Shuangqing Chen

Variants of Physics-informed neural networks (PINNs) often treat neural networks as the main solution representation, yet solutions are encoded implicitly in high-dimensional weights, making training behavior and outcomes difficult to predict or analyze across different partial differential equation (PDE) settings. In this study, we propose physics-informed spectral coefficient learning (PISCL), a network-free physics-informed formulation that represents PDE solutions using a finite set of spatial and temporal spectral modes and learns the corresponding coefficients by minimizing a residual loss. This coefficient-based representation is explicit and interpretable, since each trainable parameter corresponds to a specific mode. We evaluated PISCL on two benchmark PDEs (1D linear wave and viscous Burgers). Over repeated independent runs, it achieves MAE 0.0080 ± 0.0062 in the wave equation and MAE 0.0578 ± 0.0003 in the most challenging Burgers setting, matching or outperforming standard PINN baselines under the same sampling budget. Overall, these results indicate that neural networks are not the only viable solution representation and that explicit coefficient-based representations can provide a simple and interpretable alternative for physics-informed PDE solving.

Modern energy internets and large-scale industrial systems are becoming increasingly complex. Consequently, the rapid response capability of energy infrastructure during sudden failures has become a core element to ensure the stable operation of the social economy. Emergency repair path planning (ERPP) is a complex nonlinear combinatorial optimization problem. It is characterized by dynamic uncertainties, such as fluctuating task durations and variable traffic accessibility. This paper proposes a cross-regional emergency repair path planning (CR-ERPP) optimization model considering dynamic path conditions. The model takes into account jurisdiction ownership, cross-regional dispatch costs, path weights (congestion coefficient, grade coefficient, quality coefficient) and accident risk levels. The primary objective of this model is to minimize the total repair cost. Furthermore, an Adaptive Bitterling Fish Optimization with Evolutionary Game Theory (ABFO-EGT) is developed. It introduces adaptive mechanisms, evolutionary game theory, and a symmetric mutation strategy. These enhancements are designed to overcome the inherent limitations of traditional swarm intelligence algorithms, namely unbalanced search behavior and premature convergence to local optima. Performance analysis demonstrates that the ABFO-EGT algorithm exhibits superior convergence stability and global search capability. Case study results show that the proposed method significantly reduces the total repair cost. Specifically, the cost is reduced by 33.2% compared to manual decision-making, 27.6% compared to the GWO algorithm, and 9.1% compared to both the ACO and PSO algorithms. This study provides an efficient and reliable decision support tool for emergency management of large-scale energy systems.

In this study, we employ the homotopy renormalization (HTR) method to analytically investigate Rasmussen’s problem, which characterizes the viscous fluid motion between a pair of infinitely large, coaxially rotating disks. The original set of nonlinear ordinary differential equations is reformulated within a homotopy-based framework, allowing us to construct global asymptotic approximations with closed-form expressions. The HTR method overcomes the limitations of traditional perturbation and renormalization techniques, and avoids the need for asymptotic matching. In addition, the analytic expressions allow for direct estimation of flow parameters such as boundary layer thickness. These results demonstrate the effectiveness of the HTR method in asymptotic analysis and highlight its potential for broader applications in nonlinear fluid dynamics.

The energy consumption issue of water injection systems has always been a key focus of energy conservation and consumption reduction in oilfield production. Optimizing the operational schemes of the water injection system is of great significance for achieving energy conservation and consumption reduction goals in oilfields. This article establishes a mathematical model for optimizing the operating parameters of oilfield water injection systems, with the operating parameters of water injection pumps as design variables and the objective function of minimizing water injection energy consumption. In the model, multiple constraints such as the balance of supply and demand of water within the station, pump flow rate, and injection well pressure are considered. Using the four defensive behaviors of the Crested Porcupine Optimizer (CPO) to optimize the Particle Swarm Optimization (PSO) Algorithm, a Multi-Mechanism Threat Response Strategy for Dynamic Parameter Adjustment is proposed to form a Hybrid Particle Swarm–Crested Porcupine Algorithm (PSCPA). Compared with the other nine algorithms, the PSCPA has better solving efficiency. Applying this method to a practical case of an old oilfield, the optimized water injection system scheme reduced power consumption by 11,719.23 KWh/d, increased the average pump efficiency of the system by 9.3%, and reduced system unit consumption by 0.37 KWh/d. Therefore, this algorithm has good practicality for optimizing the operation of large-scale and highly sensitive water injection systems.

This paper presents an in-depth study of a concatenation model with power-law nonlinearity. The integral form of the original model is derived, and the corresponding dynamic system is obtained. A qualitative analysis is conducted to identify the types of equilibrium points, phase diagrams, and trajectories. From specific trajectories, we can infer that this equation has periodic and soliton solutions. To validate these conclusions, the corresponding exact solutions are constructed, and several new solutions are initially presented in this paper. Finally, by adding a specific external perturbation term, we found that this model also exhibits chaotic behavior, which is presented in this paper for the first time. Published by the Jagiellonian University 2025 authors

The safety of hydrogen-blended natural gas (HBNG) in a confined space is an issue, especially for ventilation processes. In this study, leakage and ventilation processes of low-pressure HBNG with different hydrogen-blended ratio (HBR) in a confined space are simulated and validated by experiment based on similarity criteria. For the leakage process, the leak direction and HBR do not significantly affect gas accumulation behaviour. The required time for a gas cloud to fill space decreases slightly with HBR rising and they generally show a linear relationship. For the ventilation process, the main influences on the leakage process are the total leakage mass and the ventilation conditions. The required time for hazardous gas cloud dissipation increases with total leakage mass and decreases with HBR. For different ventilation conditions, the ranking of required time to exhaust leaked gas is low > centre > high > mix. Through the analysis of pressure distribution, it is found time difference is produced by different airflow patterns. With the asymmetric layout, outside air rushes into the confined space from the high side and then flows out from the low side carrying the leaked HBNG. These findings inform the design of ventilation for HBNG utilization scenarios like restaurant facing the street.

In the early construction of an underground gas storage facility in an oil and gas field in southwest China, the increasing gas injection volume led to a continuous rise in energy consumption, which affects the economic sustainability of gas injection and extraction. In order to improve efficiency and reduce energy consumption, optimization of the pressurization process was carried out. An optimization model for the process of pressurization in underground gas storage has been established. Based on the model, a joint optimization approach is applied, where MATLAB is responsible for the iterative process of finding the optimal parameter combinations and HYSYS is responsible for the establishment of the process and calculation of the results of the process parameters. The key parameters include the outlet parameters of the compressor and the air cooler, which are critical in determining the overall energy consumption and operational performance of the system. Accordingly, the results related to the optimal parameter combinations for two-stage compression and three-stage compression were obtained in the case study. Compared with one-stage compression, two-stage and three-stage compression can diminish energy consumption by 1,464,789 kJ/h and 2,177,319 kJ/h, respectively. The reduced rate of energy consumption of three-stage compression was 16.10%, which was higher than that of two-stage compression by 10.83%. Although the construction costs of three-stage compression were higher than those of two-stage compression, from the perspective of long-term operation, three-stage compression had lower operating costs and superior economy and applicable value. The research results provided scientific references and new ideas for the optimization and adjustment of the pressurization process in underground gas storage.

Oilfield Sewage System Scheduling is a complicated, large-scale, nonlinear system problem with multiple variables. The complexity of the sewage system pipeline network connection grows along with the ongoing building of oilfield stations, and the shortcomings of the sewage system water quantity scheduling program based on human experience decision-making become increasingly apparent. The key to solving this problem is to realize the digital and intelligent scheduling of sewage systems. Taking the sewage system of an oil production plant in Daqing oilfield as the research object, the water scheduling model of the sewage system is established in this paper. Aiming at the complex nonlinear characteristics of the model, the Levy flight speed updating operator, the adaptive stochastic offset operator, and the Brownian motion selection optimization operator are established by taking advantage of the particle swarm optimization (PSO) and the cuckoo search (CS) algorithm. Based on these operators, a hybrid PSO-CS algorithm is proposed, which jumps out of the local optimum and has a strong global search capability. Comparing PSO-CS with other algorithms on the CEC2022 test set, it was found that the PSO-CS algorithm ranked first in all 12 test functions, proving the excellent solving performance of the PSO-CS algorithm. Finally, the PSO-CS is applied to solve a water scheduling model for the sewage system of an oil production plant in Daqing Oilfield. It is found that the scheduling plan optimized by PSO-CS has a 100% water supply rate to the downstream water injection station, and the total energy consumption of the scheduling plan on the same day is reduced from 879.95 × 10⁶ m⁵/d to 712.84 × 10⁶ m⁵/d, which is a 19% reduction in energy consumption. The number of water balance stations in the sewage station increased by 7, which effectively improved the water resource utilization rate of the sewage station.