Xiong Yin
Xiong Yin has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chen Liu
School of Earth Resources, China University of Geosciences, Wuhan 430074, China
2 shared publications - Weichao Yu
Pipe China Oil & Gas Control Center, Beijing 100013, China
2 shared publications - Chenxiao Zhao
PipeChina Oil & Gas Control Center, Beijing 100013, China
1 shared publication - Chuanyu Zhang
Pipe China Oil & Gas Control Center, Beijing 100013, China
1 shared publication - Dongyan Zheng
PipeChina Oil & Gas Control Center, Beijing 100013, China
1 shared publication - Haotong Wang
Pipe China Oil & Gas Control Center, Beijing 100013, China
1 shared publication
Latest Publications
- Open Access
Research on Optimization Models and Algorithms for Natural Gas Pipeline Dispatch Under Normal Conditions
With the increasing share of natural gas in the energy mix, ensuring safe and efficient pipeline operation is critical for reliable energy supply. Pipeline networks require active inventory regulation to manage operational and seasonal fluctuations, making effective dispatch strategies under complex constraints essential. A mixed-integer programming model is established to optimize dispatch with objectives of maximizing target completion, minimizing operational actions, and reducing compressor energy consumption. The network’s complex dependencies and nonlinear dynamics make the problem high-dimensional and multimodal; to address this, a tailored hybrid heuristic combining Variable Neighborhood Search (VNS) for solution exploration and Simulated Annealing (SA) for escaping local optima is developed. The algorithm generates an initial feasible solution, applies multiple neighborhood perturbation strategies, and uses a probabilistic acceptance mechanism. Interaction with simulation software enables dynamic evaluation and iterative optimization. A 24-h case study of the Northern Tai natural gas pipeline network, using actual initial inventories, gas capacities, and demand profiles, demonstrates that the method efficiently produces feasible dispatch solutions that satisfy inventory requirements while balancing target completion and energy consumption.
Open AccessResearch on Optimization Models and Algorithms for Natural Gas Pipeline Dispatch Under Normal Conditions
With the increasing share of natural gas in the energy mix, ensuring safe and efficient pipeline operation is critical for reliable energy supply. Pipeline networks require active inventory regulation to manage operational and seasonal fluctuations, making effective dispatch strategies under complex constraints essential. A mixed-integer programming model is established to optimize dispatch with objectives of maximizing target completion, minimizing operational actions, and reducing compressor energy consumption. The network’s complex dependencies and nonlinear dynamics make the problem high-dimensional and multimodal; to address this, a tailored hybrid heuristic combining Variable Neighborhood Search (VNS) for solution exploration and Simulated Annealing (SA) for escaping local optima is developed. The algorithm generates an initial feasible solution, applies multiple neighborhood perturbation strategies, and uses a probabilistic acceptance mechanism. Interaction with simulation software enables dynamic evaluation and iterative optimization. A 24-h case study of the Northern Tai natural gas pipeline network, using actual initial inventories, gas capacities, and demand profiles, demonstrates that the method efficiently produces feasible dispatch solutions that satisfy inventory requirements while balancing target completion and energy consumption.
- Open Access
Deep Spatiotemporal Surrogate Modeling of Natural Gas Pipeline Networks for Heterogeneous Equipment and Long-Horizon Forecasting
Accurate multistep-ahead prediction of natural gas pipeline-network states is essential for intelligent dispatching, yet such networks contain physically heterogeneous components (gas sources, pipelines, compressors, valves), and historical states and future dispatching commands are decoupled in both temporal scale and physical semantics. This causes conventional data-driven models to suffer from semantic entanglement and cumulative error during long-horizon forecasting. This study proposes a deep spatiotemporal surrogate model with three coordinated designs: (i) type-specific feature encoding combined with global latent-graph mapping and a shared graph convolutional network (GCN) to disentangle heterogeneous-equipment attributes and represent network-wide topological coupling; (ii) a residual-gated temporal coupling mechanism that adaptively fuses historical operating inertia with future external disturbances; and (iii) a temporal-gradient multi-objective loss with a 12-step autoregressive rolling strategy over a 6 h horizon to suppress cumulative divergence. On 85,248 samples built from field monitoring data and commercial mechanistic simulations, the model attains median relative errors of 1.15% for nodal pressure and 2.10% for pipeline flow, capturing macroscopic pressure decay and high-frequency transient flow induced by valve and compressor switching without noticeable delay, providing an efficient tool for online simulation, real-time warning, and decision support in complex natural gas pipeline networks.
Open AccessDeep Spatiotemporal Surrogate Modeling of Natural Gas Pipeline Networks for Heterogeneous Equipment and Long-Horizon Forecasting
Accurate multistep-ahead prediction of natural gas pipeline-network states is essential for intelligent dispatching, yet such networks contain physically heterogeneous components (gas sources, pipelines, compressors, valves), and historical states and future dispatching commands are decoupled in both temporal scale and physical semantics. This causes conventional data-driven models to suffer from semantic entanglement and cumulative error during long-horizon forecasting. This study proposes a deep spatiotemporal surrogate model with three coordinated designs: (i) type-specific feature encoding combined with global latent-graph mapping and a shared graph convolutional network (GCN) to disentangle heterogeneous-equipment attributes and represent network-wide topological coupling; (ii) a residual-gated temporal coupling mechanism that adaptively fuses historical operating inertia with future external disturbances; and (iii) a temporal-gradient multi-objective loss with a 12-step autoregressive rolling strategy over a 6 h horizon to suppress cumulative divergence. On 85,248 samples built from field monitoring data and commercial mechanistic simulations, the model attains median relative errors of 1.15% for nodal pressure and 2.10% for pipeline flow, capturing macroscopic pressure decay and high-frequency transient flow induced by valve and compressor switching without noticeable delay, providing an efficient tool for online simulation, real-time warning, and decision support in complex natural gas pipeline networks.