Methods in Various Fields
- Building Energy and Comfort Optimization
- Remote Sensing and Land Use
Tsinghua University
2018-2024
Short-time water demand forecasting is essential for optimal control in a distribution system (WDS). Current methods (e.g., time-series models and conventional artificial neural networks) have limited power practice due to the nonlinear nature of changes demand. In particular, 15-min time-step may not be accurate when using models. To tackle this problem, paper investigates potential deep learning short-term forecasting, developing gated recurrent unit network (GRUN) model forecast 15 min 24...
Water loss reduction is important in sustainable water resource management. As one of the main control methods, early detection hydraulic accidents district metering areas (DMAs) has emerged as a research focus. This study presents data-driven method for burst which consists three stages: prediction, classification and correction. A prediction stage used to improve accuracy flow utilizes multiple thresholds make robust time variation, an outlier feedback correction allows consecutive...
Effectively detecting leaks is critical to improving leakage control management. Acoustic detection one of the main methods, and has been widely used in water utilities. Nevertheless, effectiveness this method unsatisfactory cases with various types noise. To tackle problem, work proposes a spectrogram represent features signals, developed time–frequency convolutional neural network (TFCNN) model identify signals. The performance TFCNN was compared other classification models (i.e., decision...
At present, many machine- or deep-learning algorithms have been applied to water distribution network (WDN) leakage recognition. The higher the algorithm classification accuracy, accident recognition accuracy for WDNs. This is of great significance green water-saving systems construction. As a popular machine-learning algorithm, extreme learning machine (ELM) also in WDN due its fast speed and high accuracy. However, traditional ELM obtains model output weights based on mapping calculation...
Previous research has primarily focused on leak diagnosis algorithms under the interference of outside environment noise. However, former in detection are easily affected by noise from pipe, especially one that contains elbow This article was mainly concerned with effective and reliable approach to precisely locate leaks buried pipeline system. To overcome drawback extract source mixing signal greatest extent, this proposes a novel frequency-domain-independent component analysis (ICA) blind...
Abstract Water loss in water distribution systems is one of the major problems faced by utilities. The components losses should be accurately assessed and their priority determined. Generally, balance analysis used to quantify different identify main contributor high leakage rates. leak flow rate assumed static within a given calculation period during real losses. Errors will inevitably arise this process. This mainly due our limited understanding leak's growth To overcome problem, current...
Multivariate geo-sensory time series prediction is challenging because of the complex spatial and temporal correlations. In urban water distribution systems (WDSs), numerous spatial-correlated sensors have been deployed to continuously collect hydraulic data. Forecasts monitored flow pressure are vital importance for operational decision making, alerts, anomaly detection. To address this issue, we proposed a hybrid dual-stage spatial–temporal attention-based recurrent neural networks...
Multivariate geo-sensory time series prediction is challenging because of the complex spatial and temporal correlation. In urban water distribution systems (WDS), numerous spatial-correlated sensors have been deployed to continuously collect hydraulic data. Forecasts monitored flow pressure are vital importance for operational decision making, alerts anomaly detection. To address this issue, we proposed a hybrid dual-stage spatial-temporal attention-based recurrent neural networks (hDS-RNN)....